A method and system for early warning of wind turbine faults based on multi-model combination

Abstract

This invention relates to the field of power generation technology and discloses a method and system for early warning of wind turbine faults based on multi-model combination. The early warning method comprises the following steps: Step 1, data acquisition; Step 2, establishing an early warning model; Step 3, real-time monitoring and early warning; Step 4, fault source analysis; Step 5, fault duration estimation; and Step 6, prediction of subsequent fault conditions. This invention, through the system's estimation of fault duration based on the results of fault source analysis, combined with historical fault data and current operating data, utilizes a predictive model to predict not only the rate of fault escalation but also the degree of impact of the fault on turbine performance, thereby formulating more effective response strategies. This achieves the beneficial effect of not only providing early warning of wind turbine faults but also analyzing fault sources.

Description

Technical Field

[0001] This invention relates to the field of power generation technology, specifically to a method and system for early warning of wind turbine faults based on a combination of multiple models. Background Technology

[0002] Wind turbine fault early warning methods refer to methods that detect potential faults based on current and historical operating data of wind turbines. Based on the data source, they can be divided into fault early warning methods based on vibration data, fault early warning methods based on SCADA data, and fault early warning methods based on other signal sources (such as ultrasonic devices, infrared imagers, etc.). Among these, the high purchase and installation costs of equipment such as vibration sensors, ultrasonic devices, and infrared imagers limit the practical application of fault early warning methods based on such data. In contrast, SCADA systems have been widely used in wind farms and can provide relatively complete historical operating data of the turbines. Therefore, fault early warning methods based on SCADA data are more suitable for engineering applications and have become the mainstream method for wind turbine fault early warning.

[0003] A search revealed a method for early warning of wind turbine faults based on multi-model combination, published in CN 111798650 A. This method first collects a large amount of historical data on wind speed, pitch angle, torque setting, SCADA data on the angle between the centerline and wind direction, and power. Multiple neural network methods are used to establish full-condition power prediction sub-models for wind turbine startup-shutdown. Second, based on a data sliding window, the power prediction sub-models are used to calculate the time series of predicted power values ​​and calculate operating status indicators. Third, kernel density estimation is used to calculate the probability density function of the operating status indicators, thereby determining the basic probability allocation function of the fault warning proposition. Finally, evidence theory is used to fuse the warning results of multiple power prediction sub-models, and the fused result is compared with a set warning threshold to draw a fault warning conclusion. This invention can achieve full-condition fault warning for wind turbines and can effectively improve the accuracy of fault warning results.

[0004] Although existing technologies can provide early warnings of wind turbine faults and indicate the operating conditions of wind turbines, the prediction results can only indicate the presence of fault risk because they are based on data modeling and evidence-based prediction. However, they cannot determine the origin of the fault, the duration of the fault, or the time when it will escalate further. Summary of the Invention

[0005] Technical problems to be solved:

[0006] To address the shortcomings of existing technologies, this invention provides a wind turbine fault early warning method and system based on multi-model combination. It has the advantages of not only being able to warn of wind turbine faults but also analyzing fault sources, and being able to calculate the duration of the fault and subsequent conditions after a fault is detected, thus solving the problems of the aforementioned technologies.

[0007] Technical solution:

[0008] To achieve the above objectives, the present invention provides the following technical solution: a wind turbine fault early warning method based on multi-model combination, wherein the early warning method comprises the following steps:

[0009] Step 1: Data Acquisition: Collect various operating data of the wind turbine: wind speed, power output, temperature, and vibration;

[0010] Step 2: Establish an early warning model: Utilize random forests to build a wind turbine fault early warning model. Train the model to identify the differences between normal and abnormal states, and set an early warning threshold, which is determined by the operating data. ;

[0011] Step 3: Real-time monitoring and early warning: Input real-time data into the early warning model to continuously monitor the operating status of the wind turbine. Once the model output exceeds the early warning threshold, the early warning mechanism will be triggered immediately.

[0012] Step 4: Fault Source Analysis: When the warning is triggered, the fault source analysis program is started. Using a Bayesian network, combined with historical and real-time data, the specific cause of the warning is analyzed.

[0013] Step 5: Fault duration estimation: Based on the results of the fault source analysis, combined with historical fault data and current operating data, estimate the duration of the fault.

[0014] Step Six: Predicting the Subsequent Development of the Fault: Using a predictive model, combined with current fault data and historical fault evolution data, predict the subsequent development of the fault, including the speed of fault expansion and the degree of impact on unit performance.

[0015] A wind turbine fault early warning system based on multi-model combination, the early warning system is used for early warning methods, and the early warning system consists of a data acquisition unit, a real-time monitoring and early warning unit, an analysis unit and a prediction unit;

[0016] The data acquisition unit is used to collect wind speed, power output, temperature, and vibration operation data of the wind turbine.

[0017] The real-time monitoring and early warning unit is used to continuously monitor the operating status of the wind turbine unit. If the output exceeds the early warning threshold, the early warning mechanism will be triggered immediately.

[0018] The analysis unit is used to analyze the specific reasons that cause the warning and estimate the duration of the fault.

[0019] The prediction unit is used to predict the subsequent development of a fault based on the results of fault source analysis, including the speed of fault expansion and the degree of impact on unit performance.

[0020] Preferably, the expression for the data acquisition unit is:

[0021] Sensor data acquisition:

[0022] Wind speed sensor: ,in It's the wind speed value. It is time. This is the actual wind speed;

[0023] Power output sensor: ,in This is the power output value. It is time. It is the power converted from theoretical wind speed;

[0024] Temperature sensor: Where T is the temperature value, It is time. This is the actual temperature;

[0025] Vibration sensor: Where B is the vibration value, It is time. It is actual vibration;

[0026] Multi-source data fusion:

[0027]

[0028] in It is the merged data. , , and These are the normalized wind speed, power, temperature, and vibration data, respectively. It is a fusion function.

[0029] Preferably, the multi-source data fusion uses probabilistic fusion calculation, expressed as:

[0030]

[0031] in:

[0032] It is the fused data, which comprehensively considers information on wind speed, power, temperature, and vibration;

[0033] It is the normalized first Data sources in time The value;

[0034] The corresponding weights satisfy... .

[0035] Preferably, the early warning model expression of the real-time monitoring and early warning unit is:

[0036] Suppose a dataset containing multiple features: wind speed, power, temperature, and vibration. ,in It is the first The feature vector of each sample These are the corresponding labels, indicating normal operating status: label 0 or abnormal status: label 1;

[0037] The prediction function of a random forest is expressed as:

[0038]

[0039] Using datasets To train a random forest model, the model learns how to use feature vectors To predict tags ;

[0040] The warning threshold is set based on the running data. ;

[0041] set up and These are the mean and standard deviation of the probability values ​​output by the model under normal operating conditions. Therefore, the warning threshold is set as follows:

[0042] .

[0043] Preferably, the expression for triggering the early warning mechanism by the real-time monitoring and early warning unit is:

[0044] Early warning model:

[0045] The established random forest model is used for prediction, and the probability value output by the model is... , indicating time The probability of a wind turbine being in an abnormal state;

[0046] Warning threshold setting:

[0047] Warning threshold The average probability of being set to normal operating state Add or subtract a threshold range: ;

[0048] Triggering the early warning mechanism:

[0049] During real-time monitoring, for each time point Calculate the predicted anomaly probability if If this occurs, an early warning mechanism will be triggered, indicating that the wind turbine has an abnormal condition and requires further inspection and maintenance.

[0050]

[0051] in It is the prediction function of the random forest model, obtained by ensemble of multiple decision trees;

[0052] The trigger condition expression for the early warning mechanism is:

[0053] .

[0054] Preferably, the fault source analysis expression in the analysis unit is:

[0055] Define variables and events:

[0056] Let a set of variables This represents various factors that can lead to wind turbine failures: failure of specific components or environmental factors.

[0057] Each variable There are multiple states: ,in Representing variables The One state;

[0058] Prior probability and conditional probability:

[0059] Prior probability This indicates that, in the absence of other information, the variable... In state The probability of;

[0060] Conditional probability Indicates at a given parent node In the state, variables In state The probability of;

[0061] Fault source reasoning, using the variable elimination method, calculates the posterior probability of each fault factor:

[0062]

[0063] in This is evidence provided by real-time data;

[0064] Identify the source of the fault:

[0065]

[0066] in, Given factors In state Evidence observed at the time The probability, It is the prior probability, and It is the total probability of observing evidence.

[0067] Preferably, the expression for estimating the fault existence time in the analysis unit is:

[0068] This indicates the duration of the fault, which needs to be estimated. Historical fault data is available, including the fault start time. and end time and current real-time data, such as wind speed. ,power ,temperature ,vibration Based on the analysis of the fault source, the time when the fault started was determined. and current time :

[0069]

[0070] in:

[0071] It is the current time point. It is the time point at which the fault began.

[0072] Preferably, the expression for the rate at which the prediction unit predicts fault propagation is:

[0073]

[0074] in,

[0075] Indicates the current stage of the fault's development;

[0076] Indicates future time The degree of development of the fault.

[0077] Preferably, the expression for the degree of impact of the prediction unit on the unit performance is as follows:

[0078] Unit performance Affected by the degree of fault development The influence of this relationship establishes a functional relationship:

[0079]

[0080] Where the function It describes the specific ways in which the degree of fault development affects unit performance;

[0081] The specific expression is:

[0082]

[0083] here It is a predicted future moment. The degree of fault development, and This is the predicted value of the unit's performance at the corresponding time.

[0084] Compared with the prior art, the present invention provides a method and system for early warning of wind turbine faults based on multi-model combination, which has the following beneficial effects:

[0085] 1. This invention collects various operational data from wind turbines, including wind speed, power output, temperature, and vibration, and establishes an early warning mechanism using predictive models such as random forests. Once abnormal operational data exceeds the warning threshold, the system immediately triggers an early warning, indicating a fault or abnormal situation. When the warning is triggered, the system enters the fault source analysis phase. By combining real-time and historical data with Bayesian networks, the system infers the specific cause of the fault. This not only quickly locates the problem but also helps operators take appropriate maintenance measures in the early stages to prevent the fault from worsening. Based on the results of the fault source analysis, combined with historical fault data and current operational data, the system estimates the duration of the fault. Using predictive models, the system can predict not only the rate of fault expansion but also the degree of impact on turbine performance, thereby formulating more effective response strategies. This achieves the beneficial effect of not only providing early warnings of wind turbine faults but also analyzing the fault sources.

[0086] 2. This invention utilizes a predictive model, combining current fault data and historical fault evolution data, to predict the subsequent development of a fault. This includes the rate of fault escalation and the specific impact of the fault on the performance of the wind turbine. The formula for predicting the rate of fault escalation is: in This indicates the current stage of the fault's development. Indicates future time The degree of fault development and the impact of the fault on unit performance are predicted through a function. In progress, among which It describes the specific ways in which the degree of fault development affects unit performance, achieving the beneficial effect of being able to calculate the duration of the fault and subsequent situations after a fault is detected by early warning. Attached Figure Description

[0087] Figure 1 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0088] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0089] Please see Figure 1 A method for early warning of wind turbine faults based on multi-model combination, the steps of which are as follows:

[0090] Step 1: Data Acquisition: Collect various operating data of the wind turbine: wind speed, power output, temperature, and vibration;

[0091] Step 2: Establish an early warning model: Utilize random forests to build a wind turbine fault early warning model. Train the model to identify the differences between normal and abnormal states, and set an early warning threshold, which is determined by the operating data. ;

[0092] Step 3: Real-time monitoring and early warning: Input real-time data into the early warning model to continuously monitor the operating status of the wind turbine. Once the model output exceeds the early warning threshold, the early warning mechanism will be triggered immediately.

[0093] Step 4: Fault Source Analysis: When the warning is triggered, the fault source analysis program is started. Using a Bayesian network, combined with historical and real-time data, the specific cause of the warning is analyzed.

[0094] Step 5: Fault duration estimation: Based on the results of the fault source analysis, combined with historical fault data and current operating data, estimate the duration of the fault.

[0095] Step Six: Predicting the Subsequent Development of the Fault: Using a predictive model, combined with current fault data and historical fault evolution data, predict the subsequent development of the fault, including the speed of fault expansion and the degree of impact on unit performance.

[0096] A wind turbine fault early warning system based on multi-model combination, the early warning system is used for early warning methods, and the early warning system consists of a data acquisition unit, a real-time monitoring and early warning unit, an analysis unit and a prediction unit;

[0097] The data acquisition unit is used to collect wind speed, power output, temperature, and vibration operation data of the wind turbine.

[0098] The real-time monitoring and early warning unit is used to continuously monitor the operating status of the wind turbine unit. If the output exceeds the early warning threshold, the early warning mechanism will be triggered immediately.

[0099] The analysis unit is used to analyze the specific reasons that cause the warning and estimate the duration of the fault.

[0100] The prediction unit is used to predict the subsequent development of a fault based on the results of fault source analysis, including the speed of fault expansion and the degree of impact on unit performance.

[0101] The data acquisition unit integrates data from different sensors through multi-source data fusion, providing more comprehensive and integrated data information. Through normalization processing and fusion functions, various data are unified into a standardized range, facilitating comparison and analysis. By fusing multiple data sources, the limitations or errors of a single sensor are compensated for, improving data accuracy and reliability. Comprehensive consideration of data from multiple aspects more fully reflects the actual situation. Multi-source data fusion improves data credibility and stability, reducing the risks associated with single data sources. By integrating multiple data sources, data fluctuations and noise are reduced, enhancing data credibility. Multi-source data fusion uncovers deeper information and correlations, providing more valuable data support for subsequent analysis and decision-making. Integrated data helps users better understand system operation and trends.

[0102] The real-time monitoring and early warning unit uses prediction models such as random forests to monitor and warn of abnormal states. It can quickly and accurately identify abnormal situations in wind turbines. The combination of multiple models improves the accuracy and stability of predictions, and reduces false alarm and missed alarm rates. The system monitors the operating status of wind turbines in real time, detects abnormal situations in a timely manner, and triggers an early warning mechanism through set early warning thresholds. This allows for rapid response to abnormal situations and helps to take timely measures for maintenance and repair, reducing losses. The setting of early warning thresholds is flexible and can be adjusted according to actual conditions to adapt to different operating environments and requirements. By setting an appropriate threshold range, the sensitivity and accuracy of early warnings are balanced. The triggering of the early warning mechanism is based on the comparison between the abnormal probability output by the model and the early warning threshold, realizing an automated wind turbine fault early warning system. This reduces the need for human intervention and improves the efficiency of monitoring and early warning. The system comprehensively considers data from multiple features (wind speed, power, temperature, and vibration) and uses prediction models such as random forests for comprehensive analysis and monitoring, improving the comprehensive monitoring and early warning capabilities of wind turbine operating status.

[0103] The analysis unit uses prior probability and conditional probability to perform reasoning analysis on different fault sources, combined with evidence provided by real-time data, and comprehensively considers the impact of various factors on wind turbine faults to improve the accuracy and comprehensiveness of fault source analysis. Through variable elimination, the reasoning process for fault sources is flexibly adjusted and updated according to actual conditions to adapt to fault diagnosis needs under different circumstances, improving the system's applicability and practicality. Based on historical fault data and real-time monitoring data, combined with the results of fault source analysis, the system can relatively accurately estimate the duration of faults, facilitating rapid response and maintenance scheduling, reducing the impact and losses caused by faults. By estimating the duration of faults, the system can more accurately determine the duration of faults, helping to predict wind turbine fault conditions and maintenance needs, improving the effectiveness and response speed of the early warning system, and further ensuring the safe and stable operation of wind turbines.

[0104] By establishing a functional relationship between the fault propagation rate and turbine performance, the prediction unit enables the system to comprehensively consider the impact of fault development on turbine performance, thus improving the comprehensive analysis capability of wind turbine faults. Based on the prediction expression of fault propagation rate and turbine performance, the system can relatively accurately predict the degree of fault development and turbine performance values ​​at future moments, which helps to detect potential faults in advance and take corresponding preventive and maintenance measures. Predicting the impact of fault propagation rate and turbine performance helps the system to achieve timely early warning of future faults, improving the real-time monitoring and management capability of wind turbine operating status. Based on the prediction of fault development and turbine performance, the system can provide predictions of the turbine's operating status at future moments, which helps to optimize operation and maintenance decisions and improve the system's health management level.

[0105] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for early warning of wind turbine faults based on multi-model combination, characterized in that, The steps of the early warning method are as follows: Step 1: Data Acquisition: Collect various operating data of the wind turbine: wind speed, power output, temperature, and vibration; Step 2: Establish an early warning model: Utilize random forests to build a wind turbine fault early warning model. Train the model to identify the differences between normal and abnormal states, and set an early warning threshold, which is determined by the operating data. ; Step 3: Real-time monitoring and early warning: Input real-time data into the early warning model to continuously monitor the operating status of the wind turbine. Once the model output exceeds the early warning threshold, the early warning mechanism will be triggered immediately. Step 4: Fault Source Analysis: When the warning is triggered, the fault source analysis program is started. Using a Bayesian network, combined with historical and real-time data, the specific cause of the warning is analyzed. Step 5: Fault duration estimation: Based on the results of the fault source analysis, combined with historical fault data and current operating data, estimate the duration of the fault. Step Six: Predicting the Subsequent Development of the Fault: Using a predictive model, combined with current fault data and historical fault evolution data, predict the subsequent development of the fault, including the speed of fault expansion and the degree of impact on unit performance.

2. The wind turbine fault early warning system based on multi-model combination according to claim 1, characterized in that, The early warning system is used for early warning methods, and the early warning system consists of a data acquisition unit, a real-time monitoring and early warning unit, an analysis unit, and a prediction unit. The data acquisition unit is used to collect wind speed, power output, temperature, and vibration operation data of the wind turbine. The real-time monitoring and early warning unit is used to continuously monitor the operating status of the wind turbine unit. If the output exceeds the early warning threshold, the early warning mechanism will be triggered immediately. The analysis unit is used to analyze the specific reasons that cause the warning and estimate the duration of the fault. The prediction unit is used to predict the subsequent development of a fault based on the results of fault source analysis, including the speed of fault expansion and the degree of impact on unit performance.

3. The wind turbine fault early warning system based on multi-model combination according to claim 2, characterized in that: The expression for the data acquisition unit is: Sensor data acquisition: Wind speed sensor: ,in It's the wind speed value. It is time. This is the actual wind speed; Power output sensor: ,in This is the power output value. It is time. It is the power converted from theoretical wind speed; Temperature sensor: Where T is the temperature value, It is time. This is the actual temperature; Vibration sensor: Where B is the vibration value, It is time. It is actual vibration; Multi-source data fusion: in It is the merged data. , , and These are the normalized wind speed, power, temperature, and vibration data, respectively. It is a fusion function.

4. The wind turbine fault early warning system based on multi-model combination according to claim 3, characterized in that: The multi-source data fusion uses probabilistic fusion calculation, expressed as: in: It is the fused data, which comprehensively considers information on wind speed, power, temperature, and vibration; It is the normalized first Data sources in time The value; The corresponding weights satisfy... .

5. A wind turbine fault early warning system based on multi-model combination according to claim 4, characterized in that: The early warning model expression for the real-time monitoring and early warning unit is: Suppose a dataset containing multiple features: wind speed, power, temperature, and vibration. ,in It is the first The feature vector of each sample These are the corresponding labels, indicating normal operating status: label 0 or abnormal status: label 1; The prediction function of a random forest is expressed as: Using datasets To train a random forest model, the model learns how to use feature vectors To predict tags ; The warning threshold is set based on the running data. ; set up and These are the mean and standard deviation of the probability values ​​output by the model under normal operating conditions. Therefore, the warning threshold is set as follows: 。 6. A wind turbine fault early warning system based on multi-model combination according to claim 5, characterized in that: The expression for the real-time monitoring and early warning unit to trigger the early warning mechanism is: Early warning model: The established random forest model is used for prediction, and the probability value output by the model is... , indicating time The probability of a wind turbine being in an abnormal state; Warning threshold setting: Warning threshold The average probability of being set to normal operating state Add or subtract a threshold range: ; Triggering the early warning mechanism: During real-time monitoring, for each time point Calculate the predicted anomaly probability if If this occurs, an early warning mechanism will be triggered, indicating that the wind turbine has an abnormal condition and requires further inspection and maintenance. in It is the prediction function of the random forest model, obtained by ensemble of multiple decision trees; The trigger condition expression for the early warning mechanism is: 。 7. A wind turbine fault early warning system based on multi-model combination according to claim 2, characterized in that: The fault source analysis expression in the analysis unit is: Define variables and events: Let a set of variables This represents various factors that can lead to wind turbine failures: failure of specific components or environmental factors. Each variable There are multiple states: ,in Representing variables The One state; Prior probability and conditional probability: Prior probability This indicates that, in the absence of other information, the variable... In state The probability of; Conditional probability Indicates at a given parent node In the state, variables In state The probability of; Fault source reasoning, using the variable elimination method, calculates the posterior probability of each fault factor: in This is evidence provided by real-time data; Identify the source of the fault: in, Given factors In state Evidence observed at the time The probability, It is the prior probability, and It is the total probability of observing evidence.

8. A wind turbine fault early warning system based on multi-model combination according to claim 2, characterized in that: The expression for estimating the fault existence time in the analysis unit is: This indicates the duration of the fault, which needs to be estimated. Historical fault data is available, including the fault start time. and end time and current real-time data, such as wind speed ,power ,temperature ,vibration Based on the analysis of the fault source, the time when the fault started was determined. and current time : in: It is the current time point. It is the time point at which the fault began.

9. A wind turbine fault early warning system based on multi-model combination according to claim 2, characterized in that: The expression for the rate at which the prediction unit predicts fault propagation is: in, Indicates the current stage of the fault's development; Indicates future time The degree of development of the fault.

10. A wind turbine fault early warning system based on multi-model combination according to claim 9, characterized in that: The expression for the degree of impact of the prediction unit on the unit performance is as follows: Unit performance Affected by the degree of fault development The influence of this relationship establishes a functional relationship: Where the function It describes the specific ways in which the degree of fault development affects unit performance; The specific expression is: here It is a predicted future moment. The degree of development of the fault, and This is the predicted value of the unit's performance at the corresponding time.

Images