[go: up one dir, main page]

CN112836867A - Method and system for detecting wear amount of brakes of offshore wind turbines - Google Patents

Method and system for detecting wear amount of brakes of offshore wind turbines Download PDF

Info

Publication number
CN112836867A
CN112836867A CN202110084629.9A CN202110084629A CN112836867A CN 112836867 A CN112836867 A CN 112836867A CN 202110084629 A CN202110084629 A CN 202110084629A CN 112836867 A CN112836867 A CN 112836867A
Authority
CN
China
Prior art keywords
data
brake
wear amount
offshore wind
wear
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202110084629.9A
Other languages
Chinese (zh)
Inventor
王鸿
刘衡
王致杰
梅晓娟
许斌斌
王和尧
姚钦徽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Dianji University
Original Assignee
Shanghai Dianji University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Dianji University filed Critical Shanghai Dianji University
Priority to CN202110084629.9A priority Critical patent/CN112836867A/en
Publication of CN112836867A publication Critical patent/CN112836867A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
    • G06F16/2465—Query processing support for facilitating data mining operations in structured databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • G—PHYSICS
    • G08—SIGNALLING
    • G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
    • G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
    • G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Software Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • General Business, Economics & Management (AREA)
  • Artificial Intelligence (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Quality & Reliability (AREA)
  • Marketing (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Fuzzy Systems (AREA)
  • Signal Processing (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Wind Motors (AREA)

Abstract

本发明涉及一种海上风力发电机组制动闸磨损量的检测方法及系统，方法包括以下步骤：获取制动闸的运行数据和制动闸的磨损量；自运行数据中提取特征数据，得到由特征数据和磨损量构成的样本数据集；构建BP神经网络，包括输入层、隐藏层和输出层；基于样本数据集，对BP神经网络进行训练，得到磨损量预测模型；获取海上风力发电机组制动闸的运行数据，自运行数据中提取特征数据，输入磨损量预测模型，得到制动闸的磨损量预测值。与现有技术相比，本发明获取制动闸的运行数据，通过BP神经网络预测制动闸的磨损量，可以在日常运行中了解海上风力发电机制动闸的磨损情况，进而在制动闸产生故障之前进行主动维修，提高了整机的运行可靠性。

Figure 202110084629

The invention relates to a method and a system for detecting the wear amount of a brake of an offshore wind turbine. The method comprises the following steps: acquiring operating data of the brake and the wear amount of the brake; extracting characteristic data from the operating data to obtain A sample data set composed of feature data and wear amount; construct a BP neural network, including input layer, hidden layer and output layer; train the BP neural network based on the sample data set to obtain a wear amount prediction model; obtain the offshore wind turbine system The operating data of the brake, extract the characteristic data from the operating data, input the prediction model of the wear amount, and obtain the predicted value of the wear amount of the brake. Compared with the prior art, the present invention obtains the operation data of the brake, and predicts the wear amount of the brake through the BP neural network, so that the wear of the brake of the offshore wind turbine can be known in the daily operation. Active maintenance is carried out before failure occurs, which improves the operational reliability of the whole machine.

Figure 202110084629

Description

Method and system for detecting abrasion loss of brake of offshore wind generating set
Technical Field
The invention relates to the field of wind power generation, in particular to a method and a system for detecting the abrasion loss of a brake of an offshore wind generating set.
Background
Wind power generation is the most potential renewable energy power generation technology except for hydroelectric power generation, and in recent years, wind power generation has been rapidly developed in China, and land power generation has become popular. In order to further utilize wind resources, offshore wind power generation is starting and developing vigorously, and due to the fact that offshore wind speed is high and is not affected by obstacles and surface roughness, wind speed and wind direction are stable, turbulence is low, and offshore wind power development value is high.
When a fan is overhauled and maintained or in a strong wind state, shutdown is realized through a brake, the brake performance of the fan is inevitably influenced by continuous abrasion of the brake in the long-term use process, so that the safe operation of the fan is endangered, and particularly in an offshore wind generating set, the importance of online monitoring and service life prediction of the brake of the wind driven generator is more and more prominent.
In the prior art, an offshore wind generating set does not have a brake wear amount detection device, the brake wear amount is difficult to automatically measure, the brake wear amount can only be manually and periodically checked and maintained, the brake wear amount is immediately replaced once damage is found, real-time monitoring cannot be achieved, and a runaway phenomenon is possible to happen once the brake fails, so that danger is brought, and great loss is also caused.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a method and a system for detecting the brake wear of an offshore wind turbine generator system.
The purpose of the invention can be realized by the following technical scheme:
a method for detecting abrasion loss of a brake of an offshore wind generating set comprises the following steps:
s1: acquiring historical data, wherein the historical data comprises operation data of a brake and the abrasion loss of the brake;
s2: extracting n (n >0) pieces of feature data from the operating data, and preprocessing the feature data to obtain a sample data set consisting of the feature data and the abrasion loss;
s3: constructing a three-layer BP neural network, which comprises an input layer, a hidden layer and an output layer, wherein the number of neurons in the input layer is n, the number of neurons in the hidden layer is 2n +1, and the number of neurons in the output layer is 1;
s4: training the BP neural network based on the sample data set, and updating the weight of the BP neural network according to the following formula in the training process:
Figure BDA0002910378180000021
Figure BDA0002910378180000022
wherein, Δ wkjRepresenting input and hidden layersThe connection weight of (1); Δ vikRepresenting the connection weight of the hidden layer and the output layer; q represents the number of iterations in the training process; alpha and beta represent learning rate, gamma represents momentum factor, the value is (0, 1), when weight is updated, the ratio of weight and error in current iteration can be flexibly adjusted through gamma, and E represents error between expected output and actual output of output neuron;
s5: repeating the step S4 until the iteration number is equal to the preset iteration number threshold or the prediction error of the BP neural network is smaller than the preset training error threshold, so as to obtain a wear loss prediction model;
s6: the method comprises the steps of obtaining operation data of a brake of the offshore wind generating set, extracting characteristic data from the operation data, preprocessing the characteristic data, inputting a wear loss prediction model, and obtaining a wear loss prediction value of the brake.
Further, step S7 is also included, which specifically includes: after the preset time period, step S6 is executed, and the actual wear amount of the brake is obtained at the same time, and if the error between the actual wear amount and the predicted wear amount is greater than the preset model error threshold, step S1 is repeated.
Further, in the steps S2 and S6, before extracting the feature data from the operation data, data cleaning is further included, specifically: and denoising the operating data, and clearing abnormal data in the operating data, wherein the abnormal data is the operating data with a vacant field or the operating data with a field value not in a field specified interval.
Further, in the steps S2 and S6, the preprocessing the feature data includes data normalization, where the normalization formula is:
Figure BDA0002910378180000023
wherein x represents a characteristic data value, max represents a maximum value of the characteristic data, min represents a minimum value of the characteristic data, x represents a maximum value of the characteristic data, andnewrepresenting the normalized feature data value.
Further, in step S5, the training error threshold value is 1%.
Further, after obtaining the predicted wear amount of the brake in step S6, the method further includes: and obtaining the service life predicted value of the brake according to the model of the brake and the wear loss predicted value.
A detection system for the abrasion loss of a brake of an offshore wind generating set is based on the detection method for the abrasion loss of the brake of the offshore wind generating set, and comprises the following steps:
the data acquisition device is used for acquiring the operation data of the brake;
the data analysis platform outputs a predicted value of the abrasion loss of the brake based on the abrasion loss prediction model and the operation data of the brake;
the wireless communication device is respectively in communication connection with the data acquisition device and the data analysis platform and is used for transmitting the operation data of the brake to the data analysis platform;
and the storage device is connected with the data analysis platform and is used for storing the running data and the predicted value of the wear loss of the brake.
Further, the data acquisition device comprises an AD conversion circuit and a signal amplification circuit.
Further, the wireless communication device performs data transmission through a GPRS network.
Furthermore, the detection system also comprises a local storage device and a display system, wherein the local storage device is electrically connected with the data acquisition device and is used for storing the operation data of the brake; and the display system is connected with the data analysis platform and is used for displaying the predicted value of the abrasion loss of the brake.
Compared with the prior art, the invention has the following beneficial effects:
(1) by acquiring the operation data of the brake, and predicting the abrasion loss of the brake through the BP neural network, the abrasion condition of the brake of the offshore wind driven generator can be known in daily operation, active maintenance is carried out before the brake breaks down, and the operation reliability of the whole machine is improved.
(2) Compared with the traditional training algorithm, the weight updating formula in the BP neural network training process is improved, the weight and the ratio of errors in the current iteration can be flexibly adjusted when the weight is updated, and the algorithm performance is higher.
(3) The running data of the brake is transmitted to the data analysis platform through the wireless communication device, the abrasion loss is predicted on the data analysis platform, and the local storage device is further arranged, so that the safety of data storage is guaranteed when wireless communication fails.
Drawings
FIG. 1 is a flow chart of a method for detecting abrasion loss of a brake of an offshore wind turbine generator system.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Example 1:
a method for detecting the abrasion loss of a brake of an offshore wind generating set is shown in figure 1 and comprises the following steps:
s1: acquiring historical data, wherein the historical data comprises operation data of a brake and the abrasion loss of the brake;
s2: extracting n (n >0) pieces of feature data from the operating data, and preprocessing the feature data to obtain a sample data set consisting of the feature data and the abrasion loss;
s3: constructing a three-layer BP neural network, which comprises an input layer, a hidden layer and an output layer, wherein the number of neurons in the input layer is n, the number of neurons in the hidden layer is 2n +1, and the number of neurons in the output layer is 1;
s4: training the BP neural network based on the sample data set, and updating the weight of the BP neural network according to the following formula in the training process:
Figure BDA0002910378180000041
Figure BDA0002910378180000042
wherein, Δ wkjRepresenting the connection weight of the input layer and the hidden layer; Δ vikRepresenting the connection weight of the hidden layer and the output layer; q represents the number of iterations in the training process; alpha and beta represent learning rate, gamma represents momentum factor, the value is (0, 1), when weight is updated, the ratio of weight and error in current iteration can be flexibly adjusted through gamma, the performance of training algorithm is improved, and E represents error between expected output and actual output of output neuron;
s5: repeating the step S4 until the iteration number is equal to the preset iteration number threshold or the prediction error of the BP neural network is smaller than the preset training error threshold, so as to obtain a wear loss prediction model;
s6: the method comprises the steps of obtaining operation data of a brake of the offshore wind generating set, extracting characteristic data from the operation data, preprocessing the characteristic data, inputting a wear loss prediction model, and obtaining a wear loss prediction value of the brake.
S7: after the preset time period, step S6 is executed, and the actual wear amount of the brake is obtained at the same time, and if the error between the actual wear amount and the predicted wear amount is greater than the preset model error threshold, step S1 is repeated.
After a period of time, the error between the actual wear loss and the predicted wear loss value can be detected, if the error is too large, the prediction effect of the wear loss prediction model is not ideal, the latest data is obtained again, and the wear loss prediction model is retrained.
The operation data of the brake includes various information such as time, operation speed, braking information, voltage, current, and the like, and in steps S2 and S6, before extracting the characteristic data from the operation data, the method further includes data cleaning, specifically: and denoising the operating data, and clearing abnormal data in the operating data, wherein the abnormal data is the operating data with a vacant field or the operating data with a field value not in a field specified interval. Such as running data with missing time, running data with missing running speed, running data with a negative time value, etc.
In order to eliminate the influence of dimension between different feature data, in steps S2 and S6, the feature data are normalized by the following formula:
Figure BDA0002910378180000051
wherein x represents a characteristic data value, max represents a maximum value of the characteristic data, min represents a minimum value of the characteristic data, x represents a maximum value of the characteristic data, andnewrepresenting the normalized feature data value.
In this embodiment, the maximum number of iterations is 500, and the value of the training error threshold is 1%.
In step S6, after the predicted wear amount value of the brake is obtained, the predicted life value of the brake can be obtained according to the model number and the predicted wear amount value of the brake.
A detection system for brake wear loss of an offshore wind generating set comprises:
the data acquisition device is used for acquiring the operation data of the brake; the data acquisition device comprises an AD conversion circuit and a signal amplification circuit, converts received information to form a data packet, and sends the data packet through the wireless communication device.
In order to ensure the reliability of data storage, a local storage device can be arranged and is electrically connected with the data acquisition device and used for storing the operation data of the brake; once the wireless transmission fails, the data in the local storage may be used.
The data analysis platform outputs a predicted value of the abrasion loss of the brake based on the abrasion loss prediction model and the operation data of the brake; and after receiving the data, the data analysis platform processes the data and inputs the data into the wear loss prediction model to obtain the wear loss prediction value of the brake. A display system can be arranged to display the operation data of the brake, the predicted value of the abrasion loss and some working parameters of the wind generating set.
The wireless communication device (WTD) is respectively in communication connection with the data acquisition device and the data analysis platform and is used for transmitting the operation data of the brake to the data analysis platform; and data transmission is carried out through a GPRS network, and bidirectional data transmission between the data acquisition device and the data analysis platform is realized.
And the storage device is connected with the data analysis platform and is used for storing the running data and the predicted value of the wear loss of the brake. The storage device can use a cloud storage platform, and stored data can be checked and analyzed more flexibly in subsequent work.
And an alarm system can be further arranged, and when the obtained predicted value of the wear loss exceeds a preset safety threshold value, alarm information is sent out to remind a worker to maintain or replace the brake.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.

Claims (10)

1.一种海上风力发电机组制动闸磨损量的检测方法，其特征在于，包括以下步骤：1. a detection method of offshore wind power generating set brake wear amount, is characterized in that, comprises the following steps: S1：获取历史数据，所述历史数据包括制动闸的运行数据和制动闸的磨损量；S1: Obtain historical data, the historical data includes the operating data of the brake and the wear amount of the brake; S2：自运行数据中提取n(n>0)个特征数据，对特征数据进行预处理，得到由特征数据和磨损量构成的样本数据集；S2: extract n (n>0) characteristic data from the operating data, preprocess the characteristic data, and obtain a sample data set composed of characteristic data and wear amount; S3：构建三层BP神经网络，包括输入层、隐藏层和输出层，输入层神经元的数量为n，隐藏层神经元的数量为2n+1，输出层神经元的数量为1；S3: Build a three-layer BP neural network, including input layer, hidden layer and output layer, the number of neurons in the input layer is n, the number of neurons in the hidden layer is 2n+1, and the number of neurons in the output layer is 1; S4：基于样本数据集，对BP神经网络进行训练，在训练过程中按照以下公式更新BP神经网络的权重：S4: Based on the sample data set, the BP neural network is trained, and the weight of the BP neural network is updated according to the following formula during the training process:
Figure FDA0002910378170000011
Figure FDA0002910378170000011
Figure FDA0002910378170000012
Figure FDA0002910378170000012
 其中，Δwkj表示输入层与隐藏层的连接权重；Δvik表示隐藏层与输出层的连接权重；q表示训练过程中的迭代次数；α和β表示学习率，γ表示动量因子，E表示期望输出与输出神经元的实际输出之间的误差；Among them, Δw kj represents the connection weight between the input layer and the hidden layer; Δv ik represents the connection weight between the hidden layer and the output layer; q represents the number of iterations in the training process; α and β represent the learning rate, γ represents the momentum factor, and E represents the expectation The error between the output and the actual output of the output neuron; S5：重复步骤S4，直至迭代次数等于预设置的迭代次数阈值或BP神经网络的预测误差小于预设置的训练误差阈值，得到磨损量预测模型；S5: Repeat step S4 until the number of iterations is equal to the preset number of iterations threshold or the prediction error of the BP neural network is less than the preset training error threshold, and the wear amount prediction model is obtained; S6：获取海上风力发电机组制动闸的运行数据，自运行数据中提取特征数据，对特征数据进行预处理，输入磨损量预测模型，得到制动闸的磨损量预测值。S6: Obtain the operation data of the brake of the offshore wind turbine, extract characteristic data from the operation data, preprocess the characteristic data, input the wear amount prediction model, and obtain the wear amount prediction value of the brake. 2.根据权利要求1所述的一种海上风力发电机组制动闸磨损量的检测方法，其特征在于，还包括步骤S7，具体为：经过预设置的时间周期后，执行步骤S6，并同时获取制动闸的实际磨损量，若实际磨损量与磨损量预测值之间的误差大于预设置的模型误差阈值，则重复步骤S1。2. The method for detecting the wear amount of the brake of an offshore wind turbine according to claim 1, further comprising step S7, specifically: after a preset time period, step S6 is performed, and simultaneously Obtain the actual wear amount of the brake, if the error between the actual wear amount and the predicted value of the wear amount is greater than the preset model error threshold, repeat step S1. 3.根据权利要求1所述的一种海上风力发电机组制动闸磨损量的检测方法，其特征在于，所述步骤S2和S6中，自运行数据中提取特征数据之前，还包括数据清洗，具体为：对运行数据进行去噪处理，清除运行数据中的异常数据，所述异常数据为字段空缺的运行数据、或字段值不在字段规定区间的运行数据。3. The method for detecting the wear amount of an offshore wind turbine generator set according to claim 1, wherein in the steps S2 and S6, before extracting characteristic data from the operating data, it also includes data cleaning, Specifically, the operation data is denoised, and the abnormal data in the operation data is removed, and the abnormal data is the operation data with vacant fields or the operation data whose field values are not within the specified range of the fields. 4.根据权利要求1所述的一种海上风力发电机组制动闸磨损量的检测方法，其特征在于，所述步骤S2和S6中，对特征数据进行预处理包括数据归一化，归一化公式为：4. The method for detecting the wear amount of the brake of an offshore wind turbine according to claim 1, wherein in the steps S2 and S6, preprocessing the characteristic data includes data normalization, normalization The formula is:
Figure FDA0002910378170000021
Figure FDA0002910378170000021
 其中，x表示特征数据值，max表示特征数据的最大值，min表示特征数据的最小值，xnew表示归一化后的特征数据值。Among them, x represents the feature data value, max represents the maximum value of the feature data, min represents the minimum value of the feature data, and x new represents the normalized feature data value. 5.根据权利要求1所述的一种海上风力发电机组制动闸磨损量的检测方法，其特征在于，所述步骤S5中，训练误差阈值的取值为1％。5 . The method for detecting the wear amount of the brake of an offshore wind turbine according to claim 1 , wherein, in the step S5 , the value of the training error threshold is 1%. 6 . 6.根据权利要求1所述的一种海上风力发电机组制动闸磨损量的检测方法，其特征在于，所述步骤S6中，得到制动闸的磨损量预测值之后，还包括：根据制动闸的型号和磨损量预测值得到制动闸的寿命预测值。6 . The method for detecting the wear amount of the brake of an offshore wind turbine according to claim 1 , wherein in the step S6 , after obtaining the predicted value of the wear amount of the brake, the method further comprises: The type of brake and the predicted value of wear amount are used to obtain the predicted value of life of the brake. 7.一种海上风力发电机组制动闸磨损量的检测系统，其特征在于，基于如权利要求1-6中任一所述的海上风力发电机组制动闸磨损量的检测方法，包括：7. A detection system for brake wear of offshore wind turbines, characterized in that, based on the method for detecting wear of brakes of offshore wind turbines according to any one of claims 1-6, comprising: 数据采集装置，用于采集制动闸的运行数据；A data acquisition device, used to collect the operating data of the brake; 数据分析平台，基于磨损量预测模型和制动闸的运行数据，输出制动闸的磨损量预测值；The data analysis platform, based on the wear prediction model and the operating data of the brake, outputs the predicted value of the wear of the brake; 无线通信装置，分别与数据采集装置和数据分析平台通信连接，用于将制动闸的运行数据传输至数据分析平台；The wireless communication device is connected to the data acquisition device and the data analysis platform respectively, and is used for transmitting the operation data of the brake to the data analysis platform; 存储装置，与数据分析平台连接，用于存储制动闸的运行数据和磨损量预测值。The storage device, connected with the data analysis platform, is used for storing the operation data of the brake brake and the predicted value of the wear amount. 8.根据权利要求7所述的一种海上风力发电机组制动闸磨损量的检测系统，其特征在于，所述数据采集装置包括AD转换电路和信号放大电路。8 . The detection system for brake wear of offshore wind turbines according to claim 7 , wherein the data acquisition device comprises an AD conversion circuit and a signal amplification circuit. 9 . 9.根据权利要求7所述的一种海上风力发电机组制动闸磨损量的检测系统，其特征在于，所述无线通信装置通过GPRS网络进行数据传输。9 . The system for detecting the wear amount of brakes of offshore wind turbines according to claim 7 , wherein the wireless communication device transmits data through a GPRS network. 10 . 10.根据权利要求7所述的一种海上风力发电机组制动闸磨损量的检测系统，其特征在于，所述检测系统还包括本地存储装置，与数据采集装置电性连接，用于存储制动闸的运行数据。10 . The detection system for brake wear amount of offshore wind turbines according to claim 7 , wherein the detection system further comprises a local storage device, which is electrically connected with the data acquisition device and used for storing the braking system. 11 . Operating data of the brake.
CN202110084629.9A 2021-01-21 2021-01-21 Method and system for detecting wear amount of brakes of offshore wind turbines Pending CN112836867A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110084629.9A CN112836867A (en) 2021-01-21 2021-01-21 Method and system for detecting wear amount of brakes of offshore wind turbines

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110084629.9A CN112836867A (en) 2021-01-21 2021-01-21 Method and system for detecting wear amount of brakes of offshore wind turbines

Publications (1)

Publication Number Publication Date
CN112836867A true CN112836867A (en) 2021-05-25

Family

ID=75929286

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110084629.9A Pending CN112836867A (en) 2021-01-21 2021-01-21 Method and system for detecting wear amount of brakes of offshore wind turbines

Country Status (1)

Country Link
CN (1) CN112836867A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109856969A (en) * 2018-11-06 2019-06-07 皖西学院 A kind of failure prediction method and forecasting system based on BP neural network model
CN110259646A (en) * 2019-05-06 2019-09-20 明阳智慧能源集团股份公司 A method for early warning of wind turbine component status based on historical data
WO2020189235A1 (en) * 2019-03-20 2020-09-24 国立大学法人大阪大学 Trained model, control device, friction stir welding system, neural network system, and method for generating trained model
CN112100918A (en) * 2020-09-15 2020-12-18 中国人民解放军陆军装甲兵学院 GA-BP prediction model research method for ablation wear loss of gun barrel

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109856969A (en) * 2018-11-06 2019-06-07 皖西学院 A kind of failure prediction method and forecasting system based on BP neural network model
WO2020189235A1 (en) * 2019-03-20 2020-09-24 国立大学法人大阪大学 Trained model, control device, friction stir welding system, neural network system, and method for generating trained model
CN110259646A (en) * 2019-05-06 2019-09-20 明阳智慧能源集团股份公司 A method for early warning of wind turbine component status based on historical data
CN112100918A (en) * 2020-09-15 2020-12-18 中国人民解放军陆军装甲兵学院 GA-BP prediction model research method for ablation wear loss of gun barrel

Similar Documents

Publication Publication Date Title
US20210374506A1 (en) Method for predicting bearing life based on hidden markov model and transfer learning
CN105787584B (en) Wind turbine group fault early warning method based on cloud platform
CN104951851B (en) A kind of Wind turbines State Forecasting Model method for building up based on gray relative regression support vector machine
Zaher et al. A multi-agent fault detection system for wind turbine defect recognition and diagnosis
CN109029975B (en) Fault diagnosis method for wind power gear box
CN110259646A (en) A method for early warning of wind turbine component status based on historical data
CN108847686B (en) Photovoltaic inverter fault prediction method
CN104976139B (en) A kind of mechanical equipment state diagnostic method based on Gauss model
CN108072524B (en) Wind turbine generator gearbox bearing fault early warning method
CN107392304A (en) A kind of Wind turbines disorder data recognition method and device
CN103953490A (en) Implementation method for monitoring status of hydraulic turbine set based on HLSNE
CN113641486B (en) Intelligent turnout fault diagnosis method based on edge computing network architecture
CN108921347B (en) Wind power converter fault prediction method
CN104318485A (en) Power transmission line fault identification method based on nerve network and fuzzy logic
CN110040594A (en) A kind of elevator operation detection system and method based on convolutional neural networks
CN105547730A (en) Fault detection system of water-wheel generator set
CN103034207A (en) Infrastructure health monitoring system and implementation process thereof
CN106837707A (en) A kind of automatic trouble diagnosis system based on fault model triggering
CN117195121A (en) Wind turbine generator abnormal state identification method and system based on improved countermeasure automatic encoder
CN109236589A (en) Method and device for evaluating fan blade deicing investment scheme
CN112283050A (en) Machine vision-based online monitoring method for wind turbine blade
CN116466654A (en) Industrial control system diagnosis method and system for power plant
CN110196160A (en) A kind of wind turbine gearbox monitoring method based on residual error network
CN112836867A (en) Method and system for detecting wear amount of brakes of offshore wind turbines
CN114810507A (en) Aerogenerator trouble early warning system based on data analysis

Legal Events

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20210525