A system and method for extending the service life of a main speed increasing gearbox of a wind turbine generator set

By establishing an intelligent model of the gearbox, its remaining service life is estimated and online repaired, the problem of frequent offline maintenance of the main speed-growing gearbox of the wind turbine unit due to failures is solved, and the effect of extending the service life and reducing maintenance costs is achieved.

CN115270326BActive Publication Date: 2024-11-01HUANENG POWER INT INC HEBEI CLEAN ENERGY BRANCH +10
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210838587.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-15
Publication Date
2024-11-01
Estimated Expiration
2042-07-15

AI Technical Summary

Technical Problem

The frequent offline maintenance of the main speed-growing gear box of the wind turbine unit caused by failures has caused huge economic losses, and traditional maintenance methods cannot effectively extend the service life of the gear box.

Method used

By collecting image information of the gearbox, an intelligent model of surface morphology and usage time is established, artificial intelligence technology is used to estimate the remaining service life of the gearbox, and judge whether to perform online repair based on the loss level and repair difference, and formulate a repair plan to extend the Service life.

Benefits of technology

The accurate estimate of the remaining service life of the gearbox is achieved, extending the online service life of the gearbox and reducing the increase in costs caused by offline maintenance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115270326B_ABST
    Figure CN115270326B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of wind turbines, and in particular to a system and method for extending the service life of a main speed increasing gearbox of a wind turbine. It specifically includes: obtaining several groups of historical wind turbine gearbox operation data, and establishing a wind turbine service life prediction model; obtaining real-time image data of the wind turbine gearbox, and generating a first estimated service life value of the wind turbine, and judging whether to perform repairs according to the surface loss level of the wind turbine; obtaining image data of the wind turbine gearbox after repair, generating a second estimated service life value of the wind turbine, and judging whether to perform compensatory repairs. The remaining service life of the gearbox of the unit can be accurately estimated. The life diagnosis of the gearbox of the existing operating unit can be performed to estimate the remaining use time. Based on this, a maintenance plan is formulated and implemented. Finally, the maintenance effect is evaluated and compared. The gearbox is maintained online to extend the service life of the gearbox.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine generator sets, and in particular to a system and method for extending the service life of a main speed increasing gearbox of a wind turbine generator set. Background Art

[0002] With the rapid development of China's wind power industry, the number of wind farms put into operation in China has ranked first in the world. As of 2019, the cumulative installed capacity of wind power of Huaneng Group is nearly 19.96 million kilowatts, with more than 10,000 units. China's wind power capacity that has been put into operation has reached 209.53GW (CWEA, 2018 China Wind Power Installation Capacity Statistics Brief, released on April 4, 2019), ranking first in the world, far exceeding the second place of 96.4GW in the United States. Every year, more than 300 gearboxes of wind turbines put into operation by Huaneng Group need to be offline for maintenance, and the maintenance cost of traditional methods is huge.

[0003] The failure of the unit's speed-increasing gearbox caused shutdown and offline maintenance, causing great economic losses to the site. Conventional measures, such as regular replacement of designated lubricants and replacement of filter elements, cannot solve the problem of continued wear. Moreover, maintenance data in recent years show that the number of times the speed-increasing gearbox is offline for maintenance due to failure is increasing. According to statistics, each wind farm replaces an average of one gearbox per year, and some as many as four. The proportion ranges from 3% to 10%. In traditional maintenance methods, the speed-increasing gearbox needs to be disassembled, replaced and repaired in whole or in part by large lifting and hoisting equipment when the gearbox is shut down. The cost of replacing each gearbox is more than RMB 1.5 million. Summary of the invention

[0004] The purpose of the present invention is to extend the online service life of the gearbox and greatly reduce the cost increase problem caused by offline maintenance of the gearbox. The present invention provides a method for extending the service life of the main speed increasing gearbox of a wind turbine.

[0005] In some embodiments of the present application, by collecting image information of the gear surfaces of newly built gearboxes, faulty gearboxes, and already running gearboxes of relevant wind turbines, the characteristic values ​​of the surface morphology are extracted after preprocessing. Combined with the collected cumulative operating hours of the unit, cumulative power generation, gearbox usage time, faulty operating hours, etc., artificial intelligence technology is used to enter deep learning to establish an intelligent model of surface morphology and usage time. The verified mathematical model can accurately estimate the remaining service life of the unit gearbox.

[0006] In some embodiments of the present application, the established intelligent model is used to analyze the surface morphology image of the repaired gear to calculate the remaining service life of the gearbox after online repair. The surface data of the gearbox before repair is compared to evaluate the online maintenance effect and operating status of the gearbox.

[0007] In some embodiments of the present application, a method for extending the service life of a main speed increasing gearbox of a wind turbine is provided, comprising:

[0008] Step 1: Obtain several sets of historical wind turbine gearbox operation data and establish a wind turbine service life prediction model;

[0009] Step 2: Acquire real-time image data of the wind turbine gearbox, generate a first estimated service life value of the wind turbine, and determine whether to repair the wind turbine according to the surface loss level of the wind turbine;

[0010] Step 3: Obtain image data of the repaired wind turbine gearbox, generate a second estimated service life value of the wind turbine, and determine whether to perform compensatory repair.

[0011] In some embodiments of the present application, the obtaining of several sets of historical wind turbine gearbox operation data is specifically:

[0012] Obtain image information of the gear surfaces of newly built gearboxes, faulty gearboxes, and running gearboxes of wind turbines, obtain characteristic values ​​of surface morphology, and generate historical data of surface morphology;

[0013] Obtain the unit's cumulative operating hours, cumulative power generation, gearbox usage time, and fault operating hours data to generate operating history data;

[0014] A wind turbine service life prediction model is established based on historical surface morphology data and historical operation data.

[0015] In some embodiments of the present application, the step 2 is specifically as follows:

[0016] A preset wind turbine surface loss level matrix A is set to A(A1, A2, A3, A4), wherein A1 is a first preset wind turbine surface loss level, A2 is a second preset wind turbine surface loss level, A3 is a third preset wind turbine surface loss level, A4 is a fourth preset wind turbine surface loss level, and A1<A2<A3<A4;

[0017] A preset repair agent dosage matrix B is set as B(B1, B2, B3, B4), wherein B1 is the first preset repair agent dosage, B2 is the second preset repair agent dosage, B3 is the third preset repair agent dosage, B4 is the fourth preset repair agent dosage, and B1<B2<B3<B4;

[0018] According to the real-time operation data of the wind turbine, the surface loss grade a of the wind turbine is generated, and according to the relationship between the surface loss grade matrix A of the wind turbine and the repair agent dosage matrix B, the real-time repair agent dosage b is set, which is specifically:

[0019] When the wind turbine surface loss level a is between the first preset wind turbine surface loss level A1 and the second preset wind turbine surface loss level A2, the first preset repair agent dosage B1 is set as the real-time repair agent dosage, that is, b=B1;

[0020] When the wind turbine surface loss level a is between the second preset wind turbine surface loss level A2 and the third preset wind turbine surface loss level A3, the second preset repair agent dosage B2 is set as the real-time repair agent dosage, that is, b=B2;

[0021] When the wind turbine surface loss level a is between the third preset wind turbine surface loss level A3 and the fourth preset wind turbine surface loss level A4, the third preset repair agent dosage B3 is set as the real-time repair agent dosage, that is, b=B3;

[0022] When the wind turbine surface loss level a is greater than the fourth preset wind turbine surface loss level A4, the fourth preset repair agent dosage B4 is set as the real-time repair agent dosage, that is, b=B4.

[0023] In some embodiments of the present application, step three includes:

[0024] Generate a repair difference value according to a second estimated service life value of the wind turbine generator set and a first preset service life value of the wind turbine generator set;

[0025] Determine whether to perform compensation repair based on the repair difference.

[0026] In some embodiments of the present application, judging whether to perform compensation repair according to the repair difference includes:

[0027] A preset compensation coefficient matrix C is set to C(c1, c2, c3, c4), wherein c1 is a first preset compensation coefficient, c2 is a second preset compensation coefficient, c3 is a third preset compensation coefficient, c4 is a fourth preset compensation coefficient, and 0<c1<c2<c3<c4<0.3;

[0028] A preset repair difference matrix D is set as D(D1, D2, D3, D4), wherein D1 is a preset first repair difference, D2 is a preset second repair difference, D3 is a third preset repair difference, D4 ​​is a fourth preset repair difference, and D1<D2<D3<D4;

[0029] The repair difference d is obtained, and the compensation coefficient c is selected according to the relationship between the real-time repair difference d and the preset repair difference matrix D to compensate and repair the wind turbine gearbox:

[0030] When the repair difference c is between the preset fourth repair difference D4 and the preset third repair difference D3, the first preset compensation coefficient c1 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c1*Bi;

[0031] When the repair difference c is between the preset third repair difference D3 and the preset second repair difference D2, the second preset compensation coefficient c2 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c2*Bi;

[0032] When the repair difference c is between the preset second repair difference D2 and the preset first repair difference D1, the third preset compensation coefficient c3 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c3*Bi;

[0033] When the repair difference c is lower than the preset first repair difference D1, the first preset compensation coefficient c4 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c4*Bi.

[0034] In some embodiments of the present application, a system for extending the service life of a main speed increasing gearbox of a wind turbine is provided, comprising:

[0035] A monitoring unit is used to obtain historical operating data of the wind turbine gearbox and establish a wind turbine service life prediction model;

[0036] An image acquisition unit connected to the monitoring unit via a wireless signal, the image acquisition unit being used to acquire real-time image data of the gear surface of the running gear box;

[0037] The data processing unit is connected to the monitoring unit via wireless signals, and the image acquisition unit is used to process the image information of the gear surface of the running gear box acquired by the image acquisition unit and generate a repair instruction.

[0038] In some embodiments of the present application, the monitoring unit includes:

[0039] Operation monitoring module, used to obtain the unit's cumulative operating hours, cumulative power generation, gearbox usage time, fault operating hours data, and generate operation history data;

[0040] The image monitoring module is used to obtain image information of the gear surfaces of newly built gearboxes, faulty gearboxes, and operating gearboxes of wind turbines, obtain characteristic values ​​of surface morphology, and generate historical data of surface morphology.

[0041] In some embodiments of the present application, the monitoring unit further includes:

[0042] The central module is used to obtain historical surface morphology data and historical operation data, and to establish a wind turbine service life prediction model.

[0043] In some embodiments of the present application, the data processing unit includes:

[0044] An image information processing module, used to obtain real-time image data of the gear surface of the running gearbox and generate a feature value of the real-time surface morphology;

[0045] A first prediction module, used to obtain a characteristic value of the real-time surface morphology and generate a first estimated service life value according to a service life prediction model;

[0046] The first evaluation module generates a surface loss grade of the wind turbine according to the characteristic value of the real-time surface morphology;

[0047] The first repair module sets the amount of repair agent according to the surface loss level of the wind turbine.

[0048] In some embodiments of the present application, the data processing unit further includes:

[0049] A second prediction module is used to obtain the surface morphology characteristic value after repair and generate a second estimated service life value according to the service life prediction model;

[0050] A difference module generates a repair difference according to the first estimated service life value and the second estimated service life value;

[0051] The second repair module determines whether to perform compensation repair based on the repair difference

[0052] Compared with the prior art, the method for extending the service life of a main speed increasing gearbox of a wind turbine set according to the embodiment of the present invention has the following beneficial effects:

[0053] By establishing a prediction model of surface morphology and usage time, the remaining service life of the unit gearbox can be accurately estimated. With the prediction model as the core, the life diagnosis of the existing operating unit gearbox can be carried out to estimate the remaining service life. Based on this, a maintenance plan can be formulated and implemented. Finally, the maintenance effect is evaluated and compared. The gearbox can be repaired online to extend the service life of the gearbox. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1It is a flow chart of a method for extending the service life of a main speed increasing gearbox of a wind turbine generator set according to an embodiment of the present invention;

[0055] Figure 2 The present invention is a schematic diagram of a system structure for extending the service life of a main speed increasing gearbox of a wind turbine set according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0057] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0058] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0059] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0060] like Figure 1 As shown, a method for extending the service life of a main speed increasing gearbox of a wind turbine generator set in a preferred embodiment of the present invention comprises:

[0061] Step 1: Obtain several sets of historical wind turbine gearbox operation data and establish a wind turbine service life prediction model;

[0062] Step 2: Acquire real-time image data of the wind turbine gearbox, generate a first estimated service life value of the wind turbine, and determine whether to repair the wind turbine according to the surface loss level of the wind turbine;

[0063] Step 3: Obtain image data of the repaired wind turbine gearbox, generate a second estimated service life value of the wind turbine, and determine whether to perform compensatory repair.

[0064] Specifically, the operation data of several groups of historical wind turbine gearboxes are obtained as follows:

[0065] Obtain image information of the gear surfaces of newly built gearboxes, faulty gearboxes, and running gearboxes of wind turbines, obtain characteristic values ​​of surface morphology, and generate historical data of surface morphology;

[0066] Obtain the unit's cumulative operating hours, cumulative power generation, gearbox usage time, and fault operating hours data to generate operating history data;

[0067] A wind turbine service life prediction model is established based on historical surface morphology data and historical operation data.

[0068] Specifically, we use artificial intelligence technology to enter deep learning and build an intelligent model of surface morphology and usage time. The verified mathematical model can accurately estimate the remaining service life of the unit gearbox.

[0069] In some preferred embodiments of the present application, step 2 is specifically as follows:

[0070] A preset wind turbine surface loss level matrix A is set to A(A1, A2, A3, A4), wherein A1 is a first preset wind turbine surface loss level, A2 is a second preset wind turbine surface loss level, A3 is a third preset wind turbine surface loss level, A4 is a fourth preset wind turbine surface loss level, and A1<A2<A3<A4;

[0071] A preset repair agent dosage matrix B is set as B(B1, B2, B3, B4), wherein B1 is the first preset repair agent dosage, B2 is the second preset repair agent dosage, B3 is the third preset repair agent dosage, B4 is the fourth preset repair agent dosage, and B1<B2<B3<B4;

[0072] According to the real-time operation data of the wind turbine, the surface loss grade a of the wind turbine is generated, and according to the relationship between the surface loss grade matrix A of the wind turbine and the repair agent dosage matrix B, the real-time repair agent dosage b is set, which is specifically:

[0073] When the wind turbine surface loss level a is between the first preset wind turbine surface loss level A1 and the second preset wind turbine surface loss level A2, the first preset repair agent dosage B1 is set as the real-time repair agent dosage, that is, b=B1;

[0074] When the wind turbine surface loss level a is between the second preset wind turbine surface loss level A2 and the third preset wind turbine surface loss level A3, the second preset repair agent dosage B2 is set as the real-time repair agent dosage, that is, b=B2;

[0075] When the wind turbine surface loss level a is between the third preset wind turbine surface loss level A3 and the fourth preset wind turbine surface loss level A4, the third preset repair agent dosage B3 is set as the real-time repair agent dosage, that is, b=B3;

[0076] When the wind turbine surface loss level a is greater than the fourth preset wind turbine surface loss level A4, the fourth preset repair agent dosage B4 is set as the real-time repair agent dosage, that is, b=B4.

[0077] Specifically, the present application adopts online wear repair technology, which is to manually apply the repair material in the form of a "repair agent" directly to the gear surface.

[0078] It can be understood that in the above embodiment, the relationship between the wind turbine surface loss level matrix and the repair agent dosage matrix is ​​used to set the real-time repair agent dosage, improve the repair efficiency, shorten the repair time and achieve accurate repair.

[0079] In some preferred embodiments of the present application, step three includes:

[0080] Generate a repair difference value according to a second estimated service life value of the wind turbine generator set and a first preset service life value of the wind turbine generator set;

[0081] Determine whether to perform compensation repair based on the repair difference.

[0082] Specifically, judging whether to perform compensation repair according to the repair difference includes:

[0083] A preset compensation coefficient matrix C is set to C(c1, c2, c3, c4), wherein c1 is a first preset compensation coefficient, c2 is a second preset compensation coefficient, c3 is a third preset compensation coefficient, c4 is a fourth preset compensation coefficient, and 0<c1<c2<c3<c4<0.3;

[0084] A preset repair difference matrix D is set as D(D1, D2, D3, D4), wherein D1 is a preset first repair difference, D2 is a preset second repair difference, D3 is a third preset repair difference, D4 ​​is a fourth preset repair difference, and D1<D2<D3<D4;

[0085] The repair difference d is obtained, and the compensation coefficient c is selected according to the relationship between the real-time repair difference d and the preset repair difference matrix D to compensate and repair the wind turbine gearbox:

[0086] When the repair difference c is between the preset fourth repair difference D4 and the preset third repair difference D3, the first preset compensation coefficient c1 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c1*Bi;

[0087] When the repair difference c is between the preset third repair difference D3 and the preset second repair difference D2, the second preset compensation coefficient c2 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c2*Bi;

[0088] When the repair difference c is between the preset second repair difference D2 and the preset first repair difference D1, the third preset compensation coefficient c3 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c3*Bi;

[0089] When the repair difference c is lower than the preset first repair difference D1, the first preset compensation coefficient c4 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c4*Bi.

[0090] It can be understood that in the above embodiment, the repair difference is used to determine whether to perform compensation repair, and the compensation coefficient is selected according to the relationship between the repair difference and the preset repair difference matrix to suppress the occurrence of pitting corrosion, thereby achieving the purpose of gearbox wear control, extending the online service life of the gearbox, and significantly reducing the cost increase caused by offline maintenance of the gearbox.

[0091] In some preferred embodiments of the present application, according to the method in the above embodiments, a system for extending the service life of a main speed increasing gearbox of a wind turbine is provided, comprising:

[0092] A monitoring unit is used to obtain historical operating data of the wind turbine gearbox and establish a wind turbine service life prediction model;

[0093] An image acquisition unit is connected to the monitoring unit via a wireless signal, and is used to acquire real-time image data of the gear surface of the running gear box;

[0094] The data processing unit is connected to the monitoring unit via wireless signals, and the image acquisition unit is used to process the image information of the gear surface of the running gear box acquired by the image acquisition unit and generate a repair instruction.

[0095] Specifically, the image acquisition unit is an endoscope, which can conveniently acquire the surface state of the gear and reflect the wear state of the gear, and the detection cost is low.

[0096] Specifically, the monitoring unit collects gearbox data from at least three wind farms and more than 100 units, and uses artificial intelligence to build a mathematical model that can accurately reflect the relationship between gearbox wear and service life.

[0097] Specifically, the monitoring unit includes:

[0098] Operation monitoring module, used to obtain the unit's cumulative operating hours, cumulative power generation, gearbox usage time, fault operating hours data, and generate operation history data;

[0099] The image monitoring module is used to obtain image information of the gear surfaces of newly built gearboxes, faulty gearboxes, and operating gearboxes of wind turbines, obtain characteristic values ​​of surface morphology, and generate historical data of surface morphology.

[0100] Specifically, the monitoring unit also includes:

[0101] The central module is used to obtain historical surface morphology data and historical operation data, and to establish a wind turbine service life prediction model.

[0102] Specifically, the data processing unit includes:

[0103] An image information processing module, used to obtain real-time image data of the gear surface of the running gearbox and generate a feature value of the real-time surface morphology;

[0104] A first prediction module, used to obtain a characteristic value of the real-time surface morphology and generate a first estimated service life value according to a service life prediction model;

[0105] The first evaluation module generates a surface loss grade of the wind turbine according to the characteristic value of the real-time surface morphology;

[0106] The first repair module sets the amount of repair agent according to the surface loss level of the wind turbine.

[0107] Specifically, the data processing unit also includes:

[0108] A second prediction module is used to obtain the surface morphology characteristic value after repair and generate a second estimated service life value according to the service life prediction model;

[0109] A difference module generates a repair difference according to the first estimated service life value and the second estimated service life value;

[0110] The second repair module determines whether to perform compensation repair according to the repair difference.

[0111] According to the first concept of this application, by collecting image information of the gear surface of the newly built gearbox, faulty gearbox, and already running gearbox of the relevant wind turbine, the characteristic values ​​of the surface morphology are extracted after preprocessing. Combined with the collected cumulative operating hours of the unit, cumulative power generation, gearbox usage time, faulty operating hours, etc., artificial intelligence technology is used to enter deep learning to establish an intelligent model of surface morphology and usage time. The verified mathematical model can accurately estimate the remaining service life of the unit gearbox.

[0112] According to the second concept of this application, the established intelligent model is used to analyze the surface morphology image of the repaired gear to calculate the remaining service life of the gearbox after online repair. The surface data of the gearbox before repair is compared to evaluate the online maintenance effect and operating status of the gearbox.

[0113] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention. These improvements and substitutions should also be regarded as the scope of protection of the present invention.

Claims

1. A method for extending the service life of a main speed increasing gearbox of a wind turbine generator set, characterized in that: include: Step 1: Obtain several sets of historical wind turbine gearbox operation data and establish a wind turbine service life prediction model; Step 2: Acquire real-time image data of the wind turbine gearbox, generate a first estimated service life value of the wind turbine, and determine whether to repair the wind turbine according to the surface loss level of the wind turbine; Step 3: Obtain the image data of the wind turbine gearbox after repair, generate the second estimated service life value of the wind turbine, and determine whether to perform compensatory repair; The specific method of obtaining several groups of historical wind turbine gearbox operation data is as follows: Obtain image information of the gear surfaces of newly built gearboxes, faulty gearboxes, and running gearboxes of wind turbines, obtain characteristic values ​​of surface morphology, and generate historical data of surface morphology; Obtain the unit's cumulative operating hours, cumulative power generation, gearbox usage time, and fault operating hours data to generate operating history data; Establish a wind turbine service life prediction model based on historical surface morphology data and historical operation data; The step 2 is specifically as follows: The preset wind turbine surface loss level matrix A is set to A(A1, A2, A3, A4), where A1 is the first preset wind turbine surface loss level, A2 is the second preset wind turbine surface loss level, A3 is the third preset wind turbine surface loss level, A4 is the fourth preset wind turbine surface loss level, and A1 <A2<A3<A4; The preset repair agent dosage matrix B is set as B(B1, B2, B3, B4), where B1 is the first preset repair agent dosage, B2 is the second preset repair agent dosage, B3 is the third preset repair agent dosage, B4 is the fourth preset repair agent dosage, and B1 <B2<B3<B4; According to the real-time operation data of the wind turbine, the surface loss grade a of the wind turbine is generated, and according to the relationship between the surface loss grade matrix A of the wind turbine and the repair agent dosage matrix B, the real-time repair agent dosage b is set, which is specifically: When the wind turbine surface loss level a is between the first preset wind turbine surface loss level A1 and the second preset wind turbine surface loss level A2, the first preset repair agent dosage B1 is set as the real-time repair agent dosage, ie b = B1; When the wind turbine surface loss level a is between the second preset wind turbine surface loss level A2 and the third preset wind turbine surface loss level A3, the second preset repair agent dosage B2 is set to the real-time repair agent dosage, ie b = B2; When the wind turbine surface loss level a is between the third preset wind turbine surface loss level A3 and the fourth preset wind turbine surface loss level A4, the third preset repair agent dosage B3 is set to the real-time repair agent dosage, ie b = B3; When the wind turbine surface loss level a is greater than the fourth preset wind turbine surface loss level A4, the fourth preset repair agent dosage B4 is set as the real-time repair agent dosage, that is, b=B4; The step three comprises: Generate a repair difference value according to a second estimated service life value of the wind turbine generator set and a first preset service life value of the wind turbine generator set; Determine whether to perform compensation repair based on the repair difference.

2. The method for extending the service life of the main speed increasing gearbox of a wind turbine as claimed in claim 1, characterized in that: The determining whether to perform compensation repair according to the repair difference includes: The preset compensation coefficient matrix C is set to C(c1, c2, c3, c4), where c1 is the first preset compensation coefficient, c2 is the second preset compensation coefficient, c3 is the third preset compensation coefficient, c4 is the fourth preset compensation coefficient, and, <c1<c2<c3<c4<0.3; The preset repair difference matrix D is set to D(D1, D2, D3, D4), where D1 is the preset first repair difference, D2 is the preset second repair difference, D3 is the third preset repair difference, D4 ​​is the fourth preset repair difference, and D1 <D2<D3<D4; The repair difference d is obtained, and the compensation coefficient c is selected according to the relationship between the real-time repair difference d and the preset repair difference matrix D to compensate and repair the wind turbine gearbox: When the repair difference c is between the preset fourth repair difference D4 and the preset third repair difference D3, the first preset compensation coefficient c1 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c1*Bi; When the repair difference c is between the preset third repair difference D3 and the preset second repair difference D2, the second preset compensation coefficient c2 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c2*Bi; When the repair difference c is between the preset second repair difference D2 and the preset first repair difference D1, the third preset compensation coefficient c3 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c3*Bi; When the repair difference c is lower than the preset first repair difference D1, the first preset compensation coefficient c4 is selected to compensate the i-th preset repair agent dosage Bi, and the compensation repair agent dosage of the wind turbine gearbox is c4*Bi.

3. A system for extending the service life of a main speed increasing gearbox of a wind turbine generator set, adopting the method for extending the service life of a main speed increasing gearbox of a wind turbine generator set as described in any one of claims 1-2, characterized in that: include: A monitoring unit is used to obtain historical operating data of the wind turbine gearbox and establish a wind turbine service life prediction model; An image acquisition unit connected to the monitoring unit via a wireless signal, the image acquisition unit being used to acquire real-time image data of the gear surface of the running gear box; A data processing unit is connected to the monitoring unit via a wireless signal, and is used to process the image information of the gear surface of the running gear box acquired by the image acquisition unit, and generate a repair instruction.

4. The system for extending the service life of the main speed increasing gearbox of a wind turbine as claimed in claim 3, characterized in that: The monitoring unit comprises: The operation monitoring module is used to obtain the unit's cumulative operating hours, cumulative power generation, gearbox usage time, fault operating hours data, and generate operation history data; The image monitoring module is used to obtain image information of the gear surfaces of newly built gearboxes, faulty gearboxes, and operating gearboxes of wind turbines, obtain characteristic values ​​of surface morphology, and generate historical data of surface morphology.

5. The system for extending the service life of the main speed increasing gearbox of a wind turbine as claimed in claim 4, characterized in that: The monitoring unit also includes: The central module is used to obtain historical surface morphology data and historical operation data, and to establish a wind turbine service life prediction model.

6. The system for extending the service life of the main speed increasing gearbox of a wind turbine as claimed in claim 5, characterized in that: The data processing unit comprises: An image information processing module, used to obtain real-time image data of the gear surface of the running gearbox and generate a feature value of the real-time surface morphology; A first prediction module, used to obtain a characteristic value of the real-time surface morphology and generate a first estimated service life value according to a service life prediction model; The first evaluation module generates a surface loss grade of the wind turbine according to the characteristic value of the real-time surface morphology; The first repair module sets the amount of repair agent according to the surface loss level of the wind turbine.

7. The system for extending the service life of the main speed increasing gearbox of a wind turbine as claimed in claim 6, characterized in that: The data processing unit also includes: A second prediction module is used to obtain the surface morphology characteristic value after repair and generate a second estimated service life value according to the service life prediction model; A difference module generates a repair difference according to the first estimated service life value and the second estimated service life value; The second repair module determines whether to perform compensation repair according to the repair difference.