Disclosure of Invention
The invention aims to provide an intelligent monitoring method for industrial equipment based on visual identification and big data analysis, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
An intelligent monitoring method of industrial equipment based on visual identification and big data analysis comprises the following steps:
s100, retrieving operation attribute data of production equipment in a corresponding production line in an industrial production area, and carrying out data overall processing on the equipment numbers;
S200, acquiring a real-time operation period set of each device by extracting the operation time of each device and dividing the period, respectively analyzing the operation performance state of the device in each period, and carrying out comprehensive operation performance state analysis by combining the period length;
S300, respectively constructing attribute data development curves of equipment in each period and mapping curves of equipment running performance states in each period by combining a plane curve fitting model;
S400, evaluating the real-time running state of the equipment by combining the attribute performance association analysis results of the equipment in each period.
S100, the operation state data of each production device in the corresponding production line in the industrial production area is called, and the specific steps of carrying out data overall processing on each device number are as follows:
S101, carrying out equipment image data acquisition on production equipment by combining industrial production area monitoring sensing equipment, carrying out three-dimensional simulation on each production equipment according to the production area image data and a simulation large model, constructing a simulated production equipment scene, and respectively giving area numbers to each equipment;
s102, collecting operation attribute data of each device through the central control sensing device, and transmitting the collected data to the central control management end after database integration processing.
The industrial production area monitoring sensing equipment is a monitoring camera, and a monitoring network is constructed to collect images of all production equipment in a production area by networking the monitoring camera of the production area, wherein the central control sensing equipment is associated with a central control management end and is used for collecting operation attribute data of all equipment, and the operation attribute data are operation process data of the equipment, wherein the operation process data of the equipment comprise equipment operation temperature, humidity, pressure, rotating speed and the like;
The step S200 is to extract the running time of each device and divide the period to obtain a real-time running period set of each device, analyze the running performance state of the device in each period, and combine the period length to perform the comprehensive running performance state analysis, and the specific steps are as follows:
S201, inputting operation attribute data acquired by each device into a simulation port through a central control management end, and carrying out real-time synchronous data evolution by combining simulation devices to acquire diffraction operation state data corresponding to actual scene devices;
s202, taking the running time of the actual equipment corresponding to each simulation equipment, carrying out period division on the running time of each equipment through setting a monitoring period, constructing a running period set corresponding to each equipment, carrying out period analysis on the running performance state of the equipment in each period by combining the running period set of each equipment, respectively taking the running attribute data of the corresponding equipment in the corresponding period, analyzing the running performance of the equipment according to the running attribute data of the corresponding equipment in the period at the time point of the period in each period, wherein the running period division of the equipment adopts the same specification time scale, the period division is carried out, and the part of the equipment time which cannot be divided into a complete period is not included in the analysis step, wherein after the running time of the equipment which cannot be divided into the complete period is the running time, the running time of the redundant part is insufficient to divide one period, or the running time of the equipment is insufficient to divide one period, and then the part of the running time is not included in the data analysis, and the running time of the equipment is complemented in real time and then analyzed.
The specific steps of the running performance analysis of the equipment are as follows:
S202-1, sequentially positioning operation periods in the period set according to time sequence by calling an operation period set divided by the current real-time operation time of target equipment, calling operation attribute data of equipment at each time point in the corresponding period of the positioning period, and constructing an equipment operation attribute data matrix corresponding to the current positioning period;
S202-2, analyzing the performance factor scores of the operation data of the equipment at each time point according to the equipment operation attribute data acquired at the corresponding time point in the positioning period, wherein the calculation formula is as follows
;
The method comprises the steps of dividing a device with a corresponding number m into a number n, wherein Pf (T epsilon Tmn) is a performance factor score of running data at a corresponding time point T in the period of the number n divided by the device with the corresponding number m, rv is a performance correlation coefficient of the running attribute data with a corresponding v type, v is the running attribute data type number, Etv is the running attribute data with a v type at the moment T in the corresponding period, and alpha (v) is a performance factor parameter of the running attribute data with a corresponding v type;
S203-3, analyzing the comprehensive operation performance index of the current period by combining the performance factor scores of the equipment operation attribute data at each time point in the corresponding period, wherein the calculation formula is as follows
;
The PI (Tmn) is the comprehensive operation performance index of the n periods of the number divided by the equipment with the corresponding number m, and T is the corresponding period time length.
The method comprises the following specific steps of constructing attribute data development curves of equipment in each period and mapping curve construction of equipment running performance states in each period by combining a plane curve fitting model, and carrying out attribute performance influence correlation analysis on the corresponding attribute data development curves and equipment comprehensive running performance state curves in each period of comprehensive equipment:
S301, performing plane curve fitting on operation attribute data of equipment in each corresponding period and operation data performance factor score data of equipment in each corresponding period by using a plane curve fitting model respectively, and performing co-plane coordinate system mapping processing on various types of operation attribute data fitting curves and equipment operation data performance factor score data curves by constructing a co-scale time axis through plane mapping;
S302, according to the curve fitting mapping output result, carrying out periodic performance influence fluctuation analysis on the operation attribute data of the corresponding type of equipment and the performance factor score data of the operation data of the corresponding type of equipment in a coordinate system according to a time sequence.
Based on the corresponding period, the periodic performance influence fluctuation analysis is carried out on the operation attribute data of each type, the analysis is carried out by analyzing the difference condition between the fitting curve corresponding to the operation attribute data of each type and the performance factor score data curve of the operation data, and the calculation formula is as follows
;
Wherein Afv（Tmn) is the periodic performance influence fluctuation value of the corresponding v-type operation attribute data, te is the starting time point of the corresponding period, and the periodic performance influence fluctuation value of the corresponding type operation attribute data in the period is subjected to average calculation according to the periodic performance influence fluctuation value obtained by analysis of the corresponding type operation attribute data, wherein the calculation formula is that
;
Afave（Tmn) is the average value of the comprehensive periodic performance influence fluctuation of various types of operation attribute data in a period, and the difference part area is obtained by analyzing the difference part between each operation attribute data curve and the performance factor equal curve through integration and is analyzed by combining with the period scale, wherein the average value is the influence fluctuation value of the operation attribute data on the performance operation of the equipment.
Based on the analysis result of the periodic performance influence fluctuation value of the operation attribute data of each type in the period, the abnormal fluctuation condition of the operation attribute data in each period of the target equipment is analyzed, and the calculation formula is as follows
;
The method comprises the steps of obtaining operation attribute data in a period, wherein Api (Tmn) is a comprehensive abnormal fluctuation index of the operation attribute data in a corresponding period, PI (R) is a device health performance index, afv（Tmn）max and Afv（Tmn）min are maximum and minimum values of periodic performance influence fluctuation values of the operation attribute data in a corresponding v type, carrying out risk marking on the current period when the comprehensive abnormal fluctuation index of the operation attribute data in the period corresponding to the device is larger than a threshold value through presetting an abnormal fluctuation index threshold value of the operation attribute data of the device, and carrying out normal operation in the period when the comprehensive abnormal fluctuation index of the operation attribute data in the period is smaller than or equal to the threshold value.
In S400, the specific steps of evaluating the real-time running state of the device in combination with the analysis results of the attribute performance association of the device in each period are as follows:
According to the analysis result of the comprehensive abnormal fluctuation index of the operation attribute data of each device in the corresponding divided operation period, counting the abnormal period marked as risk, and analyzing the abnormal period proportion according to the statistical result, wherein the calculation formula is as follows
;
Wherein QT is the ratio of risk periods, and KT is the risk period.
And when the risk period ratio is smaller than the threshold value, carrying out real-time backup on the operation attribute data analysis of the target equipment, carrying out continuous period data acquisition and repeating the step of exception analysis.
Compared with the prior art, the method has the advantages that machine vision is adopted to replace manual detection to monitor the real-time state of production equipment, overall division processing is conducted on collected data through big data analysis, single-thread continuous data analysis is conducted through discretization on the running time of corresponding equipment, multi-thread discrete analysis is conducted on single-thread continuous data analysis, the performance abnormal state of the equipment is analyzed through real-time performance state of the analysis equipment and fluctuation influence degree of various types of attribute data on the equipment performance in different periods, risk division is conducted on the running period of the equipment through correlation analysis on the period abnormal fluctuation degree and performance index of the operation attribute data of the equipment, abnormal marking is conducted on the equipment according to the risk operation of the equipment, cluster abnormal management and control analysis can be conducted on the industrial production equipment in the industrial production field, accurate marking is conducted on the performance abnormal equipment through intelligent data correlation analysis processing, accurate positioning on the abnormal equipment is achieved, and the efficiency and accuracy of manual overhaul are effectively improved.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides the following technical solutions:
An intelligent monitoring method of industrial equipment based on visual identification and big data analysis comprises the following steps:
s100, retrieving operation attribute data of production equipment in a corresponding production line in an industrial production area, and carrying out data overall processing on the equipment numbers;
S200, acquiring a real-time operation period set of each device by extracting the operation time of each device and dividing the period, respectively analyzing the operation performance state of the device in each period, and carrying out comprehensive operation performance state analysis by combining the period length;
S300, respectively constructing attribute data development curves of equipment in each period and mapping curves of equipment running performance states in each period by combining a plane curve fitting model;
S400, evaluating the real-time running state of the equipment by combining the attribute performance association analysis results of the equipment in each period.
S100, the operation state data of each production device in the corresponding production line in the industrial production area is called, and the specific steps of carrying out data overall processing on each device number are as follows:
S101, carrying out equipment image data acquisition on production equipment by combining industrial production area monitoring sensing equipment, carrying out three-dimensional simulation on each production equipment according to the production area image data and a simulation large model, constructing a simulated production equipment scene, and respectively giving area numbers to each equipment;
s102, collecting operation attribute data of each device through the central control sensing device, and transmitting the collected data to the central control management end after database integration processing.
The industrial production area monitoring sensing equipment is a monitoring camera, and a monitoring network is constructed to collect images of all production equipment in a production area by networking the monitoring camera of the production area, wherein the central control sensing equipment is associated with a central control management end and is used for collecting operation attribute data of all equipment;
The step S200 is to extract the running time of each device and divide the period to obtain a real-time running period set of each device, analyze the running performance state of the device in each period, and combine the period length to perform the comprehensive running performance state analysis, and the specific steps are as follows:
S201, inputting operation attribute data acquired by each device into a simulation port through a central control management end, and carrying out real-time synchronous data evolution by combining simulation devices to acquire diffraction operation state data corresponding to actual scene devices;
S202, the running time of the actual equipment corresponding to each simulation equipment is called, the running time of each equipment is divided by setting a monitoring period, running period sets corresponding to the equipment are constructed, the running performance states of the equipment in each period are respectively analyzed by combining the running period sets of the equipment, the running attribute data of the corresponding equipment in the corresponding period are respectively called, and the running performance of the equipment is analyzed according to the running attribute data of the corresponding equipment in each period at the period time point.
The specific steps of the running performance analysis of the equipment are as follows:
S202-1, sequentially positioning operation periods in the period set according to time sequence by calling an operation period set divided by the current real-time operation time of target equipment, calling operation attribute data of equipment at each time point in the corresponding period of the positioning period, and constructing an equipment operation attribute data matrix corresponding to the current positioning period;
S202-2, analyzing the performance factor scores of the operation data of the equipment at each time point according to the equipment operation attribute data acquired at the corresponding time point in the positioning period, wherein the calculation formula is as follows
;
The method comprises the steps of dividing a device with a corresponding number m into a number n, wherein Pf (T epsilon Tmn) is a performance factor score of running data at a corresponding time point T in the period of the number n divided by the device with the corresponding number m, rv is a performance correlation coefficient of the running attribute data with a corresponding v type, v is the running attribute data type number, Etv is the running attribute data with a v type at the moment T in the corresponding period, and alpha (v) is a performance factor parameter of the running attribute data with a corresponding v type;
S203-3, analyzing the comprehensive operation performance index of the current period by combining the performance factor scores of the equipment operation attribute data at each time point in the corresponding period, wherein the calculation formula is as follows
;
The PI (Tmn) is the comprehensive operation performance index of the n periods of the number divided by the equipment with the corresponding number m, and T is the corresponding period time length.
The method comprises the following specific steps of constructing attribute data development curves of equipment in each period and mapping curve construction of equipment running performance states in each period by combining a plane curve fitting model, and carrying out attribute performance influence correlation analysis on the corresponding attribute data development curves and equipment comprehensive running performance state curves in each period of comprehensive equipment:
S301, performing plane curve fitting on operation attribute data of equipment in each corresponding period and operation data performance factor score data of equipment in each corresponding period by using a plane curve fitting model respectively, and performing co-plane coordinate system mapping processing on various types of operation attribute data fitting curves and equipment operation data performance factor score data curves by constructing a co-scale time axis through plane mapping;
S302, according to the curve fitting mapping output result, carrying out periodic performance influence fluctuation analysis on the operation attribute data of the corresponding type of equipment and the performance factor score data of the operation data of the corresponding type of equipment in a coordinate system according to a time sequence.
Based on the corresponding period, the periodic performance influence fluctuation analysis is carried out on the operation attribute data of each type, the analysis is carried out by analyzing the difference condition between the fitting curve corresponding to the operation attribute data of each type and the performance factor score data curve of the operation data, and the calculation formula is as follows
;
Wherein Afv（Tmn) is the periodic performance influence fluctuation value of the corresponding v-type operation attribute data, te is the starting time point of the corresponding period, and the periodic performance influence fluctuation value of the corresponding type operation attribute data in the period is subjected to average calculation according to the periodic performance influence fluctuation value obtained by analysis of the corresponding type operation attribute data, wherein the calculation formula is that
;
Afave（Tmn) is the average value of the comprehensive periodic performance influence of various types of operation attribute data in the period.
Based on the analysis result of the periodic performance influence fluctuation value of the operation attribute data of each type in the period, the abnormal fluctuation condition of the operation attribute data in each period of the target equipment is analyzed, and the calculation formula is as follows
;
The risk marking method comprises the steps of obtaining a comprehensive abnormal fluctuation index of operation attribute data in a corresponding period, wherein Api (Tmn) is the comprehensive abnormal fluctuation index of the operation attribute data in the corresponding period, PI (R) is the equipment health performance index, afv（Tmn）max and Afv（Tmn）min are the maximum value and the minimum value of the periodic performance influence fluctuation value of the operation attribute data in the corresponding v type, and risk marking the current period when the comprehensive abnormal fluctuation index of the operation attribute data in the corresponding equipment period in a certain period is larger than the threshold value through presetting the abnormal fluctuation index threshold value of the operation attribute data of the equipment.
In S400, the specific steps of evaluating the real-time running state of the device in combination with the analysis results of the attribute performance association of the device in each period are as follows:
According to the analysis result of the comprehensive abnormal fluctuation index of the operation attribute data of each device in the corresponding divided operation period, counting the abnormal period marked as risk, and analyzing the abnormal period proportion according to the statistical result, wherein the calculation formula is as follows
;
Wherein QT is the ratio of risk periods, and KT is the risk period.
According to the equipment risk period analysis data, a risk ratio threshold is set, and when the risk period ratio is greater than or equal to the threshold, performance abnormality marking is carried out on the target equipment;
in an embodiment:
The method comprises the steps of carrying out cluster monitoring on production equipment by a current industrial producer, carrying out equipment image data acquisition on the production equipment by combining industrial production area monitoring sensing equipment, carrying out three-dimensional simulation on each production equipment according to the production area image data and a simulation large model, constructing a simulated production equipment scene, respectively giving area numbers to each equipment, acquiring operation attribute data of each equipment by a central control sensing equipment, carrying out database integration processing on the acquired data, and then transmitting the acquired data to a central control management end, wherein the industrial production area monitoring sensing equipment is a monitoring camera, and carrying out networking connection on the monitoring camera of a production area to construct a monitoring network to carry out image acquisition on each production equipment in the production area;
The method comprises the steps of inputting operation attribute data acquired by each device into a simulation port through a central control management end, carrying out real-time synchronous data evolution by combining simulation devices to obtain diffraction operation state data corresponding to actual scene devices, calling actual device operation time corresponding to each simulation device, carrying out period division on the operation time of each device by setting a monitoring period, and constructing operation period sets corresponding to each device;
The method comprises the steps of sequentially positioning operation periods according to time sequence in a period set by calling an operation period set divided by the current real-time operation time of target equipment, calling operation attribute data of equipment at each time point in the corresponding period of the positioning period, constructing an equipment operation attribute data matrix corresponding to the current positioning period, analyzing operation data performance factor scores of equipment at each time point according to the equipment operation attribute data called at the corresponding time point in the positioning period, wherein a calculation formula is as follows
;
The comprehensive operation performance index of the current period is analyzed by combining the performance factor scores of the operation attribute data of the equipment at each time point in the corresponding period, and the calculation formula is as follows
;
Performing planar curve fitting on the operation attribute data of the equipment in each corresponding period and the operation data performance factor score data of the equipment in each corresponding period by using a planar curve fitting model, performing the same-plane coordinate system mapping processing on the fitting curve of the operation attribute data of each type and the performance factor score data curve of the operation data of the equipment by constructing a same-scale time axis through planar mapping;
based on the corresponding period, the periodic performance influence fluctuation analysis is carried out on the operation attribute data of each type, the analysis is carried out by analyzing the difference condition between the fitting curve corresponding to the operation attribute data of each type and the performance factor score data curve of the operation data, and the calculation formula is as follows
;
The average value of the periodic performance influence fluctuation values of the operation attribute data of each type in the period is calculated according to the periodic performance influence fluctuation values obtained by analyzing the operation attribute data of each type, and the calculation formula is as follows
;
Based on the analysis result of the periodic performance influence fluctuation value of the operation attribute data of each type in the period, the abnormal fluctuation condition of the operation attribute data in each period of the target equipment is analyzed, and the calculation formula is as follows
;
Through presetting an abnormal fluctuation index threshold value of the equipment operation attribute data, when the comprehensive abnormal fluctuation index of the operation attribute data in the equipment period corresponding to a certain period is larger than the threshold value, carrying out risk marking on the current period;
According to the analysis result of the comprehensive abnormal fluctuation index of the operation attribute data of each device in the corresponding divided operation period, counting the abnormal period marked as risk, and analyzing the abnormal period proportion according to the statistical result, wherein the calculation formula is as follows
;
And when the risk period ratio is smaller than the threshold value, carrying out real-time backup on the operation attribute data analysis of the target equipment, carrying out continuous period data acquisition and repeating the step of exception analysis.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the above-mentioned embodiments are merely preferred embodiments of the present invention, and the present invention is not limited thereto, but may be modified or substituted for some of the technical features thereof by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.