A method for intelligent optimization of machining process parameters of wind turbine gearbox parts

Abstract

This invention discloses an intelligent optimization method for machining process parameters of wind turbine gearbox components, relating to the field of mechanical manufacturing technology. The method includes: acquiring easily worn points A1 and A2 of the components; determining the lifespan parameters of the components and obtaining lifespan prediction parameters based on component wear simulation; and replacing the components within the wind turbine gearbox based on the lifespan prediction parameters of all components within the gearbox. This invention addresses the problem in existing intelligent optimization methods for machining process parameters of wind turbine gearbox components that lack a correlation between the component's operating state within the gearbox and the gearbox's working efficiency, resulting in a disconnect between machining parameter optimization and actual service conditions, and an inability to promptly replace and warn of abnormal component wear.

Description

Technical Field

[0001] This invention relates to the field of mechanical manufacturing technology, specifically to an intelligent optimization method for machining process parameters of wind turbine gearbox components. Background Technology

[0002] Intelligent optimization of machining process parameters for wind turbine gearbox components is a technical means that uses artificial intelligence, big data analysis, and automated control technology to monitor, dynamically adjust, and globally optimize process parameters such as cutting speed, feed rate, depth of cut, temperature, and tool path of key components such as gears, shafts, and bearing housings during the machining process. It aims to improve machining accuracy, production efficiency, and product reliability, while reducing energy consumption and scrap rate.

[0003] Existing methods for intelligent optimization of machining process parameters for wind turbine gearbox components typically involve classifying components and raw materials based on performance deviations within the gearbox, and then performing multi-specification batch processing on these components to reduce material waste. While this approach can reduce production costs, it lacks intelligent parameter optimization during component processing. It doesn't consider the operational status of components within the gearbox, the correlation between component wear and gearbox efficiency, or the need for timely replacement of abnormally worn components. Furthermore, it lacks optimization of machining parameters, leading to a disconnect between optimized machining parameters and actual service conditions. This results in a failure to provide timely warnings for abnormal component wear. For example, patent application CN119962099A discloses… This paper presents a method and system for optimizing the manufacturing process of wind turbine gears. This solution involves adapting and machining multi-specification gears from raw materials based on the gear structure of the wind turbine gearbox. This reduces material waste and lowers production costs. Other improvements to intelligent optimization methods for machining process parameters of wind turbine gearbox components typically focus on machining errors and power consumption. These methods lack an understanding of the operational status of components within the gearbox, the correlation between component wear and the gearbox's efficiency, and the need for timely replacement of abnormally worn components. Furthermore, they lack optimization of machining parameters, leading to a disconnect between optimized machining parameters and actual service conditions, and an inability to provide timely warnings for abnormal component wear. Therefore, it is necessary to improve existing intelligent optimization methods for machining process parameters of wind turbine gearbox components. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art by proposing an intelligent optimization method for machining process parameters of wind turbine gearbox components. This method addresses the lack of existing intelligent optimization methods for machining process parameters of wind turbine gearbox components that lack a correlation between the wear degree of components and the working efficiency of the wind turbine gearbox based on the operating state of the components within the gearbox, thus hindering the timely replacement of abnormally worn components. Furthermore, the method also improves the optimization of machining parameters during machining, resulting in a disconnect between the optimized machining parameters and actual service conditions, and the inability to provide timely warnings for replacing abnormally worn components.

[0005] To achieve the above objectives, this application provides a method for intelligent optimization of machining process parameters for wind turbine gearbox components, comprising the following steps:

[0006] The components with different service times in multiple wind turbine gearboxes are analyzed, and the analysis results are used to obtain the wear-prone points A1 and A2 for each component. Based on the wear state of wear-prone points A1 and A2 in the component and the working efficiency of the wind turbine gearbox in which the component is located, the life determination parameters of the component are obtained.

[0007] When machining parts, improve the wear resistance of wear-prone points A1 and A2, and obtain the life prediction parameters of parts based on wear simulation.

[0008] When the wind turbine gearbox is running, the components inside the wind turbine gearbox are replaced based on the life prediction parameters of all components inside the wind turbine gearbox, and the wear-prone points A1 and A2 of the replaced components are updated based on the replaced components.

[0009] Furthermore, the components with different service lives within multiple wind turbine gearboxes were analyzed, and the analysis results yielded the corresponding wear-prone points A1 and A2 for each component, including:

[0010] Obtain multiple wind turbine gearboxes in operation and label them all as gearboxes to be optimized; label all components inside the wind turbine gearboxes as internal components X. B1 To the internal components XB n By default, all components within the gearbox to be optimized are identical.

[0011] For any component XB inside the box m Obtain the XB internal components of all gearboxes to be optimized. m The duration of use will be determined by the use of internal components XB. mThe gearbox with the longest duration to be optimized is denoted as the wear analysis box, where m is a positive integer less than or equal to n and greater than or equal to 1; the internal components XB of the wear analysis box are... m Designated as internal component XB m Wear-out spare parts;

[0012] Obtain the wear analysis box for all components inside the box, and obtain the wear-ready parts corresponding to each component inside the box.

[0013] Furthermore, the analysis of components with varying service lives within multiple wind turbine gearboxes was conducted, and the analysis results yielded wear-prone points A1 and A2 for each component. This also included:

[0014] Based on the latest input and output power of the gearbox to be optimized, the operating efficiency of all gearboxes to be optimized is obtained, and the gearbox with the lowest operating efficiency is denoted as the power analysis gearbox; for any component XB within the gearbox m The internal components XB of the power analysis box m Designated as internal component XB m Power standby components;

[0015] The power availability of all components within the power analysis box is obtained.

[0016] Furthermore, the analysis of components with varying service lives within multiple wind turbine gearboxes was conducted, and the analysis results yielded wear-prone points A1 and A2 for each component. This also included:

[0017] For any component XB inside the box m : For the internal components XB of the box respectively m Wear analysis methods are used to analyze the wear-prone parts and power-prone parts. Based on the analysis results, wear points B1 and B2 corresponding to the wear-prone parts and power-prone parts are obtained.

[0018] The surface roughness values ​​corresponding to the wear points B1 and B2 of the wear-to-use component are denoted as C1 and C2, respectively; the surface roughness values ​​corresponding to the wear points B1 and B2 of the power-to-use component are denoted as C3 and C4, respectively; the wear points corresponding to the two larger values ​​among C1 to C4 are denoted as the internal component XB. m The easily worn points A1 and A2 are identified, and the sum of the surface roughness values ​​of easily worn points A1 and A2 is denoted as XB of the internal component. m The rough judgment value.

[0019] Furthermore, based on the wear state of wear-prone points A1 and A2 within the component, and the operating efficiency of the wind turbine gearbox where the component is located, the lifespan determination parameters of the component are obtained, including:

[0020] When the location of easily worn point A1 or easily worn point A2 is the same as the location of the wear point B1 or wear point B2 of the wear-to-use part, the working efficiency of the wear-to-use part is recorded as XB of the internal component. m Wear life parameters;

[0021] When the location of easily worn point A1 or easily worn point A2 is the same as the location of the wear point B1 or wear point B2 of the power-on-demand component, the working efficiency of the power-on-demand component is recorded as XB of the internal component. m Power life parameters;

[0022] When the internal component XB m When only wear life parameters or power life parameters exist, the internal components XB m The wear life parameter or power life parameter is denoted as XB of the internal component. m Lifespan determination parameters;

[0023] When the internal component XB m When both wear life parameters and power life parameters exist, the internal component XB m The average values ​​of the wear life parameters and power life parameters of the internal components are denoted as XB. m Lifespan determination parameters.

[0024] Furthermore, wear analysis methods include:

[0025] Based on the design drawings of the components, all surfaces of the components are sequentially designated as surface DB1 to surface DB2. q For any surface DB to be selected p Using a camera, the target surface DB in the unused parts is selected. p And the surface DB to be sampled in the component being analyzed. p Take photos and record the resulting images as the flawless surface image and the worn surface image, respectively, where p is a positive integer less than or equal to q and greater than or equal to 1;

[0026] The flawless surface image and the worn surface image are converted to grayscale, and the grayscale images are then binarized. The two resulting images are denoted as the grayscale flawless image and the grayscale worn image, respectively.

[0027] Furthermore, wear analysis methods also include:

[0028] The grayscale flawless image and the grayscale wear image are overlaid, and AI is used to mark the different areas in the overlaid image as potential wear areas; the target surface DB in the component being analyzed is then selected. p Mark the wear candidate area inside, and uniformly obtain j points within the wear candidate area, which are recorded as roughness measurement points;

[0029] A roughness meter was used to measure the roughness at all points, and the roughness with the largest value was recorded as the surface DB to be tested. p Surface roughness value;

[0030] Obtain the surface roughness values ​​of all surfaces to be analyzed, and record the roughness measurement points corresponding to the two surface roughness values ​​with the larger values ​​as wear points B1 and B2 of the component to be analyzed.

[0031] Furthermore, when machining the parts, the wear resistance at wear-prone points A1 and A2 is improved, and based on wear simulation, the life prediction parameters of the parts are obtained, including:

[0032] When machining internal components within a gearbox to be optimized, for any one of the internal components XB m Based on existing processes, improve the internal components of the XB box. m The wear resistance of easily worn points A1 and A2 was determined, and the resulting internal component XB was tested. m Recorded as a wear-resistant improved part;

[0033] Based on component wear simulation, a wear simulation of the wear-resistant improved part is performed using the gearbox to be optimized as the scenario. During the wear simulation, the working efficiency of the gearbox to be optimized is reduced from the standard efficiency to XB of the internal components. m The lifespan determination parameters are as follows, where the standard efficiency is the maximum operating efficiency of the gearbox to be optimized.

[0034] Furthermore, based on component wear simulation, the parameters for predicting component life also include:

[0035] After wear simulation, wear points B1 and B2 to be identified in the wear-resistant improved part are obtained based on wear analysis methods. The criteria for identification are: wear points B1 and B2 being identical to easily worn points A1 and A2, and the sum of the surface roughness values ​​corresponding to wear points B1 and B2 being less than XB of the internal component. m When determining the roughness value, the wear-resistant improved part is denoted as the internal component XB. m The standard improved part, and the sum of the surface roughness values ​​corresponding to the wear points B1 and B2 of the wear-resistant improved part is denoted as the internal part XB. mLifetime prediction parameters;

[0036] When the wear-resistant improved part is not recorded as an internal component XB m When obtaining the standard improved part, adjust the amount of increase in wear resistance for wear-prone points A1 and A2 when the wear-resistant improved part is obtained, and then obtain the wear-resistant improved part again until the internal component XB is obtained. m Standard improved parts.

[0037] Furthermore, when the wind turbine gearbox is in operation, based on the life prediction parameters of all components within the gearbox, the components are replaced, and based on the replaced components, the wear-prone points A1 and A2 of the components are updated, including:

[0038] When the gearbox to be optimized is running, all internal components of the gearbox to be optimized will be replaced with standard improved parts corresponding to the internal components.

[0039] For any component XB inside the box m When the working efficiency of the gearbox to be optimized and the internal components XB m When the life determination parameters are equal, obtain the XB of the internal component of the gearbox to be optimized. m The wear degree of easily worn points A1 and A2 is determined, and the sum of the wear degrees of easily worn points A1 and A2 is recorded as the real-time judgment value.

[0040] When the real-time judgment value is less than or equal to the internal component XB m When calculating the life prediction parameters, the internal components XB in the gearbox to be optimized are not considered. m Replacement is required when the real-time judgment value is greater than XB of the internal component. m When determining the life prediction parameters, the internal components XB in the gearbox to be optimized are... m Replace and re-acquire the internal components XB. m The easily worn points A1 and A2, and the internal component XB m Standard improved parts.

[0041] The beneficial effects of this invention are as follows: This application first analyzes multiple components with different usage durations within a wind turbine gearbox, and obtains the corresponding wear-prone points A1 and A2 for each component based on the analysis results. Based on the wear state of wear-prone points A1 and A2 within the component, and the working efficiency of the wind turbine gearbox containing the component, lifespan determination parameters for the component are obtained. This approach is advantageous because by analyzing components with different usage durations within the wind turbine gearbox, the wear state of the component under different working durations can be analyzed in conjunction with the actual working conditions of the component, thus ensuring that the obtained wear-prone points are the most easily worn locations of the component during operation. By combining the wear state of wear-prone points A1 and A2 within the component, and the working efficiency of the wind turbine gearbox containing the component, lifespan determination parameters for the component are obtained. This allows for determining the required working efficiency of the wind turbine gearbox when the wear state of wear-prone points A1 and A2 is at the corresponding surface roughness value. This facilitates the correlation between the wear degree of the component and the working efficiency of the wind turbine gearbox in subsequent analyses, enabling timely replacement of abnormally worn components.

[0042] This application also improves the wear resistance of easily worn points A1 and A2 on the components and obtains the component life prediction parameters based on component wear simulation. Finally, when the wind turbine gearbox is running, the components inside the wind turbine gearbox are replaced based on the life prediction parameters of all components in the wind turbine gearbox, and the easily worn points A1 and A2 on the replaced components are updated. The advantage of this is that, through component wear simulation, it is possible to obtain the wear resistance of easily worn points A1 and A2 during machining, and if the wind turbine gearbox... When the gearbox's working efficiency reaches the lifespan determination parameters, the surface roughness values ​​corresponding to wear-prone points A1 and A2 should be provided to support subsequent component replacement. During wind turbine gearbox operation, if a component is replaced, it indicates abnormal wear. Therefore, after replacement, wear-prone points A1 and A2 should be updated to ensure that the replaced component's wear level remains correlated with the wind turbine gearbox's working efficiency. This avoids the problem of machining parameter optimization being out of sync with actual service conditions, and the inability to promptly replace abnormally worn components. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating the steps of the method of the present invention;

[0044] Figure 2 This is a schematic diagram illustrating the acquisition of the wear-selectable area according to the present invention;

[0045] Figure 3This is a schematic diagram illustrating the marking of roughness measurement points according to the present invention;

[0046] Figure 4 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] Example 1, please refer to Figure 1 As shown, this application provides an intelligent optimization method for machining process parameters of wind turbine gearbox components, including the following steps:

[0049] Step S1: Analyze the components with different service times in multiple wind turbine gearboxes, and obtain the wear-prone points A1 and A2 for each component based on the analysis results; Based on the wear state of wear-prone points A1 and A2 in the component and the working efficiency of the wind turbine gearbox in which the component is located, obtain the life determination parameters of the component.

[0050] Step S1 includes: Step S101, obtaining multiple wind turbine gearboxes in operation, and labeling them all as gearboxes to be optimized; labeling all components inside the wind turbine gearboxes as internal components X. B1 To the internal components XB n By default, all components within the gearbox to be optimized are identical.

[0051] Step S102, for any one of the internal components XB m Obtain the XB internal components of all gearboxes to be optimized. m The duration of use will be determined by the use of internal components XB. m The gearbox with the longest duration to be optimized is denoted as the wear analysis box, where m is a positive integer less than or equal to n and greater than or equal to 1; the internal components XB of the wear analysis box are... m Designated as internal component XB m Wear-out spare parts;

[0052] In the specific implementation process, for example, if the number of wind turbine gearboxes that can be obtained in a data analysis is 10, and the internal component of each gearbox is a planetary gear, then when acquiring data, the wind turbine gearbox with the longest planetary gear operation time among the 10 wind turbine gearboxes can be recorded as the planetary gear wear analysis box.

[0053] Step S103: Obtain the wear analysis box for all internal components and obtain the wear-ready parts corresponding to each internal component.

[0054] Step S1 further includes: Step S104, based on the latest input power and output power of the gearbox to be optimized, obtaining the working efficiency of all gearboxes to be optimized, and recording the gearbox with the lowest working efficiency as the power analysis gearbox; for any component XB within the gearbox m The internal components XB of the power analysis box m Designated as internal component XB m Power standby components;

[0055] In the specific implementation process, the working efficiency is the output power of the gearbox to be optimized divided by the input power × 100%. By obtaining the wear analysis box and power analysis box of all internal components, it is beneficial to analyze the internal components of the gearbox with the longest working time and the internal components of the wind turbine gearbox with the lowest working efficiency when analyzing the internal components in the subsequent process. This allows us to identify the locations of high wear on the surface of the internal components when the internal components are in long-term working conditions and when the working efficiency of the wind turbine gearbox is low. This enables targeted optimization when machining the internal components. In this embodiment, by obtaining the wear analysis box and power analysis box of the planetary gear in 10 wind turbine gearboxes, we can obtain the wear-ready parts and power-ready parts corresponding to the planetary gear, providing data acquisition support for the subsequent analysis of the planetary gear.

[0056] Step S105: Obtain the power available components of all components within the power analysis box.

[0057] Step S1 further includes: Step S106, for any one of the internal components XB m : For the internal components XB of the box respectively m Wear analysis methods are used to analyze the wear-prone parts and power-prone parts. Based on the analysis results, wear points B1 and B2 corresponding to the wear-prone parts and power-prone parts are obtained.

[0058] The wear analysis method includes: Step V1, based on the design drawings of the parts, all surfaces of the parts are sequentially labeled as surface to be taken DB1 to surface to be taken DB. q For any surface DB to be selected p Using a camera, the target surface DB in the unused parts is selected. p And the surface DB to be sampled in the component being analyzed. p Take photos and record the resulting images as the flawless surface image and the worn surface image, respectively, where p is a positive integer less than or equal to q and greater than or equal to 1;

[0059] In the actual implementation process, it is assumed that all surfaces of unused parts are not worn, that is, there will be no areas with defects caused by wear in the obtained flawless surface map;

[0060] Step V2: Convert the flawless surface image and the worn surface image to grayscale, and then binarize the grayscale images. The two images obtained are recorded as the grayscale flawless image and the grayscale worn image, respectively.

[0061] In the data analysis of this embodiment, for example, the surface to be sampled corresponding to the wear of the planetary gear obtained above is photographed using a camera, and the resulting grayscale wear image is obtained after grayscale and binarization processing, as shown below. Figure 2 As shown in PP1; in addition, the grayscale flawless image of the planetary gear obtained through data acquisition is as follows. Figure 2 As shown in PP2; the image obtained by overlaying PP1 and PP2 is PP3. By using AI to analyze PP3, we can find that the different regions in the overlapping images of PP3 are MD1, MD2 and MD3, that is, the wear candidate regions are MD1, MD2 and MD3.

[0062] The wear analysis method also includes: Step V3, overlaying the grayscale flawless image and the grayscale wear image, and using AI to mark the different areas in the overlaid images as wear candidate areas; and selecting the target surface DB in the component being analyzed. p Mark the wear candidate area inside, and uniformly obtain j points within the wear candidate area, which are recorded as roughness measurement points;

[0063] In the specific implementation process, the value of j can be determined according to the actual data analysis capabilities; the purpose of obtaining roughness measurement points is to obtain the point with the highest wear degree within the wear candidate area and to measure its corresponding roughness using a roughness meter. The larger the value of j, the more detailed the wear candidate area can be measured, thus making the obtained surface roughness more consistent with the maximum roughness of the surface to be selected; in the data analysis of this embodiment, the value of j is set to 20, that is, in Figure 2 In regions MD1, MD2, and MD3, 20 points are uniformly obtained as roughness measurement points and measured using a roughness meter.

[0064] Step V4: Use a roughness meter to measure the roughness at all measurement points, and record the roughness with the largest value as the surface to be sampled (DB). p Surface roughness value;

[0065] Step V5: Obtain the surface roughness values ​​of all surfaces to be sampled, and record the roughness measurement points corresponding to the two surface roughness values ​​with larger values ​​among all surface roughness values ​​as the wear point B1 and wear point B2 of the component to be analyzed.

[0066] In the data analysis of this embodiment, by acquiring the surface roughness values ​​of all surfaces to be sampled on the planetary gear, the two surface roughness values ​​with the largest values ​​were found to be 6.1 μm and 6.3 μm, respectively, and the corresponding roughness measurement points are as follows: Figure 3 Points B1 and B2 are shown in the image. The images PP1 and PP4 containing points B1 and B2 are grayscale wear maps of the two surfaces to be sampled corresponding to the planetary gear.

[0067] Step S107: Record the surface roughness values ​​corresponding to the wear points B1 and B2 of the wear-to-use component as C1 and C2, respectively; record the surface roughness values ​​corresponding to the wear points B1 and B2 of the power-to-use component as C3 and C4, respectively; and record the wear points corresponding to the two larger values ​​among C1 to C4 as the internal component XB. m The easily worn points A1 and A2 are identified, and the sum of the surface roughness values ​​of easily worn points A1 and A2 is denoted as XB of the internal component. m The rough judgment value.

[0068] Step S1 further includes: Step S108, when the location of the easily worn point A1 or easily worn point A2 is the same as the location of the wear point B1 or wear point B2 of the wear-to-use part, the working efficiency of the wear-to-use part is recorded as XB of the internal component. m Wear life parameters;

[0069] In the data analysis of this embodiment, for example, the surface roughness values ​​of wear points B1 and B2 corresponding to the wear points of the planetary gear are 6.1μm and 6.3μm, respectively, and the surface roughness values ​​of wear points B1 and B2 corresponding to the power components are 4.8μm and 5.1μm, respectively. Through analysis, it can be found that C1, C2, C3 and C4 are 6.1μm, 6.3μm, 4.8μm and 5.1μm, respectively. The two larger values ​​are 6.1μm and 6.3μm, respectively. Therefore, the wear points corresponding to 6.1μm and 6.3μm can be recorded as wear-prone points A1 and A2, respectively, and the corresponding roughness judgment value is 12.4μm.

[0070] The above analysis shows that the wear points A1 and A2 are the same as the wear points B1 and B2 of the wear-to-use parts of the planetary gear. Therefore, the working efficiency of the wear-to-use parts can be recorded as the wear life parameter of the planetary gear, and the planetary gear does not have a power life parameter.

[0071] Step S109: When the location of the easily worn point A1 or easily worn point A2 is the same as the location of the wear point B1 or wear point B2 of the power-on-demand component, the working efficiency of the power-on-demand component is recorded as XB of the internal component. m Power life parameters;

[0072] Step S110, when the internal component XB m When only wear life parameters or power life parameters exist, the internal components XB m The wear life parameter or power life parameter is denoted as XB of the internal component. m Lifespan determination parameters;

[0073] In the data analysis of this embodiment, the wear life parameter and power life parameter of the planetary gear are 95% and 94%, respectively. The analysis shows that the planetary gear only has a wear life parameter, therefore the life determination parameter is 95%. By obtaining the life determination parameter of the planetary gear, it can be determined that when the wear state of the easily worn points A1 and A2 of the planetary gear is at the corresponding surface roughness values ​​of 6.1μm and 6.3μm, respectively, the working efficiency of the wind turbine gearbox containing the planetary gear should be 95%. This allows for the correlation between the wear degree of the planetary gear and the working efficiency of the wind turbine gearbox in subsequent analyses, enabling timely replacement of abnormally worn planetary gears.

[0074] Step S111, when the internal component XB m When both wear life parameters and power life parameters exist, the internal component XB m The average values ​​of the wear life parameters and power life parameters of the internal components are denoted as XB. m Lifespan determination parameters.

[0075] Step S2: When machining the parts, improve the wear resistance of the wear-prone points A1 and A2 of the parts, and obtain the life prediction parameters of the parts based on the wear simulation of the parts.

[0076] Step S2 includes: Step S201, when machining the internal components of the gearbox to be optimized, for any one internal component XB m Based on existing processes, improve the internal components of the XB box. m The wear resistance of easily worn points A1 and A2 was determined, and the resulting internal component XB was tested. m Recorded as a wear-resistant improved part;

[0077] In the specific implementation process, the wear resistance of wear-prone points A1 and A2 can be improved by methods that can be achieved in the existing process, such as using low-carbon alloy carburizing steel, carburizing and quenching + low-temperature tempering, and controlling the uniformity and gradient of the carburized layer.

[0078] Step S202: Based on component wear simulation, perform wear simulation on the wear-resistant improved part in the scenario of the gearbox to be optimized, and reduce the working efficiency of the gearbox to be optimized from the standard efficiency to XB of the internal components during the wear simulation. m The lifespan determination parameters are as follows, where the standard efficiency is the maximum working efficiency of the gearbox to be optimized during operation.

[0079] In practical implementation, component wear simulation can be carried out by constructing a digital twin model to simulate the working environment of the wind turbine gearbox, so as to simulate the wear of components more accurately.

[0080] Step S2 further includes: Step S203, after wear simulation, obtaining the wear point B1 and wear point B2 to be taken for the wear-resistant improved part based on the wear analysis method. When the obtained wear point B1 and wear point B2 are the same as the easily worn points A1 and A2, and the sum of the surface roughness values ​​corresponding to the wear point B1 and wear point B2 is less than XB of the internal component. m When determining the roughness value, the wear-resistant improved part is denoted as the internal component XB. m The standard improved part, and the sum of the surface roughness values ​​corresponding to the wear points B1 and B2 of the wear-resistant improved part is denoted as the internal part XB. m Lifetime prediction parameters;

[0081] In the data analysis of this embodiment, for example, after improving the wear resistance of easily worn points A1 and A2 in the planetary gear, the wear points B1 and B2 obtained by the wear analysis method after wear simulation are the same as easily worn points A1 and A2. This indicates that even if the wear resistance of easily worn points A1 and A2 is improved, they are still two points in the planetary gear that are more easily worn. Therefore, the wear state of the planetary gear can still be judged by easily worn points A1 and A2. If the wear... If the wear points B1 and B2 obtained by the wear analysis method after simulation are different from the easily worn points A1 and A2, it indicates that the easily worn points A1 and A2 are not the two most easily worn points in the planetary gear. Therefore, the wear condition of the planetary gear cannot be judged by the easily worn points A1 and A2. Thus, the wear-resistant improvement parts should be obtained again to ensure that the wear resistance of the easily worn points A1 and A2 of the planetary gear is improved, so that the wear condition of the planetary gear can still be judged by the easily worn points A1 and A2.

[0082] In addition, if the sum of the surface roughness values ​​corresponding to the wear points B1 and B2 is greater than the roughness judgment value of 12.4μm for the planetary gear, it indicates that the wear resistance of the easily worn points A1 and A2 of the planetary gear has not been effectively improved in the machining process. Therefore, the wear-resistant improved parts should be obtained again to ensure that the wear resistance of the easily worn points A1 and A2 of the planetary gear is effectively improved in the machining process.

[0083] Step S204, when the wear-resistant improved part is not recorded as an internal component XB m When obtaining the standard improved part, adjust the amount of increase in wear resistance for wear-prone points A1 and A2 when the wear-resistant improved part is obtained, and then obtain the wear-resistant improved part again until the internal component XB is obtained. m Standard improved parts.

[0084] Step S3: When the wind turbine gearbox is running, based on the life prediction parameters of all components in the wind turbine gearbox, the components in the wind turbine gearbox are replaced, and based on the replaced components, the wear-prone points A1 and A2 of the components are updated.

[0085] Step S3 includes: Step S301, when the gearbox to be optimized is running, all internal components of the gearbox to be optimized are replaced with standard improved parts corresponding to the internal components;

[0086] Step S302, for any one of the internal components XB mWhen the working efficiency of the gearbox to be optimized and the internal components XB m When the life determination parameters are equal, obtain the XB of the internal component of the gearbox to be optimized. m The wear degree of easily worn points A1 and A2 is determined, and the sum of the wear degrees of easily worn points A1 and A2 is recorded as the real-time judgment value.

[0087] Step S303, when the real-time judgment value is less than or equal to the internal component XB m When calculating the life prediction parameters, the internal components XB in the gearbox to be optimized are not considered. m Replacement is required when the real-time judgment value is greater than XB of the internal component. m When determining the life prediction parameters, the internal components XB in the gearbox to be optimized are... m Replace and re-acquire the internal components XB. m The easily worn points A1 and A2, and the internal component XB m Standard improved parts;

[0088] In the data analysis of this embodiment, for example, for a planetary gear, when the working efficiency of the gearbox to be optimized is 95%, the wear degree of the easily worn points A1 and A2 of the planetary gear is obtained, and the real-time judgment value is 12.1μm. If 12.1μm is less than or equal to the life prediction parameter of the planetary gear, it means that when the working efficiency of the gearbox to be optimized decreases to 95%, the wear degree of the two easily worn points in the planetary gear does not reach the life prediction parameter of the planetary gear, that is, the wear condition of the planetary gear is good and it can continue to work in the gearbox to be optimized.

[0089] If 12.1μm is greater than the life prediction parameter of the planetary gear, it indicates that when the working efficiency of the gearbox to be optimized decreases to 95%, the wear of the two easily worn points of the planetary gear is too large, indicating that the wear state of the planetary gear is abnormal. Therefore, the planetary gear in the gearbox to be optimized should be replaced. After re-obtaining the easily worn points A1 and A2 of the planetary gear, the standard improved part of the planetary gear should be re-obtained in the machining process to achieve intelligent optimization of the parameters in the expedited process.

[0090] Example 2, please refer to Figure 4 As shown, Figure 4The example illustrates the structure of an electronic device, which may include a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a method for intelligent optimization of machining process parameters of wind turbine gearbox components are performed to achieve the following functions: First, the components with different service times in multiple wind turbine gearboxes are analyzed, and the analysis results are used to obtain the wear-prone points A1 and A2 for each component; based on the wear state of wear-prone points A1 and A2 in the component and the working efficiency of the wind turbine gearbox in which the component is located, the life determination parameters of the component are obtained; then, when the component is machined, the wear resistance of wear-prone points A1 and A2 is improved, and the life prediction parameters of the component are obtained based on the wear simulation of the component; finally, when the wind turbine gearbox is running, the components in the wind turbine gearbox are replaced based on the life prediction parameters of all components in the wind turbine gearbox, and the wear-prone points A1 and A2 of the replaced components are updated.

[0091] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0092] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by the computer, the computer can execute the intelligent optimization method for machining process parameters of wind turbine gearbox components provided by the above methods. The method includes: firstly, analyzing multiple components with different usage times in multiple wind turbine gearboxes, and obtaining the wear-prone points A1 and A2 corresponding to each component; based on the wear state of wear-prone points A1 and A2 in the component, and the working efficiency of the wind turbine gearbox where the component is located, obtaining the component's lifespan determination parameters; then, when machining the component, improving the wear resistance at wear-prone points A1 and A2, and obtaining the component's lifespan prediction parameters based on component wear simulation; finally, when the wind turbine gearbox is running, replacing the components in the wind turbine gearbox based on the lifespan prediction parameters of all components in the wind turbine gearbox, and updating the wear-prone points A1 and A2 of the replaced components.

[0093] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the above-mentioned intelligent optimization method for machining process parameters of wind turbine gearbox components to achieve the following functions: First, it analyzes multiple components with different service times within the wind turbine gearbox and obtains the wear-prone points A1 and A2 corresponding to each component based on the analysis results; based on the wear state of wear-prone points A1 and A2 within the component and the working efficiency of the wind turbine gearbox containing the component, it obtains the component's lifespan determination parameters; then, when machining the component, it improves the wear resistance of wear-prone points A1 and A2, and obtains the component's lifespan prediction parameters based on component wear simulation; finally, when the wind turbine gearbox is running, it replaces the components within the wind turbine gearbox based on the lifespan prediction parameters of all components within the wind turbine gearbox, and updates the wear-prone points A1 and A2 of the replaced components.

[0094] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0095] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for intelligent optimization of machining process parameters for wind turbine gearbox components, characterized in that, Includes the following steps: The components with different service times in multiple wind turbine gearboxes are analyzed, and the analysis results are used to obtain the wear-prone points A1 and A2 for each component. Based on the wear state of wear-prone points A1 and A2 in the component and the working efficiency of the wind turbine gearbox in which the component is located, the life determination parameters of the component are obtained. When machining parts, improve the wear resistance of wear-prone points A1 and A2, and obtain the life prediction parameters of parts based on wear simulation. When the wind turbine gearbox is running, the components inside the wind turbine gearbox are replaced based on the life prediction parameters of all components inside the wind turbine gearbox, and the wear-prone points A1 and A2 of the replaced components are updated based on the replaced components.

2. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 1, characterized in that, The analysis focused on components with varying service lives within multiple wind turbine gearboxes, and the results yielded wear-prone points A1 and A2 for each component. Obtain multiple wind turbine gearboxes in operation and label them all as gearboxes to be optimized; label all components inside the wind turbine gearboxes as internal components X. B1 To the internal components XB n By default, all components within the gearbox to be optimized are identical. For any component XB inside the box m Obtain the XB internal components of all gearboxes to be optimized. m The duration of use will be determined by the use of internal components XB. m The gearbox with the longest duration to be optimized is denoted as the wear analysis box, where m is a positive integer less than or equal to n and greater than or equal to 1; the internal components XB of the wear analysis box are... m Designated as internal component XB m Wear-out spare parts; Obtain the wear analysis box for all components inside the box, and obtain the wear-ready parts corresponding to each component inside the box.

3. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 2, characterized in that, The analysis included components with varying service lives within multiple wind turbine gearboxes, and the results yielded wear-prone points A1 and A2 for each component. Based on the latest input and output power of the gearbox to be optimized, the operating efficiency of all gearboxes to be optimized is obtained, and the gearbox with the lowest operating efficiency is denoted as the power analysis gearbox; for any component XB within the gearbox m The internal components XB of the power analysis box m Designated as internal component XB m Power standby components; The power availability of all components within the power analysis box is obtained.

4. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 3, characterized in that, The analysis included components with varying service lives within multiple wind turbine gearboxes, and the results yielded wear-prone points A1 and A2 for each component. For any component XB inside the box m : For the internal components XB of the box respectively m Wear analysis methods are used to analyze the wear-prone parts and power-prone parts. Based on the analysis results, wear points B1 and B2 corresponding to the wear-prone parts and power-prone parts are obtained. The surface roughness values ​​corresponding to the wear points B1 and B2 of the wear-to-use component are denoted as C1 and C2, respectively; the surface roughness values ​​corresponding to the wear points B1 and B2 of the power-to-use component are denoted as C3 and C4, respectively; the wear points corresponding to the two larger values ​​among C1 to C4 are denoted as the internal component XB. m The easily worn points A1 and A2 are identified, and the sum of the surface roughness values ​​of easily worn points A1 and A2 is denoted as XB of the internal component. m The rough judgment value.

5. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 4, characterized in that, Based on the wear state of wear points A1 and A2 within the component, and the operating efficiency of the wind turbine gearbox containing the component, the life determination parameters for the component are obtained as follows: When the location of easily worn point A1 or easily worn point A2 is the same as the location of the wear point B1 or wear point B2 of the wear-to-use part, the working efficiency of the wear-to-use part is recorded as XB of the internal component. m Wear life parameters; When the location of easily worn point A1 or easily worn point A2 is the same as the location of the wear point B1 or wear point B2 of the power-on-demand component, the working efficiency of the power-on-demand component is recorded as XB of the internal component. m Power life parameters; When the internal component XB m When only wear life parameters or power life parameters exist, the internal components XB m The wear life parameter or power life parameter is denoted as XB of the internal component. m Lifespan determination parameters; When the internal component XB m When both wear life parameters and power life parameters exist, the internal component XB m The average values ​​of the wear life parameters and power life parameters of the internal components are denoted as XB. m Lifespan determination parameters.

6. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 5, characterized in that, Wear analysis methods include: Based on the design drawings of the components, all surfaces of the components are sequentially designated as surface DB1 to surface DB2. q For any surface DB to be selected p Using a camera, the target surface DB in the unused parts is selected. p And the surface DB to be sampled in the component being analyzed. p Take photos and record the resulting images as the flawless surface image and the worn surface image, respectively, where p is a positive integer less than or equal to q and greater than or equal to 1; The flawless surface image and the worn surface image are converted to grayscale, and the grayscale images are then binarized. The two resulting images are denoted as the grayscale flawless image and the grayscale worn image, respectively.

7. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 6, characterized in that, Wear analysis methods also include: The grayscale flawless image and the grayscale wear image are overlaid, and AI is used to mark the different areas in the overlaid image as potential wear areas; the target surface DB in the component being analyzed is then selected. p Mark the wear candidate area inside, and uniformly obtain j points within the wear candidate area, which are recorded as roughness measurement points; A roughness meter was used to measure the roughness at all points, and the roughness with the largest value was recorded as the surface DB to be tested. p Surface roughness value; Obtain the surface roughness values ​​of all surfaces to be analyzed, and record the roughness measurement points corresponding to the two surface roughness values ​​with the larger values ​​as wear points B1 and B2 of the component to be analyzed.

8. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 7, characterized in that, When machining parts, improve the wear resistance at wear-prone points A1 and A2, and obtain the following life prediction parameters based on part wear simulation: When machining internal components within a gearbox to optimize it, for any given internal component XB m Based on existing processes, improve the internal components of the XB box. m The wear resistance of easily worn points A1 and A2 was determined, and the resulting internal component XB was tested. m Recorded as a wear-resistant improved part; Based on component wear simulation, a wear simulation of the wear-resistant improved part is performed using the gearbox to be optimized as the scenario. During the wear simulation, the working efficiency of the gearbox to be optimized is reduced from the standard efficiency to XB of the internal components. m The lifespan determination parameters are as follows, where the standard efficiency is the maximum operating efficiency of the gearbox to be optimized.

9. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 8, characterized in that, Based on component wear simulation, the life prediction parameters for components also include: After wear simulation, wear points B1 and B2 to be identified in the wear-resistant improved part are obtained based on wear analysis methods. The criteria for identification are: wear points B1 and B2 being identical to easily worn points A1 and A2, and the sum of the surface roughness values ​​corresponding to wear points B1 and B2 being less than XB of the internal component. m When determining the roughness value, the wear-resistant improved part is denoted as the internal component XB. m The standard improved part, and the sum of the surface roughness values ​​corresponding to the wear points B1 and B2 of the wear-resistant improved part is denoted as the internal part XB. m Lifetime prediction parameters; When the wear-resistant improved part is not recorded as an internal component XB m When obtaining the standard improved part, adjust the amount of increase in wear resistance for wear-prone points A1 and A2 when the wear-resistant improved part is obtained, and then obtain the wear-resistant improved part again until the internal component XB is obtained. m Standard improved parts.

10. The intelligent optimization method for machining process parameters of wind turbine gearbox components according to claim 9, characterized in that, When the wind turbine gearbox is in operation, based on the life prediction parameters of all components inside the gearbox, the components are replaced, and based on the replaced components, the wear-prone points A1 and A2 of the components are updated, including: When the gearbox to be optimized is running, all internal components of the gearbox to be optimized will be replaced with standard improved parts corresponding to the internal components. For any component XB inside the box m When the working efficiency of the gearbox to be optimized and the internal components XB m When the life determination parameters are equal, obtain the XB of the internal component of the gearbox to be optimized. m The wear degree of easily worn points A1 and A2 is determined, and the sum of the wear degrees of easily worn points A1 and A2 is recorded as the real-time judgment value. When the real-time judgment value is less than or equal to the internal component XB m When calculating the life prediction parameters, the internal components XB in the gearbox to be optimized are not considered. m Replacement is required when the real-time judgment value is greater than XB of the internal component. m When determining the life prediction parameters, the internal components XB in the gearbox to be optimized are... m Replace and re-acquire the internal components XB. m The easily worn points A1 and A2, and the internal component XB m Standard improved parts.

Images