Wind power generation variable pitch bearing load monitoring method and system

Abstract

The application discloses a wind power generation variable-pitch bearing load monitoring method and system, comprising the following steps: S1. taking the static load applied to the variable-pitch bearing and the strain information of the variable-pitch bearing outer ring bolt as sample data; taking the sample data as training data, training a variable-pitch bearing load and bolt strain mapping relationship model, and obtaining a trained variable-pitch bearing load and bolt strain mapping relationship model; S2. collecting real-time strain information of the variable-pitch bearing outer ring bolt; and S3. inputting the real-time strain information into the trained variable-pitch bearing load and bolt strain mapping relationship model, and calculating load information of the variable-pitch bearing. The application can effectively monitor the load state of the variable-pitch bearing, and provides technical support for accurately judging whether the variable-pitch bearing is in a normal running state.

Description

Technical Field

[0001] This invention relates to the field of wind turbine pitch bearings, and more specifically to a method and system for monitoring the load of wind turbine pitch bearings. Background Technology

[0002] Due to crises in energy, finance, and climate, the global new energy industry is developing rapidly, with wind power generation being particularly prominent. Pitch bearings are a crucial core component of wind turbine generators. By driving the pitch motor, the pitch bearings rotate, changing the blade's angle of attack to maintain optimal windward alignment, thereby controlling the blade's lift and ultimately controlling its torque and power.

[0003] Pitch bearings have the highest failure rate among wind turbine generator set faults, and troubleshooting them during operation is very costly. Therefore, there is an urgent need to monitor the load status of wind turbine pitch bearings. Currently, there is a lack of effective load monitoring technology for wind turbine pitch bearings, making it impossible to accurately assess their operating status. Therefore, a method and system for monitoring the load of wind turbine pitch bearings is needed to solve the above problems. Summary of the Invention

[0004] In view of this, the purpose of this invention is to overcome the defects in the prior art and provide a method and system for monitoring the load of pitch bearings in wind power generation, which can effectively monitor the load status of pitch bearings and provide technical support for accurately determining whether the pitch bearings are in normal operating condition.

[0005] The wind power generation pitch bearing load monitoring method of the present invention includes the following steps:

[0006] S1. The static load applied to the pitch bearing and the strain information of the outer ring bolt of the pitch bearing are used as sample data; the sample data are used as training data to train the pitch bearing load and bolt strain mapping relationship model to obtain the trained pitch bearing load and bolt strain mapping relationship model.

[0007] S2. Collect real-time strain information of the outer ring bolts of the pitch bearing;

[0008] S3. Input the real-time strain information into the trained pitch bearing load and bolt strain mapping model to calculate the load information of the pitch bearing.

[0009] Furthermore, step S1 specifically includes:

[0010] S11. Apply a static load to the pitch bearing;

[0011] S12. Collect strain information of the outer ring bolts of the pitch bearing;

[0012] S13. Based on the static load and strain information, construct a model of the mapping relationship between the pitch bearing load and the bolt strain;

[0013] S14. Solve for the calibration coefficient matrix in the model of the mapping relationship between pitch bearing load and bolt strain;

[0014] S15. The value obtained by adding the static load in step S11 to the set value is taken as the updated static load, and the process returns to execute steps S11-S14.

[0015] S16. Repeat step S15 several times until the number of calibration coefficient matrices obtained reaches k. Calculate the average value of the k calibration coefficient matrices to obtain the averaged calibration coefficient matrix.

[0016] S17. The averaged calibration coefficient matrix is ​​used as the optimal calibration coefficient matrix for the pitch bearing load and bolt strain mapping relationship model, thus obtaining the trained pitch bearing load and bolt strain mapping relationship model.

[0017] Furthermore, the mapping relationship model between pitch bearing load and bolt strain is determined according to the following formula:

[0018]

[0019] Among them, F x F is the axial force in the x-direction. y F is the axial force in the y direction. z M is the axial force in the z-direction. x M is the bending moment in the x-direction. y Let D be the bending moment in the y-direction. mn The calibration coefficient matrix is ​​defined by S1, S2, S3, S4, and S5, which are the collected bolt strain information. A three-dimensional rectangular coordinate system O-xyz is established with the center of the pitch bearing as the origin O. The x-direction is any direction in the plane where the pitch bearing is located, the z-direction is the rotation direction of the pitch bearing, and the y-direction is the direction perpendicular to the xz plane.

[0020] Furthermore, the static load includes axial force, radial force, and overturning moment.

[0021] Furthermore, the load information includes the axial force F in the x-direction. x Axial force F in the y direction y Axial force F in the z direction z Bending moment M in the x direction x and the bending moment M in the y direction y .

[0022] A wind turbine pitch bearing load monitoring system includes a data acquisition unit and a remote monitoring unit;

[0023] The acquisition unit is used to acquire strain information of the outer ring bolts of the pitch bearing;

[0024] The remote monitoring unit is used to analyze and process the strain information of the outer ring bolts of the pitch bearing and calculate the load information of the pitch bearing.

[0025] Furthermore, the acquisition unit includes a strain gauge embedded in the bolt and a data acquisition terminal disposed on the bolt;

[0026] The strain gauge is communicatively connected to the data acquisition terminal; the bolt is the outer ring bolt of the pitch bearing.

[0027] Furthermore, the data acquisition terminal includes a housing, a data acquisition board disposed inside the housing, and a magnet fixedly disposed at the bottom of the housing;

[0028] The data acquisition terminal is attached to the bolt by the magnet.

[0029] Furthermore, the embedment depth of the strain gauge embedded in the bolt is determined according to the following method:

[0030] An axial force is applied to the pitch bearing, and the stress state of the outer ring bolt of the pitch bearing is analyzed by finite element method to obtain the depth at which the maximum stress of the outer ring bolt of the pitch bearing is located. The depth at which the maximum stress is located is taken as the embedment depth.

[0031] Furthermore, it also includes a display unit; the display unit is used to display the load information of the pitch bearing.

[0032] The beneficial effects of this invention are as follows: The wind turbine pitch bearing load monitoring method and system disclosed in this invention embeds multiple sets of strain sensors inside the outer ring bolts of the wind turbine pitch bearing, synchronously collects data on the outer ring bolts of the wind turbine pitch bearing, obtains the mapping relationship between bearing load and bolt strain through static load calibration, that is, calculates the calibration coefficient matrix, and finally solves and displays the load distribution of the bearing by synchronously collecting the strain data of multiple sets of bolts and the calculated calibration coefficient matrix. Attached Figure Description

[0033] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0034] Figure 1 This is a schematic diagram of the monitoring system structure of the present invention;

[0035] Figure 2 This is a schematic diagram of the data acquisition terminal structure of the present invention;

[0036] Figure 3 This is a schematic diagram of the data acquisition terminal layout structure of the present invention;

[0037] Figure 4 This is a schematic diagram of the load distribution direction of the pitch bearing of the present invention;

[0038] Figure 5 This is a schematic diagram illustrating the monitoring principle of the present invention;

[0039] Among them, 1-Pitch bearing outer ring bolt, 2-Data acquisition terminal, 3-Resistance strain gauge, 4-Remote monitoring unit, 5-Pitch bearing outer ring, 6-Data acquisition terminal No. 1, 7-Data acquisition terminal No. 2, 8-Data acquisition terminal No. 3, 9-Data acquisition terminal No. 4, 10-Data acquisition terminal No. 5, 2-1-Power supply unit, 2-2-Data acquisition board, 2-3-Housing, 2-4-Strong magnet, 2-5-Insulating sealant. Detailed Implementation

[0040] The present invention will be further described below with reference to the accompanying drawings, as shown in the figures:

[0041] The wind power generation pitch bearing load monitoring method of the present invention includes the following steps:

[0042] S1. The static load applied to the pitch bearing and the strain information of the outer ring bolt of the pitch bearing are used as sample data; the sample data are used as training data to train the pitch bearing load and bolt strain mapping relationship model to obtain the trained pitch bearing load and bolt strain mapping relationship model.

[0043] S2. Collect real-time strain information of the outer ring bolts of the pitch bearing; multiple sets (e.g., 5 sets) of real-time strain information can be collected.

[0044] S3. Input the real-time strain information into the trained pitch bearing load-bolt strain mapping model to calculate the load information of the pitch bearing. The load information includes the axial force F in the x-direction. x Axial force F in the y direction y Axial force F in the z direction z Bending moment M in the x direction x and the bending moment M in the y direction y .

[0045] In this embodiment, step S1 specifically includes:

[0046] S11. Apply a static load to the pitch bearing; wherein, the static load is applied to the wind turbine pitch bearing by a hydraulic press, and the static load includes axial force, radial force, and overturning moment; initially, the load magnitude can be F. X =100KN, F y =100KN, F z =100KN, M x =1000 kN·m, My =1000 kN·m;

[0047] S12. Collect strain information of the outer ring bolts of the pitch bearing;

[0048] S13. Based on the static load and strain information, construct a model for the mapping relationship between the pitch bearing load and the bolt strain; wherein, the model for the mapping relationship between the pitch bearing load and the bolt strain is determined according to the following formula:

[0049]

[0050] Among them, such as Figure 4 As shown, F x F is the axial force in the x-direction. y F is the axial force in the y direction. z M is the axial force in the z-direction. x M is the bending moment in the x-direction. y Let D be the bending moment in the y-direction. mn The calibration coefficient matrix is ​​defined by S1, S2, S3, S4, and S5, which are the collected bolt strain information. A three-dimensional rectangular coordinate system O-xyz is established with the center of the pitch bearing as the origin O. The x-direction is any direction in the plane where the pitch bearing is located, the z-direction is the rotation direction of the pitch bearing, and the y-direction is the direction perpendicular to the xz plane.

[0051] In this embodiment, D mn It is a 5x5 matrix; by setting 5 strain gauges to collect bolt strain information, the data values ​​of S1, S2, S3, S4, and S5 are obtained.

[0052] S14. Solve for the calibration coefficient matrix in the model of the mapping relationship between pitch bearing load and bolt strain; wherein, the calibration coefficient matrix is ​​solved by the static load calibration method, that is, by using the known pitch bearing load and bolt strain information, a set of equations is formed, and a set of calibration coefficients in the set of equations is obtained, thereby obtaining a calibration coefficient matrix composed of a set of calibration coefficients.

[0053] S15. The value obtained by adding the static load in step S11 to the set value is taken as the updated static load, and the process returns to steps S11-S14; wherein, the set value can be determined according to the actual working conditions, for example, for the axial force F x F y F z The set value is 100 kN, for bending moment M x M y The set value is 1000 kN·m;

[0054] S16. Repeat step S15 several times until the number of calibration coefficient matrices obtained reaches k. Calculate the average value of the k calibration coefficient matrices to obtain the averaged calibration coefficient matrix. In step S15, the static load after each update is increased by a set value based on the previous update. The value of k is 10. By averaging the 10 calibration coefficient matrices, the averaged calibration coefficient matrix can be obtained.

[0055] S17. The averaged calibration coefficient matrix is ​​used as the optimal calibration coefficient matrix for the pitch bearing load-bolt strain mapping model, thus obtaining the trained pitch bearing load-bolt strain mapping model. In other words, through the above steps, the optimal calibration coefficient matrix is ​​determined, and the calibration coefficient matrix D in the pitch bearing load-bolt strain mapping model is obtained. mn Through optimization, an optimized model of the mapping relationship between pitch bearing load and bolt strain is obtained.

[0056] The present invention also relates to a wind power generation pitch bearing load monitoring system, which corresponds to the above-mentioned wind power generation pitch bearing load monitoring method and can be understood as a system for implementing the above-mentioned method. The system includes a data acquisition unit and a remote monitoring unit 4.

[0057] The acquisition unit is used to acquire strain information of the outer ring bolt 1 of the pitch bearing;

[0058] The remote monitoring unit 4 is used to analyze and process the strain information of the outer ring bolt 1 of the pitch bearing and calculate the load information of the pitch bearing.

[0059] In this embodiment, as Figure 1 As shown, the acquisition unit includes a strain gauge embedded in the bolt and a data acquisition terminal 2 installed on the bolt; wherein, the strain gauge is an existing resistance strain gauge 3; the strain gauge and the data acquisition terminal 2 are in one-to-one correspondence.

[0060] The strain gauge is communicatively connected to the data acquisition terminal 2; the bolt is the outer ring bolt 1 of the pitch bearing. To transmit the data acquired by the acquisition unit, the acquisition unit is communicatively connected to the remote monitoring unit 4 via wireless communication.

[0061] In this embodiment, as Figure 2As shown, the data acquisition terminal 2 includes a housing 2-3, a data acquisition board 2-2 disposed within the housing 2-3, and a magnet fixedly disposed at the bottom of the housing 2-3. The wires leading from the resistance strain gauge 3 are connected to the relevant Wheatstone bridge circuit section on the data acquisition board 2-2 by welding. The data acquisition board 2-2 uses existing acquisition equipment, which will not be described in detail here. Of course, to maintain the normal operation of the data acquisition board 2-2, a power supply unit 2-1 is provided to supply power to the data acquisition board 2-2. The power supply unit 2-1 uses existing power supply equipment, which will not be described in detail here.

[0062] The data acquisition terminal 2 is attached to the bolt by the magnet. The magnet is a powerful magnet 2-4, which is bonded to the housing 2-3 with insulating sealant 2-5. The entire data acquisition terminal 2 is attached to the bolt by the bottommost annular powerful magnet 2-4. The entire housing of the data acquisition terminal 2 is mounted on the bolt on the outer ring of the bearing using the powerful magnet 2-4. There are five groups: data acquisition terminal 6 (number 1), data acquisition terminal 7 (number 2), data acquisition terminal 8 (number 3), data acquisition terminal 9 (number 4), and data acquisition terminal 10, evenly distributed on the outer ring of the bearing. Figure 3 As shown.

[0063] In this embodiment, the embedment depth of the strain gauge embedded in the bolt is determined according to the following method:

[0064] An axial force was applied to the pitch bearing, and the stress state of the outer ring bolt 1 of the pitch bearing was analyzed using finite element method (FEM) to obtain the depth at which the maximum stress of the outer ring bolt 1 of the pitch bearing was located. This depth was then used as the embedment depth. Specifically, using finite element method (FEM) technology, a simulation model was established using ANSYS. An axial force of 1000 kN and a radial force of 1000 kN were applied to the pitch bearing. The maximum stress of the bolt was found to be between 35 and 40 mm of the bolt depth. Therefore, this depth was set as the embedment depth of the strain gauge.

[0065] In this embodiment, the monitoring system further includes a display unit; the display unit is used to display the load information of the pitch bearing. The remote monitoring unit 4 is communicatively connected to the display unit; the display unit includes a monitor, and the remote monitoring unit 4 is externally connected to the monitor to display the bearing load distribution information after data analysis: F x F y F z M x M y Display in real time.

[0066] The monitoring system of this invention has a simple structure, is easy to install, operate, debug, maintain, has a long service life, is safe and reliable, and has high real-time and accuracy in load monitoring. It realizes remote real-time monitoring of the load status of pitch bearings and provides technical support for determining whether the bearing is in normal operating condition.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for monitoring the load of a wind turbine pitch bearing, characterized in that: Includes the following steps: S1. The static load applied to the pitch bearing and the strain information of the outer ring bolt of the pitch bearing are used as sample data; the sample data are used as training data to train the pitch bearing load and bolt strain mapping relationship model to obtain the trained pitch bearing load and bolt strain mapping relationship model. Step S1 specifically includes: S11. Apply a static load to the pitch bearing; S12. Collect strain information of the outer ring bolts of the pitch bearing; S13. Based on the static load and strain information, construct a model of the mapping relationship between the pitch bearing load and the bolt strain; S14. Solve for the calibration coefficient matrix in the model of the mapping relationship between pitch bearing load and bolt strain; S15. The value obtained by adding the static load in step S11 to the set value is taken as the updated static load, and the process returns to execute steps S11-S14. S16. Repeat step S15 several times until the solved calibration coefficient matrix reaches... So far, for The average value of each calibration coefficient matrix is ​​calculated to obtain the averaged calibration coefficient matrix. S17. The averaged calibration coefficient matrix is ​​used as the optimal calibration coefficient matrix for the pitch bearing load and bolt strain mapping relationship model, thus obtaining the trained pitch bearing load and bolt strain mapping relationship model. S2. Collect real-time strain information of the outer ring bolts of the pitch bearing; S3. Input the real-time strain information into the trained pitch bearing load and bolt strain mapping model to calculate the load information of the pitch bearing.

2. The method for monitoring the load of wind turbine pitch bearings according to claim 1, characterized in that: The following formula is used to determine the mapping relationship between pitch bearing load and bolt strain: ； in, The axial force is in the x-direction. The axial force is in the y-direction. Let be the axial force in the z-direction. Let x be the bending moment in the x-direction. Let be the bending moment in the y-direction. The calibration coefficient matrix, , , , , All data are collected bolt strain information; a three-dimensional rectangular coordinate system O-xyz is established with the center of the pitch bearing as the origin O, where the x-direction is any direction in the plane where the pitch bearing is located, the z-direction is the rotation direction of the pitch bearing, and the y-direction is the direction perpendicular to the xz plane.

3. The method for monitoring the load of wind turbine pitch bearings according to claim 1, characterized in that: The static load includes axial force, radial force, and overturning moment.

4. The method for monitoring the load of wind turbine pitch bearings according to claim 2, characterized in that: The load information includes axial force in the x-direction. Axial force in the y direction Axial force in the z direction Bending moment in the x direction and bending moment in the y direction .

5. A wind turbine pitch bearing load monitoring system, used to implement the wind turbine pitch bearing load monitoring method according to any one of claims 1-4, characterized in that: Includes a data acquisition unit and a remote monitoring unit; The acquisition unit is used to acquire strain information of the outer ring bolts of the pitch bearing; The remote monitoring unit is used to analyze and process the strain information of the outer ring bolts of the pitch bearing and calculate the load information of the pitch bearing.

6. The wind power generation pitch bearing load monitoring system according to claim 5, characterized in that: The acquisition unit includes a strain gauge embedded in the bolt and a data acquisition terminal disposed on the bolt; The strain gauge is communicatively connected to the data acquisition terminal; the bolt is the outer ring bolt of the pitch bearing.

7. The wind power generation pitch bearing load monitoring system according to claim 6, characterized in that: The data acquisition terminal includes a housing, a data acquisition board disposed inside the housing, and a magnet fixedly disposed at the bottom of the housing; The data acquisition terminal is attached to the bolt by the magnet.

8. The wind power generation pitch bearing load monitoring system according to claim 6, characterized in that: The embedment depth of the strain gauge embedded in the bolt is determined using the following method: An axial force is applied to the pitch bearing, and the stress state of the outer ring bolt of the pitch bearing is analyzed by finite element method to obtain the depth at which the maximum stress of the outer ring bolt of the pitch bearing is located. The depth at which the maximum stress is located is taken as the embedment depth.

9. The wind power generation pitch bearing load monitoring system according to claim 5, characterized in that: It also includes a display unit; the display unit is used to display the load information of the pitch bearing.

Images