Fault detection method and system for wind power equipment
By extracting and fusing features from the operating status and electrical performance data of wind power equipment, a comprehensive fault assessment value is generated, which solves the problem of inaccurate fault assessment in existing technologies and achieves efficient fault detection and maintenance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- 华电(宁夏)能源有限公司新能源分公司
- Filing Date
- 2026-02-11
- Publication Date
- 2026-05-12
AI Technical Summary
Existing technologies fail to effectively integrate multi-dimensional data from wind power equipment, resulting in inaccurate fault assessments, difficulty in meeting operation and maintenance needs, and a high risk of missed or false detections.
By acquiring the operating status and electrical performance data of wind power equipment, feature extraction and fusion processing are performed to generate a comprehensive fault assessment value, which is then used for detection in conjunction with preset thresholds.
It enables accurate detection of wind power equipment faults, reduces missed and false detections, and improves the reliability and efficiency of operation and maintenance.
Smart Images
Figure CN122014533A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of fault detection technology, specifically to a fault detection method and system for wind power equipment. Background Technology
[0002] As a core form of clean and renewable energy utilization, wind power generation has seen its installed capacity grow rapidly. Doubly fed wind turbines, with their mature technology and stable operating performance, have become the mainstream configuration in the wind power field. These wind turbines have a complex structure, with the core consisting of mechanical components such as the transmission system, rotor and pitch system, yaw system, and control system, as well as electrical components such as high and low voltage power distribution systems, 35kV combined electrical appliances, frequency converters, and converters. They are exposed to harsh outdoor conditions for a long time and need to operate under continuous high loads, which makes key components such as gearboxes, generators, main shafts, and electrical circuits prone to wear, aging, and insulation degradation, becoming high-risk points for failure.
[0003] The limitations of existing technologies include at least the following issues: existing technologies have not achieved comprehensive integration of multi-dimensional data on the operating status and electrical performance of wind power equipment, resulting in a lack of completeness in the assessment of equipment faults and difficulty in fully reflecting the actual operating conditions of the equipment; moreover, the operating status data has not been specifically subdivided and extracted in terms of thermal and power dimensions, and the data processing mode is fragmented, making it difficult to achieve collaborative analysis of multi-dimensional data, which can easily lead to insufficient accuracy in fault assessment and the occurrence of missed or false detections. This not only reduces the reliability of fault detection but also makes it difficult to meet the actual needs of efficient operation and maintenance of wind power equipment. Summary of the Invention
[0004] To address the shortcomings of existing technologies, this invention provides a fault detection method and system for wind power equipment, which solves the problem that existing technologies do not integrate and segment multi-dimensional wind power data, resulting in inaccurate fault assessments that fail to meet operation and maintenance needs.
[0005] To achieve the above objectives, the present invention provides the following technical solution: a fault detection method for wind power equipment, comprising the following steps: acquiring operational status detection data and electrical performance detection data of the target wind power equipment; extracting operational anomaly assessment values of the target wind power equipment based on the operational status detection data; extracting electrical anomaly assessment values of the target wind power equipment based on the electrical performance detection data, and fusing them with the operational anomaly assessment values to obtain fault assessment values of the target wind power equipment; and performing fault detection processing on the target wind power equipment based on the fault assessment values.
[0006] Furthermore, the operating status detection data includes speed value, gearbox temperature value, generator temperature value, engine compartment temperature value, hydraulic station pressure value, gear oil pump pressure value, and transmission vibration value.
[0007] Further, the specific steps for extracting the operational anomaly assessment value of the target wind power equipment are as follows: feature extraction processing is performed on the operational status detection data to obtain the operational detection set of the target wind power equipment, including thermal anomaly assessment value and power anomaly assessment value; the operational detection set is comprehensively processed to obtain the operational anomaly assessment value of the target wind power equipment.
[0008] Furthermore, the specific steps for obtaining the operational monitoring set of the target wind turbine are as follows: based on the gearbox temperature value, generator temperature value, and nacelle temperature value, extract the thermal anomaly assessment value of the target wind turbine; based on the transmission vibration value, hydraulic station pressure value, gear oil pump pressure value, and rotational speed value, extract the dynamic anomaly assessment value of the target wind turbine.
[0009] Further, the specific steps for extracting the electrical anomaly assessment value of the target wind power equipment are as follows: the electrical performance test data is deviated from the electrical benchmark set stored in the database to obtain the electrical deviation set of the target wind power equipment; the electrical deviation set is comprehensively processed to obtain the electrical anomaly assessment value of the target wind power equipment.
[0010] Further, the specific steps for obtaining the fault assessment value of the target wind power equipment are as follows: read the electrical anomaly assessment value and the operational anomaly assessment value, and perform normalization processing; aggregate the normalized electrical anomaly assessment value and the operational anomaly assessment value to obtain the fault assessment value of the target wind power equipment.
[0011] Furthermore, the specific steps for fault detection and processing of the target wind power equipment are as follows: compare the fault assessment value with the preset fault assessment threshold; based on the comparison result, output the fault detection result of the target wind power equipment.
[0012] A fault detection system for wind power equipment includes: a data acquisition module for acquiring operational status detection data and electrical performance detection data of a target wind power equipment; an operational evaluation module for extracting operational anomaly evaluation values of the target wind power equipment based on the operational status detection data; a comprehensive evaluation module for extracting electrical anomaly evaluation values of the target wind power equipment based on the electrical performance detection data, and fusing them with the operational anomaly evaluation values to obtain a fault evaluation value of the target wind power equipment; and a fault detection module for performing fault detection processing on the target wind power equipment based on the fault evaluation values.
[0013] The present invention has the following beneficial effects: (1) The fault detection method for wind power equipment collects operating status and electrical performance data and performs collaborative analysis to avoid judgment bias caused by single-dimensional data. Then, by subdividing and evaluating the operating status related data according to thermal and power dimensions, and comparing the electrical related data with the benchmark set to extract anomalies, it accurately captures potential problems in the core mechanical links and electrical control links, aggregates and generates a comprehensive fault assessment value, and finally compares it with the preset threshold to output the detection result. The whole process fits the training logic of fault investigation and status monitoring in the practical platform, effectively reduces missed detections and false detections, provides clear and reliable references for operation and maintenance personnel, reduces equipment downtime losses, and effectively adapts to the actual operation and maintenance scenarios of wind farms.
[0014] (2) The fault detection system for wind power equipment accurately connects to the sensors, monitoring system and detection equipment in the operation platform through the data acquisition module, automatically acquires key data related to equipment operation and electrical systems, and reduces human operation errors and workload; the operation evaluation module and the comprehensive evaluation module automatically complete data subdivision processing, anomaly extraction and fusion analysis according to the established logic, and the fault detection module quickly outputs the detection results. The entire process is streamlined and automated to meet the needs of efficient fault diagnosis in the actual operation and maintenance of wind farms and improve the accuracy of fault detection.
[0015] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description
[0016] Figure 1 This is a flowchart of a fault detection method for wind power equipment according to the present invention.
[0017] Figure 2 This is a block diagram of a fault detection system for wind power equipment according to the present invention. Detailed Implementation
[0018] Please see Figure 1 This invention provides a technical solution: a fault detection method for wind power equipment, comprising the following steps: acquiring operational status detection data and electrical performance detection data of the target wind power equipment; extracting operational anomaly assessment values of the target wind power equipment based on the operational status detection data; extracting electrical anomaly assessment values of the target wind power equipment based on the electrical performance detection data, and fusing them with the operational anomaly assessment values to obtain fault assessment values of the target wind power equipment; and performing fault detection processing on the target wind power equipment based on the fault assessment values.
[0019] The specific steps for fault detection and handling of the target wind turbine are as follows: The fault assessment value is compared with a preset fault assessment threshold; based on the comparison result, the fault detection result of the target wind turbine is output, i.e., if the fault assessment value is lower than the preset fault assessment threshold, the target wind turbine has not experienced a fault; if the fault assessment value is not lower than the preset fault assessment threshold, the target wind turbine has experienced a fault. Specifically, the operational status monitoring data includes speed, gearbox temperature, generator temperature, engine compartment temperature, hydraulic station pressure, gear oil pump pressure, and transmission vibration.
[0020] The rotational speed is acquired by a rotational speed sensor installed on the main shaft of the wind turbine or the generator shaft. The sensor captures the rotational frequency of the main shaft / generator and converts it to obtain rotational speed data, which reflects the operating speed of the transmission system.
[0021] The gearbox temperature value is collected by a temperature sensor (such as PT100). The sensor is placed on the bearing housing, lubrication oil passage or gearbox wall to directly monitor the operating temperature of the core components inside the gearbox.
[0022] The generator temperature value is obtained through a temperature sensor, which is installed on the generator stator winding, rotor core, or bearing to accurately monitor the temperature changes of the generator's core heat-generating components.
[0023] The cabin temperature is collected by temperature sensors located inside the cabin (such as next to the control cabinet or in the middle of the cabin), reflecting the overall ambient temperature of the cabin and preventing abnormal ambient temperature from affecting equipment operation.
[0024] The pressure value of the hydraulic station is collected by a pressure sensor, which is installed at the oil pipeline or accumulator interface of the hydraulic station to monitor the working pressure of the hydraulic system in real time and ensure the power supply for actions such as pitch and yaw.
[0025] The gear oil pump pressure value is collected by a pressure sensor installed on the gear oil pump outlet pipeline to monitor the lubricating oil pressure output by the oil pump and ensure that all components of the gearbox are adequately lubricated.
[0026] The transmission vibration value is collected by vibration sensors (accelerometers). The sensors are placed on the bearing housings or housings of the gearbox, generator, and main shaft to capture the vibration signals during the operation of the transmission system and reflect whether there are problems such as wear or imbalance in the components.
[0027] The specific steps for extracting the operational anomaly assessment value of the target wind turbine are as follows: Feature extraction processing is performed on the operational status detection data to obtain the operational detection set of the target wind turbine, including thermal anomaly assessment values and power anomaly assessment values; comprehensive processing is performed on the operational detection set to obtain the operational anomaly assessment value of the target wind turbine. Specifically, the thermal anomaly assessment value and the power anomaly assessment value are standardized, and the standardized thermal anomaly assessment value and the power anomaly assessment value are weighted according to preset corresponding weight coefficients (such as 0.4 and 0.6) to obtain the operational anomaly assessment value.
[0028] The specific steps to obtain the operation monitoring set of the target wind turbine are as follows: Based on the gearbox temperature value, generator temperature value, and nacelle temperature value, extract the thermal anomaly assessment value of the target wind turbine. Specifically, the gearbox temperature value, generator temperature value, and nacelle ambient temperature value are compared with the gearbox temperature benchmark value, generator temperature benchmark value, and nacelle temperature benchmark value stored in the database (absolute value is taken) to obtain the gearbox temperature difference value, generator temperature difference value, and nacelle temperature difference value. These are then standardized. Based on the standardized differences, a weighted average is applied (with preset weighting coefficients of 0.3, 0.4, and 0.3, respectively) to obtain the thermal anomaly assessment value of the target wind turbine. Based on transmission vibration values, hydraulic station pressure values, gear pump pressure values, and rotational speed values, the power anomaly assessment value of the target wind turbine is extracted. Specifically, the transmission vibration values, hydraulic station pressure values, gear pump pressure values, and rotational speed values are compared with the transmission vibration benchmark values, hydraulic station pressure benchmark values, gear pump pressure benchmark values, and rotational speed benchmark values stored in the database. The absolute values are then used to obtain the transmission vibration difference, hydraulic station pressure difference, gear pump pressure difference, and rotational speed difference. These differences are then standardized. Finally, the standardized differences are weighted (with preset weighting coefficients of 0.4, 0.2, 0.2, and 0.2, respectively) to obtain the power anomaly assessment value of the target wind turbine. It should be noted that the above benchmark values are all obtained from historical data. Taking the gearbox temperature benchmark value as an example, the historical gearbox temperature values at several historical time points are obtained and the average value is taken to obtain the gearbox temperature benchmark value.
[0029] In this implementation plan, the data is extracted according to thermal and power dimensions, which can capture different types of operational anomalies in a targeted manner. Secondly, the benchmark value is taken from the average of historical data, which refers to historical parameter records and fits the actual operating conditions of the equipment in the long term, making the anomaly judgment more based on evidence. Furthermore, the difference in the dimensions of different parameters is eliminated through standardization processing, which not only highlights the influence of core components, but also takes into account the synergistic effect of various parameters. The final operational anomaly assessment value is comprehensive and focused.
[0030] Specifically, the electrical performance test data includes stator-side current, rotor-side current, leakage current, grounding resistance, insulation resistance, and motor output power. The specific steps for extracting the electrical anomaly assessment values of the target wind turbine are as follows: The electrical performance test data is deviated from the electrical reference set stored in the database to obtain the electrical deviation set of the target wind power equipment. Specifically, the electrical reference set stored in the database includes the stator side current reference value, rotor side current reference value, leakage current reference value, grounding resistance reference value, insulation resistance reference value, and motor output power reference value. The stator side current value, rotor side current value, leakage current value, grounding resistance value, insulation resistance value, and motor output power value are respectively compared with the corresponding reference values in the electrical reference set. The difference is processed (the absolute value is taken) to obtain the stator side current deviation value, rotor side current deviation value, leakage current deviation value, grounding resistance deviation value, insulation resistance deviation value, and motor output power deviation value, which is the electrical deviation set. The electrical deviation set is comprehensively processed to obtain the electrical anomaly assessment value of the target wind power equipment. Specifically, the stator side current deviation value, rotor side current deviation value, leakage current deviation value, grounding resistance deviation value, insulation resistance deviation value, and motor output power deviation value are standardized. The standardized deviation values are then weighted according to preset weighting coefficients (such as 0.15, 0.15, 0.2, 0.2, 0.2, 0.1) to obtain the electrical anomaly assessment value.
[0031] It should be noted that the above reference values are all obtained from historical data. Taking the stator current reference value as an example, the historical stator current values at several historical time points are obtained and the average value is taken to obtain the stator current reference value.
[0032] The stator-side current value is collected by a current transformer installed in the generator stator output cabinet. The transformer is wrapped around the three-phase output cable of the stator and converts the large current into a standard small current signal. After transmission, the stator-side current data is obtained, which reflects the working current status of the stator winding.
[0033] The rotor-side current value is obtained through the current transformer in the rotor-side converter circuit. The transformer is arranged on the connection line between the rotor winding and the converter to collect the current signal of the rotor circuit in real time, which is adapted to the operating conditions of rotor frequency conversion power supply.
[0034] The leakage current value is collected using a leakage current tester. The tester is connected to the equipment's grounding circuit and winding circuit. When the equipment is energized or a test voltage is applied, the leakage current value to ground is measured to determine whether there is any hidden deterioration in the insulation.
[0035] The grounding resistance value is obtained through a grounding resistance tester. The tester injects test current into the grounding electrode of the equipment and measures the resistance value of the grounding loop to ensure that the grounding system meets the requirements for safe operation.
[0036] Insulation resistance is measured by an insulation megohmmeter. A DC voltage is applied to the generator stator and rotor windings or power cables, and the insulation resistance between the windings and ground is collected to check for insulation moisture and damage.
[0037] The motor output power is calculated by a power transmitter. The transmitter synchronously collects stator side voltage and current signals, combines them with power factor parameters, and calculates the generator output power to intuitively reflect the power generation efficiency and load level.
[0038] The specific steps to obtain the fault assessment value of the target wind turbine are as follows: Read the electrical anomaly assessment value and the operational anomaly assessment value, and perform normalization processing (that is, map their values between 0 and 1); aggregate the normalized electrical anomaly assessment value and the operational anomaly assessment value to obtain the fault assessment value of the target wind turbine, that is: weight the normalized electrical anomaly assessment value and the operational anomaly assessment value with preset corresponding weight coefficients (such as the weight coefficient corresponding to the electrical anomaly assessment value is 0.5, and the weight coefficient corresponding to the operational anomaly assessment value is 0.5) to obtain the fault assessment value of the target wind turbine.
[0039] In this implementation plan, the electrical benchmark value is taken from the historical data average, based on the actual parameters of the equipment during long-term operation, rather than being randomly selected. This provides a reliable reference for deviation calculation and aligns with the actual long-term operating conditions of wind power equipment. Secondly, various electrical deviation values are standardized and weighted, with weights tilted towards key safety indicators such as leakage current, grounding resistance, and insulation resistance. This comprehensively covers the core electrical detection dimensions while highlighting the impact of high-risk parameters, accurately reflecting the degree of abnormality in electrical components. Finally, the electrical and operational anomaly assessment values are normalized and then merged with equal weights to eliminate the dimensional differences between the two types of assessment values. This approach considers both mechanical and electrical operating conditions, avoiding the one-sidedness of single-dimensional assessments. The resulting fault assessment value is objective and comprehensive, providing an accurate and reliable basis for subsequent fault detection and meeting the needs of accurate fault diagnosis in the actual operation and maintenance of wind farms.
[0040] Please see Figure 2This invention provides a technical solution: a fault detection system for wind power equipment, comprising: a data acquisition module for acquiring operational status detection data and electrical performance detection data of the target wind power equipment; an operational evaluation module for extracting operational anomaly evaluation values of the target wind power equipment based on the operational status detection data; a comprehensive evaluation module for extracting electrical anomaly evaluation values of the target wind power equipment based on the electrical performance detection data, and fusing them with the operational anomaly evaluation values to obtain a fault evaluation value of the target wind power equipment; and a fault detection module for performing fault detection processing on the target wind power equipment based on the fault evaluation values.
[0041] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.
[0042] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
Claims
1. A fault detection method for wind power equipment, characterized in that, Includes the following steps: Acquire operational status monitoring data and electrical performance monitoring data of the target wind turbine equipment; Based on the operational status detection data, extract the operational anomaly assessment value of the target wind power equipment; Based on the electrical performance test data, the electrical anomaly assessment value of the target wind power equipment is extracted and fused with the operational anomaly assessment value to obtain the fault assessment value of the target wind power equipment. Based on the fault assessment value, fault detection and processing are performed on the target wind power equipment.
2. The fault detection method for wind power equipment according to claim 1, characterized in that, The operational status detection data includes speed value, gearbox temperature value, generator temperature value, engine compartment temperature value, hydraulic station pressure value, gear oil pump pressure value, and transmission vibration value.
3. The fault detection method for wind power equipment according to claim 2, characterized in that, The specific steps for extracting the operational anomaly assessment values of the target wind turbine are as follows: The operation status detection data is processed by feature extraction to obtain the operation detection set of the target wind power equipment, including thermal anomaly assessment value and power anomaly assessment value; The operational detection set is comprehensively processed to obtain the operational anomaly assessment value of the target wind power equipment.
4. The fault detection method for wind power equipment according to claim 3, characterized in that, The specific steps to obtain the operational monitoring set of the target wind turbine are as follows: Based on the gearbox temperature value, generator temperature value, and nacelle temperature value, extract the thermal anomaly assessment value of the target wind power equipment; Based on the transmission vibration value, hydraulic station pressure value, gear oil pump pressure value, and rotational speed value, the power anomaly assessment value of the target wind power equipment is extracted.
5. The fault detection method for wind power equipment according to claim 1, characterized in that, The specific steps for extracting the electrical anomaly assessment values of the target wind turbine are as follows: The electrical performance test data is deviated from the electrical reference set stored in the database to obtain the electrical deviation set of the target wind power equipment; The electrical deviation set is processed to obtain the electrical anomaly assessment value of the target wind power equipment.
6. The fault detection method for wind power equipment according to claim 1, characterized in that, The specific steps to obtain the fault assessment value of the target wind turbine are as follows: Read the electrical anomaly assessment value and the operational anomaly assessment value, and perform normalization processing; The normalized electrical anomaly assessment value and the operational anomaly assessment value are aggregated to obtain the fault assessment value of the target wind power equipment.
7. The fault detection method for wind power equipment according to claim 1, characterized in that, The specific steps for fault detection and handling of the target wind turbine equipment are as follows: The fault assessment value is compared with a preset fault assessment threshold. Based on the comparison and processing results, the fault detection results of the target wind power equipment are output.
8. A fault detection system for wind power equipment, employing the fault detection method for wind power equipment according to any one of claims 1-7, characterized in that, include: The data acquisition module is used to acquire operational status monitoring data and electrical performance monitoring data of the target wind power equipment; The operation evaluation module is used to extract the operation anomaly evaluation value of the target wind power equipment based on the operation status detection data; The comprehensive evaluation module is used to extract the electrical anomaly evaluation value of the target wind power equipment based on the electrical performance test data, and to fuse it with the operation anomaly evaluation value to obtain the fault evaluation value of the target wind power equipment. The fault detection module is used to perform fault detection processing on the target wind power equipment based on the fault assessment value.