A wind turbine generator fault diagnosis system

Abstract

The present invention relates to the technical field of wind power generation, and in particular to a wind turbine generator set fault diagnosis system, comprising: a detection module, wherein the detection module can obtain working parameters of the wind turbine generator and internal environmental parameters of the wind turbine generator; a comprehensive diagnosis module, wherein the comprehensive diagnosis module can obtain data of the detection module, analyze and predict the data, and output the analysis result; an adaptive control module, wherein the adaptive control module can output a wind turbine generator control instruction according to the analysis result of the comprehensive diagnosis module, so as to adjust the working parameters and working state of the wind turbine generator; and a communication module, wherein the communication module can obtain the analysis result of the comprehensive diagnosis module and the control instruction information output by the adaptive control module, and send the analysis result and the control instruction information to a host computer.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation, and in particular to a fault diagnosis system for a wind power generator set. Background Art

[0002] As the core equipment of wind power generation system, the operation status of wind turbines directly affects the power generation efficiency and reliability of the whole system. The operating environment of the wind turbines is harsh, the structure is complex, and the fault diagnosis is challenging.

[0003] The existing wind turbine fault diagnosis system relies on regular maintenance and manual inspections, which is inefficient, costly, and difficult to detect potential faults in a timely manner. The wind power industry urgently needs an efficient, reliable, and intelligent fault diagnosis system to address the defects of the existing system, improve the diagnostic efficiency, accuracy, real-time, and intelligence level, and meet the needs of industry development. Summary of the invention

[0004] The present invention collects the working parameters of the wind turbine generator set based on the deployed multiple sensors, processes and analyzes the working parameters through the machine learning model, predicts whether a fault will occur in the future, and, under the premise of predicting a fault, determines the type of data that causes the fault, generates corresponding control instructions, and executes the preset operation corresponding to the control. The prediction results and control instruction information are then sent to the host computer, so that the staff can grasp the operating status and fault prediction information of the wind turbine in real time, monitor the execution of control instructions, and determine whether manual intervention is required.

[0005] The technical solution proposed by the present invention is: a wind turbine generator set fault diagnosis system, the method comprising:

[0006] A detection module, wherein the detection module is configured to obtain operating parameters of the wind turbine and internal environmental parameters of the wind turbine;

[0007] A comprehensive diagnosis module, wherein the comprehensive diagnosis module is configured to obtain data from the detection module, analyze and predict the data, and output the analysis results; specifically, by importing a pre-trained detection model for analysis and prediction, the influence of different operating parameters of the wind turbine on the probability of failure of the wind turbine generator set is determined;

[0008] An adaptive control module, wherein the adaptive control module is configured to output a wind turbine generator control instruction according to the analysis result of the comprehensive diagnosis module, so as to adjust the working parameters and working state of the wind turbine generator;

[0009] A communication module is configured to obtain the analysis results of the comprehensive diagnosis module and the control instruction information output by the adaptive control module, and send the analysis results and the control instruction information to a host computer.

[0010] Preferably, the detection module includes a plurality of current sensors, voltage sensors, rotation speed sensors and temperature and humidity sensors. The output current of the wind turbine is collected through the current sensor, the output voltage of the wind turbine generation angle is collected through the voltage sensor, the rotation speed of the wind turbine impeller is collected through the rotation speed sensor, and the temperature and humidity inside the wind turbine are collected through the temperature and humidity sensor.

[0011] Preferably, the comprehensive diagnosis module is configured to acquire data from the detection module, analyze and predict the data, and output the analysis results, including the following steps:

[0012] Collect data from current sensors, voltage sensors, speed sensors, and temperature and humidity sensors at a preset collection frequency and perform preprocessing;

[0013] Construct current data set, voltage data set, rotation speed data set and temperature and humidity data set respectively;

[0014] Input the data in the current data set, voltage data set, speed data set, and temperature and humidity data set into the detection model, and output the fault probability;

[0015] Analyze the failure probability and output the analysis results.

[0016] Preferably, the respectively constructing of the current data set, the voltage data set, the rotation speed data set and the temperature and humidity data set comprises the following steps:

[0017] Constructing the output current dataset ,in, , Represents the normalized time Output current when

[0018] Constructing the output voltage dataset ,in, , Indicates time Output voltage at

[0019] Constructing a rotation speed dataset ,in, , Indicates time The impeller speed at

[0020] Constructing temperature and humidity dataset ,in, , Indicates time The temperature and humidity vector at time , and Respectively represent the normalized moments Temperature and humidity data at that time.

[0021] Preferably, the step of inputting data in the current data set, the voltage data set, the rotation speed data set, and the temperature and humidity data set into the detection model and outputting the fault probability comprises the following steps:

[0022] Importing a pre-trained detection model ,in, and They represent intercept one and intercept two respectively. and represents regression coefficient one and regression coefficient two, and represent error term 1 and error term 2 respectively, and Represent weight one and weight two respectively, Indicates input variables, , and represent the first failure probability, the second failure probability and the failure probability value respectively;

[0023] Extract characteristic data from the current data set, the voltage data set, the speed data set, and the temperature and humidity data set to form a current characteristic input vector, a voltage characteristic input vector, a speed characteristic input vector, and a temperature and humidity characteristic input vector;

[0024] Input the data in the current characteristic input vector, voltage characteristic input vector, speed characteristic input vector and temperature and humidity characteristic input vector into the detection model, and output the first fault probability , the second failure probability and the failure probability value .

[0025] Preferably, extracting characteristic data from the current data set, the voltage data set, the speed data set and the temperature and humidity data set to form a current characteristic input vector, a voltage characteristic input vector, a speed characteristic input vector and a temperature and humidity characteristic input vector comprises the following steps:

[0026] From the output current data set Extract characteristic data to form current characteristic input vector ,in, Respectively represent the maximum current value and the average current value in the output current data set;

[0027] From the output voltage data set Extract characteristic data to form voltage characteristic input vector ,in, Respectively represent the maximum voltage value and the average voltage value in the output voltage data set;

[0028] From the rotation speed dataset Extract characteristic data to form a velocity characteristic input vector ,in, They represent the maximum speed and voltage speed in the rotation speed data set respectively;

[0029] From the temperature and humidity dataset Extract characteristic data to form temperature characteristic input vector ,in, Respectively represent the maximum temperature, average temperature, maximum humidity and average humidity in the temperature and humidity dataset.

[0030] Preferably, the data in the current characteristic input vector, the voltage characteristic input vector, the speed characteristic input vector and the temperature and humidity characteristic input vector are input into the detection model, and the first fault probability is output. , the second failure probability and the failure probability value , including the following steps:

[0031] from , , and ,extract and Composition of key data set 1:

[0032] ;

[0033] Enter the elements of key data set 1 as input variables into , output the first failure probability;

[0034] from , , and ,extract and Composition of key data set 2: ;

[0035] Enter the elements of key data set 2 as input variables into , output the second failure probability;

[0036] The first and second failure probabilities are input into , output failure probability.

[0037] Preferably, analyzing the failure probability and outputting the analysis result comprises the following steps:

[0038] Get the preset safety threshold ,if , , it is judged that the wind turbine will fail at a future moment, and the prediction result is sent to the host computer;

[0039] Get the preset first safety threshold ,if , , then it is determined that the occurrence of the wind turbine fault is related to the elements of the key data set 1, and the control instruction 1 is output;

[0040] Get the preset first safety threshold ,if , , then it is determined that the occurrence of wind turbine fault is related to the elements of key data set 2, and control instruction 2 is output.

[0041] Preferably, the adaptive control module is configured to output a wind turbine control instruction according to the analysis result of the comprehensive diagnosis module to adjust the working parameters and working state of the wind turbine, including the following steps:

[0042] Obtain control instruction 1, the adaptive control module parses instruction 1, and adjusts the speed and blade angle of the wind turbine generator;

[0043] Obtaining control instruction 2, the adaptive control module parses control instruction 2 and adjusts output power and speed of the wind turbine generator;

[0044] Control instruction 1 and control instruction 2 are sent to the host computer through the communication module for recording, which makes it easy for technical personnel to obtain the adjustment process and determine whether manual intervention is required.

[0045] Preferably, it also includes an energy storage monitoring module, which includes an energy storage battery power monitoring unit, and the energy storage battery power monitoring unit is used to monitor the power of the energy storage battery connected to the wind turbine generator set. The charging efficiency of the energy storage battery is monitored by the energy storage battery power monitoring unit to determine whether the wind turbine generator set is faulty.

[0046] The method of monitoring the charging efficiency of the energy storage battery by the energy storage battery power monitoring unit and determining whether the wind turbine generator set is faulty comprises the following steps:

[0047] Obtain the energy storage battery power data within a preset time period from the energy storage battery power monitoring unit to form the energy storage battery power time series ,in, express The energy storage battery power at all times;

[0048] Calculating charging efficiency ,in, Indicates the charging speed threshold, When the battery is charged, it is judged as a charging failure;

[0049] Get the preset safety threshold ,if , When , it is judged that the charging fault is related to the wind turbine fault;

[0050] An alarm signal is sent to the host computer through the communication module.

[0051] Beneficial effects of the present invention:

[0052] 1. In the present invention, the adaptive control module uses historical data and real-time data for analysis, providing a scientific basis for control decisions. The adaptive control module is combined with the analysis results of the comprehensive diagnosis module to determine the operating status of the wind turbine generator set. By analyzing key data set 1 and key data set 2, the system can provide a more accurate prediction of the probability of failure, which helps to discover potential problems in advance and take preventive measures. Through real-time monitoring and automatic adjustment, the system can promptly detect and handle abnormal situations, avoiding downtime losses caused by sudden failures.

[0053] 2. The present invention collects various parameters of the wind turbine generator set through multiple sensors, and uses the multiple parameters as input variables of the detection model. Through this multi-data fusion method, the prediction accuracy of the detection model is improved. The detection model consists of three expressions. The first expression is based on the maximum value data of the current, voltage, and wind turbine speed for prediction. The second expression is based on the average value data of the current, voltage, and wind turbine speed for prediction. The data type that causes the fault is distinguished to facilitate the analysis of the cause or fault point of the fault. Different instructions are used for different data types, which greatly improves the accuracy of fault diagnosis. The third expression is used to obtain the probability of generator failure. By assigning different weights to the maximum value data and the average value data, it is convenient to represent the impact of each group of data on the wind turbine generator set failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 The module diagram of a wind turbine generator set fault diagnosis system of the present invention is shown in FIG.

[0055] Figure 2 It is a flow chart of the fault diagnosis process of the present invention. DETAILED DESCRIPTION

[0056] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0057] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0058] refer to Figure 1-Figure 2 The technical solution provided by the present invention is: a wind turbine fault diagnosis system, comprising: a detection module, a comprehensive diagnosis module, an adaptive control module and a communication module connected to the comprehensive diagnosis module and the adaptive control module. The communication module is configured to obtain the analysis results of the comprehensive diagnosis module and the control instruction information output by the adaptive control module, and send the analysis results and the control instruction information to a host computer.

[0059] The detection module is configured to obtain the working parameters of the wind turbine and the internal environmental parameters of the wind turbine. Specifically, the detection module includes a plurality of current sensors, voltage sensors, rotation speed sensors and temperature and humidity sensors. The output current of the wind turbine is collected by the current sensor, the output voltage of the wind power generation angle is collected by the voltage sensor, the rotation speed of the wind turbine impeller is collected by the rotation speed sensor, and the temperature and humidity inside the wind turbine are collected by the temperature and humidity sensor.

[0060] The comprehensive diagnosis module is configured to obtain data from the detection module, analyze and predict the data, and output the analysis results; specifically, by importing a pre-trained detection model for analysis and prediction, the influence of different operating parameters of the wind turbine on the probability of failure of the wind turbine generator set is determined. Specifically, the following steps are included:

[0061] Collect data from current sensors, voltage sensors, rotation speed sensors, and temperature and humidity sensors at a preset collection frequency and perform preprocessing; construct current data sets, voltage data sets, rotation speed data sets, and temperature and humidity data sets respectively; input data in the current data sets, voltage data sets, rotation speed data sets, and temperature and humidity data sets into the detection model, and output the fault probability; analyze the fault probability, and output the analysis results. The process of constructing the data set is as follows:

[0062] Constructing the output current dataset ,in, , Represents the normalized time The output current at 10000 W / m; This data set is used to analyze the current changes of wind turbines under different working conditions and provide basic data support for fault diagnosis.

[0063] Constructing the output voltage dataset ,in, , Indicates time By recording and analyzing voltage data, abnormal voltage fluctuations or deviations can be identified, helping to detect potential electrical faults in advance.

[0064] Constructing a rotation speed dataset ,in, , Indicates time The dataset is used to monitor the speed changes of wind turbines, help identify wear or failure of mechanical components, and ensure the stability of equipment operation.

[0065] Constructing temperature and humidity dataset ,in, , Indicates time The temperature and humidity vector at time , and Respectively represent the normalized moments By analyzing the temperature and humidity data, the impact of environmental conditions on wind turbine operation can be evaluated and maintenance strategies can be optimized.

[0066] The process of predicting the failure probability is as follows:

[0067] Importing a pre-trained detection model ,in, and They represent intercept one and intercept two respectively. and represents regression coefficient one and regression coefficient two, and represent error term 1 and error term 2 respectively, and Represent weight one and weight two respectively, Indicates input variables, , and represent the first failure probability, the second failure probability and the failure probability value respectively;

[0068] Feature data are extracted from the current data set, voltage data set, speed data set, and temperature and humidity data set to form a current feature input vector, a voltage feature input vector, a speed feature input vector, and a temperature and humidity feature input vector; specifically:

[0069] From the output current data set Extract characteristic data to form current characteristic input vector ,in, Respectively represent the maximum current value and the average current value in the output current data set; from the output voltage data set Extract characteristic data to form voltage characteristic input vector ,in, Respectively represent the maximum voltage value and the average voltage value in the output voltage data set; from the rotation speed data set Extract characteristic data to form a velocity characteristic input vector ,in, They represent the maximum speed and voltage speed in the rotation speed dataset; from the temperature and humidity dataset Extract characteristic data to form temperature characteristic input vector ,in, Respectively represent the maximum temperature, average temperature, maximum humidity and average humidity in the temperature and humidity dataset.

[0070] Input the data in the current characteristic input vector, voltage characteristic input vector, speed characteristic input vector and temperature and humidity characteristic input vector into the detection model, and output the first fault probability , the second failure probability and the failure probability value . Specifically:

[0071] from , , and ,extract and Composition of key data set 1:

[0072] ;

[0073] Enter the elements of key data set 1 as input variables into , output the first failure probability;

[0074] from , , and ,extract and Composition of key data set 2: ;

[0075] Enter the elements of key data set 2 as input variables into , output the second failure probability;

[0076] The first and second failure probabilities are input into , output failure probability.

[0077] The adaptive control module is configured to output a wind turbine control instruction according to the analysis result of the comprehensive diagnosis module to adjust the working parameters and working state of the wind turbine. Specifically, the following steps are included:

[0078] Get the preset safety threshold ,if , , it is judged that the wind turbine will fail at a future moment, and the prediction result is sent to the host computer;

[0079] Get the preset first safety threshold ,if , , then it is determined that the occurrence of the wind turbine fault is related to the elements of the key data set 1, and the control instruction 1 is output;

[0080] Get the preset first safety threshold ,if , , then it is determined that the occurrence of wind turbine fault is related to the elements of key data set 2, and control instruction 2 is output.

[0081] The process of adaptive adjustment is as follows:

[0082] Obtain control instruction 1, the adaptive control module parses instruction 1, and adjusts the speed and blade angle of the wind turbine generator;

[0083] Obtaining control instruction 2, the adaptive control module parses control instruction 2 and adjusts output power and speed of the wind turbine generator;

[0084] Control instruction 1 and control instruction 2 are sent to the host computer through the communication module for recording, which makes it easy for technical personnel to obtain the adjustment process and determine whether manual intervention is required.

[0085] Specifically: The wind force is monitored by wind speed measuring equipment. If the wind speed variation range is small, the excitation current can be adjusted by the control system to stabilize the output voltage.

[0086] Since the output voltage of a wind turbine is usually related to reactive power, a reactive regulator can be applied. The reactive regulator can adjust the wind power generation system according to the changes in the grid load, so that reactive power can be reasonably injected or absorbed, thereby maintaining reactive stability. Alternatively, the double-fed technology is used to draw power from the grid through a frequency converter, which is then connected to the rotor of the generator after frequency conversion, and the speed of the generator is adjusted online to ensure constant output frequency; the direct drive technology is directly connected to the generator, and the inverter is used to control the rectification and inversion of the frequency converter to ensure constant output frequency, which to a certain extent solves the problem of voltage instability caused by uneven speed of wind turbines.

[0087] In addition, the working state of the wind turbine is regulated by the brake device of the wind turbine. When the wind speed is too high, in order to prevent the wind turbine from overspeeding, the brake device can reduce the speed of the wind rotor by increasing resistance. This helps to protect the generator and other key components from damage caused by overspeeding.

[0088] When the wind speed exceeds the rated value, the variable pitch wind turbine can change the angle of attack of the airflow on the blades by adjusting the pitch angle of the blades, thereby changing the aerodynamic torque obtained by the wind turbine, and then controlling the output power, which helps to maintain the stability of the output power.

[0089] When shutdown is required, the brake device can gradually stop the wind rotor to avoid sudden shutdown and impact on the wind turbine. In the case of level 3 fault or disconnection of the safety chain, the brake device can also achieve emergency shutdown to ensure the safety of the wind turbine.

[0090] By adjusting the angle of the blades, the brake device can help wind turbines maintain the optimal tip speed ratio at different wind speeds, thereby maximizing the capture of wind energy and improving power generation efficiency.

[0091] The brake device can reduce the dynamic and static loads on the blade root of the wind rotor by adjusting the blade angle, thus extending the service life of the wind turbine. In some small wind turbines, the brake device can also be used as a way to adjust the speed by deflecting the wind rotor to change the effective wind receiving area, thereby adjusting the speed of the wind rotor. The existence of the brake device enables the wind turbine to better adapt to different wind conditions, including adverse conditions such as strong winds and gusts.

[0092] In some preferred embodiments, the energy storage monitoring module includes an energy storage battery power monitoring unit, and the energy storage battery power monitoring unit is used to monitor the power of the energy storage battery connected to the wind turbine generator set. The charging efficiency of the energy storage battery is monitored by the energy storage battery power monitoring unit to determine whether the wind turbine generator set is faulty.

[0093] The method of monitoring the charging efficiency of the energy storage battery by the energy storage battery power monitoring unit and determining whether the wind turbine generator set is faulty comprises the following steps:

[0094] Obtain the energy storage battery power data within a preset time period from the energy storage battery power monitoring unit to form the energy storage battery power time series ,in, express The energy storage battery power at all times;

[0095] Calculating charging efficiency ,in, Indicates the charging speed threshold, When the battery is charged, it is judged as a charging failure;

[0096] Get the preset safety threshold ,if , When , it is judged that the charging fault is related to the wind turbine fault;

[0097] An alarm signal is sent to the host computer through the communication module.

[0098] When the maximum output voltage and current of the wind turbine are too high, they can be adjusted in the following ways: Use a dedicated voltage stabilizer or current stabilizer to adjust the output voltage and current. For example, the 78XX series integrated voltage stabilizer can be used to stabilize the DC voltage. For AC output, a bridge rectifier can be used to convert AC to DC, and then the voltage can be further stabilized through filter capacitors and voltage regulator diodes.

[0099] Adjust the impeller's windward angle to maintain stable blade torque and speed. In extreme cases, such as super typhoons, special methods such as locking the blades or disconnecting the engine can be used to avoid accidents. Energy storage batteries are used as buffers, regulators and energy storage devices to smooth voltage fluctuations and ensure stable power supply.

[0100] For situations that require more complex regulation, stable output over a wide input range can be achieved by adjusting the parameters of the DC-DC converter or high-frequency switching power supply.

[0101] The embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the above-mentioned computer-readable medium of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0102] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0103] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A wind turbine fault diagnosis system, characterized in that: include: A detection module, wherein the detection module is configured to obtain operating parameters of the wind turbine and internal environmental parameters of the wind turbine; A comprehensive diagnosis module, wherein the comprehensive diagnosis module is configured to obtain data from the detection module, analyze and predict the data, and output the analysis results; specifically, by importing a pre-trained detection model for analysis and prediction, the influence of different operating parameters of the wind turbine on the probability of failure of the wind turbine generator set is determined; An adaptive control module, wherein the adaptive control module is configured to output a wind turbine generator control instruction according to the analysis result of the comprehensive diagnosis module, so as to adjust the working parameters and working state of the wind turbine generator; A communication module, wherein the communication module is configured to obtain the analysis results of the comprehensive diagnosis module and the control instruction information output by the adaptive control module, and send the analysis results and the control instruction information to the host computer; The comprehensive diagnosis module is configured to acquire data from the detection module, analyze and predict the data, and output the analysis results, including the following steps: Collect data from current sensors, voltage sensors, speed sensors, and temperature and humidity sensors at a preset collection frequency and perform preprocessing; Construct current data set, voltage data set, rotation speed data set and temperature and humidity data set respectively; Input the data in the current data set, voltage data set, speed data set, and temperature and humidity data set into the detection model, and output the fault probability; The following steps are involved: Importing a pre-trained detection model ,in, and They represent intercept one and intercept two respectively. and represents regression coefficient one and regression coefficient two, and represent error term 1 and error term 2 respectively, and Represent weight one and weight two respectively, Indicates input variables, , and represent the first failure probability, the second failure probability and the failure probability value respectively; Extract characteristic data from the current data set, the voltage data set, the speed data set, and the temperature and humidity data set to form a current characteristic input vector, a voltage characteristic input vector, a speed characteristic input vector, and a temperature and humidity characteristic input vector; Input the data in the current characteristic input vector, voltage characteristic input vector, speed characteristic input vector and temperature and humidity characteristic input vector into the detection model, and output the first fault probability , the second failure probability and the failure probability value ; Analyze the failure probability and output the analysis results, including the following steps: Get the preset safety threshold ,if , , it is judged that the wind turbine will fail at a future moment, and the prediction result is sent to the host computer; Get the preset first safety threshold ,if , , then it is determined that the occurrence of the wind turbine fault is related to the elements of the key data set 1, and the control instruction 1 is output; Get the preset first safety threshold ,if , , then it is determined that the occurrence of wind turbine fault is related to the elements of key data set 2, and control instruction 2 is output.

2. A wind turbine generator fault diagnosis system according to claim 1, characterized in that: The detection module includes multiple current sensors, voltage sensors, speed sensors and temperature and humidity sensors. The output current of the wind turbine is collected through the current sensor, the output voltage of the wind power generation angle is collected through the voltage sensor, the rotation speed of the wind turbine impeller is collected through the speed sensor, and the temperature and humidity inside the wind turbine are collected through the temperature and humidity sensor.

3. A wind turbine generator fault diagnosis system according to claim 2, characterized in that: The method of respectively constructing a current data set, a voltage data set, a rotation speed data set, and a temperature and humidity data set comprises the following steps: Constructing the output current dataset ,in, , Represents the normalized time Output current when Constructing the output voltage dataset ,in, , Indicates time Output voltage at Constructing a rotation speed dataset ,in, , Indicates time The impeller speed at Constructing temperature and humidity dataset ,in, , Indicates time The temperature and humidity vector at time , and Respectively represent the normalized moments Temperature and humidity data at that time.

4. A wind turbine generator fault diagnosis system according to claim 3, characterized in that: The method of extracting characteristic data from the current data set, the voltage data set, the rotation speed data set and the temperature and humidity data set to form a current characteristic input vector, a voltage characteristic input vector, a rotation speed characteristic input vector and a temperature and humidity characteristic input vector comprises the following steps: From the output current data set Extract characteristic data to form current characteristic input vector ,in, Respectively represent the maximum current value and the average current value in the output current data set; From the output voltage data set Extract characteristic data to form voltage characteristic input vector ,in, Respectively represent the maximum voltage value and the average voltage value in the output voltage data set; From the rotation speed dataset Extract characteristic data to form a velocity characteristic input vector ,in, They represent the maximum speed and voltage speed in the rotation speed data set respectively; From the temperature and humidity dataset Extract characteristic data to form temperature characteristic input vector ,in, Respectively represent the maximum temperature, average temperature, maximum humidity and average humidity in the temperature and humidity dataset.

5. A wind turbine generator fault diagnosis system according to claim 4, characterized in that: The data in the current characteristic input vector, the voltage characteristic input vector, the speed characteristic input vector and the temperature and humidity characteristic input vector are input into the detection model, and the first fault probability is output. , the second failure probability and the failure probability value , including the following steps: from , , and ,extract and Composition of key data set 1: ； Enter the elements of key data set 1 as input variables into , output the first failure probability; from , , and ,extract and Composition of key data set 2: ; Enter the elements of key data set 2 as input variables into , output the second failure probability; The first and second failure probabilities are input into , output failure probability.

6. A wind turbine generator fault diagnosis system according to claim 5, characterized in that: The adaptive control module is configured to output a wind turbine generator control instruction according to the analysis result of the comprehensive diagnosis module to adjust the working parameters and working state of the wind turbine generator, including the following steps: Obtain control instruction 1, the adaptive control module parses instruction 1, and adjusts the speed and blade angle of the wind turbine generator; Obtaining control instruction 2, the adaptive control module parses control instruction 2 and adjusts output power and speed of the wind turbine generator; Control instruction 1 and control instruction 2 are sent to the host computer through the communication module for recording, which makes it easy for technical personnel to obtain the adjustment process and determine whether manual intervention is required.

7. A wind turbine generator fault diagnosis system according to claim 1, characterized in that: It also includes an energy storage monitoring module, which includes an energy storage battery power monitoring unit, and the energy storage battery power monitoring unit is used to monitor the power of the energy storage battery connected to the wind turbine generator set, and monitor the charging efficiency of the energy storage battery through the energy storage battery power monitoring unit to determine whether the wind turbine generator set is faulty; The method of monitoring the charging efficiency of the energy storage battery by the energy storage battery power monitoring unit and determining whether the wind turbine generator set is faulty comprises the following steps: Obtain the energy storage battery power data within a preset time period from the energy storage battery power monitoring unit to form the energy storage battery power time series ,in, express The energy storage battery power at all times; Calculating charging efficiency ,in, Indicates the charging speed threshold, When the battery is charged, it is judged as a charging failure; Get the preset safety threshold ,if , When , it is judged that the charging fault is related to the wind turbine fault; An alarm signal is sent to the host computer through the communication module.

Images