技术领域technical field
本发明涉及监控领域，尤指一种管制员工作负荷预测方法和系统。The invention relates to the monitoring field, in particular to a controller workload prediction method and system.
背景技术Background technique
伴随着航空运输业的发展，为了保证各类飞行活动的安全和有序，空中交通管制服务应运而生并不断得到发展完善，至20世纪80年代趋于成熟。现代空中交通管制服务的主要内容是：空中交通管制员(简称为“管制员”，下同)依托现代通信、导航、监视技术，对所辖航空器实施管理和控制，协调和指导其运动路径和模式，以防止空中航空器与航空器相撞及在机场机动区内航空器与障碍物相撞，维护和加快空中交通的有序流动。这项任务的执行者是空中交通管制员(简称为“管制员”，下同)。管制员主要工作是通过雷达显示的实时信息，密切监控飞行动态，并通过无线电通信设备向机组发布各种指令，是一个集眼、手、嘴等多感官共同协调的工作。最繁忙时段，个体管制员需同时管制十几架航空器，因此，管制员脑力劳动强度大、工作负荷高，经常需要倒班，容易出现不同水平的疲劳状态，对管制员工作负荷进行预测并对可能产生超负荷的时段进行干预，可以有效避免疲劳状态的产生。With the development of the air transport industry, in order to ensure the safety and order of various flight activities, the air traffic control service came into being and was continuously developed and improved until it became mature in the 1980s. The main content of modern air traffic control services is: Air traffic controllers (referred to as "controllers", the same below) rely on modern communication, navigation, and surveillance technologies to manage and control aircraft under their jurisdiction, coordinate and guide their movement paths and Mode to prevent collisions between aircraft in the air and collisions between aircraft and obstacles in the maneuvering area of the airport, and maintain and speed up the orderly flow of air traffic. The executor of this task is the air traffic controller (abbreviated as "controller", the same below). The main job of the controller is to closely monitor the flight dynamics through the real-time information displayed by the radar, and issue various instructions to the crew through the radio communication equipment. During the busiest period, individual controllers need to control more than a dozen aircraft at the same time. Therefore, controllers have high mental labor intensity and high workload. Intervention during periods of overload can effectively avoid the occurrence of fatigue.
专利文献CN104636890A于2015年05月20日公开了一种空中交通管制员工作负荷测量方法。该方法包括步骤A：确定管制负荷测量指标，该管制负荷测量指标包括眼动指标和语音指标；步骤B：实时记录各眼动指标对应的眼动指标数据，以及各语音指标对应的语音指标数据；步骤C：对记录的眼动指标数据进行因子分析，计算出眼动指标数据的眼动综合因子；步骤D：以眼动综合因子和语音指标为输入因素，管制工作负荷值为输出因素，建立管制负荷回归模型。Patent document CN104636890A disclosed a method for measuring the workload of air traffic controllers on May 20, 2015. The method includes step A: determining control load measurement indicators, the control load measurement indicators include eye movement indicators and voice indicators; step B: recording eye movement indicator data corresponding to each eye movement indicator and voice indicator data corresponding to each voice indicator in real time ; Step C: Carry out factor analysis to the recorded eye movement index data, and calculate the eye movement comprehensive factor of the eye movement index data; Step D: take the eye movement comprehensive factor and the voice index as input factors, and the control workload value is the output factor, Establish a regulatory load regression model.
专利文献CN102306297A于2012年01月04公开了一种空中交通管制员工作负荷测量方法。该方法首先对基本空中交通事件进行分类，其次基于人类工效学确立基本管制行为的分类，并通过雷达语音记录仪统计分析管制通话，建立易观测的管制员工作负荷统计模型，然后通过机器学习，得到通过空中交通事件确定的基本管制单元工作负荷，并确定该工作负荷的修正系数，最后利用该系数修正易观测的管制员工作负荷统计模型，确定管制员工作负荷测量模型。本发明可实现对于管制员工作负荷准确量化度量，为民航管制技能培训、空域扇区容量评估及空域规划设计提供了依据。Patent document CN102306297A disclosed a method for measuring the workload of air traffic controllers on January 04, 2012. This method first classifies basic air traffic events, and then establishes the classification of basic control behaviors based on ergonomics, and uses radar voice recorders to statistically analyze control calls, and establishes an easy-to-observe statistical model of controller workload, and then through machine learning, Obtain the workload of the basic control unit determined by air traffic events, and determine the correction coefficient of the workload, and finally use the coefficient to modify the easy-to-observe controller workload statistical model, and determine the controller workload measurement model. The invention can realize accurate quantitative measurement of the controller's workload, and provides a basis for civil aviation control skill training, airspace sector capacity evaluation and airspace planning and design.
关于管制员工作负荷预测的研究，目前主要体现在管制员工作负荷的测评技术上，自20世纪70年代以来陆续演化出了三类管制员工作负荷测评方法，即：The research on controller workload prediction is mainly reflected in the controller workload evaluation technology. Since the 1970s, three types of controller workload evaluation methods have evolved, namely:
(1)根据管制员生理、行为特征分析，得出管制工作负荷强度。测量的生理指标包括电击皮肤的反应、心率、心电图、血压、体液等，行为指标包括设备操作次数、陆空通话时间记录等。(1) Based on the analysis of the controller's physiological and behavioral characteristics, the control workload intensity is obtained. The measured physiological indicators include the response to electric shock skin, heart rate, electrocardiogram, blood pressure, body fluids, etc., and the behavioral indicators include the number of equipment operations, land and air call time records, etc.
(2)采取观察和问卷形式的主观测评方法，如ATWIT技术(airtrafficworkloadinputtechnique，美国联邦航空局的空中交通负荷输入技术)、NASA-TLX量表(taskloadindex，美国国家航空航天局的任务负荷量表)、SWAT量表(subjectiveworkloadanalysistechnique，主观工作负荷分析技术)和MCH法(modifiedcooper-harperratings，库柏-哈柏修正法)等。(2) Subjective evaluation methods in the form of observation and questionnaires, such as ATWIT technology (airtrafficworkloadinputtechnique, FAA's air traffic load input technology), NASA-TLX scale (taskloadindex, NASA's task load scale) , SWAT scale (subjective workload analysis technique, subjective workload analysis technique) and MCH method (modifiedcooper-harperratings, Cooper-Harper revision method), etc.
(3)将管制员工作进行细分，对于看得见的工作测计所消耗的时间，对于看不见的工作转化为时间上的消耗，以时间度量方式实现对管制员工作负荷的定量评估。此类方法包括ICAO推荐的DORATASK法(DirectorateofOperationResearchandAnalysisoftheUnitedKingdom，英国运筹研究与分析理事会提出)和MBB法(Messerschmidt，BglkowandBlohmofGermany，德国梅塞施密特、特尔科和布卢姆提出)，以及RAMS法(Re-organizedATCMathematicalSimulator，欧洲空管实验中心提出)。(3) Subdivide the work of the controller, measure the time consumed for the visible work, convert the time consumption for the invisible work, and realize the quantitative evaluation of the controller's workload by means of time measurement. Such methods include the DORATASK method recommended by ICAO (Directorate of Operation Research and Analysis of the United Kingdom, proposed by the Operational Research Research and Analysis Council of the United Kingdom), the MBB method (Messerschmidt, Bglkow and BlohmofGermany, proposed by Messerschmidt, Telko and Bloom of Germany), and the RAMS method (Re -organizedATCMathematicalSimulator, proposed by the European Air Traffic Control Experimental Center).
目前管制员工作负荷预测的相关研究内容，主要存在以下不足：(1)研究方法方面，定性研究较多，定量研究较少，导致客观性不足。(2)研究指标方面，多从直接反映管制员工作负荷的指标入手，较少考虑管制员工作负荷的影响因子指标，指标维度较为单一，不够全面、综合，预测可靠性不高。(3)应用性方面，既有研究仍停留在实验室研究阶段，主要服务于战略决策，而面向空中交通管制单位的实际工程应用少。由于上述不足，导致目前国内外对于管制员工作负荷预测的研究在客观性、全面性、综合性、准确性和可操作性等方面均有所欠缺。At present, the relevant research content of controller workload prediction mainly has the following deficiencies: (1) In terms of research methods, there are more qualitative research and less quantitative research, resulting in insufficient objectivity. (2) In terms of research indicators, most of them start with the indicators that directly reflect the controller's workload, and less consider the influencing factor indicators of the controller's workload. The index dimension is relatively single, not comprehensive and comprehensive, and the prediction reliability is not high. (3) In terms of applicability, existing research is still at the stage of laboratory research, which mainly serves strategic decision-making, while there are few actual engineering applications for air traffic control units. Due to the above deficiencies, the current domestic and foreign research on controller workload prediction is lacking in objectivity, comprehensiveness, comprehensiveness, accuracy and operability.
发明内容Contents of the invention
本发明提供一种更高效的、可提高客观性、预测准确性的管制员工作负荷预测方法和系统。The invention provides a more efficient controller workload prediction method and system that can improve objectivity and prediction accuracy.
本发明的目的是通过以下技术方案来实现的：The purpose of the present invention is achieved through the following technical solutions:
一种管制员工作负荷预测方法，包括步骤：A controller workload prediction method, comprising the steps of:
步骤1：选取一定时间间隔的管制扇区空中交通流态势指标，及态势指标对应的管制员工作负荷指数作为样本数据；Step 1: Select the air traffic flow situation indicators of the control sector at a certain time interval, and the controller workload index corresponding to the situation indicators as sample data;
步骤2：根据上述样本数据，建立线性回归模型和非线性回归模型；Step 2: Based on the above sample data, establish a linear regression model and a nonlinear regression model;
步骤3：通过拟合度、显著性和误差分析，对线性回归模型和非线性回归模型进行比对，确定管制员工作负荷预测多重回归模型；Step 3: Through the fit, significance and error analysis, compare the linear regression model and the nonlinear regression model, and determine the controller workload prediction multiple regression model;
步骤4：将实时管制扇区空中交通流态势指标导入管制员工作负荷预测多重回归模型，得到管制员工作负荷指数。Step 4: Import the real-time control sector air traffic flow situation index into the multiple regression model of controller workload prediction to obtain the controller workload index.
进一步的，所述步骤1中的管制扇区空中交通流态势指标包括扇区运行通行性指标、扇区运行复杂性指标、扇区运行安全性指标和扇区运行经济性指标。Further, the control sector air traffic flow situation indicators in the step 1 include sector operation accessibility indicators, sector operation complexity indicators, sector operation safety indicators and sector operation economic indicators.
进一步的，所述管制扇区空中交通流态势指标包括扇区运行通行性指标、扇区运行复杂性指标、扇区运行安全性指标和扇区运行经济性指标；Further, the air traffic flow situation index of the control sector includes a sector operation traffic index, a sector operation complexity index, a sector operation safety index and a sector operation economic index;
扇区通行性检测指标分别包括扇区流量、扇区航行里程、扇区航行时间和扇区交通流密度；Sector trafficability detection indicators include sector flow, sector voyage mileage, sector voyage time and sector traffic flow density;
扇区复杂性检测指标包括扇区航空器爬升次数、扇区航空器下降次数、扇区航空器改速次数、扇区航空器改航次数；Sector complexity detection indicators include sector aircraft climb times, sector aircraft descent times, sector aircraft speed changes, sector aircraft diversion times;
扇区安全性检测指标包括扇区短期冲突告警频率和扇区最低安全高度告警频率；Sector security detection indicators include sector short-term conflict alarm frequency and sector minimum safety altitude alarm frequency;
扇区经济性检测指标包括扇区饱和度、扇区排队长度、扇区航空器延误架次率、扇区航空器延误时间、扇区航空器平均延误时间。Sector economy detection indicators include sector saturation, sector queuing length, sector aircraft delay rate, sector aircraft delay time, and sector aircraft average delay time.
进一步的，所述步骤2中对样本数据进行标准化转换；标准化转换过程如下：Further, in the step 2, the sample data is standardized and converted; the normalized conversion process is as follows:
令xij、x′ij分别表示第i个样本的原始数据和经过标准化转换后的数据，sj分别表示第j个指标数据的均值和方差，则：Let xij , x′ij respectively denote the original data of the i-th sample and the data after standardized transformation, sj respectively represent the mean and variance of the jth index data, then:
进一步的，所述步骤2具体包括：Further, the step 2 specifically includes:
根据上述标准化样本数据x'ij(i＝1,2,…m,j＝1,2,…n)，分别建立多重线性回归模型和多重非线性回归模型，并求解系数bi，According to the above-mentioned standardized sample data x'ij (i=1,2,...m,j=1,2,...n), respectively establish a multiple linear regression model and a multiple nonlinear regression model, and solve the coefficient bi ,
其中多重线性回归模型为：where the multiple linear regression model is:
Y＝XB+U(式1)Y=XB+U (Formula 1)
其中，in,
多重非线性回归模型为：The multiple nonlinear regression model is:
Y＝f[(b1,b2,…,bk)；X1,X2,…,Xn](式2)Y=f[(b1 ,b2 ,...,bk ); X1 ,X2 ,...,Xn ] (Formula 2)
其中因变量Y为管制员负荷指数，自变量X为n项管制扇区空中交通流态势指标，m表示m组时间间隔下的管制扇区运行性能指标样本，U为除了m个自变量对因变量Y的影响之外的随机误差，服从正态分布，f表示非线性回归函数。Among them, the dependent variable Y is the controller load index, the independent variable X is the air traffic flow situation index of n control sectors, m represents the control sector operation performance index samples under m groups of time intervals, and U is the independent variables except m independent variables for the factor The random error outside the influence of the variable Y, obeys the normal distribution, and f represents the nonlinear regression function.
进一步的，所述步骤3具体包括：Further, the step 3 specifically includes:
根据各模型返回的可决系数R2值、F检验、t检验，分别验证并比较两种回归模型的拟合度、显著性，在模型拟合度较高、显著性明显的基础上，计算两种回归模型的检测误差，并选取误差最小的一种模型，作为管制员工作负荷预测的多重回归模型。According to the coefficient of determination R2 value, F test and t test returned by each model, respectively verify and compare the fitting degree and significance of thetwo regression models, and calculate the The detection errors of the two regression models, and the model with the smallest error is selected as the multiple regression model for controller workload prediction.
进一步的，步骤4中的实时管制扇区空中交通流态势指标在输入多重回归模型之前要进行标准化转换；标准化转换过程如下：Further, the real-time control sector air traffic flow situation indicators in step 4 need to be standardized before being input into the multiple regression model; the standardized conversion process is as follows:
根据m组时间间隔的样本数据的n项指标的均值方差sj，对管制扇区空中交通流态势指标tj(j＝1,2,...,n)进行标准化转换：将转换后的数据tj'导入到管制员工作负荷预测多重回归模型中。The mean value of n indicators based on the sample data of m groups of time intervals Variance sj , perform standardized transformation on the air traffic flow situation index tj (j=1,2,...,n) in the control sector: Import the transformed datatj ' into a multiple regression model for controller workload prediction.
进一步的，所述方法还包括步骤5，当管制员工作负荷指数超出阈值，管制员工作负荷响应告警。Further, the method further includes step 5, when the controller workload index exceeds the threshold, the controller workload responds to an alarm.
一种管制员工作负荷的预测系统，包括：构件模块：选取管制扇区空中交通流态势指标，将相关指标对应的管制员工作负荷预测样本数据代入多重线性回归模型和多重非线性回归模型中进行拟合；得到多重线性回归模型和多重非线性回归模型的参数估计值；通过统计检验，计算检测误差，确定管制员工作负荷预测多重回归模型；预测模块：将管制扇区空中交通流态势指标预测数据导入管制员工作负荷预测多重回归模型，得到管制员工作负荷的预测结果。A controller workload forecasting system, comprising: a component module: select the control sector air traffic flow situation indicators, and substitute the controller workload prediction sample data corresponding to the relevant indicators into the multiple linear regression model and the multiple nonlinear regression model Fitting; obtain the estimated values of the parameters of the multiple linear regression model and the multiple nonlinear regression model; through statistical testing, calculate the detection error, and determine the controller workload prediction multiple regression model; prediction module: predict the air traffic flow situation index of the control sector The data is imported into the multi-regression model of controller workload prediction, and the prediction result of controller workload is obtained.
进一步的，系统还包括，标准化转换模块：用于对样本数据以及管制扇区空中交通流态势指标实时数据进行标准化转换；报警模块：当预测结果超出阈值，管制员工作负荷响应告警。Further, the system also includes a standardized conversion module: used for standardized conversion of sample data and real-time data of air traffic flow situation indicators in the control sector; alarm module: when the predicted result exceeds the threshold, the controller workload responds to the alarm.
进一步的，所述预测系统还包括管制扇区交通流态势检测数据库，与所述管制扇区交通流态势检测数据库耦合的数据引接装置和指标采集装置；Further, the prediction system also includes a control sector traffic flow situation detection database, a data connection device and an index collection device coupled with the control sector traffic flow situation detection database;
所述数据引接装置包括分别与所述管制扇区交通流态势检测数据库耦合的电报数据接口、综合航迹数据接口和管制语音数据接口；The data connection device includes a telegram data interface, an integrated track data interface and a control voice data interface respectively coupled with the control sector traffic flow situation detection database;
所述指标采集装置用于采集管制扇区空中交通流态势指标，所述管制扇区空中交通流态势指标包括扇区运行通行性指标、扇区运行复杂性指标、扇区运行安全性指标和扇区运行经济性指标；扇区通行性检测指标分别包括扇区流量、扇区航行里程、扇区航行时间和扇区交通流密度；扇区复杂性检测指标包括扇区航空器爬升次数、扇区航空器下降次数、扇区航空器改速次数、扇区航空器改航次数；扇区安全性检测指标包括扇区短期冲突告警频率和扇区最低安全高度告警频率；扇区经济性检测指标包括扇区饱和度、扇区排队长度、扇区航空器延误架次率、扇区航空器延误时间、扇区航空器平均延误时间；The index collection device is used to collect the air traffic flow situation index of the control sector, and the air traffic flow situation index of the control sector includes a sector operation passability index, a sector operation complexity index, a sector operation safety index and a sector operation index. Zone operation economic indicators; sector traffic detection indicators include sector flow, sector mileage, sector flight time and sector traffic flow density; sector complexity detection indicators include sector aircraft climb times, sector aircraft The number of descents, the number of aircraft speed changes in the sector, and the number of aircraft diversions in the sector; the sector safety detection indicators include the sector short-term conflict alarm frequency and the sector minimum safe altitude alarm frequency; the sector economy detection indicators include sector saturation , sector queuing length, sector aircraft delay rate, sector aircraft delay time, sector aircraft average delay time;
所述构件模块从所述管制扇区交通流态势检测数据库中读取所述管制员工作负荷预测相关指标和管制员工作负荷预测样本数据；所述预测模块从所述管制扇区交通流态势指标检测数据库中读取所述管制扇区空中交通流态势指标预测数据。The component module reads the controller workload prediction related indicators and the controller workload prediction sample data from the control sector traffic flow situation detection database; the prediction module reads the control sector traffic flow situation index The air traffic flow situation indicator prediction data of the control sector is read from the detection database.
本发明的有益效果：Beneficial effects of the present invention:
本发明采用定量分析方法，通过对海量运行数据的不间断检测和计算分析，推算出精确的未来时段空中交通流态势指标数据，并依靠对历史数据的挖掘，获取空中交通流态势与管制员工作负荷之间的关系，在此基础上对管制员工作负荷进行预测，具有客观、高效、准确的优势，规避了人工预测易疲劳、易主观化等经验型管理的缺陷问题。更为重要的是，所提系统能够满足空中交通管制单位对管制员工作负荷进行实时预测和告警的实际需求，对于提升管制运行管理水平、优化管制空域结构具有数据支持作用。本发明将影响管制员工作负荷的空中交通流态势多维度指标进行全面、综合考虑，从而实现对管制员工作负荷的有效预测。所设计的管制员工作负荷预测系统，能够应用于工程单位，具有很强的操作性。The present invention adopts a quantitative analysis method, calculates accurate air traffic flow situation index data in the future period through continuous detection and calculation and analysis of massive operating data, and relies on historical data mining to obtain air traffic flow situation and controller work information. Based on the relationship between loads, predicting the workload of controllers has the advantages of being objective, efficient, and accurate, and avoids the shortcomings of empirical management such as manual predictions that are prone to fatigue and subjectivity. More importantly, the proposed system can meet the actual needs of air traffic control units for real-time prediction and warning of controller workload, and it has a data support role in improving the level of control operation management and optimizing the structure of control airspace. The invention comprehensively and comprehensively considers the multi-dimensional indicators of the air traffic flow situation that affect the controller's workload, so as to realize the effective prediction of the controller's workload. The designed controller workload prediction system can be applied to engineering units and has strong operability.
附图说明Description of drawings
图1是本发明实施例一管制员工作负荷预测方法的示意图；Fig. 1 is a schematic diagram of a controller workload prediction method according to an embodiment of the present invention;
图2是本发明实施例一管制员工作负荷预测系统的示意图；Fig. 2 is a schematic diagram of a controller workload prediction system according to an embodiment of the present invention;
图3是本发明实施例二管制员工作负荷预测的系统逻辑结构示意图；Fig. 3 is a schematic diagram of the logical structure of the system for predicting the controller's workload in the second embodiment of the present invention;
图4是本发明实施例二管制员工作负荷预测的系统网络结构示意图；Fig. 4 is a schematic diagram of the system network structure of the controller's workload prediction in the second embodiment of the present invention;
图5是本发明实施例二管制员工作负荷预测的系统功能结构示意图；Fig. 5 is a schematic diagram of the functional structure of the system for predicting the controller's workload in the second embodiment of the present invention;
图6是本发明实施例三综合航迹数据采集功能结构示意图；Fig. 6 is a schematic diagram of the functional structure of integrated track data collection in Embodiment 3 of the present invention;
图7是本发明实施例三语音数据采集流程示意图；Fig. 7 is a schematic diagram of the voice data acquisition flow chart of Embodiment 3 of the present invention;
图8是本发明实施例三电报数据采集功能结构示意图；Fig. 8 is a schematic diagram of the functional structure of telegraph data collection in Embodiment 3 of the present invention;
图9是本发明实施例四管制员工作负荷预测的方法示意图；Fig. 9 is a schematic diagram of a method for predicting the controller's workload in Embodiment 4 of the present invention;
图10是本发明实施例四多重非线性回归拟合结果示意图；Fig. 10 is a schematic diagram of the result of multiple nonlinear regression fitting in Example 4 of the present invention;
图11是本发明实施例四多重非线性回归拟合误差示意图；Fig. 11 is a schematic diagram of multiple nonlinear regression fitting error in Embodiment 4 of the present invention;
图12是本发明实施例五管制员工作负荷预测系统的结构示意图；Fig. 12 is a schematic structural diagram of a five-controller workload forecasting system according to an embodiment of the present invention;
其中：1、构件模块；2、预测模块；3、标准化转换模块；4、报警模块：5、运行指标检测数据库；6、数据引接装置；7、指标采集装置。Among them: 1. Component module; 2. Prediction module; 3. Standardization conversion module; 4. Alarm module; 5. Operation index detection database; 6. Data connection device; 7. Index collection device.
具体实施方式Detailed ways
下面结合附图和较佳的实施例对本发明作进一步说明。The present invention will be further described below in conjunction with the accompanying drawings and preferred embodiments.
实施例一Embodiment one
如图1所示，本实施方式公开的管制员工作负荷预测方法，其包括步骤：As shown in Figure 1, the controller workload prediction method disclosed in this embodiment includes steps:
S1、选取管制扇区空中交通流态势指标，将相关指标对应的管制员工作负荷指数作为样本数据代入多重线性回归模型和多重非线性回归模型中进行拟合；得到多重线性回归模型和多重非线性回归模型参数估计值，建立重线性回归模型和多重非线性回归模型；S1. Select the air traffic flow situation index in the control sector, and use the controller workload index corresponding to the relevant index as the sample data into the multiple linear regression model and the multiple nonlinear regression model for fitting; the multiple linear regression model and the multiple nonlinear regression model are obtained Regression model parameter estimates, establishment of heavy linear regression models and multiple nonlinear regression models;
S2、通过拟合度、显著性和误差分析，对线性回归模型和非线性回归模型进行比对，确定管制员工作负荷预测多重回归模型；S2, through the fitting degree, significance and error analysis, compare the linear regression model and the nonlinear regression model, and determine the controller workload prediction multiple regression model;
S3、将管制扇区空中交通流态势指标实时数据导入管制员工作负荷预测多重回归模型，得到管制员工作负荷指数的预测结果。S3. Import the real-time data of air traffic flow situation indicators in the control sector into the multiple regression model of controller workload prediction to obtain the prediction result of the controller workload index.
如图2所示，本实施方式还公开一种管制员工作负荷的预测系统，包括，As shown in Figure 2, this embodiment also discloses a forecasting system for controller workload, including:
构件模块：选取管制员工作负荷预测相关指标，将相关指标对应的管制员工作负荷预测样本数据代入多重回归模型中进行拟合；得到多重回归模型的参数估计值和样本输出值；将参数估计值、样本输出值导入多重回归模型，得到样本回归函数；Component module: select the relevant indicators of controller workload prediction, and substitute the corresponding controller workload prediction sample data into the multiple regression model for fitting; obtain the parameter estimates and sample output values of the multiple regression model; , The sample output value is imported into the multiple regression model to obtain the sample regression function;
预测模块：将管制扇区空中交通流态势指标预测数据导入样本回归函数，得到管制员工作负荷的预测结果。Prediction module: import the prediction data of the air traffic flow situation index in the control sector into the sample regression function to obtain the prediction result of the controller's workload.
回归分析是多元统计分析中的一个重要分支，它是通过一组检测变量(即自变量)来检测一个或者多个响应变量(即因变量)的统计方法。只有一个因变量的情况称为一元回归，多个因变量称为多元回归。考虑到管制员工作负荷受到多种因素影响，设定管制员工作负荷作为单一响应变量，因此，此处采用一元多重回归方法(简称多重回归)，对管制员工作负荷进行预测。Regression analysis is an important branch of multivariate statistical analysis. It is a statistical method to detect one or more response variables (ie dependent variables) through a set of detection variables (ie independent variables). The case with only one dependent variable is called a univariate regression, and the case of multiple dependent variables is called a multiple regression. Considering that the controller's workload is affected by many factors, the controller's workload is set as a single response variable. Therefore, the single variable multiple regression method (referred to as multiple regression) is used here to predict the controller's workload.
根据回归函数的线性关系，可以分为多重线性回归和多重非线性回归两种基本的函数模型。本发明可以采用两种模型都用，然后选择误差小的一种作为最终的预测模型，也可以单选一种进行预测，以简化运算过程。According to the linear relationship of the regression function, it can be divided into two basic function models: multiple linear regression and multiple nonlinear regression. In the present invention, both models can be used, and the one with the smaller error can be selected as the final forecasting model, or one can be single-selected for forecasting, so as to simplify the operation process.
本发明采用定量分析方法，通过对海量运行数据的不间断检测和计算分析，推算出精确的未来时段空中交通流态势指标数据，并依靠对历史数据的挖掘，获取空中交通流态势与管制员工作负荷之间的关系，在此基础上对管制员工作负荷进行预测，具有客观、高效、准确的优势，规避了人工预测易疲劳、易主观化等经验型管理的缺陷问题。更为重要的是，所提系统能够满足空中交通管制单位对管制员工作负荷进行实时预测和告警的实际需求，对于提升管制运行管理水平、优化管制空域结构具有数据支持作用。本发明将影响管制员工作负荷的空中交通流态势多维度指标进行全面、综合考虑，从而实现对管制员工作负荷的有效预测。所设计的管制员工作负荷预测系统，能够应用于工程单位，具有很强的操作性。The present invention adopts a quantitative analysis method, calculates accurate air traffic flow situation index data in the future period through continuous detection and calculation and analysis of massive operating data, and relies on historical data mining to obtain air traffic flow situation and controller work information. Based on the relationship between loads, predicting the workload of controllers has the advantages of being objective, efficient, and accurate, and avoids the shortcomings of empirical management such as manual predictions that are prone to fatigue and subjectivity. More importantly, the proposed system can meet the actual needs of air traffic control units for real-time prediction and warning of controller workload, and it has a data support role in improving the level of control operation management and optimizing the structure of control airspace. The invention comprehensively and comprehensively considers the multi-dimensional indicators of the air traffic flow situation that affect the controller's workload, so as to realize the effective prediction of the controller's workload. The designed controller workload prediction system can be applied to engineering units and has strong operability.
实施例二Embodiment two
本实施方式公开一种系统架构，作为本发明管制员工作负荷预测方系统的实施平台，可用于实施本发明所述的预测方法。This embodiment discloses a system architecture, which can be used to implement the prediction method described in the present invention as the implementation platform of the controller workload forecasting system of the present invention.
本实施方式的管制员工作负荷预测系统结构如图3所示。空中交通管制员工作负荷预测系统主要包括一套管制扇区交通流态势检测数据库和数据引接、指标采集三大功能模块。管制扇区交通流态势检测数据库将各信息采集点采集的空中交通流态势数据(包括雷达综合航迹数据、电报数据、VHF录音数据等)归类、保存，为管制员工作负荷预测提供数据依据。The structure of the controller workload prediction system in this embodiment is shown in FIG. 3 . The air traffic controller workload prediction system mainly includes a set of control sector traffic flow situation detection database and three functional modules of data connection and index collection. The traffic flow situation detection database in the control sector classifies and saves the air traffic flow situation data (including radar comprehensive track data, telegram data, VHF recording data, etc.) collected by each information collection point, and provides data basis for controller workload prediction .
图4、5公开了一种实现本发明预测系统的网络结构及相应的功能模块结构。系统通过数据采集服务器收集实时数据，通过管制扇区交通流态势检测服务器和管制员工作负荷预测及告警服务器实时监视运行数据，并对未来时段的管制员工作负荷进行预测，并对工作负荷超出阈值的时段进行告警。整个系统的网络平台将依托现有的管理信息网，采集平台和空管生产网络进行物理隔离，保证数据的单向传递，阻止网络攻击，以保障相关数据安全性和生产运行系统可靠性。Figures 4 and 5 disclose a network structure and corresponding functional module structure for realizing the prediction system of the present invention. The system collects real-time data through the data acquisition server, monitors the operating data in real time through the traffic flow situation detection server in the control sector and the controller workload prediction and alarm server, and predicts the controller workload in the future, and when the workload exceeds the threshold time period for alerting. The network platform of the entire system will rely on the existing management information network, and the collection platform will be physically isolated from the air traffic control production network to ensure the one-way transmission of data and prevent network attacks, so as to ensure the security of relevant data and the reliability of the production and operation system.
实施例三Embodiment Three
本实施方式公开一种管制运行数据采集方案，包括但不局限于管制员工作负荷预测相关指标、管制员工作负荷预测样本数据和管制扇区空中交通流态势指标预测数据的采集。This embodiment discloses a control operation data collection scheme, including but not limited to the collection of controller workload prediction related indicators, controller workload prediction sample data and control sector air traffic flow situation index prediction data collection.
本研究以管制员工作负荷指数为因变量，记为Y。管制扇区空中交通流态势指标共计15项，记自变量X为：In this study, the controller workload index is used as the dependent variable, denoted as Y. There are a total of 15 air traffic flow situation indicators in the control sector, and the independent variable X is recorded as:
X＝{Xi,i＝1,2,…,15}(式3.1)X={Xi , i=1,2,...,15} (Formula 3.1)
其中，扇区通行性检测指标为{X1,X2,X3,X4}，分别表示扇区流量、扇区航行里程、扇区航行时间和扇区交通流密度；扇区复杂性检测指标为{X5,X6,X7,X8}，分别表示扇区航空器爬升次数、扇区航空器下降次数、扇区航空器改速次数、扇区航空器改航次数；扇区安全性检测指标为{X9,X10}，分别表示扇区短期冲突告警频率和扇区最低安全高度告警频率；扇区经济性检测指标为{X11,X12,X13,X14,X15}，分别表示扇区饱和度、扇区排队长度、扇区航空器延误架次率、扇区航空器延误时间、扇区航空器平均延误时间。这些参数指标的主要从以下几个方面采集获得。Among them, the sector trafficability detection index is {X1 ,X2 ,X3 ,X4 }, respectively representing sector flow, sector mileage, sector voyage time and sector traffic flow density; sector complexity detection The indicators are {X5 , X6 , X7 , X8 }, respectively representing the number of climbs of aircraft in the sector, the number of descents of aircraft in the sector, the number of speed changes of aircraft in the sector, and the number of diversions of aircraft in the sector; the safety detection indicators of the sector is {X9 ,X10 }, which respectively represent the sector short-term conflict warning frequency and the sector minimum safety altitude warning frequency; the sector economy detection index is {X11 ,X12 ,X13 ,X14 ,X15 }, Respectively represent sector saturation, sector queuing length, sector aircraft delay rate, sector aircraft delay time, and sector aircraft average delay time. These parameter indicators are mainly collected from the following aspects.
综合航迹采集Integrated Track Collection
空管自动化系统对航管一、二次雷达等监视信号进行数据融汇和数据处理，输出综合航迹信息，其主要的处理模块包括雷达前端处理模块，雷达数据处理模块和飞行计划处理模块。The air traffic control automation system performs data fusion and data processing on surveillance signals such as air traffic control primary and secondary radar, and outputs comprehensive track information. Its main processing modules include radar front-end processing modules, radar data processing modules and flight plan processing modules.
本技术方案从空管自动化系统采集综合航迹数据，通过网络的方式进行传输。数据采集服务器对采集的综合航迹数据进行解析，获取航空器的高度、速度、位置等信息用于指标的计算。This technical solution collects comprehensive track data from the air traffic control automation system and transmits it through the network. The data acquisition server analyzes the collected comprehensive track data, and obtains information such as the altitude, speed, and position of the aircraft for the calculation of indicators.
综合航迹数据采集模块包括航迹数据格式转换模块、航迹数据解析模块、航迹数据存储模块，如图6所示。The comprehensive track data acquisition module includes a track data format conversion module, a track data analysis module, and a track data storage module, as shown in Figure 6.
语音数据采集Voice Data Acquisition
管制员与飞行员通过VHF通信系统实现陆空语音通话。该系统由甚高频(VeryHighFrequency，VHF)收发电台及信号传输、处理装置组成。The controller and the pilot realize the land-air voice communication through the VHF communication system. The system is composed of VHF (Very High Frequency, VHF) transceiver station and signal transmission and processing devices.
语音数据采集从配线架上并接采集语音信号，将陆空通话信息进行解码和存储，用于管制员管制指挥通话负荷的分析。Voice data collection collects voice signals parallelly from the distribution frame, decodes and stores land and air call information, and uses it for controllers to control and command call load analysis.
如图7所示，席位语音数据由内话系统配线架通过带屏蔽网线并接引入系统数据采集服务器，语音通道与席位(扇区)对应。As shown in Figure 7, the seat voice data is connected to the system data collection server through the intercom system distribution frame through a shielded network cable, and the voice channel corresponds to the seat (sector).
语音信号从配线架上高阻抗(录音模块为200K欧姆)采集(管制员地空通话)席位语音，不影响地空通话和语音记录，采用多对电缆线将语音信号从配线架引接至语音处理器，实现对多个席位语音的采集和分析。The voice signal is collected from the distribution frame with high impedance (recording module is 200K ohm) (controller ground-to-air call) seat voice, which does not affect the ground-to-air call and voice recording. Multiple pairs of cables are used to lead the voice signal from the distribution frame to the The voice processor realizes the collection and analysis of the voices of multiple seats.
电报数据采集Telegram Data Acquisition
转报系统是收发民用航空飞行动态固定电报的枢纽装置，民用航空飞行动态固定电报的报文由若干个规定的数据编组按固定顺序排列而成。The relay system is a pivotal device for sending and receiving civil aviation flight dynamic fixed telegrams. The messages of civil aviation flight dynamic fixed telegrams are composed of several specified data groups arranged in a fixed order.
电报数据采集模块引接转报系统输出的电报数据，并对数据进行格式转换、解析和存储，获取飞行计划数据，如图8所示。该模块将接收到的电报数据解析后存储到数据库中保存，用于扇区运行性能指标计算。The telegram data acquisition module connects the telegram data output by the relay system, and performs format conversion, parsing and storage on the data to obtain the flight plan data, as shown in Figure 8. This module parses the received telegram data and stores it in the database for calculation of sectoral performance indicators.
管制扇区空中交通流态势指标采集Collection of air traffic flow situation indicators in control sector
系统从空管自动化系统、转报系统、内话系统中收集综合航迹、飞行计划、语音通信等实时运行数据，以国际民航组织(简称为“ICAO”，下同)、美国联邦航空局(FAA)相关文件为参考，建立管制扇区空中交通流态势指标体系，包括：扇区运行通行性指标，包括扇区流量、扇区航行里程、扇区航行时间和扇区交通流密度；扇区运行复杂性指标，包括扇区航空器爬升次数、扇区航空器下降次数、扇区航空器改速次数、扇区航空器改航次数；扇区经济性指标，包括扇区饱和度、扇区排队长度、扇区航空器延误架次率、扇区航空器延误时间、扇区航空器平均延误时间。并基于指标体系输出管制扇区空中交通流态势指标检测结果。系统提供良好的人机界面，供用户查看各种实时统计图形。The system collects real-time operational data such as comprehensive flight paths, flight plans, and voice communications from the air traffic control automation system, relay system, and intercom system. FAA) related documents are used as a reference to establish a control sector air traffic flow situation indicator system, including: sector operation traffic indicators, including sector flow, sector flight mileage, sector flight time and sector traffic flow density; sector Operational complexity indicators, including sector aircraft climb times, sector aircraft descent times, sector aircraft speed changes, sector aircraft diversion times; sector economic indicators, including sector saturation, sector queue length, sector Aircraft delay rate in the area, aircraft delay time in the sector, and average aircraft delay time in the sector. And based on the index system, the detection results of air traffic flow situation indicators in the control sector are output. The system provides a good man-machine interface for users to view various real-time statistical graphics.
扇区运行通行性指标Sector operation feasibility index
(1)扇区流量(1) Sector traffic
扇区流量是指管制扇区单位时间内所管辖的航空器架次。系统通过引接空管自动化系统综合航迹数据获取空中航空器的位置信息，结合已配置的扇区边界信息，计算得到扇区流量。Sector traffic refers to the number of aircraft sorties under the jurisdiction of the control sector per unit time. The system obtains the position information of the airborne aircraft by connecting the comprehensive track data of the air traffic control automation system, and combines the configured sector boundary information to calculate the sector flow.
(2)扇区航行里程(2) Sector mileage
扇区航行里程是指管制扇区单位时间内所管辖的航空器航行里程的总和。设管制扇区单位时间内航空器架次数为n，第j架航空器的航行里程为Mi，扇区航行里程为Mtotal，则系统通过引接空管自动化系统综合航迹数据获取空中航空器的位置信息，结合已配置的扇区边界信息，计算得到扇区航行里程。Sector mileage refers to the sum of the mileage of aircraft under the jurisdiction of the control sector unit time. Assuming that the number of aircraft movements per unit time in the control sector is n, the flight mileage of the jth aircraft is Mi , and the sector flight mileage is Mtotal , then The system obtains the position information of the airborne aircraft by connecting the comprehensive track data of the air traffic control automation system, and combines the configured sector boundary information to calculate the sector mileage.
(3)扇区航行时间(3) Sector sailing time
扇区航行时间是指管制扇区单位时间内所管辖的航空器航行时间的总和。设管制扇区单位时间内航空器架次数为n，第i架航空器的航行时间为Ti，扇区航行时间为Ttotal，则系统通过引接空管自动化系统综合航迹数据获取空中航空器的位置信息，结合已配置的扇区边界信息，计算得到扇区航行时间。Sector flight time refers to the sum of the flight time of aircraft under the jurisdiction of the control sector unit time. Assuming that the number of aircrafts in the control sector unit time is n, the flight time of the i-th aircraft is Ti , and the sector flight time is Ttotal , then The system obtains the position information of the airborne aircraft by connecting the comprehensive track data of the air traffic control automation system, and combines the configured sector boundary information to calculate the sector flight time.
(4)扇区交通流密度(4) Sector traffic flow density
扇区交通流密度是对管制扇区单位时间内所管辖的航空器架次密集程度的测度。设扇区面积为Ssec，单位时间内扇区流量为n，单位时间内扇区交通流密度为Dsec，则Dsec＝n/Ssec。系统读取配置的扇区边界信息得到扇区面积，结合扇区流量计算得到扇区交通流密度。Sector traffic density is a measure of the density of aircraft sorties under the jurisdiction of the control sector per unit time. Let the sector area be Ssec , the sector traffic per unit time be n, and the sector traffic flow density per unit time be Dsec , then Dsec =n/Ssec . The system reads the configured sector boundary information to obtain the sector area, and calculates the sector traffic flow density in combination with the sector flow.
扇区运行复杂性指标Sector Operational Complexity Index
(1)扇区航空器爬升次数(1) Number of aircraft climbs in the sector
扇区航空器爬升次数是指管制扇区单位时间内所管辖的航空器爬升次数的总和。设管制扇区单位时间内航空器架次数为n，第i架航空器的爬升次数为ci，扇区航空器爬升次数为ctotal，则系统引接实时综合航迹数据，对扇区中航空器的爬升情况进行监视与统计，一个航空器爬升一个高度层为爬升一次，计算得到扇区航空器爬升次数。The number of climbs of aircraft in a sector refers to the sum of the number of climbs of aircraft under the jurisdiction of the control sector per unit time. Assuming that the number of aircrafts in the control sector per unit time is n, the number of climbs of the i-th aircraft is ci , and the number of climbs of aircraft in the sector is ctotal , then The system connects the real-time comprehensive track data to monitor and count the climb situation of aircraft in the sector. An aircraft climbs one altitude layer to climb once, and the number of climbs of the aircraft in the sector is calculated.
(2)扇区航空器下降次数(2) Number of aircraft descents in the sector
扇区航空器下降次数是指管制扇区单位时间内航空器下降次数的总和。设管制扇区单位时间内航空器架次数为n，第i架航空器的下降次数为Di，扇区航空器下降次数为Dtotal，则系统引接实时综合航迹数据，对扇区中航空器的下降情况进行监视与统计，一个航空器下降一个高度层为下降一次，计算得到扇区航空器爬升次数。The number of aircraft descents in the sector refers to the sum of the number of aircraft descents in the control sector per unit time. Assuming that the number of aircrafts in the control sector per unit time is n, the number of descents of the i-th aircraft is Di , and the number of descents of aircraft in the sector is Dtotal , then The system connects the real-time comprehensive track data to monitor and count the aircraft's descent in the sector. One aircraft descends to one altitude level to descend once, and the number of aircraft climbs in the sector is calculated.
(3)扇区航空器改速次数(3) Number of aircraft speed changes in the sector
扇区航空器改速次数是指管制扇区单位时间内航空器速度改变次数的总和。设管制扇区单位时间内航空器架次数为n，第i架航空器的改速次数为Si，扇区航空器改速次数为Stotal，则系统引接实时综合航迹数据，对扇区中航空器的速度改变情况进行监视与统计，一个航空器速度连续改变达到设定参数为一次速度改变，计算得到扇区航空器改速次数。The number of aircraft speed changes in a sector refers to the sum of the number of aircraft speed changes in the control sector per unit time. Assuming that the number of aircrafts in the control sector per unit time is n, the number of speed changes of the i-th aircraft is Si , and the number of speed changes of aircraft in the sector is Stotal , then The system connects the real-time comprehensive track data to monitor and count the speed changes of aircraft in the sector. A continuous change in the speed of an aircraft reaches the set parameter as a speed change, and the number of speed changes of the aircraft in the sector is calculated.
(4)扇区航空器改航次数(4) Number of aircraft diversions in the sector
扇区航空器改航次数是指管制扇区单位时间内航空器航向改变次数的总和。设管制扇区单位时间内航空器架次数为n，第i架航空器的改航次数为Hi，扇区航空器改航次数为Htotal，则系统引接实时综合航迹数据，对扇区中航空器的航向改变情况进行监视与统计，一个航空器航向连续改变达到设定参数为一次航向改变，计算得到扇区航空器改航次数。The number of aircraft diversions in a sector refers to the sum of the number of aircraft course changes in the control sector per unit time. Assuming that the number of aircraft movements per unit time in the control sector is n, the number of diversions of the i-th aircraft is Hi , and the number of diversions of aircraft in the sector is Htotal , then The system uses real-time comprehensive track data to monitor and count the course changes of aircraft in the sector. The continuous course change of an aircraft reaches the set parameter as one course change, and the number of aircraft diversions in the sector is calculated.
1.1.1.1.1扇区运行安全性指标1.1.1.1.1 Sector operation security indicators
(1)扇区短期冲突告警频率(1) Sector short-term collision alarm frequency
扇区短期冲突告警频率是指管制扇区单位时间内所管辖的航空器短期冲突告警次数，由系统引接空管自动化系统的STCA告警数据统计得到。The sector short-term conflict warning frequency refers to the number of aircraft short-term conflict warnings under the jurisdiction of the control sector per unit time, which is obtained from the statistics of the STCA warning data connected to the air traffic control automation system by the system.
(2)扇区最低安全高度告警频率(2) Alarm frequency of the minimum safe altitude in the sector
扇区最低安全高度告警频率是指管制扇区单位时间内所管辖的航空器最低安全高度告警次数，由系统引接空管自动化系统的MSAW告警数据统计得到。The minimum safe altitude warning frequency of a sector refers to the number of minimum safe altitude warnings of aircraft under the jurisdiction of the control sector per unit time, which is obtained from the statistics of the MSAW warning data connected to the air traffic control automation system by the system.
1.1.1.1.2扇区运行经济性指标1.1.1.1.2 Economic indicators of sector operation
(1)扇区饱和度(1) Sector saturation
扇区饱和度是指管制扇区单位时间内流量与容量的比值，管制扇区单位时间内所能管辖的航空器最大数量标定为管制扇区容量。设管制扇区单位时间内航空器架次数为n，管制扇区容量为C，扇区饱和度为Satusec，则Satusec＝n/C。系统读取配置的扇区容量参数，结合扇区流量计算得到扇区饱和度。Sector saturation refers to the ratio of traffic flow to capacity per unit time of the control sector, and the maximum number of aircraft that can be controlled by the control sector per unit time is calibrated as the control sector capacity. Assuming that the number of aircraft sorties per unit time in the control sector is n, the capacity of the control sector is C, and the saturation of the sector is Satusec , then Satusec = n/C. The system reads the configured sector capacity parameters and calculates the sector saturation in combination with sector traffic.
(2)扇区排队长度(2) Sector queue length
在管制扇区单位时间内所管辖的航空器中，如进入扇区时出现盘旋等待等排队状况，则定义其为排队航空器，定义扇区排队长度为排队航空器的数量。系统引接综合航迹数据，判断目标航空器是否在扇区边界进行盘旋等待，并计算得到扇区排队长度。Among the aircraft under the jurisdiction of the control sector unit time, if there is a queuing situation such as circling and waiting when entering the sector, it is defined as a queuing aircraft, and the sector queuing length is defined as the number of queuing aircraft. The system leads the integrated track data to judge whether the target aircraft is circling and waiting at the boundary of the sector, and calculates the sector queue length.
(3)扇区航空器延误架次率(3) Sector aircraft delay rate
在管制扇区单位时间内所管辖的航空器中，航行时间超出了正常范围的航空器定义为延误航空器，航行时间超出正常范围的部分定义为延误时间。设管制扇区单位时间内航空器架次数为n，扇区航空器的延误架次数为d，扇区航空器的延误架次率为Dratsec，则Dratsec＝d/n。系统引接综合航迹数据，对每架航空器在管制扇区中的实际飞行时间与经验飞行时间进行对比，若实际飞行时间大于经验飞行时间，则视为延误航空器，并计算得到扇区航空器延误架次率。Among the aircraft under the jurisdiction of the control sector unit time, the aircraft whose flight time exceeds the normal range is defined as the delayed aircraft, and the part of the flight time which exceeds the normal range is defined as the delayed time. Assuming that the number of aircraft sorties in the control sector per unit time is n, the number of delayed aircraft in the sector is d, and the rate of delayed aircraft in the sector is Dratsec , then Dratsec = d/n. The system imports the comprehensive track data, and compares the actual flight time of each aircraft in the control sector with the experienced flight time. If the actual flight time is greater than the experienced flight time, it is regarded as a delayed aircraft, and the number of delayed aircraft in the sector is calculated. Rate.
(4)扇区航空器延误时间(4) Sector aircraft delay time
在管制扇区单位时间内所管辖的航空器中，航行时间超出了正常范围的航空器定义为延误航空器，航行时间超出正常范围的部分定义为延误时间，延误时间总和定义为扇区航空器延误时间。设管制扇区单位时间内航空器架次数为n，第i架航空器的延误时间为Delayi，扇区航空器延误时间为Delaysec，则系统引接综合航迹数据，对每架航空器在管制扇区中的实际飞行时间与经验飞行时间进行对比，若实际飞行时间大于经验飞行时间，则视为延误航空器，并计算得到扇区航空器延误时间。Among the aircraft under the jurisdiction of the control sector unit time, the aircraft whose flight time exceeds the normal range is defined as the delayed aircraft, the part of the flight time beyond the normal range is defined as the delayed time, and the total delay time is defined as the sector aircraft delay time. Assuming that the number of aircrafts in the control sector unit time is n, the delay time of the i-th aircraft is Delayi , and the delay time of the aircraft in the sector is Delaysec , then The system imports the comprehensive track data, and compares the actual flight time of each aircraft in the control sector with the experienced flight time. If the actual flight time is greater than the experienced flight time, it will be regarded as a delayed aircraft, and the delayed time of the aircraft in the sector will be calculated. .
(5)扇区航空器平均延误时间(5) Average delay time of aircraft in the sector
在管制扇区单位时间内所管辖的航空器中，航行时间超出了正常范围的航空器定义为延误航空器，航行时间超出正常范围的部分定义为延误时间。设扇区航空器延误时间为Delaysec，管制扇区单位时间内航空器架次数为n，扇区航空器的平均延误时间为Davgsec，则Davgsec＝Delaysec/n。系统引接综合航迹数据，对每架航空器在管制扇区中的实际飞行时间与经验飞行时间进行对比，若实际飞行时间大于经验飞行时间，则视为延误航空器，并计算得到扇区航空器平均延误时间。Among the aircraft under the jurisdiction of the control sector unit time, the aircraft whose flight time exceeds the normal range is defined as the delayed aircraft, and the part of the flight time which exceeds the normal range is defined as the delayed time. Let the delay time of aircraft in the sector be Delaysec , the number of aircraft sorties per unit time in the control sector be n, and the average delay time of aircraft in the sector be Davgsec , then Davgsec = Delaysec /n. The system imports the comprehensive track data, and compares the actual flight time of each aircraft in the control sector with the experienced flight time. If the actual flight time is greater than the experienced flight time, it is regarded as a delayed aircraft, and the average delay of aircraft in the sector is calculated. time.
管制员工作负荷标志指标采集Controller Workload Indicator Collection
管制员为完成管制任务需承受身体上和精神上的压力，这些压力可以转化为时间上的消耗，通过时间消耗来缓解承受到的压力和完成客观任务的要求，这个时间消耗的长短就是管制员工作负荷的大小。在可测计的管制员工作时间消耗中，陆空通话信道占用率是反映管制员工作负荷的标志指标。Controllers need to bear physical and mental pressure in order to complete control tasks. These pressures can be converted into time consumption. Time consumption can be used to relieve the pressure and complete the requirements of objective tasks. The length of this time consumption is the controller The size of the workload. Among the measurable working time consumption of controllers, the occupancy rate of land and air communication channels is a symbolic index reflecting the workload of controllers.
陆空通话信道占用率是指管制扇区单位时间内陆空通话时长占比。设管制扇区在单位时间T内共陆空通话m次，第i次陆空通话的时间长度为Ti，陆空通话信道占用率为Trate，则系统引接管制语音数据，分析对应扇区管制席位的管制员与飞行员通话开始时间和结束时间，然后将每段通话的时长进行累加，从而得到扇区陆空通话时长，进而计算得到陆空通话信道占用率。The land-air call channel occupancy rate refers to the proportion of land-air call time in the control sector per unit time. Assuming that the control sector has a total of m land-air calls within a unit time T, the time length of the i-th land-air call is Ti , and the land-air call channel occupancy rate is Trate , then The system introduces the control voice data, analyzes the start time and end time of the call between the controller and the pilot in the corresponding sector control seat, and then accumulates the duration of each call to obtain the sector land-air call duration, and then calculates the land-air call channel Occupancy rate.
管制扇区空中交通流态势指标预测Prediction of Situation Index of Air Traffic Flow in Control Sector
系统通过实时引接空管自动化系统综合航迹数据和转报系统民用航空飞行动态固定格式电报数据，获取航空器的飞行计划数据，包括航班号、起飞时间、起飞机场、落地时间、落地机场等信息，通过综合航迹获得已起飞航班在空中高度、速度和位置等信息，并通过4D航迹预测技术对未来时段航空器的位置信息进行推算。通过推算未来时段的航空器位置信息获得未来交通流态势指标的数据。其中，为实现基于4D航迹预测技术为实现精准预测，系统建立了航空器基础信息与运行性能数据库，航路航线信息数据库。The system obtains the flight plan data of the aircraft, including flight number, departure time, departure airport, landing time, landing airport, etc. , Obtain information such as the altitude, speed and position of the flight that has taken off in the air through the integrated track, and calculate the position information of the aircraft in the future period through the 4D track prediction technology. The data of future traffic flow situation indicators are obtained by calculating the aircraft position information in the future period. Among them, in order to achieve accurate prediction based on 4D track prediction technology, the system has established a database of basic aircraft information and operating performance, and a database of air route information.
实施例四Embodiment four
本实施方式公开一种管制员工作负荷预测方法，该方法可以选用实施例二的硬件平台来实现，其涉及的工作负荷预测相关指标的选取，管制员工作负荷预测样本数据和管制扇区空中交通流态势指标预测数据的采集可参考实施例三。This embodiment discloses a controller workload prediction method, which can be realized by selecting the hardware platform of the second embodiment, which involves the selection of workload prediction related indicators, controller workload prediction sample data and control sector air traffic For the collection of flow situation index prediction data, reference may be made to the third embodiment.
本实施方式同时采用多重线性回归和多重非线性回归模型，从两者中选择检测误差最小的模型作为最终的预测模型。In this embodiment, multiple linear regression and multiple nonlinear regression models are used simultaneously, and the model with the smallest detection error is selected from the two as the final prediction model.
(1)多重线性回归，是利用线性函数来拟合多个自变量Xi(i＝1,2,…,n)和单个因变量Y的关系，从而确定多重线性回归模型的参数bi(i＝0,1,2,…,n)，回归至原假设方程中，通过回归方程来检测因变量的趋势。多重线性回归模型的一般形式为：(1) Multiple linear regression is to use a linear function to fit the relationship between multiple independent variables Xi (i =1,2,...,n) and a single dependent variable Y, so as to determine the parameters bi of the multiple linear regression model ( i=0,1,2,...,n), return to the null hypothesis equation, and detect the trend of the dependent variable through the regression equation. The general form of a multiple linear regression model is:
Y＝b0+b1X1+b2X2+…+biXi+…+bnXn+μ(式4.1)Y＝b0 +b1 X1 +b2 X2 +…+bi Xi +…+bn Xn +μ (Formula 4.1)
其中，μ为除了n个自变量对因变量Y的影响之外的随机误差，服从正态分布。Among them, μ is the random error except the influence of n independent variables on the dependent variable Y, which obeys the normal distribution.
假设统计样本有m组统计资料，则多重线性回归模型的矩阵形式可以表示为：Assuming that the statistical samples have m groups of statistical data, the matrix form of the multiple linear regression model can be expressed as:
Y＝XB+U(式4.2)Y=XB+U (Formula 4.2)
其中，in,
(式4.3) (Formula 4.3)
(2)多重非线性回归，则是假定自变量(预测指标)和因变量(管制员工作负荷)之间呈现非线性关系，多重非线性模型一般可以表示为：(2) Multiple nonlinear regression assumes that there is a nonlinear relationship between the independent variable (predictor) and the dependent variable (controller workload). The multiple nonlinear model can generally be expressed as:
Y＝f[(b1,b2,…,bk)；X1,X2,…,Xn](式4.4)Y=f[(b1 ,b2 ,…,bk ); X1 ,X2 ,…,Xn ] (Formula 4.4)
其中非线性回归函数可以根据样本数据特征，采用二次函数、幂函数、指数函数、双曲线函数等形式。本实施方式以二次函数进行举例说明：Among them, the nonlinear regression function can adopt the form of quadratic function, power function, exponential function, hyperbolic function, etc. according to the characteristics of the sample data. This embodiment is illustrated with a quadratic function:
多重回归模型的参数bi估计出来后，即求出样本回归函数后，还需进一步对该样本回归函数进行统计检验，包括拟合度检验、显著性检验，以及参数的置信区间估计等，然后计算检测误差，最终选择误差小的模型作为最终的预测模型。After the parameter bi of the multiple regression model is estimated, that is, after the sample regression function is obtained, further statistical testing of the sample regression function is required, including fitting test, significance test, and parameter confidence interval estimation, etc., and then Calculate the detection error, and finally select the model with the smallest error as the final prediction model.
根据各模型返回的可决系数R2值、F检验、t检验，分别验证并比较两种回归模型的拟合度、显著性，在模型拟合度较高、显著性明显的基础上，计算两种回归模型的检测误差，并选取误差最小的一种模型，作为扇区运行性能综合检测的多重回归模型。According to the coefficient of determination R2 value, F test and t test returned by each model, respectively verify and compare the fitting degree and significance of thetwo regression models, and calculate the The detection error of the two regression models, and the model with the smallest error is selected as the multiple regression model for the comprehensive detection of sector operating performance.
基于多重回归的管制员工作负荷预测算法主要包括四部分，即回归模型的构建、回归模型的比选、管制员工作负荷预测以及管制员工作负荷响应告警。参见图9，具体算法步骤为：The controller workload prediction algorithm based on multiple regression mainly includes four parts, namely, the construction of the regression model, the comparison and selection of the regression model, the controller workload prediction and the controller workload response alarm. Referring to Figure 9, the specific algorithm steps are:
步骤1：选取变量Step 1: Select variables
参考实施例三，根据M组以小时为时长的样本输入数据，得到前文所述15个指标的输入值。同时，以管制员陆空通话信道占用率作为管制员工作负荷指标Y。得到的样本指标数据示例如下所示：Referring to Example 3, the input values of the 15 indicators mentioned above are obtained according to the input data of M groups of samples with a duration of hours. At the same time, the controller's workload index Y is taken as the controller's land-air communication channel occupancy rate. An example of the resulting sample metric data is shown below:
表1管制员工作负荷预测指标样本数据示例Table 1 Sample data example of controller workload prediction index
其中，自变量X＝{Xi,i＝1,2,…,15}为管制扇区空中交通流态势指标，共计15项。将表1的X1～X15的1～M组数据和Y的M组数据分别代入公式4.3、4.4。Among them, the independent variable X={Xi ,i=1,2,...,15} is the air traffic flow situation index in the control sector, and there are 15 items in total. Substitute the 1~M groups of data of X1 to X15 in Table 1 and the M group of data of Y into formulas 4.3 and 4.4 respectively.
其中，扇区通行性检测指标为{X1,X2,X3,X4}，分别表示扇区流量、扇区航行里程、扇区航行时间和扇区交通流密度；扇区复杂性检测指标为{X5,X6,X7,X8}，分别表示扇区航空器爬升次数、扇区航空器下降次数、扇区航空器改速次数、扇区航空器改航次数；扇区安全性检测指标为{X9,X10}，分别表示扇区短期冲突告警频率和扇区最低安全高度告警频率；扇区经济性检测指标为{X11,X12,X13,X14,X15}，分别表示扇区饱和度、扇区排队长度、扇区航空器延误架次率、扇区航空器延误时间、扇区航空器平均延误时间。Among them, the sector trafficability detection index is {X1 ,X2 ,X3 ,X4 }, respectively representing sector flow, sector mileage, sector voyage time and sector traffic flow density; sector complexity detection The indicators are {X5 , X6 , X7 , X8 }, respectively representing the number of climbs of aircraft in the sector, the number of descents of aircraft in the sector, the number of speed changes of aircraft in the sector, and the number of diversions of aircraft in the sector; the safety detection indicators of the sector is {X9 ,X10 }, which respectively represent the sector short-term conflict warning frequency and the sector minimum safety altitude warning frequency; the sector economy detection index is {X11 ,X12 ,X13 ,X14 ,X15 }, Respectively represent sector saturation, sector queuing length, sector aircraft delay rate, sector aircraft delay time, and sector aircraft average delay time.
步骤2：数据处理Step 2: Data Processing
考虑到不同指标间存在量纲不同以及数量级差异，为方便模型的回归分析，需要对指标数据进行标准化转换。Considering that there are different dimensions and orders of magnitude between different indicators, in order to facilitate the regression analysis of the model, it is necessary to standardize the conversion of the indicator data.
令xij、x′ij分别表示第i个样本的原始数据和经过标准化转换后的数据，sj分别表示第j(j＝1,2,…,15)个指标数据的均值和方差，则：Let xij , x′ij respectively denote the original data of the i-th sample and the data after standardized transformation, sj respectively represent the mean and variance of the jth (j=1,2,…,15) index data, then:
(式4.6) (Formula 4.6)
将标准化转换之后的数据x′ij，作为回归分析的输入数据。The data x′ij after standardized transformation is used as the input data of the regression analysis.
步骤3：构建回归模型Step 3: Build the regression model
参考实施例二、三，分别构建多重线性回归模型和多重非线性回归模型，其中，非线性回归模型选用二次函数的形式。通过对样本数据进行拟合，得到两类函数的参数估计值和样本输出值其中代表式4.4的b0～bn或式4.5的b0～b2n的估计值。Referring to Examples 2 and 3, a multiple linear regression model and a multiple nonlinear regression model were respectively constructed, wherein the nonlinear regression model was in the form of a quadratic function. By fitting the sample data, the parameter estimates of the two types of functions are obtained and sample output values in Represents the estimated value of b0 to bn in Formula 4.4 or b0 to b2n in Formula 4.5.
步骤4：检验回归模型Step 4: Test the regression model
根据各模型返回的可决系数R2值、F检验、t检验，分别验证并比较两种回归模型的拟合度、显著性，在模型拟合度较高、显著性明显的基础上，计算两种回归模型的检测误差，并选取误差最小的一种模型，作为管制员工作负荷预测的多重回归模型。According to the coefficient of determination R2 value, F test and t test returned by each model, respectively verify and compare the fitting degree and significance of thetwo regression models, and calculate the The detection errors of the two regression models, and the model with the smallest error is selected as the multiple regression model for controller workload prediction.
步骤5：回归模型结果输出Step 5: Regression model result output
根据N组样本数据得到的15个指标的均值方差sj，将管制扇区空中交通流态势指标预测数据作为输入数据，并进行标准化转换，为处理后的输入数据。进行标准化处理之后，将导入到管制员工作负荷预测回归模型中，得到管制员工作负荷指数的预测结果。The average value of 15 indicators obtained from the sample data of N groups Variance sj , will control sector air traffic flow situation index forecast data As input data, and normalized transformation, is the processed input data. After normalization, the Import it into the controller workload prediction regression model to get the prediction result of the controller workload index.
步骤6：管制员工作负荷响应告警Step 6: Controller Workload Response to Alerts
根据管制员工作负荷的预测结果，参照设定的管制员工作负荷响应告警标准，对达到告警标准的，由系统产生告警。According to the prediction result of the controller's workload, refer to the set controller's workload response alarm standard, and if the alarm standard is reached, the system will generate an alarm.
根据上述算法流程，采集成都ACC01扇区相关指标数据共计400组，分别采用线性函数和非线性函数(二次函数)对样本数据进行拟合，拟合计算得到两类函数的R2、p值，以及平均误差、最大误差、最小误差等拟合性能数据。对基于多重线性回归模型和非线性回归模型的管制员工作负荷预测模型分别比较拟合效果。结论如下：According to the above algorithm flow, a total of 400 groups of related index data in Chengdu ACC01 sector were collected, and linear functions and nonlinear functions (quadratic functions) were used to fit the sample data respectively, and the R2 and p values of the two types of functions were obtained from the fitting calculation , and fitting performance data such as average error, maximum error, and minimum error. The fitting effects of the controller workload prediction models based on the multiple linear regression model and the nonlinear regression model were compared respectively. conclusion as below:
表2多重回归拟合效果对比Table 2 Comparison of multiple regression fitting effects
根据上表，本实施方式的非线性函数的拟合度、显著性和误差等指标都略优于线性函数。因此，此处选取非线性函数，作为管制员工作负荷的预测模型。该模型的拟合效果图和预测误差图如图10、11所示：According to the above table, the fitting degree, significance, error and other indicators of the nonlinear function in this embodiment are slightly better than the linear function. Therefore, a nonlinear function is selected here as a predictive model of controller workload. The fitting effect diagram and prediction error diagram of the model are shown in Figures 10 and 11:
综上，基于多重非线性回归的管制员工作负荷预测模型为：In summary, the controller workload prediction model based on multiple nonlinear regression is:
(式4.7)(Formula 4.7)
根据式4.7，对管制员工作负荷进行预测。根据管制扇区空中交通流态势预测结果，获取未来5个时段的交通流态势指标数据。经过标准化处理之后，带入式4.7中，计算得到未来5个时段的管制员工作负荷预测结果，如下表所示。According to Equation 4.7, the controller workload is predicted. According to the prediction results of air traffic flow situation in the control sector, the traffic flow situation index data of the next five periods are obtained. After standardized processing, it is brought into Equation 4.7 to calculate the predicted results of controller workload in the next five time periods, as shown in the table below.
表3管制员工作负荷预测实例分析Table 3 Example analysis of controller workload forecast
根据管制员工作负荷告警标准，对未来时段管制员的工作负荷达到告警标准的，进行相应告警。According to the controller's workload alarm standard, if the controller's workload in the future period reaches the alarm standard, a corresponding alarm will be issued.
本预测方法以及相应的系统在投入运行后，需要进行相应的管理。推荐的系统管理有以下几条：After the prediction method and the corresponding system are put into operation, corresponding management is required. Recommended system management is the following:
①管理使用用户权限，为每位用户分配用户名和权限，保证数据的安全性，防止数据外泄。① Manage and use user permissions, assign user names and permissions to each user, ensure data security, and prevent data leakage.
②每位用户对应0到多个角色，每个角色可以由管理人员灵活分配访问和操作的权限。②Each user corresponds to 0 to multiple roles, and each role can be flexibly assigned access and operation permissions by the management personnel.
③设置系统运行必须的参数，包括地图参数、电报处理与雷达数据处理参数、长期班期时刻表、系统显示参数设置、其他需要设置的参数。③Set the parameters necessary for system operation, including map parameters, telegram processing and radar data processing parameters, long-term shift schedule, system display parameter settings, and other parameters that need to be set.
④提供日志管理功能，负责纪录系统的操作，保留重要数据的操作信息。包括：日志纪录模块、日志查询模块、日志备份与清除模块。④Provide the log management function, responsible for recording the operation of the system, and retaining the operation information of important data. Including: log recording module, log query module, log backup and clearing module.
⑤提供参数配置功能，为系统维护人员提供参数配置的工具。⑤Provide parameter configuration function and provide parameter configuration tools for system maintenance personnel.
⑥提供数据导入导出功能。⑥Provide data import and export functions.
实现本发明预测方法和系统的建议配置如下：A suggested configuration for implementing the prediction method and system of the present invention is as follows:
实施例五Embodiment five
本实施方式的管制员工作负荷预测方法，包括步骤：The controller workload prediction method of the present embodiment comprises steps:
根据管制员工作负荷预测相关指标和管制员工作负荷预测样本数据构建多重回归模型。根据M组以小时为时长的样本输入数据，得到管制员工作负荷预测相关指标的输入值；以管制员陆空通话信道占用率作为管制员工作负荷指标，得到管制员工作负荷预测样本数据。A multiple regression model is constructed based on the relevant indicators of controller workload prediction and the sample data of controller workload prediction. According to the hour-long sample input data of group M, the input value of the controller workload prediction related indicators is obtained; the controller workload prediction sample data is obtained by taking the controller's land-air communication channel occupancy rate as the controller workload indicator.
将管制扇区空中交通流态势指标预测数据导入多重回归模型。Import the forecast data of air traffic flow situation indicators in the control sector into the multiple regression model.
考虑到不同指标间存在量纲不同以及数量级差异，在构建多重回归模型之前，先对输入的管制员工作负荷预测相关指标和管制员工作负荷预测样本数据进行标准化转换；相应的，对导入多重回归模型的管制扇区空中交通流态势指标预测数据先进行标准化转换；这样可以方便模型的回归分析。Considering that there are differences in dimensions and orders of magnitude among different indicators, before constructing the multiple regression model, the input controller workload prediction related indicators and controller workload prediction sample data are first standardized and converted; correspondingly, importing multiple regression The forecast data of the air traffic flow situation index in the control sector of the model is first standardized and transformed; this can facilitate the regression analysis of the model.
多重回归模型包括多重线性回归模型和多重非线性回归模型，其中，非线性回归模型选用二次函数。模型函数参考上述实施例。The multiple regression model includes a multiple linear regression model and a multiple nonlinear regression model, wherein the nonlinear regression model uses a quadratic function. For the model function, refer to the above-mentioned embodiments.
分别通过多重线性回归模型和多重非线性回归模型对管制员工作负荷预测样本数据进行拟合，得到两组样本回归函数，对两组样本回归函数进行统计检验，所述统计检验步骤包括拟合度和显著性检验，在拟合度和显著性超过预设值时，再计算检测误差。Fitting the controller workload prediction sample data through multiple linear regression models and multiple non-linear regression models respectively to obtain two sets of sample regression functions, and performing a statistical test on the two sets of sample regression functions, the statistical test steps include the degree of fitting And significance test, when the fitting degree and significance exceed the preset value, then calculate the detection error.
将管制扇区空中交通流态势指标预测数据导入检测误差最小的一种多重回归模型，得到预测结果。The forecast data of the air traffic flow situation index in the control sector is imported into a multiple regression model with the smallest detection error, and the forecast result is obtained.
当预测结果超出阈值，管制员工作负荷响应告警。When the predicted result exceeds the threshold, the controller workload responds to the alarm.
所述管制扇区空中交通流态势指标包括扇区运行通行性指标、扇区运行复杂性指标、扇区运行安全性指标和扇区运行经济性指标；扇区通行性检测指标分别包括扇区流量、扇区航行里程、扇区航行时间和扇区交通流密度；扇区复杂性检测指标包括扇区航空器爬升次数、扇区航空器下降次数、扇区航空器改速次数、扇区航空器改航次数；扇区安全性检测指标包括扇区短期冲突告警频率和扇区最低安全高度告警频率；扇区经济性检测指标包括扇区饱和度、扇区排队长度、扇区航空器延误架次率、扇区航空器延误时间、扇区航空器平均延误时间。The air traffic flow situation indicators in the control sector include the sector operation passability index, the sector operation complexity index, the sector operation safety index and the sector operation economy index; the sector passability detection indexes respectively include the sector flow , sector flight mileage, sector flight time, and sector traffic flow density; sector complexity detection indicators include sector aircraft climb times, sector aircraft descent times, sector aircraft speed changes, and sector aircraft diversion times; Sector safety detection indicators include sector short-term conflict alarm frequency and sector minimum safety altitude alarm frequency; sector economy detection indicators include sector saturation, sector queue length, sector aircraft delay rate, sector aircraft delay rate Time, sector average delay time of aircraft.
如图12所示，本实施方式还公开一种管制员工作负荷的预测系统。其包括运行指标检测数据库，与管制扇区运行指标检测数据库耦合的数据引接装置和指标采集装置。As shown in FIG. 12 , this embodiment also discloses a forecasting system for controller workload. It includes an operation index detection database, a data connection device and an index collection device coupled with the control sector operation index detection database.
数据引接装置包括分别与管制扇区运行指标检测数据库耦合的电报数据接口、综合航迹数据接口和管制语音数据接口；指标采集装置用于采集管制扇区空中交通流态势指标，管制扇区空中交通流态势指标包括扇区运行通行性指标、扇区运行复杂性指标、扇区运行安全性指标和扇区运行经济性指标。The data connection device includes a telegraph data interface, an integrated track data interface and a control voice data interface respectively coupled with the control sector operation index detection database; the index collection device is used to collect the control sector air traffic flow situation indicators, control sector air traffic The flow situation index includes sector operation passability index, sector operation complexity index, sector operation safety index and sector operation economy index.
构件模块：选取管制扇区空中交通流态势指标，将相关指标对应的管制员工作负荷预测样本数据代入多重线性回归模型和多重非线性回归模型中进行拟合；得到多重线性回归模型和多重非线性回归模型的参数估计值；通过统计检验，计算检测误差，确定管制员工作负荷预测多重回归模型；Component module: Select the air traffic flow situation indicators in the control sector, and substitute the controller workload prediction sample data corresponding to the relevant indicators into the multiple linear regression model and the multiple nonlinear regression model for fitting; get the multiple linear regression model and the multiple nonlinear regression model Estimated values of the parameters of the regression model; through statistical testing, calculation of detection errors, and determination of multiple regression models for controller workload prediction;
预测模块：将管制扇区空中交通流态势指标预测数据导入管制员工作负荷预测多重回归模型，得到管制员工作负荷的预测结果。Prediction module: Import the forecast data of air traffic flow situation indicators in the control sector into the multiple regression model of controller workload prediction to obtain the prediction result of controller workload.
标准化转换模块：用于对样本数据以及管制扇区空中交通流态势指标实时数据进行标准化转换；Standardized conversion module: used for standardized conversion of sample data and real-time data of air traffic flow situation indicators in control sectors;
报警模块：当预测结果超出阈值，管制员工作负荷响应告警。Alarm module: When the predicted result exceeds the threshold, the controller workload responds to the alarm.
构件模块从管制扇区运行指标检测数据库中读取管制员工作负荷预测相关指标和管制员工作负荷预测样本数据；预测模块从管制扇区运行指标检测数据库中读取管制扇区空中交通流态势指标预测数据。The component module reads the controller workload prediction related indicators and the controller workload prediction sample data from the control sector operation index detection database; the prediction module reads the control sector air traffic flow situation indicators from the control sector operation index detection database forecast data.
所述指标采集装置用于采集管制扇区空中交通流态势指标，所述管制扇区空中交通流态势指标包括扇区运行通行性指标、扇区运行复杂性指标、扇区运行安全性指标和扇区运行经济性指标；扇区通行性检测指标分别包括扇区流量、扇区航行里程、扇区航行时间和扇区交通流密度；扇区复杂性检测指标包括扇区航空器爬升次数、扇区航空器下降次数、扇区航空器改速次数、扇区航空器改航次数；扇区安全性检测指标包括扇区短期冲突告警频率和扇区最低安全高度告警频率；扇区经济性检测指标包括扇区饱和度、扇区排队长度、扇区航空器延误架次率、扇区航空器延误时间、扇区航空器平均延误时间.The index collection device is used to collect the air traffic flow situation index of the control sector, and the air traffic flow situation index of the control sector includes a sector operation passability index, a sector operation complexity index, a sector operation safety index and a sector operation index. Zone operation economic indicators; sector traffic detection indicators include sector flow, sector mileage, sector flight time and sector traffic flow density; sector complexity detection indicators include sector aircraft climb times, sector aircraft The number of descents, the number of aircraft speed changes in the sector, and the number of aircraft diversions in the sector; the sector safety detection indicators include the sector short-term conflict alarm frequency and the sector minimum safe altitude alarm frequency; the sector economy detection indicators include sector saturation , sector queuing length, sector aircraft delay rate, sector aircraft delay time, and sector aircraft average delay time.
以上内容是结合具体的优选实施方式对本发明所作的进一步详细说明，不能认定本发明的具体实施只局限于这些说明。对于本发明所属技术领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干简单推演或替换，都应当视为属于本发明的保护范围。The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be assumed that the specific implementation of the present invention is limited to these descriptions. For those of ordinary skill in the technical field of the present invention, without departing from the concept of the present invention, some simple deduction or replacement can be made, which should be regarded as belonging to the protection scope of the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645215.3ACN105205565A (en) | 2015-09-30 | 2015-09-30 | Controller workload prediction method and system based on multiple regression model |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510645215.3ACN105205565A (en) | 2015-09-30 | 2015-09-30 | Controller workload prediction method and system based on multiple regression model |
| Publication Number | Publication Date |
|---|---|
| CN105205565Atrue CN105205565A (en) | 2015-12-30 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510645215.3APendingCN105205565A (en) | 2015-09-30 | 2015-09-30 | Controller workload prediction method and system based on multiple regression model |
| Country | Link |
|---|---|
| CN (1) | CN105205565A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944472A (en)* | 2017-11-03 | 2018-04-20 | 北京航空航天大学 | A kind of airspace operation situation computational methods based on transfer learning |
| CN108171379A (en)* | 2017-12-28 | 2018-06-15 | 无锡英臻科技有限公司 | A kind of electro-load forecast method |
| CN111091244A (en)* | 2019-12-16 | 2020-05-01 | 武汉材料保护研究所有限公司 | Engine lubricating oil change period prediction method |
| CN111126685A (en)* | 2019-12-16 | 2020-05-08 | 武汉材料保护研究所有限公司 | Method for establishing engine lubricating oil quality prediction model |
| CN111968414A (en)* | 2020-08-26 | 2020-11-20 | 成都民航空管科技发展有限公司 | 4D trajectory prediction method and device based on big data and AI and electronic equipment |
| CN114530059A (en)* | 2022-01-14 | 2022-05-24 | 南京航空航天大学 | Dynamic configuration method and system for multi-sector monitoring seat |
| CN116313079A (en)* | 2023-02-22 | 2023-06-23 | 上海交通大学 | A method and system for evaluating the contribution rate of functional channels to pilot workload |
| CN116504105A (en)* | 2023-05-22 | 2023-07-28 | 四川大学 | An air traffic control command human-machine collaborative safety monitoring system and method |
| CN117978916A (en)* | 2024-04-01 | 2024-05-03 | 中国民用航空飞行学院 | A method and device for predicting traffic load of controllers |
| CN118762560A (en)* | 2024-06-14 | 2024-10-11 | 中国民航大学 | A method and system for evaluating airspace capacity of air route network |
| Title |
|---|
| 何元清 等: "《大学计算机基础》", 31 August 2013* |
| 周品: "《MATLAB概率与数理统计》", 30 November 2012* |
| 李鸿吉: "《Visual Basic 6.0数理统计实用算法》", 30 September 2003, 科学出版社* |
| 袁霄 等: ""基于扇区动态复杂性因素的航空管制员工作负荷计算"", 《安全与环境学报》* |
| 郭少英 等: "《市场调研与分析技术》", 31 October 2008* |
| 麦好: "《机器学习实践指南 案例应用解析》", 30 April 2014* |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107944472B (en)* | 2017-11-03 | 2019-05-28 | 北京航空航天大学 | A kind of airspace operation situation calculation method based on transfer learning |
| CN107944472A (en)* | 2017-11-03 | 2018-04-20 | 北京航空航天大学 | A kind of airspace operation situation computational methods based on transfer learning |
| CN108171379A (en)* | 2017-12-28 | 2018-06-15 | 无锡英臻科技有限公司 | A kind of electro-load forecast method |
| CN108171379B (en)* | 2017-12-28 | 2021-12-17 | 无锡英臻科技有限公司 | Power load prediction method |
| CN111091244B (en)* | 2019-12-16 | 2023-02-03 | 武汉材料保护研究所有限公司 | A method for predicting the oil change interval of engine lubricating oil |
| CN111091244A (en)* | 2019-12-16 | 2020-05-01 | 武汉材料保护研究所有限公司 | Engine lubricating oil change period prediction method |
| CN111126685A (en)* | 2019-12-16 | 2020-05-08 | 武汉材料保护研究所有限公司 | Method for establishing engine lubricating oil quality prediction model |
| CN111126685B (en)* | 2019-12-16 | 2023-02-03 | 武汉材料保护研究所有限公司 | Method for establishing engine lubricating oil quality prediction model |
| CN111968414A (en)* | 2020-08-26 | 2020-11-20 | 成都民航空管科技发展有限公司 | 4D trajectory prediction method and device based on big data and AI and electronic equipment |
| CN111968414B (en)* | 2020-08-26 | 2022-08-05 | 成都民航空管科技发展有限公司 | 4D trajectory prediction method, device and electronic device based on big data and AI |
| CN114530059A (en)* | 2022-01-14 | 2022-05-24 | 南京航空航天大学 | Dynamic configuration method and system for multi-sector monitoring seat |
| CN114530059B (en)* | 2022-01-14 | 2023-03-10 | 南京航空航天大学 | A dynamic configuration method and system for multi-sector monitoring seats |
| CN116313079A (en)* | 2023-02-22 | 2023-06-23 | 上海交通大学 | A method and system for evaluating the contribution rate of functional channels to pilot workload |
| CN116504105A (en)* | 2023-05-22 | 2023-07-28 | 四川大学 | An air traffic control command human-machine collaborative safety monitoring system and method |
| CN116504105B (en)* | 2023-05-22 | 2025-07-04 | 四川大学 | A human-machine collaborative safety monitoring system and method for air traffic control commander |
| CN117978916A (en)* | 2024-04-01 | 2024-05-03 | 中国民用航空飞行学院 | A method and device for predicting traffic load of controllers |
| CN117978916B (en)* | 2024-04-01 | 2024-05-28 | 中国民用航空飞行学院 | A method and device for predicting traffic load of controllers |
| US12431031B1 (en)* | 2024-04-01 | 2025-09-30 | Civil Aviation Flight University Of China | Method and device for predicting call load of controller |
| US20250308395A1 (en)* | 2024-04-01 | 2025-10-02 | Civil Aviation Flight University Of China | Method and device for predicting call load of controller |
| CN118762560A (en)* | 2024-06-14 | 2024-10-11 | 中国民航大学 | A method and system for evaluating airspace capacity of air route network |
| Publication | Publication Date | Title |
|---|---|---|
| CN105205565A (en) | Controller workload prediction method and system based on multiple regression model | |
| CN105225539B (en) | The method and system of sector runnability composite index based on principal component analysis | |
| CN105261240B (en) | A kind of sector runnability method for comprehensive detection and system based on cluster analysis | |
| CN105225193A (en) | A kind of method and system of the sector runnability aggregative index based on multiple regression model | |
| CN104835354A (en) | Control load management system and controller workload evaluation method | |
| CN210924883U (en) | Bridge structure health monitoring system | |
| Burns et al. | An empirically benchmarked human reliability analysis of general aviation | |
| CN103903101A (en) | General aviation multi-source information supervisory platform and method | |
| CN119761832B (en) | Airport security management method and system | |
| CN105160201A (en) | Genetic algorithm back propagation (GABP) neural network based controller workload prediction method and system | |
| CN105225007A (en) | A kind of sector runnability method for comprehensive detection based on GABP neural network and system | |
| Dai et al. | Modeling go-around occurrence using principal component logistic regression | |
| CN118533759A (en) | A water quality index prediction system based on surface water | |
| CN101515409A (en) | Method for confirming airspace capacity through regression analysis on control workload | |
| CN102842075A (en) | Method for determining sector capacity according to space-time distribution characteristic of workload of controllers | |
| CN104361088A (en) | Congestion data processing method based on real-time weight analysis in SCADA (supervisory control and data acquisition) system | |
| CN105206115B (en) | A kind of air traffic control sector traffic capacity detection method based on principal component analysis | |
| CN117829599A (en) | Unmanned aerial vehicle take-off and landing security risk assessment system and method based on multi-mode data fusion | |
| CN105118333B (en) | A kind of air traffic control analog simulation method for detecting abnormality and device based on multiple regression model | |
| Wanke et al. | Modeling traffic prediction uncertainty for traffic management decision support | |
| Wang et al. | Pilot workload measurement model based on task complexity analysis | |
| CN110989042A (en) | Intelligent prediction method for highway fog-clustering risk | |
| CN116258381A (en) | Quantitative evaluation method and device for operation command work | |
| Borjalilu et al. | Entropy-based model for aerodromes safety risk assessment to implement safety management systems | |
| CN204856924U (en) | Control load management system |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication | Application publication date:20151230 |