A wind power converter fault self-adaptive diagnosis system

Abstract

The application provides a wind power converter fault self-adaptive diagnosis system, which comprises a data acquisition module, a fault diagnosis module, a fault pre-identification module and an evaluation decision module; the data acquisition module is used for collecting operation parameters and environmental influence parameters of the wind power converter; the fault diagnosis module is used for monitoring the operation state of the wind power converter according to the operation parameters and detecting whether a fault occurs in the operation process of the wind power converter; the fault pre-identification module is used for analyzing the influence degree of each environmental influence parameter on the fault generation in the short term and the long term; and the evaluation decision module is used for combining the analysis result of the fault pre-identification module to complete the identification of the fault cause and provide maintenance decision support; through the analysis of the short-term and long-term environmental influence parameters and operation parameters, the application can accurately identify and diagnose the fault of the wind power converter, and ensure the timely response and treatment of various potential problems.

Description

Technical Field

[0001] This invention relates to the field of wind turbine fault diagnosis systems, and more particularly to an adaptive fault diagnosis system for wind power converters. Background Technology

[0002] In the wind power industry, the stable operation of wind power converters is crucial to ensuring the efficiency and reliability of the entire wind power generation system. However, because wind power converters operate in harsh environments and are affected by various external factors, they are prone to various failures. If these failures are not detected and diagnosed in a timely manner, they may lead to significant economic losses and energy production interruptions. Therefore, developing a system that can effectively diagnose wind power converter failures, especially a system that can analyze the causes of failures from multiple dimensions and make maintenance decisions quickly, is of great significance for improving the operational efficiency of wind farms and reducing maintenance costs.

[0003] A review of publicly available technical solutions reveals that CN115659133A proposes a fault diagnosis method for wind power converters. This method uses the three-phase output current of the wind power converter as the diagnostic signal. It employs a variational mode decomposition algorithm to decompose and extract data features from the acquired current signals under normal and fault conditions. A random forest network model is then constructed to train, identify, and classify the feature vectors, yielding the fault diagnosis result. This invention addresses single and double open-circuit fault diagnosis of IGBT modules in wind power converters, enabling remote status monitoring and rapid acquisition of fault-related information after a fault occurs, aiding in fault troubleshooting and reducing the impact of maintenance and downtime on production efficiency. However, this solution is limited to specific types of faults and cannot diagnose faults caused by other types of external environmental factors. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of current systems by proposing an adaptive fault diagnosis system for wind power converters.

[0005] The present invention adopts the following technical solution:

[0006] An adaptive fault diagnosis system for wind power converters, the system comprising a data acquisition module, a fault diagnosis module, a fault pre-identification module, and an evaluation and decision module;

[0007] The data acquisition module is used to collect the operating parameters and environmental impact parameters of the wind power converter; the fault diagnosis module is used to monitor the operating status of the wind power converter according to the operating parameters and detect whether a fault occurs during the operation of the wind power converter; the fault pre-identification module is used to analyze the degree of impact of each environmental impact parameter on the fault in the short and long term; the assessment and decision module is used to identify the cause of the fault by combining the analysis results of the fault pre-identification module and provide maintenance decision support.

[0008] The data acquisition module includes an operating parameter acquisition unit and an environmental parameter acquisition unit; the operating parameter acquisition unit is used to collect the operating parameters of the wind power converter; the environmental parameter acquisition unit is used to collect environmental impact parameters that may cause the wind power converter to fail.

[0009] The fault diagnosis module includes a status monitoring unit and a fault detection unit; the status monitoring unit is used to monitor the operating parameters of the converter, and the fault detection unit is used to determine whether the wind power converter has malfunctioned based on the changes in the operating parameters of the converter.

[0010] Furthermore, the fault detection unit also includes a preset standard operating parameter benchmark library, which contains the threshold range of each operating parameter when the wind power converter is running normally; the fault detection unit compares the real-time operating parameters of the wind power converter with the threshold range of each corresponding operating parameter in the parameter benchmark library, and if at least one operating parameter exceeds its threshold range, it determines that the wind power converter has failed.

[0011] Furthermore, the fault pre-identification module includes a data storage unit, a short-term trend analysis unit, and a long-term trend analysis unit; the data storage unit is used to store operating parameters and environmental impact parameters with time-series markers; the short-term trend analysis unit is used to analyze the degree of influence of each environmental impact parameter on the occurrence of faults in the wind power converter in a short period of time; the long-term trend analysis unit is used to analyze the degree of influence of each environmental impact parameter on the occurrence of faults in the wind power converter in a long period of time.

[0012] Furthermore, the assessment and decision-making module includes a cause identification unit and a maintenance decision support unit; the cause identification unit is used to accurately identify the cause of the fault by combining the influence of various environmental impact parameters on the failure of the wind power converter in the short and long term; the maintenance decision support unit is used to provide decision support for maintenance and repair based on the identification results of the fault classification unit.

[0013] Furthermore, the workflow of the short-term trend analysis unit is as follows:

[0014] S11: Based on historical datasets, establish a data relationship model for the influence of environmental impact parameters on the operating parameters of wind power converters using computer fitting; the data relationship model is expressed as follows:

[0015] y i =β i1 (x1)+β i2 (x2)+…+β in (x n )+∈ i ;

[0016] Among them, y i Let x be the value corresponding to the i-th type of environmental impact parameter. j β is the value corresponding to the j-th operating parameter of the wind power converter. ij () is the model fitting function between the i-th environmental impact parameter and the j-th operating parameter of the wind power converter, where 1≤j≤n, and n is the total number of operating parameters; ∈ i The residual error of the i-th environmental impact parameter in the fitted model;

[0017] S12: When the fault detection unit detects a fault, it acquires the values ​​of operating parameters and environmental impact parameters within a time interval T, with the current time as the time cutoff point, where T is a pre-set short-term acquisition period.

[0018] S13: Set multiple detection time points within a short acquisition period, where the time interval between adjacent detection time points is the same; perform the following steps for each environmental impact parameter:

[0019] S131: Substitute the values ​​of the environmental impact parameters at each detection time point into the data relationship model to obtain the values ​​of each operating parameter of the wind power converter in the data relationship model at each detection time point after substitution.

[0020] S132: Obtain the operating parameter types that cause wind power converter failures. Assume there are l types of operating parameters that cause wind power converter failures, satisfying 1≤l≤n; for each type of operating parameter that causes wind power converter failures, execute:

[0021] S1321: Calculate the absolute value of the difference between the actual operating parameter values ​​and the operating parameter values ​​in the data relationship model at each detection time point, and extract the smallest absolute value among all absolute values ​​as the short-term impact comparison coefficient of this environmental impact parameter on the operating parameter that causes wind power converter failure; let the short-term impact comparison coefficient be W. i，k Where i is the type of environmental impact parameter, and k is the type of operating parameter that causes the wind power converter failure; satisfying 1≤k≤l;

[0022] S14: For each type of operating parameter that leads to wind power converter failure, calculate the short-term impact comparison coefficient W of the corresponding environmental impact parameters. i，k Sorted by size, the smaller the short-term impact comparison coefficient, the greater the impact of the environmental impact parameter on the failure of the wind power converter in the short term.

[0023] Furthermore, the long-term trend analysis unit determines the normal threshold range of each environmental impact parameter by using historical data and industry standards, and evaluates the impact of each environmental impact parameter on the failure of the wind power converter over a long period of time based on the abnormal duration of each environmental impact parameter not being within the normal threshold range during the set long-term collection period.

[0024] The beneficial effects achieved by this invention are:

[0025] This invention collects the operating parameters and environmental impact parameters of wind power converters through a data acquisition module, ensuring comprehensive and detailed data support for fault diagnosis. By monitoring the equipment's operating status in real time and quickly detecting abnormal changes in operating parameters, it improves the speed of fault response and helps reduce downtime and related costs caused by faults. By comprehensively considering the impact of short-term and long-term environmental impact parameters on faults, the system can assess the potential causes of faults at multiple time scales, enhancing the accuracy of fault prediction and the depth of fault cause analysis, thus providing a scientific basis for maintenance decisions. Attached Figure Description

[0026] The invention will be further understood from the following description taken in conjunction with the accompanying drawings. The components in the drawings are not necessarily drawn to scale, but rather the emphasis is on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0027] Figure 1 This is a schematic diagram of the overall modules of the present invention.

[0028] Figure 2 This is a schematic diagram of the workflow of the short-term trend analysis unit of the present invention.

[0029] Figure 3 This is a schematic diagram of the workflow of the long-term trend analysis unit of the present invention. Detailed Implementation

[0030] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to its embodiments. It should be understood that the specific embodiments described herein are only for explaining the present invention and are not intended to limit the present invention. Other systems, methods, and / or features of this embodiment will become apparent to those skilled in the art after reviewing the following detailed description. It is intended that all such additional systems, methods, features, and advantages are included within this specification, are included within the scope of the present invention, and are protected by the appended claims. Further features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.

[0031] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or component referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present patent. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0032] Example 1:

[0033] like Figure 1 As shown, this embodiment provides a wind power converter fault adaptive diagnosis system, which includes a data acquisition module, a fault diagnosis module, a fault pre-identification module, and an evaluation and decision module.

[0034] The data acquisition module is used to collect the operating parameters and environmental impact parameters of the wind power converter; the fault diagnosis module is used to monitor the operating status of the wind power converter according to the operating parameters and detect whether a fault occurs during the operation of the wind power converter; the fault pre-identification module is used to analyze the degree of impact of each environmental impact parameter on the fault in the short and long term; the assessment and decision module is used to identify the cause of the fault by combining the analysis results of the fault pre-identification module and provide maintenance decision support.

[0035] The data acquisition module includes an operating parameter acquisition unit and an environmental parameter acquisition unit. The operating parameter acquisition unit is used to collect the operating parameters of the wind power converter, including but not limited to voltage, current, temperature and vibration data of the wind power converter. The environmental parameter acquisition unit is used to collect environmental impact parameters that may cause wind power converter failures, including but not limited to ambient wind speed, ambient temperature and grid load.

[0036] The fault diagnosis module includes a status monitoring unit and a fault detection unit; the status monitoring unit is used to monitor the operating parameters of the converter, and the fault detection unit is used to determine whether the wind power converter has malfunctioned based on the changes in the operating parameters of the converter.

[0037] Furthermore, the fault detection unit also includes a preset standard operating parameter benchmark library, which contains the threshold range of each operating parameter when the wind power converter is running normally; the fault detection unit compares the real-time operating parameters of the wind power converter with the threshold range of each corresponding operating parameter in the parameter benchmark library, and if at least one operating parameter exceeds its threshold range, it determines that the wind power converter has failed.

[0038] Furthermore, the fault pre-identification module includes a data storage unit, a short-term trend analysis unit, and a long-term trend analysis unit; the data storage unit is used to store operating parameters and environmental impact parameters with time-series markers; the short-term trend analysis unit is used to analyze the degree of influence of each environmental impact parameter on the occurrence of faults in the wind power converter in a short period of time; the long-term trend analysis unit is used to analyze the degree of influence of each environmental impact parameter on the occurrence of faults in the wind power converter in a long period of time.

[0039] Furthermore, the assessment and decision-making module includes a cause identification unit and a maintenance decision support unit; the cause identification unit is used to accurately identify the cause of the fault by combining the influence of various environmental impact parameters on the failure of the wind power converter in the short and long term; the maintenance decision support unit is used to provide decision support for maintenance and repair based on the identification results of the fault classification unit.

[0040] Furthermore, the workflow of the short-term trend analysis unit is as follows:

[0041] S11: Based on historical datasets, establish a data relationship model for the influence of environmental impact parameters on the operating parameters of wind power converters using computer fitting; the data relationship model is expressed as follows:

[0042] y i =β i1 (x1)+β i2 (x2)+…+β in (x n )+∈ i ;

[0043] Among them, y i Let x be the value corresponding to the i-th type of environmental impact parameter. j β is the value corresponding to the j-th operating parameter of the wind power converter. ij() is the model fitting function between the i-th environmental impact parameter and the j-th operating parameter of the wind power converter, where 1≤j≤n, and n is the total number of operating parameters; ∈ i The residual error of the i-th environmental impact parameter in the fitted model;

[0044] S12: When the fault detection unit detects a fault, it acquires the values ​​of operating parameters and environmental impact parameters within a time interval T, with the current time as the time cutoff point, where T is a pre-set short-term acquisition period.

[0045] S13: Set multiple detection time points within a short acquisition period, where the time interval between adjacent detection time points is the same; perform the following steps for each environmental impact parameter:

[0046] S131: Substitute the values ​​of the environmental impact parameters at each detection time point into the data relationship model to obtain the values ​​of each operating parameter of the wind power converter in the data relationship model at each detection time point after substitution.

[0047] S132: Obtain the operating parameter types that cause wind power converter failures. Assume there are l types of operating parameters that cause wind power converter failures, satisfying 1≤l≤n; for each type of operating parameter that causes wind power converter failures, execute:

[0048] S1321: Calculate the absolute value of the difference between the actual operating parameter values ​​and the operating parameter values ​​in the data relationship model at each detection time point, and extract the smallest absolute value among all absolute values ​​as the short-term impact comparison coefficient of this environmental impact parameter on the operating parameter that causes wind power converter failure; let the short-term impact comparison coefficient be W. i，k Where i is the type of environmental impact parameter, and k is the type of operating parameter that causes the wind power converter failure; satisfying 1≤k≤l;

[0049] S14: For each type of operating parameter that leads to wind power converter failure, calculate the short-term impact comparison coefficient W of the corresponding environmental impact parameters. i，k Sorted by size, the smaller the short-term impact comparison coefficient, the greater the impact of the environmental impact parameter on the failure of the wind power converter in the short term.

[0050] Furthermore, the long-term trend analysis unit determines the normal threshold range of each environmental impact parameter by using historical data and industry standards, and evaluates the impact of each environmental impact parameter on the failure of the wind power converter over a long period of time based on the abnormal duration of each environmental impact parameter not being within the normal threshold range during the set long-term collection period.

[0051] Example 2:

[0052] This embodiment should be understood to include at least all the features of any of the foregoing embodiments, and to further improve upon them;

[0053] In the wind power converter fault adaptive diagnosis system provided in this embodiment, the long-term trend analysis unit assesses the degree of influence of each environmental impact parameter on the occurrence of wind power converter faults over a long period of time by monitoring and evaluating the abnormal duration of environmental impact parameters in each time period before the occurrence of faults.

[0054] Specifically, the workflow of the long-term trend analysis unit is as follows:

[0055] S21: Obtain the normal threshold range for environmental impact parameters through historical data and industry standards;

[0056] S22: When the fault detection unit detects a fault, it acquires environmental impact parameters within a time interval of q*T with the current time as the time cutoff point, where q*T is a pre-set long-term acquisition period. In this embodiment, q is set to ≥10.

[0057] S23: For each environmental impact parameter, calculate its long-term impact comparison coefficient:

[0058]

[0059] Among them, Q i Let t be the long-term impact comparison coefficient corresponding to the i-th environmental impact parameter. i，p Within the long-term data collection period, the time during which the i-th environmental influence parameter is outside its normal threshold range is within the p-th time interval closest to the current time cutoff point; where 1≤p≤q;

[0060] S24: Compare the long-term impact coefficients Q for each environmental impact parameter. i Sorted by size, the larger the long-term impact comparison coefficient, the greater the impact of the environmental impact parameter on the failure of the wind power converter over the long term.

[0061] In calculating the long-term impact comparison coefficient, the weighted processing of the environmental impact parameters within each short-term collection period within the long-term collection period fully considers the urgency and actual impact of each time period, thereby improving the timeliness and accuracy of the analysis; at the same time, it reveals the long-term trend of environmental impact parameters, which helps to more effectively predict and prevent potential failures.

[0062] Specifically, the workflow of the cause identification unit is as follows:

[0063] S31: Calculate the combined impact value of each environmental impact parameter:

[0064]

[0065] Among them, E i Let δ be the comprehensive impact value of the i-th environmental impact parameter. k γ is a pre-defined standardized adjustment value for the kth type of operating parameter that causes wind power converter failure, used to unify the measurement of the short-term impact comparison coefficient of different types of operating parameters; γ is a pre-defined long-term impact adjustment coefficient, used to adjust the degree of influence of the long-term impact comparison coefficient on the comprehensive impact value.

[0066] S32: Sort the comprehensive impact values ​​of each environmental impact parameter from smallest to largest, and extract the environmental impact parameters corresponding to the top z comprehensive impact values ​​in the sorted sequence. Use the changes or anomalies of the extracted environmental impact parameters as the causes of the fault; where z is the number of selections, which can be set according to user needs.

[0067] Furthermore, after obtaining the identification results from the fault classification unit, the maintenance decision support unit establishes a connection between the fault cause and the maintenance and repair decision based on historical maintenance records, and sends specific maintenance suggestions and operating steps to the user.

[0068] The content disclosed above is only a preferred and feasible embodiment of the present invention, and is not intended to limit the scope of protection of the present invention. Therefore, all equivalent technical changes made based on the content of the present invention specification and drawings are included within the scope of protection of the present invention. Furthermore, the elements therein can be updated as technology develops.

Claims

1. A wind power converter fault adaptive diagnosis system, characterized in that, The system includes a data acquisition module, a fault diagnosis module, a fault pre-identification module, and an evaluation and decision-making module; The data acquisition module is used to collect the operating parameters and environmental impact parameters of the wind power converter; the fault diagnosis module is used to monitor the operating status of the wind power converter according to the operating parameters and detect whether a fault occurs during the operation of the wind power converter. The fault pre-identification module is used to analyze the impact of various environmental impact parameters on the occurrence of faults in the short and long term; the assessment and decision module is used to combine the analysis results of the fault pre-identification module to identify the causes of faults and provide maintenance decision support. The data acquisition module includes an operating parameter acquisition unit and an environmental parameter acquisition unit; the operating parameter acquisition unit is used to collect the operating parameters of the wind power converter; the environmental parameter acquisition unit is used to collect environmental impact parameters that may cause the wind power converter to fail. The fault diagnosis module includes a status monitoring unit and a fault detection unit; the status monitoring unit is used to monitor the operating parameters of the converter, and the fault detection unit is used to determine whether the wind power converter has malfunctioned based on the changes in the operating parameters of the converter. The fault pre-identification module includes a data storage unit, a short-term trend analysis unit, and a long-term trend analysis unit. The data storage unit stores operating parameters and environmental impact parameters with time-series markers. The short-term trend analysis unit analyzes the impact of each environmental impact parameter on the occurrence of faults in the wind power converter within a short period of time. The long-term trend analysis unit analyzes the impact of each environmental impact parameter on the occurrence of faults in the wind power converter within a long period of time. The workflow of the short-term trend analysis unit is as follows: S11: Based on historical datasets, establish a data relationship model for the influence of environmental impact parameters on the operating parameters of wind power converters using computer fitting; the data relationship model is expressed as follows: ； in, For the first The corresponding values ​​of the environmental impact parameters, For the first wind power converter The values ​​corresponding to the various operating parameters For the first Environmental impact parameters and the first environmental impact parameter of wind power converter The model fitting function between the various operating parameters, where , This represents the total number of runtime parameters. For the first The residual error of various environmental impact parameters in the fitted model; S12: When the fault detection unit detects a fault, it acquires the current time as the time cutoff point. The values ​​of operating parameters and environmental impact parameters within the time period, among which For a pre-set short-term data collection period; S13: Set multiple detection time points within a short acquisition period, where the time interval between adjacent detection time points is the same; perform the following steps for each environmental impact parameter: S131: Substitute the values ​​of the environmental impact parameters at each detection time point into the data relationship model to obtain the values ​​of each operating parameter of the wind power converter in the data relationship model at each detection time point after substitution. S132: Obtain the types of operating parameters that cause wind power converter failures. Assume there are a total of [number] types of operating parameters that cause wind power converter failures. Seed, satisfy For each type of operating parameter that causes a wind power converter failure, perform the following: S1321: Calculate the absolute value of the difference between the actual operating parameter values ​​and the operating parameter values ​​in the data relationship model at each detection time point, and extract the smallest absolute value among all absolute values ​​as the short-term impact comparison coefficient of this environmental impact parameter on the operating parameter that causes wind power converter failure; let the short-term impact comparison coefficient be... ,in For the types of environmental impact parameters, The types of operating parameters that cause wind power converter failures; satisfying ; S14: For each type of operating parameter that leads to wind power converter failure, calculate the short-term impact comparison coefficient of the corresponding environmental impact parameters. Sort by size, the smaller the short-term impact comparison coefficient, the greater the impact of the environmental impact parameter on the failure of the wind power converter in the short term.

2. The wind power converter fault adaptive diagnosis system according to claim 1, characterized in that, The fault detection unit also includes a preset standard operating parameter benchmark library, which contains the threshold range of each operating parameter when the wind power converter is running normally. The fault detection unit compares the real-time operating parameters of the wind power converter with the threshold ranges of the corresponding operating parameters in the parameter reference library. If at least one operating parameter exceeds its threshold range, the wind power converter is determined to have malfunctioned.

3. The wind power converter fault adaptive diagnosis system according to claim 1, characterized in that, The assessment and decision-making module includes a cause identification unit and a maintenance decision support unit. The cause identification unit is used to accurately identify the cause of the fault by combining the impact of various environmental influence parameters on the failure of the wind power converter in the short and long term. The maintenance decision support unit is used to provide decision support for maintenance and repair based on the identification results of the fault classification unit.

4. The wind power converter fault adaptive diagnosis system according to claim 1, characterized in that, The long-term trend analysis unit determines the normal threshold range of each environmental impact parameter by using historical data and industry standards, and evaluates the impact of each environmental impact parameter on the failure of the wind power converter over a long period of time based on the abnormal duration of each environmental impact parameter not being within the normal threshold range during the set long-term collection period.

Images