Wind driven generator main shaft fault detection system and method based on numerical simulation calculation and statistical analysis

Abstract

The invention relates to a wind driven generator spindle fault detection system and method based on numerical simulation calculation and statistical analysis, and belongs to the field of wind power. Comprising a torque measuring system, a wind speed measuring system, a data processing system, a data storage system and a display system, a fan torque fault database based on a statistical model is used for judging the operation condition of a main shaft of the wind driven generator under the condition that a detection part is not disassembled, and the judgment result is displayed and output in real time. The real-time monitoring of the working condition of the wind driven generator is realized, and the torque fault database can be continuously corrected through historical data. According to the method, the effect that the working state of the wind driven generator can be known under the condition that main parts of a transmission system are not disassembled is achieved, the link of halting for disassembling the parts for overhauling is omitted, manpower and material resources are saved, and working operation of a fan is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the field of wind power, and in particular relates to a wind turbine main shaft fault detection system and method based on numerical simulation calculation and statistical analysis. Background Art

[0002] Wind power generation is a renewable energy technology that converts wind energy into electrical energy. In a wind power generation system, the main shaft is an important component of the wind turbine, which is responsible for transferring the wind energy captured by the windmill blades to the generator to generate electricity. Therefore, the normal operation of the main shaft is crucial to the efficiency and reliability of the entire wind power generation system. However, due to long-term operation and harsh external environmental conditions, the main shaft may suffer from various faults such as wear, fatigue, corrosion, etc. If these faults are not detected and handled in time, they may cause the efficiency of the wind turbine to decrease or even be damaged, thereby affecting the power generation efficiency and safety of the entire wind farm. The present invention applies torque detection technology and statistical analysis methods to the main shaft fault detection system, aiming to establish an effective state monitoring and fault diagnosis mechanism, help the unit improve safety, stability and economy, and timely understand the operation of the wind turbine main shaft, so as to achieve the purpose of early prevention and timely troubleshooting. Summary of the invention

[0003] The purpose of the present invention is to solve the problem of detecting the working state of the main shaft of a wind turbine transmission system, and to provide a wind turbine main shaft fault detection system and method based on numerical simulation calculation and statistical analysis.

[0004] The present invention adds a main shaft fault detection system to the original wind turbine system, measures the torque value of the main shaft, uses numerical simulation technology and statistical analysis methods to establish a main shaft torque fault judgment database, and obtains the working status of the wind turbine main shaft through comparison and judgment.

[0005] To achieve the above-mentioned purpose, the technical solution of the present invention is: a wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis, comprising: a torque measurement system, a wind speed measurement system, a data processing system, a data storage system, and a display system; the torque measurement system is placed at the input main shaft and the output main shaft of the wind turbine gearbox; the wind speed measurement system is placed above the wind turbine cabin; the data processing system is connected to the torque measurement system, the wind speed measurement system, the data storage system, and the display system for signal transmission.

[0006] In one embodiment of the present invention, a torque measurement system detects the torque at the input main shaft and the output main shaft of the wind turbine gearbox; a wind speed measurement system detects the real-time wind speed and yaw error angle of the environment; a data processing system processes the data including torque, wind speed and yaw error angle measured by the torque measurement system and the wind speed measurement system, and makes a judgment on the current operating status of the wind turbine; a data storage system is responsible for storing data; and a display system displays information including torque, wind speed, wind direction and the operating status of the wind turbine in real time.

[0007] In one embodiment of the present invention, the data processing system processes the data including torque and wind speed measured by the torque measurement system and the wind speed measurement system, and makes a judgment on the current operating status of the wind turbine generator, that is, the data processing system compares the data including torque, wind speed and yaw error angle measured by the torque measurement system and the wind speed measurement system with the torque threshold value under the corresponding working condition in the torque fault judgment database, and obtains a judgment result; specifically including:

[0008] The process of establishing the spindle torque fault determination database;

[0009] The process of judging abnormal spindle torque.

[0010] In one embodiment of the present invention, the process of establishing a spindle torque fault determination database specifically includes:

[0011] The main shaft torque of the wind turbine generator under different wind speeds and different yaw error angles is numerically simulated and calculated to obtain the theoretical prediction value of the main shaft torque of the wind turbine generator under different wind speeds and different yaw error angles;

[0012] Collect the actual values ​​of the main shaft torque of the wind turbine under different working conditions, and obtain multiple groups of actual values ​​of the main shaft torque of the wind turbine under different wind speeds and different yaw error angles;

[0013] Calculate the deviation between the actual value of the wind turbine main shaft torque and the theoretical predicted value, and record it in the wind turbine operation history database;

[0014] Statistical processing is performed on the deviation data between the actual value and the theoretical value of the wind turbine main shaft torque value under each working condition, a statistical model fitting is established for the deviation between the wind turbine main shaft torque value and the theoretical value under different working conditions, and parameter inversion and parameter testing are performed on the model;

[0015] The statistical model is used to determine the deviation threshold between the actual value and the theoretical value of the wind turbine main shaft torque under different working conditions.

[0016] In one embodiment of the present invention, the spindle torque abnormality judgment process specifically includes:

[0017] Obtain the current wind turbine main shaft torque information, ambient wind speed and wind turbine yaw error angle;

[0018] Obtaining the theoretical value of the main shaft torque of the wind turbine generator under the current wind speed and yaw error angle from the database, and calculating the deviation between the actual value and the theoretical value of the main shaft torque of the wind turbine generator under the current situation;

[0019] The calculated deviation value is compared with the deviation threshold in the database. If it exceeds the deviation threshold, it is considered abnormal, otherwise it is considered normal.

[0020] The judgment results are output to the display system.

[0021] In one embodiment of the present invention, the process of establishing the spindle torque fault determination database is iteratively corrected according to the operation history data, and the correction process includes the following steps:

[0022] The wind turbine main shaft fault detection system records the difference between the actual value and the theoretical value of the main shaft torque detected under different working conditions in the wind turbine operation history database;

[0023] The torque difference data judged as normal is selected, and the statistical model of the deviation value between the wind turbine main shaft torque value and the theoretical value under the corresponding working condition is corrected to redefine the torque deviation threshold.

[0024] The present invention also provides a method for detecting a main shaft fault of a wind turbine generator based on numerical simulation calculation and statistical analysis, comprising:

[0025] The spindle torque fault judgment database was established;

[0026] Abnormal spindle torque judgment.

[0027] In one embodiment of the present invention, establishing a spindle torque fault determination database includes the following steps:

[0028] S11) performing numerical simulation calculation on the main shaft torque of the wind turbine generator at different wind speeds and different yaw error angles to obtain theoretical prediction values ​​of the main shaft torque of the wind turbine generator at different wind speeds and different yaw error angles;

[0029] S12) collecting actual values ​​of the main shaft torque of the wind turbine under different working conditions, and obtaining multiple groups of actual values ​​of the main shaft torque of the wind turbine under different wind speeds and different yaw error angles;

[0030] S13) calculating the deviation between the actual value of the wind turbine main shaft torque and the theoretical predicted value, and recording it in the wind turbine operation history database;

[0031] S14) statistically processing the deviation data between the actual value and the theoretical value of the wind turbine main shaft torque value under each working condition, establishing a statistical model fitting for the deviation between the wind turbine main shaft torque value and the theoretical value under different working conditions, and performing parameter inversion and parameter testing on the model;

[0032] S15) Using a statistical model to determine a deviation threshold between an actual value and a theoretical value of the wind turbine main shaft torque under different working conditions.

[0033] In one embodiment of the present invention, the spindle torque abnormality determination includes the following steps:

[0034] S21) obtaining the current wind turbine main shaft torque information, ambient wind speed and wind turbine yaw error angle;

[0035] S22) obtaining a theoretical value of the main shaft torque of the wind turbine generator under the current wind speed and yaw error angle from a database, and calculating a deviation between an actual value and a theoretical value of the main shaft torque of the wind turbine generator under the current situation;

[0036] S23) comparing the calculated deviation value with the deviation threshold in the database, if it exceeds the deviation threshold range, it is determined to be abnormal, otherwise it is determined to be normal;

[0037] S24) Output the judgment result to the display system.

[0038] In the spindle torque abnormality judgment, if there is no torque fault judgment data corresponding to the current working condition in the database, two adjacent groups of data are selected and the judgment data are obtained by using the interpolation method.

[0039] In one embodiment of the present invention, the spindle torque fault determination database is iteratively corrected according to the operation history data, and the correction process includes the following steps:

[0040] S31) recording the difference between the actual value and the theoretical value of the main shaft torque detected under different working conditions in a wind turbine operation history database;

[0041] S32) selecting torque difference data determined to be normal, correcting the statistical model of the deviation between the wind turbine main shaft torque value and the theoretical value under the corresponding working condition, and re-determining the torque deviation threshold.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. Compared with the existing wind turbine system, the method of the present invention can know the working status of the main shaft transmission system of the wind turbine without disassembling the main components of the wind turbine, eliminating the need to shut down and disassemble components for maintenance, saving manpower and material resources.

[0044] 2. The present invention proposes a real-time measurement method for indirectly monitoring the working status of the transmission system. This method can obtain the working status of the transmission system without stopping the system or disassembling parts, and responds in real time through the display system, which is convenient for maintenance personnel to grasp the current working status of the system in time, greatly improving the detection efficiency; the normal operation of the equipment is not interfered with during the detection process, and shutdown is avoided, thereby ensuring the working operation of the fan. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a flow chart of a wind turbine main shaft fault detection system and method based on numerical simulation calculation and statistical analysis provided by the present invention;

[0046] Figure 2 It is a schematic diagram of the structure of a horizontal wind turbine;

[0047] Figure 3 This is a schematic diagram of the installation of a laser radar anemometer;

[0048] Figure 4 This is a schematic diagram of the installation of a flexible torque sensor;

[0049] Figure 5 It is a database diagram. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] The present invention provides a wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis, comprising: a torque measurement system, a wind speed measurement system, a data processing system, a data storage system, and a display system; the torque measurement system is placed at the input main shaft and the output main shaft of the wind turbine gearbox; the wind speed measurement system is placed above the wind turbine cabin; the data processing system is connected with the torque measurement system, the wind speed measurement system, the data storage system, and the display system for signal transmission.

[0052] The present invention also provides a method for detecting a main shaft fault of a wind turbine generator based on numerical simulation calculation and statistical analysis, comprising:

[0053] The spindle torque fault judgment database was established;

[0054] Abnormal spindle torque judgment.

[0055] The following is the specific implementation process of the present invention.

[0056] See also Figure 1 , a wind turbine main shaft fault detection system and detection method based on numerical simulation calculation and statistical analysis, the specific steps are as follows:

[0057] like Figure 2 , Figure 3 As shown in FIG. 1 , a flexible torque sensor is installed on the impeller shaft of a wind turbine; Figure 4 As shown, a horizontal laser radar is installed on the top of the nacelle of the wind turbine; a torque measurement system with a flexible torque sensor as the core, a wind speed measurement system with a horizontal laser radar as the core, and a display system are connected to a control system with an industrial computer as the core.

[0058] Based on the piezoresistive effect, the flexible torque sensor converts physical deformation into electrical signal output and outputs the measured spindle torque data; by emitting laser into the atmosphere and receiving the reflected signal to measure wind speed and wind direction, the horizontal laser radar can output high-precision wind speed and yaw error angle data; the acquired data is transmitted to the industrial computer through network sharing, and the industrial computer processes the relevant torque, wind speed, yaw error angle and other information measured by the torque measurement system and wind speed measurement system, and compares the data with the torque threshold under the corresponding working condition in the torque fault judgment database to obtain the judgment result, and transmits the current torque, wind speed, spindle working status and other information to the display system for output. Then the wind turbine maintenance personnel can directly get to know the wind turbine operating status.

[0059] The torque fault determination method determines the torque fault as follows:

[0060] S1) The transmission line transmits the real-time spindle torque data obtained by the flexible torque sensor and the real-time wind speed and yaw error angle data obtained by the horizontal laser radar to the industrial computer through network sharing.

[0061] S2) The industrial computer obtains the theoretical value of the main shaft torque of the wind turbine generator under the current wind speed and yaw error angle from the database, and calculates the deviation between the actual value and the theoretical value of the main shaft torque of the wind turbine generator under the current situation.

[0062] S3) Compare the calculated deviation value with the deviation value threshold in the database, and if it exceeds the threshold range, it is determined to be abnormal, otherwise it is determined to be normal.

[0063] In the torque fault determination method, if there is no torque fault determination data corresponding to the current working condition in the database, two adjacent groups of data are selected and the determination data is obtained by using the interpolation method.

[0064] Establish a torque fault determination database required to implement the torque fault determination method, such as Figure 5 As shown, the following steps are included:

[0065] S1) According to the material properties and design parameters of the horizontal axis wind turbine, the corresponding aerodynamic and structural dynamic models are established, and numerical simulation calculations are performed in combination with the finite element method (FEM) and computational fluid dynamics (CFD) to obtain the theoretical values ​​of the main shaft torque of the wind turbine at different wind speeds and different yaw error angles.

[0066] S2) The collected real-time torque data of the main shaft, real-time wind speed and real-time yaw error angle of the wind turbine are transmitted to the industrial computer through the transmission line. The industrial computer integrates and processes the information to obtain the deviation values ​​between the actual and theoretical values ​​of multiple groups of wind turbine main shafts under different working conditions, and creates a wind turbine operation history database.

[0067] S3) Statistically process the deviation data between the actual value and the theoretical value of the wind turbine main shaft torque value under each working condition, establish a normal distribution model for the deviation between the wind turbine main shaft torque value and the theoretical value under different working conditions, and perform parameter inversion and parameter test on the model.

[0068] S4) using a normal distribution model to determine the deviation threshold between the actual value and the theoretical value of the wind turbine main shaft torque under different working conditions.

[0069] The deviation threshold between the actual value and the theoretical value of the spindle torque in the torque fault judgment database is determined by the following method: From the 2σ principle in the normal distribution, it can be seen that the probability that a data point falls between (μ-2σ, μ+2σ) is close to 95.4%. Therefore, the μ-2σ and μ+2σ values ​​of the corresponding indicators are used as the judgment thresholds of the database (where μ and σ are the mean and standard deviation of the normal distribution model).

[0070] The torque fault judgment database is updated regularly based on historical data to improve the accuracy of fault prediction. The update method is as follows:

[0071] S1) During operation, the wind turbine main shaft fault detection system records the difference between the actual value and the theoretical value of the main shaft torque detected under different working conditions in the wind turbine operation history database.

[0072] S2) selecting the torque difference data judged to be normal, modifying the normal distribution model of the deviation between the wind turbine main shaft torque value and the theoretical value under the working condition, obtaining a new mean and variance, and re-determining the torque deviation threshold.

[0073] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0074] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0076] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0077] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

Claims

1. A wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis, characterized in that: include: Torque measurement system, wind speed measurement system, data processing system, data storage system, display system; The torque measurement system is placed at the input main shaft and the output main shaft of the wind turbine gearbox; the wind speed measurement system is placed above the wind turbine cabin; the data processing system is connected to the torque measurement system, the wind speed measurement system, the data storage system, and the display system for signal transmission.

2. The wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis according to claim 1 is characterized in that: The torque measurement system detects the torque at the input and output shafts of the wind turbine gearbox; the wind speed measurement system detects the real-time wind speed and yaw error angle of the environment; the data processing system processes the data including torque, wind speed and yaw error angle measured by the torque measurement system and the wind speed measurement system, and makes a judgment on the current operating status of the wind turbine; the data storage system is responsible for storing data; the display system displays information including torque, wind speed, wind direction and the operating status of the wind turbine in real time.

3. The wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis according to claim 2 is characterized in that: The data processing system processes the torque and wind speed data measured by the torque measurement system and the wind speed measurement system, and makes judgments on the current operating status of the wind turbine, including: The process of establishing the spindle torque fault determination database; The process of judging abnormal spindle torque.

4. The wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis according to claim 3 is characterized in that: The process of establishing the spindle torque fault judgment database specifically includes: The main shaft torque of the wind turbine generator under different wind speeds and different yaw error angles is numerically simulated and calculated to obtain the theoretical prediction value of the main shaft torque of the wind turbine generator under different wind speeds and different yaw error angles; Collect the actual values ​​of the main shaft torque of the wind turbine under different working conditions, and obtain multiple groups of actual values ​​of the main shaft torque of the wind turbine under different wind speeds and different yaw error angles; Calculate the deviation between the actual value of the wind turbine main shaft torque and the theoretical predicted value, and record it in the wind turbine operation history database; Statistical processing is performed on the deviation data between the actual value and the theoretical value of the wind turbine main shaft torque value under each working condition, a statistical model fitting is established for the deviation between the wind turbine main shaft torque value and the theoretical value under different working conditions, and parameter inversion and parameter testing are performed on the model; The statistical model is used to determine the deviation threshold between the actual value and the theoretical value of the wind turbine main shaft torque under different working conditions.

5. The wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis according to claim 3 is characterized in that: The spindle torque abnormality judgment process specifically includes: Obtain the current wind turbine main shaft torque information, ambient wind speed and wind turbine yaw error angle; Obtaining the theoretical value of the main shaft torque of the wind turbine generator under the current wind speed and yaw error angle from the database, and calculating the deviation between the actual value and the theoretical value of the main shaft torque of the wind turbine generator under the current situation; The calculated deviation value is compared with the deviation threshold in the database. If it exceeds the deviation threshold, it is considered abnormal, otherwise it is considered normal. The judgment results are output to the display system.

6. The wind turbine main shaft fault detection system based on numerical simulation calculation and statistical analysis according to claim 4 is characterized in that: The process of establishing the spindle torque fault judgment database will be iteratively corrected according to the historical operation data. The correction process includes the following steps: The wind turbine main shaft fault detection system records the difference between the actual value and the theoretical value of the main shaft torque detected under different working conditions in the wind turbine operation history database; The torque difference data judged as normal is selected, and the statistical model of the deviation value between the wind turbine main shaft torque value and the theoretical value under the corresponding working condition is corrected to redefine the torque deviation threshold.

7. A method for detecting main shaft faults of wind turbines based on numerical simulation calculation and statistical analysis, characterized in that: include: The spindle torque fault judgment database was established; Abnormal spindle torque judgment.

8. The method for detecting main shaft fault of a wind turbine generator based on numerical simulation calculation and statistical analysis according to claim 7, characterized in that: The establishment of the spindle torque fault judgment database includes the following steps: S11) performing numerical simulation calculation on the main shaft torque of the wind turbine generator at different wind speeds and different yaw error angles to obtain theoretical prediction values ​​of the main shaft torque of the wind turbine generator at different wind speeds and different yaw error angles; S12) collecting actual values ​​of the main shaft torque of the wind turbine under different working conditions, and obtaining multiple groups of actual values ​​of the main shaft torque of the wind turbine under different wind speeds and different yaw error angles; S13) calculating the deviation between the actual value of the wind turbine main shaft torque and the theoretical predicted value, and recording it in the wind turbine operation history database; S14) statistically processing the deviation data between the actual value and the theoretical value of the wind turbine main shaft torque value under each working condition, establishing a statistical model fitting for the deviation between the wind turbine main shaft torque value and the theoretical value under different working conditions, and performing parameter inversion and parameter testing on the model; S15) Using a statistical model to determine a deviation threshold between an actual value and a theoretical value of the wind turbine main shaft torque under different working conditions.

9. The method for detecting main shaft fault of a wind turbine generator based on numerical simulation calculation and statistical analysis according to claim 7, characterized in that: The spindle torque abnormality judgment includes the following steps: S21) obtaining the current wind turbine main shaft torque information, ambient wind speed and wind turbine yaw error angle; S22) obtaining a theoretical value of the main shaft torque of the wind turbine generator under the current wind speed and yaw error angle from a database, and calculating a deviation between an actual value and a theoretical value of the main shaft torque of the wind turbine generator under the current situation; S23) comparing the calculated deviation value with the deviation threshold in the database, if it exceeds the deviation threshold range, it is determined to be abnormal, otherwise it is determined to be normal; S24) Output the judgment result to the display system.

10. The wind turbine main shaft fault detection method based on numerical simulation calculation and statistical analysis according to claim 8, characterized in that: The spindle torque fault judgment database will be iteratively corrected based on the operation history data. The correction process includes the following steps: S31) recording the difference between the actual value and the theoretical value of the main shaft torque detected under different working conditions in a wind turbine operation history database; S32) selecting torque difference data determined to be normal, correcting the statistical model of the deviation between the wind turbine main shaft torque value and the theoretical value under the corresponding working condition, and re-determining the torque deviation threshold.

Images