技术领域Technical Field
本发明涉及机械结构测试与健康监测技术领域，尤其是涉及一种风电螺栓状态的检测方法及系统。The present invention relates to the technical field of mechanical structure testing and health monitoring, and in particular to a method and system for detecting the status of wind power bolts.
背景技术Background Art
风电塔筒螺栓长期承受交变载荷与复杂环境作用，易发生疲劳断裂导致结构失效。传统检测依赖定期人工巡检与局部传感器网络，仅能获取离散时间点的静态数据，难以及时发现动态载荷下的突发应力异常。Wind turbine tower bolts are subjected to alternating loads and complex environmental conditions for a long time, and are prone to fatigue fracture, leading to structural failure. Traditional detection relies on regular manual inspections and local sensor networks, which can only obtain static data at discrete time points and are difficult to detect sudden stress anomalies under dynamic loads in a timely manner.
现有技术中采用固定参数有限元模型进行应力预测，但未考虑叶轮转速、变桨动作等实时工况对结构边界条件的影响，导致模型计算结果与实际应力分布存在显著偏差。同时，异常预警依赖单一应变阈值判定，无法区分机械谐振、温度形变等不同失效模式。The existing technology uses a fixed parameter finite element model for stress prediction, but does not consider the impact of real-time working conditions such as impeller speed and pitch action on structural boundary conditions, resulting in a significant deviation between the model calculation results and the actual stress distribution. At the same time, the abnormal warning relies on a single strain threshold judgment and cannot distinguish between different failure modes such as mechanical resonance and temperature deformation.
此类方法因忽略工况应力的动态耦合关系，常出现误报警或漏检现象。且无法定位异常载荷源头，导致运维措施滞后或针对性不足，难以有效延长螺栓使用寿命并降低维护成本。Such methods often cause false alarms or missed detections due to ignoring the dynamic coupling relationship of working stress. They are also unable to locate the source of abnormal loads, resulting in delayed or insufficiently targeted operation and maintenance measures, making it difficult to effectively extend the service life of bolts and reduce maintenance costs.
发明内容Summary of the invention
为解决上述问题，本发明提供了一种风电螺栓状态的检测方法方法、系统，采用无线应变传感器网络、动态有限元模型修正与多维疲劳损伤分析技术，实时生成全塔筒应力分布图谱并关联外部工况数据，能够精准评估螺栓寿命衰减率、定位载荷异常源并输出分级维护策略。To solve the above problems, the present invention provides a method and system for detecting the status of wind power bolts, which adopts wireless strain sensor networks, dynamic finite element model correction and multi-dimensional fatigue damage analysis technology to generate a real-time stress distribution map of the entire tower and associate it with external working condition data. It can accurately evaluate the bolt life decay rate, locate the abnormal load source and output a graded maintenance strategy.
上述目标可以通过如下方案实现：The above objectives can be achieved through the following solutions:
一种风电螺栓状态的检测方法，包括在塔筒每层预设周向位置设置监测点，获取各监测点的实时应变数据；从风电场远动通信系统实时获取机组的运行工况数据，包括风速、变桨偏航数据、发电机转矩及叶轮转速；根据所述运行工况数据动态生成塔筒结构的有限元模型，利用所述实时应变数据修正所述有限元模型；结合所述有限元模型和所述实时应变数据，采用应力场梯度补偿算法对未监测点的应变进行推算，生成全塔筒螺栓的应力分布图谱；将所述应力分布图谱输入预设的疲劳损伤模型，计算螺栓寿命衰减率并将所述实时应变数据与所述运行工况数据中的变桨偏航数据进行时序关联分析，定位外部载荷异常源，得到定位结果；当检测到所述寿命衰减率超过预设阈值时，生成分级预警信号并根据所述定位结果输出维护策略。A method for detecting the status of wind power bolts, comprising setting monitoring points at preset circumferential positions on each layer of a tower, and obtaining real-time strain data of each monitoring point; obtaining real-time operating condition data of the unit from a wind farm telecontrol communication system, including wind speed, pitch yaw data, generator torque and impeller speed; dynamically generating a finite element model of a tower structure according to the operating condition data, and correcting the finite element model using the real-time strain data; combining the finite element model and the real-time strain data, using a stress field gradient compensation algorithm to infer the strain of unmonitored points, and generating a stress distribution map of the bolts of the entire tower; inputting the stress distribution map into a preset fatigue damage model, calculating the bolt life decay rate, and performing time-series correlation analysis on the real-time strain data and the pitch yaw data in the operating condition data, locating the abnormal source of the external load, and obtaining a positioning result; when it is detected that the life decay rate exceeds a preset threshold, generating a graded warning signal and outputting a maintenance strategy according to the positioning result.
可选地，所述在塔筒每层预设周向位置设置监测点包括：在塔筒主风向冲击面的两侧对称布设第一传感器子集，相邻传感器的周向间距按预设角度设置；在塔筒法兰连接处的高弯矩区域布设第二传感器子集，采用正交排列方式采集三维应变分量。Optionally, setting monitoring points at preset circumferential positions on each floor of the tower includes: symmetrically arranging a first subset of sensors on both sides of the main wind direction impact surface of the tower, and the circumferential spacing between adjacent sensors is set at a preset angle; arranging a second subset of sensors in the high bending moment area of the tower flange connection, and collecting three-dimensional strain components in an orthogonal arrangement.
可选地，所述根据所述运行工况数据动态生成塔筒结构的有限元模型包括：根据所述叶轮转速生成等效离心力载荷，根据所述发电机转矩计算传动链扭矩波动值；将所述等效离心力载荷与所述传动链扭矩波动值进行矢量合成，生成随时间变化的动态载荷矩阵；将所述动态载荷矩阵输入至基于塔筒原始设计参数建立的基准模型，生成包含时变边界条件的有限元模型。Optionally, the dynamically generating a finite element model of the tower structure according to the operating condition data includes: generating an equivalent centrifugal force load according to the impeller speed, and calculating a transmission chain torque fluctuation value according to the generator torque; vector synthesizing the equivalent centrifugal force load and the transmission chain torque fluctuation value to generate a dynamic load matrix that varies with time; inputting the dynamic load matrix into a benchmark model established based on the original design parameters of the tower to generate a finite element model containing time-varying boundary conditions.
可选地，所述采用应力场梯度补偿算法对未监测点的应变进行推算，生成全塔筒螺栓的应力分布图谱包括：从所述实时应变数据中提取相邻监测点的应变差值，计算局部区域的曲率变化特征量；将所述曲率变化特征量与所述有限元模型的理论梯度进行对比，计算残余应力偏差系数；根据所述残余应力偏差系数迭代调整未监测点的弹性模量，直至利用有限元模型计算的预测应力与实测应力的误差收敛至设定区间，输出预测应力构建应力分布图谱。Optionally, the use of a stress field gradient compensation algorithm to extrapolate the strain of unmonitored points to generate a stress distribution map of the entire tower bolts includes: extracting strain differences between adjacent monitoring points from the real-time strain data, and calculating a curvature change characteristic quantity in a local area; comparing the curvature change characteristic quantity with a theoretical gradient of the finite element model, and calculating a residual stress deviation coefficient; iteratively adjusting the elastic modulus of the unmonitored points according to the residual stress deviation coefficient until the error between the predicted stress calculated using the finite element model and the measured stress converges to a set interval, and outputting the predicted stress to construct a stress distribution map.
可选地，所述将所述应力分布图谱输入预设的疲劳损伤模型，计算螺栓寿命衰减率并将所述实时应变数据与所述运行工况数据中的变桨偏航数据进行时序关联分析，定位外部载荷异常源，得到定位结果包括：获取螺栓材料的S-N曲线及历史载荷谱数据，建立应变幅值与疲劳损伤度的映射关系，计算得到螺栓寿命衰减率；对所述应力分布图谱进行雨流计数法处理，提取等效交变应力幅值序列；将所述等效交变应力幅值序列与所述变桨偏航数据进行卷积运算，生成工况耦合的疲劳累积因子，定位外部载荷异常源，得到定位结果。Optionally, the stress distribution map is input into a preset fatigue damage model, the bolt life decay rate is calculated, and the real-time strain data is time-series correlated with the pitch and yaw data in the operating condition data to locate the abnormal external load source, and the positioning result is obtained, including: obtaining the S-N curve and historical load spectrum data of the bolt material, establishing a mapping relationship between the strain amplitude and the fatigue damage degree, and calculating the bolt life decay rate; performing rain flow counting method processing on the stress distribution map to extract the equivalent alternating stress amplitude sequence; performing convolution operation on the equivalent alternating stress amplitude sequence and the pitch and yaw data to generate a fatigue accumulation factor coupled with the operating condition, locating the abnormal external load source, and obtaining the positioning result.
可选地，所述方法还包括：当实测应力与预测应力的偏差持续超过设定次数时，提取各监测点的应力相位延迟特征；根据所述相位延迟特征调整有限元模型中阻尼系数及材料屈服强度的权重比例；将修正后的模型参数存储至历史数据库，作为下次模型初始化的基准值。Optionally, the method also includes: when the deviation between the measured stress and the predicted stress continues to exceed a set number of times, extracting the stress phase delay characteristics of each monitoring point; adjusting the weight ratio of the damping coefficient and the material yield strength in the finite element model according to the phase delay characteristics; and storing the corrected model parameters in a historical database as a reference value for the next model initialization.
可选地，所述分级预警信号的生成依据为：构建包含应力波动熵值、温度载荷敏感度及环境腐蚀速率的多维预警参数集；当单个参数超过一级阈值时触发状态提示，当至少两个参数的组合效应超过二级阈值时触发紧急停运指令。Optionally, the generation basis of the graded warning signal is: constructing a multidimensional warning parameter set including stress fluctuation entropy value, temperature load sensitivity and environmental corrosion rate; triggering a status prompt when a single parameter exceeds the first-level threshold, and triggering an emergency shutdown command when the combined effect of at least two parameters exceeds the second-level threshold.
可选地，所述应力波动熵值的计算包括：对指定时间窗内的应变数据进行傅里叶变换，提取预设频段的能量分布特征；根据所述能量分布特征计算应力波动熵值，当低频段能量占比超过预设占比时判定为谐振风险模式。Optionally, the calculation of the stress fluctuation entropy value includes: performing Fourier transform on the strain data within a specified time window to extract energy distribution characteristics of a preset frequency band; calculating the stress fluctuation entropy value based on the energy distribution characteristics, and determining it as a resonance risk mode when the proportion of low-frequency band energy exceeds a preset proportion.
可选地，所述方法还包括：当识别到谐振风险模式时，同步采集机组振动传感器的轴向加速度数据；将所述加速度数据与所述低频段能量进行幅频相关性分析，若相关系数大于预设相关值则在维护策略中添加振动抑制装置的调试任务。Optionally, the method also includes: when a resonance risk mode is identified, synchronously collecting axial acceleration data of the unit vibration sensor; performing amplitude-frequency correlation analysis on the acceleration data and the low-frequency band energy, and if the correlation coefficient is greater than a preset correlation value, adding a debugging task for the vibration suppression device to the maintenance strategy.
基于相同的发明构思，本发明还提供了一种风电螺栓状态的检测系统，所述系统包括：无线应变传感器组，部署在塔筒每层预设周向位置，用于获取各监测点的实时应变数据；工况数据采集模块，用于从风电场远动通信系统实时获取机组的运行工况数据，包括风速、变桨偏航数据、发电机转矩及叶轮转速；有限元模型构建模块，用于根据所述运行工况数据动态生成塔筒结构的有限元模型，利用所述实时应变数据修正所述有限元模型；应力分布生成模块，用于结合所述有限元模型和所述实时应变数据，采用应力场梯度补偿算法对未监测点的应变进行推算，生成全塔筒螺栓的应力分布图谱；异常分析定位模块，用于将所述应力分布图谱输入预设的疲劳损伤模型，计算螺栓寿命衰减率并将所述实时应变数据与所述运行工况数据中的变桨偏航数据进行时序关联分析，定位外部载荷异常源，得到定位结果；预警决策模块，用于当检测到所述寿命衰减率超过预设阈值时，生成分级预警信号并根据所述定位结果输出维护策略。Based on the same inventive concept, the present invention also provides a wind power bolt status detection system, the system comprising: a wireless strain sensor group, deployed at a preset circumferential position on each layer of the tower, for obtaining real-time strain data of each monitoring point; a working condition data acquisition module, for obtaining real-time operating condition data of the unit from the wind farm telecontrol communication system, including wind speed, pitch yaw data, generator torque and impeller speed; a finite element model construction module, for dynamically generating a finite element model of the tower structure according to the operating condition data, and using the real-time strain data to correct the finite element model; a stress distribution generation module, for In combination with the finite element model and the real-time strain data, a stress field gradient compensation algorithm is used to calculate the strain of unmonitored points to generate a stress distribution map of the entire tower bolts; an abnormal analysis and positioning module is used to input the stress distribution map into a preset fatigue damage model, calculate the bolt life decay rate and perform time-series correlation analysis between the real-time strain data and the variable pitch yaw data in the operating condition data to locate the abnormal source of the external load and obtain a positioning result; an early warning decision module is used to generate a graded early warning signal and output a maintenance strategy based on the positioning result when it is detected that the life decay rate exceeds a preset threshold.
与现有技术相比，本发明具有如下优点：Compared with the prior art, the present invention has the following advantages:
1、本发明通过部署无线应变传感器组并融合动态有限元模型修正技术，实现了全塔筒螺栓应力分布的高精度实时推算；结合应力场梯度补偿算法，突破了传统单点监测的局限性，可准确预测未布设传感器的关键位置应变值，显著提升监测覆盖率及数据可靠性；1. The present invention realizes high-precision real-time estimation of the stress distribution of bolts in the entire tower by deploying a wireless strain sensor group and integrating dynamic finite element model correction technology. Combined with the stress field gradient compensation algorithm, it breaks through the limitations of traditional single-point monitoring, accurately predicts the strain values of key positions where sensors are not deployed, and significantly improves monitoring coverage and data reliability.
2、本发明采用运行工况数据与应变信号的时序关联分析，能够精准定位外部载荷异常源；通过卷积运算揭示变桨偏航动作与应力波动之间的因果关系，解决了传统方法中异常事件关联性分析模糊的问题，为针对性维护提供直接依据；2. The present invention uses the time series correlation analysis of operating condition data and strain signals to accurately locate the source of external load anomalies; the causal relationship between pitch yaw action and stress fluctuation is revealed through convolution operation, which solves the problem of fuzzy correlation analysis of abnormal events in traditional methods and provides a direct basis for targeted maintenance;
3、本发明建立多维预警参数集与分级决策机制，综合评估应力波动熵值、温度敏感度及腐蚀速率等多因素耦合效应，实现从早期预警到紧急停机的动态响应；相较于单一阈值报警机制，有效降低误报率并防止恶性失效；3. The present invention establishes a multi-dimensional warning parameter set and a hierarchical decision-making mechanism to comprehensively evaluate the coupling effects of multiple factors such as stress fluctuation entropy, temperature sensitivity and corrosion rate, and realize dynamic response from early warning to emergency shutdown; compared with a single threshold alarm mechanism, it effectively reduces the false alarm rate and prevents malignant failures;
4、本发明构建基于疲劳损伤模型与历史数据的寿命衰减率计算模型，可动态更新螺栓剩余寿命预测值；结合雨流计数法与材料S-N曲线，量化交变应力对螺栓老化的影响，为预防性维护计划制定提供科学依据。4. The present invention constructs a life decay rate calculation model based on fatigue damage model and historical data, which can dynamically update the predicted value of the remaining life of the bolt; combined with the rain flow counting method and the material S-N curve, it quantifies the impact of alternating stress on bolt aging, providing a scientific basis for the formulation of preventive maintenance plans.
本发明的其它特征和优点将在随后的说明书中阐述，并且，部分地从说明书中变得显而易见，或者通过实施本发明而了解。本发明的目的和其他优点可通过在说明书、权利要求书以及附图中所指出的结构来实现和获得。Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
图1是本发明实施例的一种风电螺栓状态的检测方法的流程示意图。FIG1 is a schematic flow chart of a method for detecting the status of a wind power bolt according to an embodiment of the present invention.
图2是本发明实施例的塔筒周向传感器布设示意图。FIG. 2 is a schematic diagram of the arrangement of circumferential sensors of the tower according to an embodiment of the present invention.
图3是本发明实施例的塔筒周向应力分布图谱。FIG. 3 is a diagram showing the circumferential stress distribution of the tower according to an embodiment of the present invention.
图4是本发明实施例的风电螺栓材料S-N曲线。FIG4 is an S-N curve of the wind power bolt material according to an embodiment of the present invention.
图5是本发明实施例的螺栓寿命衰减曲线。FIG. 5 is a bolt life attenuation curve according to an embodiment of the present invention.
图6是本发明实施例的一种风电螺栓状态的检测系统的结构示意图。FIG. 6 is a schematic structural diagram of a wind power bolt status detection system according to an embodiment of the present invention.
具体实施方式DETAILED DESCRIPTION
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地说明，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
参照图1，本发明的一个实施例提出了一种风电螺栓状态的检测方法，采用无线应变传感器网络、动态有限元模型修正与多维疲劳损伤分析技术，实时生成全塔筒应力分布图谱并关联外部工况数据，能够精准评估螺栓寿命衰减率、定位载荷异常源并输出分级维护策略。1 , an embodiment of the present invention proposes a method for detecting the status of wind power bolts, which uses a wireless strain sensor network, dynamic finite element model correction and multi-dimensional fatigue damage analysis technology to generate a full-tower stress distribution map in real time and associate it with external working condition data. It can accurately evaluate the bolt life decay rate, locate the abnormal load source and output a graded maintenance strategy.
该实施例的所述方法具体包括：The method of this embodiment specifically includes:
在塔筒每层预设周向位置设置监测点，获取各监测点的实时应变数据；Monitoring points are set at preset circumferential positions on each floor of the tower to obtain real-time strain data of each monitoring point;
具体的，根据塔筒结构力学特性，在每层塔筒的法兰连接区域及主风向迎风面分布无线应变传感器，并通过LoRa通信协议将传感数据上传至边缘计算节点。其中，无线应变传感器为无源式设计，通过压电效应将机械应变转换为电荷信号，经信号调理电路生成数字化应变波形。其中，预设周向位置为根据塔筒受力仿真结果预先设定的传感器布设点，覆盖法兰螺栓群的高应力集中区域；实时应变数据为传感器采集的微应变值，表征螺栓连接部位的形变量；无线应变传感器组为由多个传感器构成的分布式监测网络，支持同步采样与数据融合。Specifically, according to the mechanical characteristics of the tower structure, wireless strain sensors are distributed in the flange connection area and the windward side of each tower layer, and the sensor data is uploaded to the edge computing node through the LoRa communication protocol. Among them, the wireless strain sensor is a passive design, which converts mechanical strain into a charge signal through the piezoelectric effect, and generates a digital strain waveform through the signal conditioning circuit. Among them, the preset circumferential position is the sensor layout point pre-set according to the tower force simulation results, covering the high stress concentration area of the flange bolt group; the real-time strain data is the micro-strain value collected by the sensor, which characterizes the deformation of the bolt connection part; the wireless strain sensor group is a distributed monitoring network composed of multiple sensors, which supports synchronous sampling and data fusion.
示例性地，在某2MW风电机组塔筒的第二层法兰处，按间隔50度布设16个无线应变传感器，并与基准电阻应变片比对。传感器组成功捕捉到风速突变时法兰面应变的非对称分布特征，且数据延时小于200ms。通过合理的布设策略实现对关键区域的动态监测，且无源设计避免供电线路对塔筒结构的干扰，确保长期可靠性。For example, 16 wireless strain sensors were deployed at 50-degree intervals on the second-layer flange of a 2MW wind turbine tower and compared with the reference resistance strain gauge. The sensor group successfully captured the asymmetric distribution characteristics of the flange surface strain when the wind speed suddenly changed, and the data delay was less than 200ms. Dynamic monitoring of key areas is achieved through a reasonable deployment strategy, and the passive design avoids interference of the power supply line on the tower structure, ensuring long-term reliability.
从风电场远动通信系统实时获取机组的运行工况数据，包括风速、变桨偏航数据、发电机转矩及叶轮转速；Obtain the unit's operating data in real time from the wind farm telecontrol communication system, including wind speed, pitch data, generator torque and rotor speed;
具体的，通过电力系统IEC 60870-5-104通信规约与风电场监控系统（SCADA）对接，以每秒1次的频率读取机组实时运行参数。通过数据解析模块将原始报文转换为结构化工况数据流，并与应变数据时间戳对齐。其中，远动通信系统为基于电力专用网络的数据传输系统，保障敏感数据的安全隔离；发电机转矩为风轮传递给发电机的旋转力矩，反映机械载荷强度；叶轮转速为风轮每分钟转数（RPM），表征气动载荷的动态特性。Specifically, the power system IEC 60870-5-104 communication protocol is used to connect with the wind farm monitoring system (SCADA) to read the real-time operating parameters of the unit at a frequency of once per second. The original message is converted into a structured working condition data stream through the data analysis module and aligned with the strain data timestamp. Among them, the telecontrol communication system is a data transmission system based on a power-specific network to ensure the safe isolation of sensitive data; the generator torque is the rotational torque transmitted to the generator by the wind wheel, reflecting the mechanical load intensity; the impeller speed is the number of revolutions per minute (RPM) of the wind wheel, which characterizes the dynamic characteristics of the aerodynamic load.
根据所述运行工况数据动态生成塔筒结构的有限元模型，利用所述实时应变数据修正所述有限元模型；Dynamically generate a finite element model of the tower structure according to the operating condition data, and modify the finite element model using the real-time strain data;
具体的，基于塔筒设计图纸建立基准有限元模型，包含壳单元模拟塔壁、梁单元模拟连接螺栓。根据实时风速计算等效风压分布载荷，根据叶轮转速生成离心力载荷向量，并通过动态载荷矩阵更新模型边界条件。将实时应变数据代入对应节点，修正有限元模型的位移量。其中，有限元模型为将塔筒离散为网格单元进行力学计算的数值模型；动态载荷矩阵为包含时间变量的载荷分布数据，反映外部激励的瞬态特征。Specifically, a baseline finite element model is established based on the tower design drawings, including shell units to simulate the tower wall and beam units to simulate the connecting bolts. The equivalent wind pressure distribution load is calculated according to the real-time wind speed, the centrifugal force load vector is generated according to the impeller speed, and the model boundary conditions are updated through the dynamic load matrix. The real-time strain data is substituted into the corresponding nodes to correct the displacement of the finite element model. Among them, the finite element model is a numerical model that discretizes the tower into grid units for mechanical calculations; the dynamic load matrix is the load distribution data containing time variables, reflecting the transient characteristics of external excitation.
结合所述有限元模型和所述实时应变数据，采用应力场梯度补偿算法对未监测点的应变进行推算，生成全塔筒螺栓的应力分布图谱；Combining the finite element model and the real-time strain data, a stress field gradient compensation algorithm is used to calculate the strain of unmonitored points to generate a stress distribution map of the entire tower bolts;
具体的，提取相邻监测点的实测应变差值，计算局部区域的曲率变化量。结合有限元模型的应力梯度理论值，通过最小二乘法拟合残余应力修正系数。利用修正后的材料本构方程迭代计算未监测点的应变分布，直至收敛条件满足。其中，应力场梯度补偿算法为基于实测数据与模型预测差异的动态修正方法；残余应力修正系数为表征模型预测误差的加权因子。Specifically, the measured strain difference between adjacent monitoring points is extracted to calculate the curvature change of the local area. Combined with the stress gradient theoretical value of the finite element model, the residual stress correction coefficient is fitted by the least squares method. The strain distribution of the unmonitored points is iteratively calculated using the corrected material constitutive equation until the convergence condition is met. Among them, the stress field gradient compensation algorithm is a dynamic correction method based on the difference between the measured data and the model prediction; the residual stress correction coefficient is a weighting factor that characterizes the model prediction error.
将所述应力分布图谱输入预设的疲劳损伤模型，计算螺栓寿命衰减率并将所述实时应变数据与所述运行工况数据中的变桨偏航数据进行时序关联分析，定位外部载荷异常源，得到定位结果；Input the stress distribution map into a preset fatigue damage model, calculate the bolt life decay rate, and perform time series correlation analysis on the real-time strain data and the pitch yaw data in the operating condition data to locate the abnormal source of the external load and obtain a positioning result;
将所述高风险位置对应的所述实时应变数据与所述运行工况数据中的变桨偏航数据进行时序关联分析，定位外部载荷异常源，得到定位结果；Performing time series correlation analysis on the real-time strain data corresponding to the high-risk position and the pitch yaw data in the operating condition data to locate the abnormal source of the external load and obtain a positioning result;
具体的，对高风险螺栓的应变波动数据进行短时傅里叶变换，提取主导频率分量。与变桨角度、偏航误差角的时域信号进行交叉相关性分析，识别两者相位同步性。若某频率分量与变桨动作周期匹配，则判定为气动载荷异常导致的谐振。Specifically, the strain fluctuation data of high-risk bolts is subjected to short-time Fourier transform to extract the dominant frequency component. A cross-correlation analysis is performed with the time domain signals of the pitch angle and yaw error angle to identify the phase synchronization between the two. If a frequency component matches the pitch action cycle, it is determined to be a resonance caused by abnormal aerodynamic load.
当检测到所述寿命衰减率超过预设阈值时，生成分级预警信号并根据所述定位结果输出维护策略。When it is detected that the life decay rate exceeds a preset threshold, a graded warning signal is generated and a maintenance strategy is output according to the positioning result.
具体的，根据螺栓的剩余寿命预测值定义三级预警机制：一级为观察提示，二级为计划性维护建议，三级为紧急停机指令。关联异常源的定位结果，生成针对性维护方案，如变桨系统校准或法兰面松动复紧。Specifically, a three-level early warning mechanism is defined based on the predicted value of the remaining life of the bolts: the first level is an observation reminder, the second level is a planned maintenance suggestion, and the third level is an emergency shutdown instruction. The location results of the associated abnormal source are used to generate targeted maintenance plans, such as calibration of the variable pitch system or re-tightening of the loose flange surface.
具体的，本方法通过融合无源传感网络、实时工况数据与动态有限元建模技术，建立螺栓应变监测与外部载荷的闭环反馈机制。通过动态修正模型参数补偿理论计算偏差，并利用多源数据关联分析定位异常载荷源头，解决了传统监测中模型静态化与数据孤立导致的精度不足问题。Specifically, this method establishes a closed-loop feedback mechanism for bolt strain monitoring and external load by integrating passive sensor networks, real-time working condition data, and dynamic finite element modeling technology. The theoretical calculation deviation is compensated by dynamically correcting model parameters, and the source of abnormal load is located by multi-source data correlation analysis, which solves the problem of insufficient accuracy caused by static model and isolated data in traditional monitoring.
示例性地，在内蒙古某风场对一台3MW机组实施本方法，成功捕捉到台风过境期间塔筒第三层螺栓群的应力异常波动。通过比对SCADA数据，定位异常源为变桨系统响应延迟导致的不对称风载荷。触发二级预警并建议调整变桨控制参数。维护后检测显示该区域螺栓应力峰值下降至少30%。通过数据融合与动态建模实现对复杂工况的快速响应，显著提升预警准确性与维护措施的针对性，避免非计划停机损失。For example, this method was implemented on a 3MW unit at a wind farm in Inner Mongolia, and the abnormal stress fluctuations of the bolt group on the third layer of the tower during the typhoon were successfully captured. By comparing the SCADA data, the abnormal source was located as the asymmetric wind load caused by the delayed response of the pitch system. The secondary warning was triggered and it was recommended to adjust the pitch control parameters. Post-maintenance detection showed that the peak stress of the bolts in this area dropped by at least 30%. Through data fusion and dynamic modeling, rapid response to complex working conditions can be achieved, which significantly improves the accuracy of warnings and the pertinence of maintenance measures, and avoids unplanned downtime losses.
可选地，如图2所示，所述在塔筒每层预设周向位置设置监测点包括：Optionally, as shown in FIG2 , the step of setting monitoring points at preset circumferential positions on each floor of the tower includes:
在塔筒主风向冲击面的两侧对称布设第一传感器子集，相邻传感器的周向间距按预设角度设置；A first subset of sensors is symmetrically arranged on both sides of the main wind direction impact surface of the tower, and the circumferential spacing between adjacent sensors is set according to a preset angle;
具体的，根据塔筒风振响应特性分析，确定主风向冲击面的中心轴线，沿该轴线两侧各延伸10度范围内作为第一传感器子集部署区域。每个子集包含8-12个无线应变传感器即主风向传感器，以塔筒中心线为对称轴镜像分布。相邻传感器的周向间距满足45≤≤60度，覆盖总弧长的计算公式为：Specifically, according to the analysis of the tower wind vibration response characteristics, the central axis of the main wind direction impact surface is determined, and the area within 10 degrees on both sides of the axis is used as the first sensor subset deployment area. Each subset contains 8-12 wireless strain sensors, namely the main wind direction sensors, which are distributed in a mirror image with the center line of the tower as the symmetry axis. The circumferential spacing of adjacent sensors is Satisfy 45≤ ≤60 degrees, the calculation formula for the total arc length covered is:
； ;
式中，为单个子集传感器数量，取50度时，实际配置时取整数值8个传感器。安装位置通过激光定位仪校准周向分布，确保相邻传感器应变梯度测量的连续性。主风向冲击面为塔筒迎风面左右15度的弧形区域，受气动载荷影响最显著；第一传感器子集为对称分布的应变监测节点集群，通过交叉验证监测主载荷方向的应变分布均匀性；周向间距45-60度为兼顾监测密度与冗余性的优化区间值，防止风载突变时关键区域漏检。In the formula, is the number of sensors in a single subset, When taking 50 degrees , in actual configuration, an integer value of 8 sensors is taken. The installation position is calibrated by a laser locator to ensure the continuity of strain gradient measurement of adjacent sensors. The main wind impact surface is an arc area 15 degrees to the left and right of the windward surface of the tower, which is most significantly affected by the aerodynamic load; the first sensor subset is a symmetrically distributed strain monitoring node cluster, which monitors the uniformity of strain distribution in the main load direction through cross-validation; the circumferential spacing of 45-60 degrees is the optimized interval value that takes into account monitoring density and redundancy to prevent missed detection of key areas when the wind load changes suddenly.
在塔筒法兰连接处的弯矩区域布设第二传感器子集，采用正交排列方式采集三维应变分量。The second subset of sensors is arranged in the bending moment area of the tower flange connection, and the three-dimensional strain components are collected in an orthogonal arrangement.
具体的，在法兰连接面上下各延伸20cm的环形区域布设正交应变片组，即法兰面传感器，每组包含三个相互正交的应变检测方向。水平方向应变片与法兰面切线方向平行，垂直方向与螺栓轴向重合，斜向45度设置第三应变片。单个法兰面配置3组正交单元，形成立体监测网格。通过正交应变数据计算三维主应力方向：Specifically, orthogonal strain gauge groups, i.e. flange surface sensors, are arranged in annular areas extending 20 cm above and below the flange connection surface. Each group contains three mutually orthogonal strain detection directions. The horizontal strain gauge is parallel to the tangent direction of the flange surface, the vertical direction coincides with the bolt axis, and the third strain gauge is set at an angle of 45 degrees. Three groups of orthogonal units are configured on a single flange surface to form a three-dimensional monitoring grid. The three-dimensional principal stress direction is calculated using the orthogonal strain data:
； ;
； ;
式中，为平面主应力最大值，为平面主应力最小值，、为正交轴方向应变，为剪切应变分量。其中，弯矩区域为法兰连接面弯矩值超过塔筒壁平均弯矩300%的区域；第二传感器子集为多向应变测量的高密度布设组；正交排列方式为三方向交错分布的应变片组构型，用于解耦复合受力状态下各应力分量。In the formula, is the maximum plane principal stress, is the minimum plane principal stress, , is the strain in the orthogonal axis direction, The moment area is the area where the moment value of the flange connection surface exceeds 300% of the average moment of the tower wall; the second sensor subset is a high-density arrangement group for multi-directional strain measurement; the orthogonal arrangement is a strain gauge group configuration with staggered distribution in three directions, which is used to decouple the stress components under the composite stress state.
示例性地，在某5MW海上机组塔筒第四层法兰处，于主风向冲击面两侧各布设9个传感器，周向间距55度。法兰面高弯矩区部署三组正交传感器，每组间隔120度。现场测试期间监测到8号螺栓位水平向应变突增，同步正交传感器显示剪切应变增幅达120μɛ。经模型反演发现该点存在螺栓松动引起的弯矩重分布。通过对称布设的第一子集数据验证异常区域应变不对称率超过50%，正交布置的第二子集数据准确识别出剪切应变主导的失效模式，支撑维护人员实施定位复紧作业。对称布设策略成功捕捉载荷分布的空间不对称特征，正交排列的三维应变检测有效区分弯曲与剪切载荷的耦合作用。相较于单一方向布设方案，本方法通过多向数据融合准确识别螺栓松动引发的复合应力状态变化，避免误判单纯拉伸应力超标导致的误报警，提升缺陷类型判别精度。For example, at the fourth-layer flange of a 5MW offshore unit tower, 9 sensors were arranged on both sides of the main wind impact surface, with a circumferential spacing of 55 degrees. Three groups of orthogonal sensors were deployed in the high bending moment area of the flange surface, with each group spaced 120 degrees apart. During the field test, a sudden increase in horizontal strain was detected at the No. 8 bolt position, and the synchronous orthogonal sensor showed that the shear strain increase reached 120μɛ. The model inversion found that there was a moment redistribution caused by bolt loosening at this point. The first subset of data with symmetrical layout verified that the strain asymmetry rate in the abnormal area exceeded 50%, and the second subset of data with orthogonal layout accurately identified the failure mode dominated by shear strain, supporting maintenance personnel to perform positioning and re-tightening operations. The symmetrical layout strategy successfully captured the spatial asymmetric characteristics of the load distribution, and the orthogonally arranged three-dimensional strain detection effectively distinguished the coupling effects of bending and shear loads. Compared with the single-direction layout scheme, this method accurately identified the changes in the composite stress state caused by bolt loosening through multi-directional data fusion, avoided false alarms caused by misjudgment of excessive pure tensile stress, and improved the accuracy of defect type discrimination.
可选地，所述根据所述运行工况数据动态生成塔筒结构的有限元模型包括：Optionally, dynamically generating a finite element model of the tower structure according to the operating condition data includes:
根据所述叶轮转速生成等效离心力载荷，根据所述发电机转矩计算传动链扭矩波动值；Generate an equivalent centrifugal force load according to the impeller speed, and calculate a transmission chain torque fluctuation value according to the generator torque;
具体的，采用叶轮实际转速值基于刚体动力学原理计算等效离心力载荷。设置叶轮质量分布数据存储模块，包含每个叶片的质心坐标与质量数据。计算等效离心力时，将叶轮离散为多个质量微元，计算总离心力得到等效离心力载荷，对于等效离心力载荷，有：Specifically, the equivalent centrifugal force load is calculated based on the rigid body dynamics principle using the actual speed of the impeller. An impeller mass distribution data storage module is set up, which contains the coordinates of the center of mass and mass data of each blade. When calculating the equivalent centrifugal force, the impeller is discretized into multiple mass microelements, and the total centrifugal force is calculated to obtain the equivalent centrifugal force load. ,have:
； ;
式中，为质量微元的数量，为第个质量微元的质量，为叶轮角速度，为第个质量微元距旋转轴的径向距离。发电机转矩数据经滑差频率补偿后，利用转矩脉动率计算公式得出传动链扭矩波动值，对于传动链扭矩波动值，有：In the formula, is the number of mass elements, For the The mass of a mass element, is the impeller angular velocity, For the The radial distance of a mass microelement from the rotating axis. After the generator torque data is compensated for the slip frequency, the torque fluctuation value of the transmission chain is obtained using the torque pulsation rate calculation formula. ,have:
； ;
其中，、为常系数，为统计周期内平均转矩，为齿轮箱啮合基频，为随机扰动分量。叶轮转速为风轮旋转角速度的量化表征参数；等效离心力载荷为叶轮回转运动产生的惯性力等效值；传动链扭矩波动值为齿轮啮合与电气控制复合作用下的转矩振荡幅值。in, , is a constant coefficient, is the average torque in the statistical period, is the gearbox meshing fundamental frequency, is the random disturbance component. The impeller speed is the quantitative characterization parameter of the wind wheel rotation angular velocity; the equivalent centrifugal force load is the equivalent value of the inertial force generated by the impeller rotation motion; the transmission chain torque fluctuation value is the torque oscillation amplitude under the combined action of gear meshing and electrical control.
将所述等效离心力载荷与所述传动链扭矩波动值进行矢量合成，生成随时间变化的动态载荷矩阵；Performing vector synthesis of the equivalent centrifugal force load and the transmission chain torque fluctuation value to generate a dynamic load matrix that varies with time;
具体的，设定动态载荷矩阵维度为Q×3，Q为时间节点数，三维空间坐标。按时间序列对齐等效离心力载荷与传动链扭矩波动值，采用空间矢量叠加方法，计算载荷分量，对于动态载荷向量，有：Specifically, the dimension of the dynamic load matrix is set to Q×3, where Q is the number of time nodes and the three-dimensional space coordinates. The equivalent centrifugal force load and the torque fluctuation value of the transmission chain are aligned in time series, and the load components are calculated using the space vector superposition method. For the dynamic load vector ,have:
； ;
式中，、为载荷耦合权重系数，为离心力作用方向向量（径向），为扭矩作用方向向量（切向），通过每5ms时间步长更新动态载荷向量，生成动态载荷矩阵。等效离心力载荷与传动链扭矩波动值的矢量合成为考虑作用方向正交性的空间叠加操作；动态载荷矩阵为按时间序列记录的动态载荷向量集合，用于有限元模型时变边界条件设置。In the formula, , is the load coupling weight coefficient, is the direction vector of the centrifugal force (radial), is the torque action direction vector (tangential), and the dynamic load matrix is generated by updating the dynamic load vector every 5ms time step. The vector synthesis of the equivalent centrifugal force load and the torque fluctuation value of the transmission chain is a spatial superposition operation considering the orthogonality of the action direction; the dynamic load matrix is a set of dynamic load vectors recorded in time series, which is used to set the time-varying boundary conditions of the finite element model.
将所述动态载荷矩阵输入至基于塔筒原始设计参数建立的基准模型，生成包含时变边界条件的有限元模型。The dynamic load matrix is input into a benchmark model established based on the original design parameters of the tower to generate a finite element model including time-varying boundary conditions.
具体的，基于塔筒材料证书中的弹性模量、泊松比建立基准有限元模型，采用四面体单元划分网格。导入动态载荷矩阵后，在模型底座施加固定约束，顶部加载动态载荷参数。通过隐式动力学求解器更新每个时间步的位移场，公式表达为：Specifically, a benchmark finite element model is established based on the elastic modulus and Poisson's ratio in the tower material certificate, and the mesh is divided using tetrahedral elements. After importing the dynamic load matrix, a fixed constraint is applied to the base of the model, and the dynamic load parameters are loaded on the top. The displacement field of each time step is updated through the implicit dynamics solver, and the formula is expressed as:
； ;
式中，为质量矩阵，为阻尼系数矩阵，为屈服强度矩阵，为节点位移向量，为动态载荷向量，为阻尼系数权重，为屈服强度权重。有限元模型为基于连续介质力学方程的数值仿真模型；时变边界条件为随时间演变的载荷与约束设置。In the formula, is the mass matrix, is the damping coefficient matrix, is the yield strength matrix, is the node displacement vector, is the dynamic load vector, is the damping coefficient weight, is the yield strength weight. The finite element model is a numerical simulation model based on the continuous medium mechanics equation; the time-varying boundary conditions are the load and constraint settings that evolve over time.
示例性地，在某海上风电项目6.2MW机组调试阶段，测得叶轮转速11.2rpm，发电机转矩2450kN·m。计算得到离心力载荷，传动链扭矩波动值。通过矢量合成生成动态载荷矩阵，输入塔筒有限元模型后，预测第三层法兰面30度位置螺栓应力波动范围为±127MPa。现场在对应位置加装验证传感器，实测应力波动±139MPa，相对误差8.6%。建模时通过动态载荷更新成功捕获阵风冲击下的应力波动规律。动态载荷合成方法准确表征了旋转机械载荷与传动链扰动的叠加效应，时变边界条件的动态更新使有限元模型能够反映瞬时风速变化对结构的冲击响应。相较于静态载荷模型，本方法提升了对极端工况下应力峰值的捕捉能力，为后续寿命预测提供精确输入。For example, during the commissioning phase of a 6.2MW unit in an offshore wind power project, the impeller speed was measured to be 11.2rpm and the generator torque was 2450kN·m. The centrifugal force load was calculated as , transmission chain torque fluctuation value . The dynamic load matrix was generated by vector synthesis and input into the tower finite element model. The predicted bolt stress fluctuation range at the 30-degree position of the third-layer flange surface was ±127MPa. Verification sensors were installed at the corresponding positions on site, and the measured stress fluctuation was ±139MPa, with a relative error of 8.6%. During modeling, the stress fluctuation law under gust impact was successfully captured through dynamic load update. The dynamic load synthesis method accurately characterizes the superposition effect of rotating machinery load and transmission chain disturbance. The dynamic update of time-varying boundary conditions enables the finite element model to reflect the impact response of instantaneous wind speed changes on the structure. Compared with the static load model, this method improves the ability to capture stress peaks under extreme working conditions and provides accurate input for subsequent life prediction.
可选地，如图3所示，所述采用应力场梯度补偿算法对未监测点的应变进行推算，生成全塔筒螺栓的应力分布图谱包括：Optionally, as shown in FIG3 , the step of using a stress field gradient compensation algorithm to infer the strain of unmonitored points and generating a stress distribution map of the entire tower bolts includes:
从所述实时应变数据中提取相邻监测点的应变差值，计算局部区域的曲率变化特征量；Extracting strain differences between adjacent monitoring points from the real-time strain data and calculating curvature change characteristic quantities of the local area;
具体的，选取同一塔筒层内周向间距的相邻监测点A、B，读取其实测应变值与，计算一阶应变梯度。根据塔筒半径R与周向弧长，计算应变曲率特征量：Specifically, select the circumferential spacing within the same tower layer Adjacent monitoring points A and B are used to read the actual measured strain values. and , calculate the first-order strain gradient According to the tower radius R and the circumferential arc length , calculate the strain curvature characteristic :
； ;
该曲率变化特征量表征单位长度内的应变变化速率，用以描述局部区域的弯曲变形剧烈程度。相邻监测点为同一塔筒层周向间隔45-60度的两个传感器节点；曲率变化特征量为基于实测应变梯度推算的几何弯曲参数，反映结构局部塑性变形程度。The curvature change characteristic quantity represents the strain change rate per unit length and is used to describe the severity of the bending deformation in the local area. Adjacent monitoring points are two sensor nodes with a circumferential interval of 45-60 degrees on the same tower layer; the curvature change characteristic quantity is a geometric bending parameter calculated based on the measured strain gradient, reflecting the degree of local plastic deformation of the structure.
将所述曲率变化特征量与所述有限元模型的理论梯度进行对比，计算残余应力偏差系数；Comparing the curvature change characteristic quantity with the theoretical gradient of the finite element model to calculate the residual stress deviation coefficient;
具体的，从有限元模型导出对应位置的理论应变梯度，并计算理论曲率特征量。定义残余应力偏差系数为实测与理论曲率的比值，对于残余应力偏差系数，有：Specifically, the theoretical strain gradient at the corresponding position is derived from the finite element model , and calculate the theoretical curvature characteristic The residual stress deviation coefficient is defined as the ratio of the measured curvature to the theoretical curvature. ,have:
； ;
当残余应力偏差系数绝对值超过预设值如0.15时触发修正流程。残余应力偏差系数为模型预测精度评价指标，负值表示模型高估结构刚度，正值表明实际应力集中超出预期。When the absolute value of the residual stress deviation coefficient exceeds a preset value such as 0.15, the correction process is triggered. The residual stress deviation coefficient is an evaluation index for the model prediction accuracy. A negative value indicates that the model overestimates the structural stiffness, and a positive value indicates that the actual stress concentration exceeds expectations.
根据所述残余应力偏差系数迭代调整未监测点的弹性模量，直至利用有限元模型计算的预测应力与实测应力的误差收敛至设定区间，输出预测应力构建应力分布图谱。The elastic modulus of the unmonitored point is iteratively adjusted according to the residual stress deviation coefficient until the error between the predicted stress calculated by the finite element model and the measured stress converges to a set interval, and the predicted stress is output to construct a stress distribution map.
具体的，基于线性弹性本构方程计算预测应力，对于预测应力，有：Specifically, the predicted stress is calculated based on the linear elastic constitutive equation. ,have:
； ;
式中，为未监测点的弹性模量，为未监测点的应变。其中，未监测点的应变通过有限元模型中未监测点的节点位移量乘以应变位移矩阵得到，应变位移矩阵通过有限元模型建模的输入数据得到。对于修正后的弹性模量，有：In the formula, is the elastic modulus of the unmonitored point, is the strain of the unmonitored point. The strain of the unmonitored point is obtained by multiplying the node displacement of the unmonitored point in the finite element model by the strain displacement matrix, and the strain displacement matrix is obtained by the input data of the finite element model. For the modified elastic modulus ,have:
； ;
式中，为修正前的弹性模量，为材料灵敏度因子，为的符号函数。对当前未监测区域的网格单元弹性模量进行空间插值调整，每次修正步长限幅±5%。经3至5次迭代后检查最大相对误差是否低于10%，达标后终止迭代，输出修正后的全域应力分布图谱；误差收敛为计算的预测应力与实测应力的最大偏差率连续三次迭代均低于阈值的状态。In the formula, is the elastic modulus before correction, is the material sensitivity factor, for The sign function of . The elastic modulus of the grid cells in the currently unmonitored area is adjusted by spatial interpolation, and the step size of each correction is limited to ±5%. After 3 to 5 iterations, check whether the maximum relative error is less than 10%. If it meets the standard, the iteration is terminated and the corrected global stress distribution map is output; the error convergence is the state where the maximum deviation rate between the calculated predicted stress and the measured stress is lower than the threshold for three consecutive iterations.
本方法通过实测应变梯度与理论模型的对比反馈，逆向标定材料参数偏差，利用迭代修正机制消除残余应力计算误差。其技术效果体现在：对复杂装配结构中不可测区域的应力分布实现高精度推算，克服传统有限元分析中因材料参数固化导致的工程预测偏差，为螺栓寿命评估提供可靠的动态应力数据基础。This method reversely calibrates the material parameter deviation by comparing the measured strain gradient with the theoretical model, and eliminates the residual stress calculation error by using an iterative correction mechanism. Its technical effect is reflected in: achieving high-precision calculation of stress distribution in unmeasurable areas in complex assembly structures, overcoming the engineering prediction deviation caused by the solidification of material parameters in traditional finite element analysis, and providing a reliable dynamic stress data basis for bolt life assessment.
可选地，所述将所述应力分布图谱输入预设的疲劳损伤模型，计算螺栓寿命衰减率并将所述实时应变数据与所述运行工况数据中的变桨偏航数据进行时序关联分析，定位外部载荷异常源，得到定位结果包括：Optionally, the step of inputting the stress distribution map into a preset fatigue damage model, calculating the bolt life decay rate, and performing time series correlation analysis on the real-time strain data and the pitch yaw data in the operating condition data to locate the abnormal external load source, and obtaining the positioning result includes:
获取螺栓材料的S-N曲线及历史载荷谱数据，建立应变幅值与疲劳损伤度的映射关系，计算得到螺栓寿命衰减率；Obtain the S-N curve and historical load spectrum data of the bolt material, establish the mapping relationship between strain amplitude and fatigue damage degree, and calculate the bolt life attenuation rate;
具体的，如图4所示，基于材料疲劳试验数据构建S-N曲线，每个数据点对应特定应力幅值下螺栓失效的循环次数。整合机组历史运行中的载荷时间序列，利用雨流计数法统计各个应力幅值的循环次数。根据Miner线性累积损伤法则计算总损伤量，对于疲劳损伤度，其公式为：Specifically, as shown in Figure 4, the SN curve is constructed based on the material fatigue test data. Each data point corresponds to the number of cycles of bolt failure under a specific stress amplitude. The load time series in the historical operation of the unit is integrated, and the number of cycles of each stress amplitude is counted using the rain flow counting method. The total damage is calculated according to the Miner linear cumulative damage law. , the formula is:
； ;
式中，为应力幅值的数量，为第个应力幅值对应的实际循环次数，为第个应力幅值在S-N曲线中对应的破坏循环次数。寿命衰减率定义为疲劳损伤度占临界损伤（D=1）的百分比，当D=0.7时，衰减率为70%。其中，S-N曲线为通过实验获得的材料疲劳特性曲线，横坐标表示应力幅值，纵坐标表示对应循环次数；历史载荷谱为螺栓实际服役过程中记录的载荷时间历程，螺栓寿命衰减曲线如图5所示；疲劳损伤度为基于累计损伤理论计算的疲劳损伤量化指标。In the formula, is the number of stress amplitudes, For the The actual number of cycles corresponding to the stress amplitude is For the The number of failure cycles corresponding to a stress amplitude in the SN curve. The life decay rate is defined as the percentage of fatigue damage to critical damage (D=1). When D=0.7, the decay rate is 70%. Among them, the SN curve is the material fatigue characteristic curve obtained through experiments, the horizontal axis represents the stress amplitude, and the vertical axis represents the corresponding number of cycles; the historical load spectrum is the load-time history recorded during the actual service of the bolt, and the bolt life decay curve is shown in Figure 5; the fatigue damage degree is a quantitative indicator of fatigue damage calculated based on the cumulative damage theory.
对所述应力分布图谱进行雨流计数法处理，提取等效交变应力幅值序列；Processing the stress distribution spectrum by rain flow counting method to extract equivalent alternating stress amplitude sequence;
具体的，将应力分布图谱中每个螺栓位置的时间-应力数据按一分钟窗口分割，采用四峰检测法识别闭合应力循环。对每个循环提取幅值与均值，按照Goodman公式修正平均应力影响，得到等效交变应力幅值序列，修正公式为：Specifically, the time-stress data of each bolt position in the stress distribution map is divided into one-minute windows, and the four-peak detection method is used to identify closed stress cycles. The amplitude and mean are extracted for each cycle, and the average stress effect is corrected according to the Goodman formula to obtain the equivalent alternating stress amplitude sequence. The correction formula is:
； ;
式中，为实际应力幅值，为循环平均应力，为材料极限强度。雨流计数法为将非规则应力波形分解为独立循环的统计方法；等效交变应力幅值为考虑平均应力影响后的等效常幅应力值。In the formula, is the actual stress amplitude, is the cyclic mean stress, is the ultimate strength of the material. The rainflow counting method is a statistical method that decomposes irregular stress waveforms into independent cycles; the equivalent alternating stress amplitude is the equivalent constant amplitude stress value after considering the influence of the average stress.
将所述等效交变应力幅值序列与所述变桨偏航数据进行卷积运算，生成工况耦合的疲劳累积因子，定位外部载荷异常源，得到定位结果。The equivalent alternating stress amplitude sequence is convolved with the pitch yaw data to generate a fatigue accumulation factor coupled with working conditions, locate the abnormal source of the external load, and obtain a positioning result.
具体的，对变桨角度数据采用滑动平均滤波后，与等效交变应力幅值序列进行时域卷积，计算得到卷积值，有：Specifically, the pitch angle data is filtered by sliding average, and then convolved with the equivalent alternating stress amplitude sequence in the time domain to calculate the convolution value ,have:
； ;
其中，为等效交变应力幅值序列，随时间变化的函数，为积分时长，为变桨角度变化率随时间变化的函数，为当前时间，为积分中的时间变量。设定匹配阈值，当卷积峰值超过阈值时，判定变桨动作与应力波动的关联性。遍历所有工况参数，选取最大卷积值对应的参数作为异常源。卷积运算为衡量两信号时序相关性的数学操作；疲劳累积因子为表征外部工况与应力响应的耦合强度指标。in, is the equivalent alternating stress amplitude sequence, which changes with time The function of change, is the integral duration, is the rate of change of pitch angle over time The function of change, is the current time, is the time variable in the integral. Set the matching threshold. When the convolution peak exceeds the threshold, determine the correlation between the pitch action and the stress fluctuation. Traverse all working condition parameters and select the parameter corresponding to the maximum convolution value as the abnormal source. The convolution operation is a mathematical operation to measure the time series correlation of two signals; the fatigue accumulation factor is an indicator of the coupling strength between the external working condition and the stress response.
示例性地，在某2MW机组中，对M24螺栓应用上述方法。其S-N曲线显示150MPa应力幅值对应的破坏循环次数为10000次循环。实测雨流计数得到等效幅值135MPa的循环累计1500次，计算疲劳损伤度D=1500/10000=0.15，即寿命衰减15%。变桨数据卷积分析发现偏航角抖动与应力峰值出现0.8秒延迟，相关性达0.92，定位偏航轴承间隙异常。通过量化损伤与工况关联，精准识别导致螺栓加速老化的外部诱因。For example, in a 2MW unit, the above method is applied to M24 bolts. Its S-N curve shows that the number of failure cycles corresponding to a stress amplitude of 150MPa is 10,000 cycles. The measured rain flow count obtained a cumulative cycle of 1500 cycles with an equivalent amplitude of 135MPa, and the fatigue damage degree was calculated to be D=1500/10000=0.15, that is, the life decay was 15%. The convolution analysis of the pitch data found that there was a 0.8 second delay between the yaw angle jitter and the stress peak, and the correlation reached 0.92, locating the abnormal yaw bearing clearance. By quantifying the correlation between damage and working conditions, the external factors that lead to accelerated aging of bolts can be accurately identified.
可选地，所述方法还包括：Optionally, the method further comprises:
当实测应力与预测应力的偏差持续超过设定次数时，提取各监测点的应力相位延迟特征；When the deviation between the measured stress and the predicted stress continues to exceed the set number of times, the stress phase delay characteristics of each monitoring point are extracted;
具体的，连续5次检测到同一测点应力误差大于15%时，采集实测应力与预测应力的时序数据。进行频域相位分析，通过傅里叶变换获取主频分量的相位差，有：Specifically, when the stress error at the same measuring point is greater than 15% for five consecutive times, the time series data of the measured stress and the predicted stress are collected. Frequency domain phase analysis is performed to obtain the phase difference of the main frequency component through Fourier transform. ,have:
； ;
式中，为实测应力，为预测应力，表示实测滞后于理论响应。相位延迟特征为表征结构动态响应滞后的频域参数。In the formula, is the measured stress, To predict stress, It means that the measured response lags behind the theoretical response. The phase delay feature is a frequency domain parameter that characterizes the lag in the dynamic response of the structure.
根据所述相位延迟特征调整有限元模型中阻尼系数及材料屈服强度的权重比例；Adjusting the weight ratio of the damping coefficient and the material yield strength in the finite element model according to the phase delay characteristics;
具体的，建立相位差与材料参数的映射关系，对于阻尼系数权重和屈服强度权重，其更新规则为，对于更新后的阻尼系数权重，有：Specifically, a mapping relationship between phase difference and material parameters is established, and for the damping coefficient weight and yield strength weight , its update rule is, for the updated damping coefficient weight ,have:
； ;
式中，为阻尼系数的拟合系数，对于更新后的屈服强度权重，有：In the formula, is the fitting coefficient of the damping coefficient, for the updated yield strength weight ,have:
； ;
式中，为屈服强度的拟合系数。当时增加阻尼系数权重以补偿动态响应延迟，降低屈服强度权重以反映塑性变形累积。In the formula, is the fitting coefficient of yield strength. The damping coefficient weight is increased to compensate for the dynamic response delay, and the yield strength weight is reduced to reflect the accumulation of plastic deformation.
将修正后的模型参数存储至历史数据库，作为下次模型初始化的基准值。The modified model parameters are stored in the historical database as the reference values for the next model initialization.
具体的，在数据库中建立参数版本链，保存调整后的阻尼系数、屈服强度及对应的时序标签。下次建模时优先加载最近三次修正结果的平均值作为初始参数。历史数据库为存储模型迭代参数的时序化存储系统。Specifically, a parameter version chain is established in the database to save the adjusted damping coefficient, yield strength and corresponding time series labels. The average of the three most recent correction results is loaded as the initial parameter for the next modeling. The historical database is a time-series storage system for storing model iteration parameters.
本方法通过逆向修正有限元模型参数，补偿环境与材料性能劣化带来的偏差。突破传统模型静态化局限；实现异常源的因果追溯；提升剩余寿命预测的工程实用性；为预防性维护提供直接决策依据。This method compensates for the deviation caused by the environment and material performance degradation by reversely correcting the finite element model parameters. It breaks through the static limitations of traditional models, realizes the causal tracing of abnormal sources, improves the engineering practicality of remaining life prediction, and provides a direct decision-making basis for preventive maintenance.
可选地，所述分级预警信号的生成依据为：Optionally, the generation basis of the graded warning signal is:
构建包含应力波动熵值、温度载荷敏感度及环境腐蚀速率的多维预警参数集；Construct a multidimensional early warning parameter set including stress fluctuation entropy value, temperature load sensitivity and environmental corrosion rate;
具体的，通过实时采集螺栓监测点的应变时序数据，采用滑动窗口分析法提取20分钟内的应力波动序列，运用信息熵理论计算其统计离散度。同时，通过温度传感器获取螺栓表面温度值及其变化率，结合材料热膨胀系数建立温度应力响应曲线，计算单位温度变化的应力偏移量作为温度载荷敏感度。环境腐蚀速率根据盐雾传感器数据与材质耐蚀系数计算腐蚀当量值，整合上述三个参数形成多维向量。Specifically, by collecting the strain time series data of the bolt monitoring point in real time, the sliding window analysis method is used to extract the stress fluctuation sequence within 20 minutes, and the information entropy theory is used to calculate its statistical discreteness. At the same time, the temperature value and its change rate of the bolt surface are obtained through the temperature sensor, and the temperature stress response curve is established in combination with the thermal expansion coefficient of the material. The stress offset per unit temperature change is calculated as the temperature load sensitivity. The environmental corrosion rate calculates the corrosion equivalent value based on the salt spray sensor data and the material corrosion resistance coefficient, and the above three parameters are integrated to form a multidimensional vector.
其中，应力波动熵值为基于频域能量分布的结构应力无序度指标，反映载荷冲击的随机性；温度载荷敏感度为螺栓应力随温度波动产生的偏移响应系数；环境腐蚀速率为金属材料在特定温湿度条件下的单位时间腐蚀厚度；多维预警参数集为多个物理量融合形成的综合评价向量，表征复合材料退化状态。Among them, the stress fluctuation entropy value is an indicator of structural stress disorder based on frequency domain energy distribution, which reflects the randomness of load impact; the temperature load sensitivity is the offset response coefficient of bolt stress caused by temperature fluctuation; the environmental corrosion rate is the corrosion thickness per unit time of metal materials under specific temperature and humidity conditions; the multidimensional warning parameter set is a comprehensive evaluation vector formed by the fusion of multiple physical quantities, which characterizes the degradation state of the composite material.
当单个参数超过一级阈值时触发状态提示，当至少两个参数的组合效应超过二级阈值时触发紧急停运指令。When a single parameter exceeds the first-level threshold, a status prompt is triggered, and when the combined effect of at least two parameters exceeds the second-level threshold, an emergency shutdown command is triggered.
具体的，设置一级阈值为各参数历史数据的95%分位值，二级阈值为通过支持向量机训练得到的复合临界值。例如，当应力波动熵值H>4.2或温度载荷敏感度>0.15MPa/℃时发出黄色预警；若同时熵值超限且环境腐蚀速率>0.1mm/月，则触发停机信号。组合效应采用权重叠加模型：Specifically, the first-level threshold is set as the 95% percentile of the historical data of each parameter, and the second-level threshold is the composite critical value obtained through support vector machine training. For example, when the stress fluctuation entropy value H>4.2 or the temperature load sensitivity>0.15MPa/℃, a yellow warning is issued; if the entropy value exceeds the limit and the environmental corrosion rate>0.1mm/month at the same time, a shutdown signal is triggered. The combined effect adopts a weighted superposition model:
； ;
式中，为应力波动熵值的权重，为温度载荷敏感度的权重，为环境腐蚀速率的权重，当时判定为紧急状态。一级阈值为单一参数的预警触发条件，基于统计学方法定义；二级阈值为多物理量非线性耦合作用下的失效边界，通过机器学习划分决策面；组合效应为多参数交互影响下的失效率加权评估结果。In the formula, is the weight of the stress fluctuation entropy value, is the weight of temperature load sensitivity, is the weight of the environmental corrosion rate, when The first-level threshold is the warning trigger condition of a single parameter, which is defined based on statistical methods; the second-level threshold is the failure boundary under the nonlinear coupling of multiple physical quantities, and the decision surface is divided through machine learning; the combined effect is the weighted evaluation result of the failure rate under the interaction of multiple parameters.
示例性地，检测周期内，环境腐蚀速率因台风过境升至0.13mm/月（超过一级阈值0.1mm/月）触发黄色提示。同时应力波动熵值H=4.8，组合权重值S=0.92，触发紧急状态停运指令。运维团队现场检查发现螺栓表面40%锈蚀并存在应力腐蚀裂纹。单一腐蚀速率超标给出早期预警，复合参数超限准确识别潜在断裂风险，避免法兰面整体失效导致的齿轮箱损毁。多维参数协同判定增强预警可靠性，有效区分正常磨蚀与恶性腐蚀的界限。For example, during the detection period, the environmental corrosion rate rose to 0.13mm/month (exceeding the first-level threshold of 0.1mm/month) due to the passage of the typhoon, triggering a yellow prompt. At the same time, the stress fluctuation entropy value H=4.8, and the combined weight value S=0.92, triggering an emergency shutdown order. The operation and maintenance team found on-site inspection that 40% of the bolt surface was rusted and stress corrosion cracks existed. Exceeding the limit of a single corrosion rate gives an early warning, and exceeding the limit of a composite parameter accurately identifies potential fracture risks, avoiding damage to the gearbox caused by overall failure of the flange surface. Multi-dimensional parameter collaborative judgment enhances the reliability of early warning and effectively distinguishes the boundary between normal abrasion and malignant corrosion.
可选地，所述应力波动熵值的计算包括：Optionally, the calculation of the stress fluctuation entropy value includes:
对指定时间窗内的应变数据进行傅里叶变换，提取预设频段的能量分布特征；Perform Fourier transform on the strain data within the specified time window to extract the energy distribution characteristics of the preset frequency band;
具体的，以60秒为时间窗口采集应变信号，执行快速傅里叶变换（FFT）后的频率精度为0.1Hz。计算频域能量分布时，划分三个特征段；低频段为0.5-5Hz，对应塔筒整体摆动频率；中频段为5-20Hz，对应传动链扭振频率；高频段为20-50Hz，对应螺栓局部松动异响。总能量标准化后，低频能量占比公式为：Specifically, the strain signal is collected in a 60-second time window, and the frequency accuracy after fast Fourier transform (FFT) is 0.1Hz. When calculating the frequency domain energy distribution, three characteristic segments are divided; the low frequency segment is 0.5-5Hz, corresponding to the overall swing frequency of the tower; the medium frequency segment is 5-20Hz, corresponding to the torsional vibration frequency of the transmission chain; the high frequency segment is 20-50Hz, corresponding to the local loosening of the bolts. After the total energy is normalized, the low frequency energy accounts for The formula is:
； ;
式中，为低频段能量积分值，为全频段总能量。傅里叶变换为将时域信号转换为频域能量谱的分析方法；能量分布特征为特定频段能量占全频带的比例值，用于识别振动模态。In the formula, is the energy integral value of the low frequency band, is the total energy of the entire frequency band. Fourier transform is an analysis method that converts time domain signals into frequency domain energy spectra; the energy distribution feature is the ratio of the energy of a specific frequency band to the entire frequency band, which is used to identify vibration modes.
根据所述能量分布特征计算应力波动熵值，当低频段能量占比超过预设占比时判定为谐振风险模式。The stress fluctuation entropy value is calculated according to the energy distribution characteristics, and when the proportion of low-frequency energy exceeds a preset proportion, it is determined to be a resonance risk mode.
具体的，应力波动熵值计算方式为：Specifically, the stress fluctuation entropy value The calculation method is:
； ;
其中，为低频段归一化能量占比,为中频段归一化能量占比,为高频段归一化能量占比，为低频段能量，为中频段能量，为高频段能量，为总能量。预设占比可以是70%，若且，判定为低频谐振主导模式，特征为单一频率能量高度集中。谐振风险模式为结构在窄带激励下引发的共振状态，导致应力幅值倍增。in, is the normalized energy ratio of the low frequency band, is the normalized energy ratio of the mid-frequency band, is the normalized energy proportion of the high frequency band, is the low frequency energy, is the mid-frequency energy, is the high frequency energy, is the total energy. The default ratio can be 70%. and , which is determined to be a low-frequency resonance dominant mode, characterized by a high concentration of single-frequency energy. The resonance risk mode is a resonant state caused by the structure under narrow-band excitation, resulting in a doubling of the stress amplitude.
示例性地，现场监测到螺栓应力低频能量占比达83%，应力波动熵值。触发谐振预警后检查发现叶轮质量块脱落导致转速波动，诱发2.4Hz塔筒摆动。维护后低频能量占比降至52%，恢复正常分布。通过频段能量聚焦特性识别隐性共振源，避免持续谐振导致的螺栓疲劳断裂。熵值量化显著提升对异常振动模式的捕捉灵敏度。For example, the low-frequency energy of bolt stress was monitored on site to account for 83%, and the stress fluctuation entropy value After the resonance warning was triggered, it was found that the impeller mass block fell off, causing the speed to fluctuate, inducing the 2.4Hz tower swing. After maintenance, the proportion of low-frequency energy dropped to 52%, returning to normal distribution. The hidden resonance source was identified through the frequency band energy focusing characteristics to avoid fatigue fracture of bolts caused by continuous resonance. Entropy value quantification significantly improves the sensitivity of capturing abnormal vibration modes.
可选地，所述方法还包括：Optionally, the method further comprises:
当识别到谐振风险模式时，同步采集机组振动传感器的轴向加速度数据；When a resonance risk mode is identified, the axial acceleration data of the unit vibration sensor is collected synchronously;
具体的，在触发谐振预警后，以2000Hz采样率同步获取齿轮箱轴向振动加速度信号。通过抗混叠滤波保留0-1000Hz有效频宽，采用三阶巴特沃斯滤波器消除高频噪声。数据对齐方式采用IEEE 1588精确时间协议（PTP），应变与加速度信号时标误差小于1ms。轴向加速度数据为沿传动链轴线方向的振动强度量化指标；同步采集为多传感器数据的时间轴对齐技术，确保事件关联性分析。Specifically, after the resonance warning is triggered, the gearbox axial vibration acceleration signal is synchronously acquired at a sampling rate of 2000Hz. The effective bandwidth of 0-1000Hz is retained through anti-aliasing filtering, and a third-order Butterworth filter is used to eliminate high-frequency noise. The data alignment method uses the IEEE 1588 Precision Time Protocol (PTP), and the time error between the strain and acceleration signals is less than 1ms. The axial acceleration data is a quantitative indicator of the vibration intensity along the axis of the transmission chain; the synchronous acquisition is a time axis alignment technology for multi-sensor data to ensure event correlation analysis.
将所述加速度数据与所述低频段能量进行幅频相关性分析，若相关系数大于预设相关值则在维护策略中添加振动抑制装置的调试任务。An amplitude-frequency correlation analysis is performed on the acceleration data and the low-frequency band energy, and if the correlation coefficient is greater than a preset correlation value, a debugging task of the vibration suppression device is added to the maintenance strategy.
具体的，采用交叉谱密度法计算加速度幅值与应力低频段能量的相关系数：Specifically, the acceleration amplitude is calculated using the cross spectral density method: Low frequency energy with stress Correlation coefficient :
； ;
式中，为协方差函数，为加速度幅值的标准差，为应力低频段能量的标准差。当时判定两者强相关，需在维护清单中添加动力吸振器调平或阻尼器更换任务。幅频相关性分析为评估振动与应力信号频率成分匹配度的数学方法；振动抑制装置为用于吸收或耗散机械振动能量的附加设备。In the formula, is the covariance function, is the standard deviation of the acceleration amplitude, is the standard deviation of the stress low frequency band energy. If the two are strongly correlated, it is necessary to add the task of dynamic vibration absorber leveling or damper replacement to the maintenance list. Amplitude-frequency correlation analysis is a mathematical method to evaluate the matching degree of frequency components of vibration and stress signals; vibration suppression device is an additional device used to absorb or dissipate mechanical vibration energy.
示例性地，谐振预警触发后，同步振动数据显示3.7Hz强加速度分量，与应变信号低频能量相关系数。维护团队加装调频质量阻尼器（TMD）后，振动幅值下降56%，应力波动熵值回归正常范围。通过跨传感器数据分析精准定位振动-应力耦合路径，指导针对性减振措施部署，解决复合激励引发的螺栓阵列失效问题。For example, after the resonance warning is triggered, the synchronous vibration data shows a 3.7 Hz strong acceleration component, which is correlated with the low-frequency energy of the strain signal. After the maintenance team installed a tuned mass damper (TMD), the vibration amplitude dropped by 56% and the stress fluctuation entropy returned to the normal range. Through cross-sensor data analysis, the vibration-stress coupling path was accurately located, guiding the deployment of targeted vibration reduction measures to solve the problem of bolt array failure caused by composite excitation.
该方法通过多维参数耦合分析（应力波动、温度敏感、环境腐蚀）构建动态预警体系，结合频域能量熵评估与振动信号协同验证，实现螺栓健康状态的精细化诊断。谐振风险检测模块通过频段能量聚焦识别结构共振，同步振动关联分析精确定位振源。其有益效果包括：突破单一参数监测的误判局限，通过多物理场数据融合区分正常应变与恶性损伤；谐振模式与振动源的实时匹配提升故障溯源效率；预警策略分级递进，既避免频繁误报又确保失效风险及时遏制。示例性验证中，某潮间带风电项目应用本方法后，在台风季前通过腐蚀速率与熵值组合预警发现螺栓群渗氢脆化，避免整机倒塔事故。通过熵值监测与阻尼器联调，使螺栓平均服役寿命延长。This method constructs a dynamic early warning system through multi-dimensional parameter coupling analysis (stress fluctuation, temperature sensitivity, environmental corrosion), combines frequency domain energy entropy evaluation with vibration signal collaborative verification, and realizes refined diagnosis of bolt health status. The resonance risk detection module identifies structural resonance through frequency band energy focusing, and accurately locates the vibration source through synchronous vibration correlation analysis. Its beneficial effects include: breaking through the misjudgment limitation of single parameter monitoring, distinguishing normal strain from malignant damage through multi-physical field data fusion; real-time matching of resonance mode and vibration source improves fault tracing efficiency; early warning strategy is hierarchical and progressive, which not only avoids frequent false alarms but also ensures timely containment of failure risks. In the exemplary verification, after applying this method to a certain intertidal zone wind power project, hydrogen embrittlement of the bolt group was discovered through a combined early warning of corrosion rate and entropy value before the typhoon season, avoiding the accident of the whole machine tower collapse. Through entropy monitoring and damper adjustment, the average service life of the bolts is extended.
基于相同的发明构思，如图6所示，本发明还提供了一种风电螺栓状态的检测系统，所述系统包括：Based on the same inventive concept, as shown in FIG6 , the present invention further provides a wind power bolt status detection system, the system comprising:
无线应变传感器组，部署在塔筒每层预设周向位置，用于获取各监测点的实时应变数据；Wireless strain sensor groups are deployed at preset circumferential positions on each floor of the tower to obtain real-time strain data at each monitoring point;
工况数据采集模块，用于从风电场远动通信系统实时获取机组的运行工况数据，包括风速、变桨偏航数据、发电机转矩及叶轮转速；The operating data acquisition module is used to obtain the operating data of the unit in real time from the wind farm telecontrol communication system, including wind speed, pitch and pitch data, generator torque and impeller speed;
有限元模型构建模块，用于根据所述运行工况数据动态生成塔筒结构的有限元模型，利用所述实时应变数据修正所述有限元模型；A finite element model building module, used to dynamically generate a finite element model of the tower structure according to the operating condition data, and to modify the finite element model using the real-time strain data;
应力分布生成模块，用于结合所述有限元模型和所述实时应变数据，采用应力场梯度补偿算法对未监测点的应变进行推算，生成全塔筒螺栓的应力分布图谱；A stress distribution generation module, for combining the finite element model and the real-time strain data, using a stress field gradient compensation algorithm to calculate the strain of unmonitored points, and generating a stress distribution map of the entire tower bolts;
异常分析定位模块，用于将所述应力分布图谱输入预设的疲劳损伤模型，计算螺栓寿命衰减率并将所述实时应变数据与所述运行工况数据中的变桨偏航数据进行时序关联分析，定位外部载荷异常源，得到定位结果；An abnormality analysis and positioning module is used to input the stress distribution map into a preset fatigue damage model, calculate the bolt life decay rate and perform time series correlation analysis on the real-time strain data and the pitch yaw data in the operating condition data, locate the abnormal source of the external load, and obtain a positioning result;
预警决策模块，用于当检测到所述寿命衰减率超过预设阈值时，生成分级预警信号并根据所述定位结果输出维护策略。The early warning decision module is used to generate a graded early warning signal and output a maintenance strategy according to the positioning result when it is detected that the life decay rate exceeds a preset threshold.
需要说明的是上述各个单元之间的电气连接，并不必然表示线路的直接连接，间接连接的方式，只要实现本发明的目的即可适用于本发明的实施例。以上所述者，仅为本发明的示例性实施例，不能以此限定本发明的范围。It should be noted that the electrical connection between the above-mentioned units does not necessarily mean direct connection of the lines, and the indirect connection mode can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention.
即但凡依本发明教导所作的等效变化与修饰，皆仍属本发明涵盖的范围内。本领域技术人员在考虑说明书及实践真理的公开后，将容易想到本发明的其他实施方案。本申请旨在涵盖本发明的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本发明的一般性原理并包括本发明未记载的本技术领域中的公知常识或惯用技术手段。That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present invention. This application is intended to cover any variation, use or adaptive change of the present invention, which follows the general principles of the present invention and includes common knowledge or customary technical means in the art that are not described in the present invention.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510479460.5ACN119984799B (en) | 2025-04-17 | 2025-04-17 | Method and system for detecting state of wind power bolt |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510479460.5ACN119984799B (en) | 2025-04-17 | 2025-04-17 | Method and system for detecting state of wind power bolt |
| Publication Number | Publication Date |
|---|---|
| CN119984799A CN119984799A (en) | 2025-05-13 |
| CN119984799Btrue CN119984799B (en) | 2025-07-04 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510479460.5AActiveCN119984799B (en) | 2025-04-17 | 2025-04-17 | Method and system for detecting state of wind power bolt |
| Country | Link |
|---|---|
| CN (1) | CN119984799B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120159726B (en)* | 2025-05-16 | 2025-07-18 | 湖南理工职业技术学院 | A wind power generation state monitoring method and system |
| CN120234572B (en)* | 2025-06-03 | 2025-08-26 | 新一代工业智能科技(天津)有限公司 | Excavator bucket tooth detection method, system and electronic equipment |
| CN120275038B (en)* | 2025-06-09 | 2025-08-22 | 龙岩学院 | High-speed rotation transmission device online monitoring method based on multi-sensor cooperation |
| CN120538824B (en)* | 2025-07-24 | 2025-09-30 | 冈田精机(常州)有限公司 | A high-precision spindle performance testing method and system |
| CN120522009B (en)* | 2025-07-25 | 2025-09-19 | 上海高博航空制造有限公司 | An online detection and control system for aviation seat production and processing |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114893360A (en)* | 2022-05-23 | 2022-08-12 | 国家电投集团科学技术研究院有限公司 | Method and system for identifying abnormal vibration and monitoring running state of tower of wind turbine generator |
| CN117006001A (en)* | 2023-08-10 | 2023-11-07 | 苏州先机动力科技有限公司 | Vibration sensor-based health management system and monitoring method for fan tower barrel-bolt |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4290074A1 (en)* | 2022-06-09 | 2023-12-13 | Akselos S.A. | Method and system for modelling a wind power generation structure |
| CN115750229A (en)* | 2022-11-10 | 2023-03-07 | 中国华能集团清洁能源技术研究院有限公司 | Wind turbine generator system all-state monitoring system based on multi-source sensing |
| CN118133638B (en)* | 2024-05-08 | 2024-08-02 | 中铁北京工程局集团有限公司 | Method and system for monitoring construction of movable formwork based on finite element simulation |
| CN118601811A (en)* | 2024-06-28 | 2024-09-06 | 中节能风力发电股份有限公司 | A wind turbine tower state monitoring system and method |
| CN118709497A (en)* | 2024-08-27 | 2024-09-27 | 北京云庐科技有限公司 | Wind turbine tower monitoring method, system and medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114893360A (en)* | 2022-05-23 | 2022-08-12 | 国家电投集团科学技术研究院有限公司 | Method and system for identifying abnormal vibration and monitoring running state of tower of wind turbine generator |
| CN117006001A (en)* | 2023-08-10 | 2023-11-07 | 苏州先机动力科技有限公司 | Vibration sensor-based health management system and monitoring method for fan tower barrel-bolt |
| Publication number | Publication date |
|---|---|
| CN119984799A (en) | 2025-05-13 |
| Publication | Publication Date | Title |
|---|---|---|
| CN119984799B (en) | Method and system for detecting state of wind power bolt | |
| US7895018B2 (en) | Event monitoring via combination of signals | |
| Oh et al. | A novel method and its field tests for monitoring and diagnosing blade health for wind turbines | |
| CN104142229B (en) | A kind of wind power generating set flange bolt on-line monitoring and fault diagnosis system | |
| Li et al. | A review of damage detection methods for wind turbine blades | |
| CA2868643C (en) | Wind turbine and method for evaluating the health state of the blades thereof | |
| US20100004878A1 (en) | Wind turbine monitoring | |
| CN104995402B (en) | It is abnormal to detect blade construction | |
| US20090246019A1 (en) | Wind turbine monitoring | |
| BRPI0711641A2 (en) | process and device for monitoring rotor blade status in wind power installations | |
| CA2653351A1 (en) | Wind turbine monitoring | |
| CN109869286A (en) | Vibration of wind generating set state monitoring method | |
| CN106677996A (en) | Method for detecting vibration anomaly of tower drum of wind generating set | |
| CN103245913B (en) | Method and system for detecting and analyzing subsynchronous oscillation signals of large generator set | |
| GB2459726A (en) | A method of detecting ice formation on wind turbine blades and other methods of wind turbine monitoring | |
| KR101358397B1 (en) | Fault detection appaturas and method for wind turbin base on acceleration sensor and output power | |
| KR102456262B1 (en) | Prediction Method and Systems of Wind Turbine Load and Life-time Based On Vibration Data | |
| EP3642481B1 (en) | A method for determining wind turbine blade edgewise load recurrence | |
| CN119063779A (en) | A method and system for detecting the transport status of a floating body of a floating photovoltaic power station | |
| Faulkner et al. | Structural health monitoring systems in difficult environments—offshore wind turbines | |
| Wang et al. | Degradation assessment of wind turbine based on additional load measurements | |
| EP4303434A1 (en) | Method for monitoring, localizing and providing alarm when cracks are observed in wind turbine blades | |
| Wait et al. | Wind-induced instabilities and monitoring of wind turbine | |
| JP2017089590A (en) | Wind power generator and wind farm | |
| Entezami et al. | Wind turbine condition monitoring system |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |