Abnormal Detection and Fault Diagnosis Method and Device for Wind Turbine Generator Sets

Abstract

The present invention provides an abnormal detection and fault diagnosis method and device for wind turbine generators. The method includes: analyzing specific failure modes and fault transmission mechanisms for wind turbine generators; performing abnormal detection and data fusion judgment based on data mining methods to detect the abnormal state of wind turbine generators; and using the obtained analysis results of failure modes and abnormal state detection, and combining data characteristics and failure modes to perform fault diagnosis. In this way, based on data mining and root cause analysis, by analyzing and mining a large amount of historical operation data and simulation data, the key parameter information and change patterns hidden in the data are discovered, so as to accurately identify and diagnose the abnormal state and faults of wind turbine generators. By integrating failure mode analysis and data mining methods to carry out root cause analysis, the cause of the fault and the key factors leading to the fault can be fully determined, providing guidance for fault repair; the detection efficiency is higher and the diagnostic accuracy is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of anomaly detection and fault diagnosis, and more particularly, to an anomaly detection and fault diagnosis method and device for wind turbines. Background Art

[0002] With the increasing global demand for renewable energy, wind power generation, as a clean and sustainable energy form, has been gradually widely used. As the core component of the wind power generation system, wind turbines play an important role in converting wind energy into electrical energy. However, due to the long-term operation of wind turbines in a complex and changeable natural environment, various anomalies and faults exist in their operation process, which may lead to a decline in the performance of the generator set, damage or even shutdown, seriously affecting the power generation efficiency and reliability of the wind farm.

[0003] Traditional methods for anomaly detection and fault diagnosis of wind turbines mainly rely on manual inspections and sensor monitoring, but this method has problems such as high labor costs, low detection efficiency, and insufficient diagnostic accuracy.

[0004] Therefore, there is an urgent need to propose a technical solution that can automatically, efficiently, and accurately detect anomalies and diagnose faults in wind turbines. Summary of the Invention

[0005] In view of this, the present invention proposes an anomaly detection and fault diagnosis method and device for wind turbines, aiming to solve the problems of high labor costs, low detection efficiency, and insufficient diagnostic accuracy in the existing methods for anomaly detection and fault diagnosis of wind turbines.

[0006] In a first aspect, the present application provides an anomaly detection and fault diagnosis method for wind turbines, including:

[0007] Analyze specific failure modes and fault transfer mechanisms for wind turbines;

[0008] Perform anomaly detection and data fusion judgment based on data mining methods to detect the abnormal state of wind turbines;

[0009] Use the obtained analysis results of failure modes and anomaly state detection, and combine data characteristics and failure modes to perform fault diagnosis.

[0010] Further, the step of analyzing specific failure modes and fault transfer mechanisms for wind turbines includes:

[0011] Obtain the composition structure data of wind turbines;

[0012] Use the composition structure data to perform failure mode and effect analysis to determine specific failure modes and fault transfer mechanisms;

[0013] Based on the historical operation data of the wind turbine generator set, the fault tree analysis method is adopted to determine the specific failure modes and fault transfer mechanisms.

[0014] Furthermore, the acquisition of the composition structure data of the wind turbine generator set includes:

[0015] Clarify the composition structure of the wind turbine generator set to determine the composition structure data of the wind turbine generator set; each component of the wind turbine generator set includes a wind wheel, a generator, and a transmission system.

[0016] Furthermore, the use of the composition structure data for failure mode and effect analysis includes:

[0017] For each component of the wind turbine generator set, systematically consider various failure modes, identify potential failure situations, and evaluate their impacts on the performance and operation of the wind turbine generator set; the various failure modes include mechanical failures, electrical failures, transmission failures, and structural failures.

[0018] Furthermore, the use of the historical operation data of the wind turbine generator set and the fault tree analysis method to determine the specific failure modes and fault transfer mechanisms includes:

[0019] By taking an undesirable wind turbine generator set fault event or a failure event that has occurred as the top event for analysis, strictly analyze the fault causal logic layer by layer from top to bottom, find out the necessary and sufficient direct causes of the fault event layer by layer, draw the fault tree, and finally find all possible causes and combinations of causes that lead to the occurrence of the top event.

[0020] Furthermore, based on the data mining method for anomaly detection and data fusion judgment to detect the abnormal state of the wind turbine generator set, including:

[0021] Data preprocessing; judging the fault dynamics based on thresholds / envelopes; performing parameter analysis based on data mining; extracting abnormal features.

[0022] Furthermore, the data preprocessing includes:

[0023] Process the measured data from SCADA / CMS and the fan simulation data; clean and denoise the original data, remove possible outliers and noise, and ensure the accuracy and reliability of the data; perform normalization and standardization operations on the data to convert data from different data sources and different dimensions into a unified data format and range, and prepare for subsequent data analysis and mining.

[0024] Furthermore, the judgment of the fault dynamics based on thresholds / envelopes includes:

[0025] Obtain the abnormal characteristics during operation; monitor and judge various parameters of the wind turbine by setting appropriate thresholds and envelope ranges; adopt the strategy of comparing the measured data with the preset thresholds in real time; when the parameter values exceed the threshold range or envelope range, determine the corresponding part of the wind turbine as an abnormal state or a fault condition, and trigger the corresponding alarm or warning signal.

[0026] Furthermore, the parameter analysis based on data mining includes:

[0027] Adopt data mining algorithms and technologies to analyze and process a large amount of historical operation data and simulation condition data, and extract key parameters and characteristics related to abnormal states and faults; by analyzing and comparing these parameters and characteristics, it can be accurately judged whether there is an abnormality in the current state of the wind turbine.

[0028] Furthermore, the extraction of abnormal characteristics includes: extracting and analyzing the characteristic patterns and rules in the abnormal data to help determine the nature and type of the abnormality and provide more accurate information for fault diagnosis.

[0029] In a second aspect, the present application provides an abnormal detection and fault diagnosis device for a wind turbine, which is characterized by including: a failure mode analysis module, an abnormal state detection module, and an abnormal diagnosis module.

[0030] The failure mode analysis module includes a composition structure determination unit, an FMEA unit, and an FTA unit.

[0031] The abnormal state detection module includes a data preprocessing unit, a fault dynamic judgment unit based on thresholds / envelopes, a parameter analysis unit based on data mining, and an abnormal characteristic extraction unit.

[0032] The abnormal diagnosis module locates the faults of the wind turbine by combining hybrid reasoning and machine learning technologies; uses the failure mode analysis result as part of the mechanism information analysis and performs hybrid reasoning with the abnormal parameters of the corresponding data to accurately determine the location of the fault.

[0033] In a third aspect, the present application provides a terminal, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor executes the computer program to implement any one of the methods described in the first aspect.

[0034] In a fourth aspect, the present application provides a computer storage medium storing computer-executable instructions for executing any one of the methods described in the first aspect.

[0035] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned by practice of the present invention. Brief Description of the Drawings

[0036] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0037] Figure 1 is a schematic flow chart of an abnormal detection and fault diagnosis method for a wind turbine generator set according to an embodiment of the present application;

[0038] Figure 2 is a schematic composition diagram of an abnormal detection and fault diagnosis device for a wind turbine generator set according to an embodiment of the present application;

[0039] Figure 3 is a schematic composition diagram of a terminal applying the method according to an embodiment of the present application. Detailed Embodiments

[0040] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art. It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other.

[0041] Failure Mode and Effect Analysis, FMEA.

[0042] Fault Tree Analysis, FTA.

[0043] In recent years, data mining technology has been more and more widely applied in the industrial field, and it has shown great potential in abnormal detection and fault diagnosis.

[0044] The present application provides a technical solution for abnormal detection and fault diagnosis of a wind turbine generator set. In view of the current situation in the prior art that there is a lack of fault analysis by combining the measured data and simulation data of the wind turbine generator set, the present application combines data mining, mechanism models and domain knowledge to provide abnormal detection and fault diagnosis technologies for wind turbine generator sets.

[0045] Such as Figure 1As shown in the figure, the method for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiment of the present application includes the following steps:

[0046] S100: For a wind turbine generator set, analyze specific failure modes and fault transmission mechanisms.

[0047] S200: Based on data mining methods, perform abnormal detection and data fusion judgment to detect the abnormal state of the wind turbine generator set;

[0048] S300: Use the obtained failure mode analysis results and abnormal state detection, and combine data characteristics and failure modes to perform fault diagnosis, that is, abnormal diagnosis.

[0049] The method for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiment of the present application is based on data mining and root cause analysis and is used for the abnormal detection and fault diagnosis of wind turbine generator sets. The data mining technology can analyze and mine a large amount of historical operation data and simulation data to discover key parameter information and change patterns hidden in the data, so as to accurately identify and diagnose the abnormal state and faults of wind turbine generator sets. Combining failure mode analysis and data mining methods to carry out root cause analysis can fully determine the causes of faults and the key factors leading to faults, providing guidance for fault repair. In this way, it is possible to automatically, efficiently, and accurately detect the abnormalities of wind turbine generator sets and diagnose faults.

[0050] The method for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiment of the present application accurately detects the abnormal state of the wind turbine generator set by using data mining technology and combining a large amount of historical operation data and simulation data. The accurate detection results of the abnormal state include: abnormal changes in various operating parameters, equipment failures, and performance degradation. Identify the faults of the wind turbine generator set and diagnose the faults, including determining the fault type, fault location, and fault cause. Based on root cause analysis technology, deeply analyze the causes and key factors of the faults, providing guidance and suggestions for fault repair.

[0051] In this way, the method for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiment of the present application is beneficial to improving the reliability and operating efficiency of the wind turbine generator set, reducing maintenance costs and downtime, and enhancing the overall performance of the wind power generation system.

[0052] In this way, the method for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiment of the present application uses data mining and root cause analysis technologies to provide an advanced method for abnormal detection and fault diagnosis of wind turbine generator sets, which can improve the reliability and operating efficiency of the wind power generation system and promote the development of the renewable energy field.

[0053] In some embodiments, in step S100, for a wind turbine generator set, analyzing specific failure modes and fault transfer mechanisms includes the following steps:

[0054] S110: Obtain the composition structure data of the wind turbine generator set;

[0055] S120: Use the composition structure data to conduct a failure mode and effects analysis to determine specific failure modes and fault transfer mechanisms;

[0056] S130: According to the historical operation data of the wind turbine generator set, use the fault tree analysis method to determine specific failure modes and fault transfer mechanisms.

[0057] In some embodiments, obtaining the composition structure data of the wind turbine generator set in step S110 includes: clarifying the composition structure of the wind turbine generator set and determining the composition structure data of the wind turbine generator set. Specifically, each component of the wind turbine generator set includes key components such as a wind wheel, a generator, and a transmission system.

[0058] In some embodiments, it further includes: using the composition structure data to describe each component of the wind turbine generator set, and in detail describing the structure, function, and interaction relationship between each component, and finding out the influence relationship and potential fault sources between different components.

[0059] In some embodiments, using the composition structure data to conduct a failure mode and effects analysis in step S120 includes: for each component of the wind turbine generator set, systematically considering various failure modes, identifying potential fault situations, and evaluating their impacts on the performance and operation of the wind turbine generator set. Specifically, the various failure modes include mechanical failures, electrical failures, transmission failures, and structural failures.

[0060] In some embodiments, FMEA analyzes each product, equipment subsystem, part of the wind turbine generator set, and each process constituting the process one by one, finds out all potential failure modes, and analyzes their possible consequences, so as to take necessary measures in advance.

[0061] In this way, by deeply understanding the composition structure of the wind turbine generator set, the influence relationship and potential fault sources between different components can be found out, and the possible mechanism causing the fault can be confirmed.

[0062] In some embodiments, according to the historical operation data of the wind turbine generator set in step S130, using the fault tree analysis method to determine specific failure modes and fault transfer mechanisms includes:

[0063] By taking an unwanted wind turbine failure event or an already occurred failure event as the top event for analysis, and conducting a strict hierarchical fault causal logic analysis from top to bottom, the necessary and sufficient direct causes of the fault event are found layer by layer, a fault tree is drawn, and finally all possible causes and combinations of causes leading to the top event are found.

[0064] In this way, the fault tree analysis method can be used to analyze the fault transmission mechanism and influence path. Constructing a fault tree can adopt a systematic method to gradually trace the path of fault occurrence and possible results, determine the key factors leading to the fault and possible risk points, further be used to identify and analyze the root causes of wind turbine faults, and can guide fault diagnosis and repair.

[0065] In some embodiments, in step S200, based on the data mining method, anomaly detection and data fusion judgment are performed to detect the abnormal state of the wind turbine, including: data preprocessing; judging the fault dynamics based on thresholds / envelopes; performing parameter analysis based on data mining; extracting abnormal features.

[0066] The data preprocessing includes: processing the measured data from SCADA / CMS and the wind turbine simulation data; cleaning and denoising the original data, removing possible outliers and noise to ensure the accuracy and reliability of the data; performing normalization and standardization operations on the data to convert data from different data sources and different dimensions into a unified data format and range, preparing for subsequent data analysis and mining.

[0067] The judging of the fault dynamics based on thresholds / envelopes includes: obtaining the abnormal features during operation; monitoring and judging various parameters of the wind turbine by setting appropriate thresholds and envelope ranges; adopting a strategy of comparing the measured data with the preset thresholds in real time; when the parameter value exceeds the threshold range or envelope range, the corresponding part of the wind turbine is determined to be in an abnormal state or a fault condition, and the corresponding alarm or warning signal is triggered.

[0068] The performing of parameter analysis based on data mining includes: using data mining algorithms and techniques to analyze and process a large amount of historical operation data and simulation condition data, extracting key parameters and features related to abnormal states and faults; by analyzing and comparing these parameters and features, it can be accurately judged whether the current state of the wind turbine is abnormal.

[0069] The extracting of abnormal features includes: extracting and analyzing the feature patterns and rules in the abnormal data to help determine the nature and type of the anomaly and provide more accurate information for fault diagnosis.

[0070] In some embodiments, in step S300, using the obtained failure mode analysis results and abnormal state detection, combining data characteristics and failure modes for fault diagnosis includes: locating faults in the wind turbine generator set by combining hybrid reasoning and machine learning techniques; using the failure mode analysis results as part of the mechanism information analysis, performing hybrid reasoning with the abnormal parameters of the corresponding data, so as to accurately determine the location of the fault.

[0071] As Figure 2 shown, the abnormal detection and fault diagnosis device for wind turbine generator sets according to the embodiments of the present application includes: a failure mode analysis module, an abnormal state detection module, and an abnormal diagnosis module.

[0072] As Figure 2 shown, the failure mode analysis module includes a composition structure determination unit, an FMEA unit, and an FTA unit.

[0073] The composition structure determination unit is used to obtain the composition structure data of the wind turbine generator set; the FMEA unit is used to perform failure mode and effect analysis using the composition structure data to determine specific failure modes and fault transfer mechanisms; the FTA unit is used to determine specific failure modes and fault transfer mechanisms by using the fault tree analysis method according to the historical operation data of the wind turbine generator set.

[0074] As Figure 2 shown, the abnormal state detection module includes a data preprocessing unit, a fault dynamic judgment unit based on threshold / envelope, a parameter analysis unit based on data mining, and an abnormal feature extraction unit;

[0075] The data preprocessing unit is used to process the measured data from SCADA / CMS and the fan simulation data. The data preprocessing unit cleans and denoises the original data, removes possible outliers and noises, and ensures the accuracy and reliability of the data. The data preprocessing unit performs normalization and standardization operations on the data, converts data from different data sources and different dimensions into a unified data format and range, and prepares for subsequent data analysis and mining.

[0076] The fault dynamic judgment unit based on threshold / envelope is an important part in the process of abnormal detection and fault diagnosis. The fault dynamic judgment unit is used to dynamically judge and obtain abnormal features during operation. The fault dynamic judgment unit monitors and judges various parameters of the wind turbine generator set by setting appropriate thresholds and envelope ranges; adopts a strategy of comparing the measured data with the preset thresholds in real time; when the parameter value exceeds the threshold range or the envelope range, the corresponding part of the wind turbine generator set is determined to be in an abnormal state or a fault condition, and the corresponding alarm or warning signal is triggered.

[0077] The parameter analysis unit based on data mining uses data mining algorithms and technologies to analyze and process a large amount of historical operation data and simulation working condition data, and extracts key parameters and features related to abnormal states and faults. By analyzing and comparing these parameters and features, it can accurately determine whether there is an abnormality in the current state of the wind turbine generator set.

[0078] The abnormal feature extraction unit further extracts and analyzes the feature patterns and rules in the abnormal data to help determine the nature and type of the abnormality, and provides more accurate information for fault diagnosis.

[0079] As Figure 2 shown, the abnormal diagnosis module includes a fault root cause reasoning unit or a hybrid reasoning unit and a machine learning unit.

[0080] The fault root cause reasoning unit takes the failure mode analysis result as the mechanism information analysis and the abnormal parameter part of the corresponding data, and hybridly infers the fault causes and related parameters of the wind turbine generator set.

[0081] In this way, the fault root cause reasoning module hybridly infers the failure mode analysis result with the mechanism information analysis and the abnormal parameter part of the corresponding data, so as to achieve an accurate diagnosis of the fault causes and related parameters of the wind turbine generator set.

[0082] The fault root cause reasoning unit uses the result of failure mode analysis, that is, the information obtained by analyzing and evaluating the failure mode of the wind turbine generator set, to infer the possible root causes of the fault.

[0083] In this way, failure mode analysis can help identify potential fault modes and fault transfer mechanisms, thus providing a basis for subsequent fault diagnosis. After deeply understanding and analyzing the working principle of the wind turbine generator set, the interaction between components, etc., and obtaining knowledge about the system operation mechanism, the fault root cause reasoning unit combines the mechanism information analysis and the abnormal parameter part of the corresponding data, hybridly infers by mixing information from different sources, and determines the specific causes and related parameters of the fault of the wind turbine generator set.

[0084] The fault root cause reasoning unit comprehensively analyzes the failure mode, mechanism information and abnormal parameters to identify the root factors of the fault, reveals the specific mechanisms and paths of the fault occurrence, and provides guidance and basis for fault repair and prevention.

[0085] The abnormal diagnosis module locates the fault of the wind turbine generator set by combining hybrid reasoning and machine learning technologies; takes the failure mode analysis result as part of the mechanism information analysis, and conducts hybrid reasoning with the abnormal parameters of the corresponding data, so as to accurately determine the location of the fault.

[0086] The method for detecting abnormalities and diagnosing faults of a wind turbine generator set according to the embodiments of the present application is based on data mining and root cause analysis, and adopts data mining and root cause analysis technologies, which can quickly and efficiently diagnose the faults of the wind turbine generator set.

[0087] The method for detecting abnormalities and diagnosing faults of a wind turbine generator set according to the embodiments of the present application analyzes a large amount of historical data and real-time monitoring data, discovers the laws and patterns hidden in the data, identifies the types, locations and causes of faults, accurately detects the abnormal state of the wind turbine generator set and diagnoses faults, improves the accuracy of detection, reduces the false alarm rate and missed alarm rate, ensures the accurate diagnosis of faults, and provides guidance and suggestions for fault repair. Compared with the traditional manual inspection and sensor monitoring methods, the present invention can greatly shorten the time for fault diagnosis and improve the efficiency of fault handling.

[0088] The method for detecting abnormalities and diagnosing faults of a wind turbine generator set according to the embodiments of the present application can timely detect the abnormal state and faults of the wind turbine generator set and provide accurate diagnostic results, thereby helping the operation and maintenance personnel to take effective measures for repair and adjustment in time. By dealing with faults in time, the downtime of the wind turbine generator set can be reduced, and the power generation efficiency and reliability of the wind farm can be improved.

[0089] The method for detecting abnormalities and diagnosing faults of a wind turbine generator set according to the embodiments of the present application can deeply analyze the root causes and key factors of faults, and provide guidance and suggestions for improving the overall performance of the wind power system.

[0090] The method and device for detecting abnormalities and diagnosing faults of a wind turbine generator set according to the embodiments of the present application can operate automatically, can realize the real-time monitoring and fault diagnosis of the wind turbine generator set, reduce the labor cost and the frequency of equipment maintenance, and reduce the maintenance cost.

[0091] The method and device for detecting abnormalities and diagnosing faults of a wind turbine generator set according to the embodiments of the present application are based on data mining and root cause analysis, and have strong scalability and adaptability. They can be applied to different types and scales of wind turbine generator sets, and can be customized according to the actual situation to meet the needs of different users.

[0092] In summary, the method and device for detecting abnormalities and diagnosing faults of a wind turbine generator set according to the embodiments of the present application implement an abnormal detection data fusion judgment method that combines data mining and failure analysis, and belong to an abnormal detection data fusion judgment method that combines data mining technology and failure analysis. By performing data mining analysis on a large amount of historical operation data and combining the results of failure analysis, the abnormal state of the wind turbine generator set is accurately identified and judged. The key steps include data preprocessing, feature extraction, model construction and result analysis, etc.

[0093] Thus, the method and device for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiments of the present application include an abnormal detection data fusion judgment step based on data mining and failure analysis; a wind turbine generator set fault analysis step based on a combination of measured data and simulation data; and a fault location step based on hybrid reasoning and machine learning.

[0094] In summary, the method and device for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiments of the present application are based on a combination of measured data and simulation data to achieve fault analysis of the wind turbine generator set; a fault analysis method for a wind turbine generator set based on a combination of measured data and simulation data; by combining and analyzing the measured data and simulation data, the operating state and fault conditions of the wind turbine generator set can be evaluated more comprehensively, and the accuracy and reliability of fault diagnosis can be improved.

[0095] In summary, the method and device for abnormal detection and fault diagnosis of a wind turbine generator set according to the embodiments of the present application are based on hybrid reasoning and machine learning to achieve fault location; fault location of a wind turbine generator set based on hybrid reasoning and machine learning. By combining hybrid reasoning and machine learning technologies, the faults of the wind turbine generator set are located. This method uses the failure mode analysis result as part of the mechanism information analysis and performs hybrid reasoning with the abnormal parameters of the corresponding data to accurately determine the location of the fault.

[0096] As Figure 3 shown, the embodiments of the present application also provide a terminal 8 to execute the above method. Figure 3 As Figure 3 shown, the terminal 8 includes: a processor 800, a memory 801, a bus 802, and a communication interface 803. The processor 800, the communication interface 803, and the memory 801 are connected through the bus 802; a computer program that can run on the processor 800 is stored in the memory 801, and when the processor 800 runs the computer program, it executes the method provided in any of the foregoing embodiments of the present application.

[0097] Among them, the memory 801 may include a high-speed random access memory (RAM: Random Access Memory), and may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 803 (which can be wired or wireless), a communication connection between this device network element and at least one other network element is realized, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0098] The bus 802 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 801 is used to store programs. After receiving an execution instruction, the processor 800 executes the program. Any implementation manner of the method disclosed in any embodiment of the foregoing embodiments of the present invention can be applied to or implemented by the processor 800.

[0099] The processor 800 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 800 or by instructions in the form of software. The above-mentioned processor 800 can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present invention can be directly embodied as being executed and completed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 801, and the processor 800 reads the information in the memory 801 and combines its hardware to complete the steps of the above method.

[0100] The terminal provided in the embodiments of the present invention and the method in the embodiments of the present invention are based on the same inventive concept and have the same beneficial effects as the method adopted, run, or implemented by it.

[0101] The embodiments of the present application also provide a computer-readable storage medium corresponding to the method provided in the foregoing embodiments. The computer-readable storage medium is an optical disc, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the method provided in any of the foregoing embodiments.

[0102] It should be noted that examples of the computer-readable storage medium may further include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, or other optical and magnetic storage media, which will not be elaborated herein one by one.

[0103] The computer-readable storage medium provided by the above embodiments of the present application and the method of the embodiments of the present invention are based on the same inventive concept and have the same beneficial effects as the methods adopted, run, or implemented by the application programs stored therein.

[0104] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for abnormal detection and fault diagnosis of wind turbines, characterized in that, Including: Facing a wind turbine generator set, analyze specific failure modes and fault transmission mechanisms; The analysis of specific failure modes and fault transmission mechanisms for the wind turbine generator set includes: Obtain the composition structure data of the wind turbine generator set; Utilize the composition structure data to conduct a failure mode and effects analysis to determine specific failure modes and fault transmission mechanisms; Based on the historical operation data of the wind turbine generator set, use the fault tree analysis method to determine specific failure modes and fault transmission mechanisms; the determination of specific failure modes and fault transmission mechanisms based on the historical operation data of the wind turbine generator set by using the fault tree analysis method includes: Take an undesirable wind turbine generator set fault event or a failure event that has occurred as the top event as the object of analysis, and strictly analyze the fault causal logic layer by layer from top to bottom, find out the necessary and sufficient direct causes of the fault event layer by layer, draw a fault tree, and finally find all possible causes and combinations of causes that lead to the occurrence of the top event; Conduct anomaly detection and data fusion judgment based on data mining methods to detect the abnormal state of the wind turbine generator set; among them, the detection of the abnormal state of the wind turbine generator set by conducting anomaly detection and data fusion judgment based on data mining methods includes: Data preprocessing; judge the fault dynamics based on thresholds / envelopes; conduct parameter analysis based on data mining; extract abnormal features; among them, the parameter analysis based on data mining includes: Adopt data mining algorithms and technologies to analyze and process a large amount of historical operation data and simulation condition data, and extract key parameters and features related to abnormal states and faults; by analyzing and comparing these parameters and features, it is possible to accurately judge whether there is an abnormality in the current state of the wind turbine generator set; The extraction of abnormal features includes: extracting and analyzing the feature patterns and rules in the abnormal data to help determine the nature and type of the abnormality and provide more accurate information for fault diagnosis; Utilize the obtained failure mode analysis results and abnormal state detection, and combine data features and failure modes to conduct fault diagnosis.

2. The method according to claim 1, wherein The obtaining of the composition structure data of the wind turbine generator set includes: Clarify the composition structure of the wind turbine generator set and determine the composition structure data of the wind turbine generator set; each component of the wind turbine generator set includes a wind wheel, a generator, and a transmission system.

3. The method according to claim 1, characterized in that, The utilization of the composition structure data to conduct a failure mode and effects analysis includes: For each component of the wind turbine generator set, systematically consider various failure modes, identify potential fault situations, and evaluate their impacts on the performance and operation of the wind turbine generator set; the various failure modes include mechanical faults, electrical faults, transmission faults, and structural faults.

4. The method according to claim 1, characterized in that The data preprocessing includes: Process the measured data from SCADA / CMS and the fan simulation data; clean and denoise the original data, remove possible outliers and noise, and ensure the accuracy and reliability of the data; perform normalization and standardization operations on the data to convert data from different data sources and different dimensions into a unified data format and range, and prepare for subsequent data analysis and mining.

5. The method according to claim 1, wherein The judgment of fault dynamics based on thresholds / envelopes includes: Obtain the abnormal characteristics during operation; monitor and judge various parameters of the wind turbine by setting appropriate thresholds and envelope ranges; adopt the strategy of comparing the measured data with the preset thresholds in real time; when the parameter values exceed the threshold range or the envelope range, determine the corresponding part of the wind turbine as an abnormal state or a fault condition, and trigger the corresponding alarm or warning signal.

6. An abnormal detection and fault diagnosis device for a wind turbine generator set, characterized in that, For implementing the abnormal detection and fault diagnosis method for wind turbines described in any one of claims 1 to 5, including: a failure mode analysis module, an abnormal state detection module, and an abnormal diagnosis module; The failure mode analysis module includes a component structure determination unit, an FMEA unit, and an FTA unit; wherein, the component structure determination unit is used to obtain the component structure data of the wind turbine; the FMEA unit is used to perform failure mode and effect analysis by using the component structure data to determine specific failure modes and fault transfer mechanisms; the FTA unit is used to determine specific failure modes and fault transfer mechanisms by using the fault tree analysis method according to the historical operation data of the wind turbine; The abnormal state detection module includes a data preprocessing unit, a fault dynamic judgment unit based on thresholds / envelopes, a parameter analysis unit based on data mining, and an abnormal feature extraction unit; wherein, the parameter analysis unit based on data mining performs parameter analysis based on data mining, including: Adopt data mining algorithms and technologies to analyze and process a large amount of historical operation data and simulation condition data, and extract key parameters and features related to abnormal states and faults; by analyzing and comparing these parameters and features, it is possible to accurately judge whether there is an abnormality in the current state of the wind turbine. The extraction of abnormal features includes: extracting and analyzing the feature patterns and rules in the abnormal data to help determine the nature and type of the abnormality and provide more accurate information for fault diagnosis. The abnormal diagnosis module locates the faults of the wind turbine by combining hybrid reasoning and machine learning technologies; uses the failure mode analysis result as part of the mechanism information analysis and performs hybrid reasoning with the abnormal parameters of the corresponding data to accurately determine the location of the fault.

Images