Method and system for optimizing manufacturing process of wind turbine gear

Abstract

The invention provides a wind turbine gear manufacturing process optimization method and system, and relates to the technical field of data processing, and the method comprises the steps: synchronizing K groups of gear performance information to a performance deviation analysis module to obtain a plurality of groups of gears with the same performance and a plurality of gear processing raw materials; performing group division on the K groups of gear parameter information according to multiple groups of same-performance gears to obtain multiple groups of gear specification information; and according to the multiple sets of gear specification information and the multiple standard material specification information, optimizing milling is carried out, multiple sets of plate milling strategies are obtained, and batch milling manufacturing of K functional gears is carried out. The technical problems that in the prior art, wind turbine gears are generally machined in a batch machining mode that gears with the same design parameters are machined on blanks, machining raw materials are wasted, and the production cost is high are solved. The technical effects that multi-specification-parameter gear adaptive machining of the blank is carried out based on the wind power case gear composition, waste of machining raw materials is reduced, and meanwhile the production cost is reduced are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for optimizing the manufacturing process of a wind turbine gear. Background Art

[0002] Under traditional processing methods, gear manufacturing companies usually purchase a large number of gear blanks of the same specifications, and then cut them into the required size and shape during the processing. This method improves production efficiency to a certain extent, but there is also obvious waste of raw materials, because a large number of blanks may not be fully utilized after processing, resulting in waste of resources and unnecessary additional costs, which not only affects the sustainable economy of the company, but also has a negative effect on the environment.

[0003] In summary, the prior art generally processes wind turbine gears by batch processing gears with the same design parameters on blanks, which results in a waste of processing raw materials and a high production cost. Summary of the invention

[0004] The present application provides a method and system for optimizing the manufacturing process of wind turbine gears, which is used to solve the technical problem that the prior art generally uses a batch processing method for wind turbine gears with the same design parameters on blanks to process the gears, which causes waste of processing raw materials and leads to high production costs.

[0005] In view of the above problems, the present application provides a method and system for optimizing the manufacturing process of wind turbine gears.

[0006] The first aspect of the present application provides a method for optimizing the manufacturing process of wind turbine gears, the method comprising: interactively obtaining target design information of a wind turbine gearbox, wherein the target design information comprises K groups of gear parameter information and K groups of gear performance information, the K groups of gear parameter information and the K groups of gear performance information are based on an association mapping of K functional gears, K being a positive integer; pre-building a performance deviation analysis module; synchronizing the K groups of gear performance information to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance; calling processing raw materials according to the multiple groups of gears with the same performance to obtain multiple gear processing raw materials; interactively obtaining multiple standard material specification information of the multiple gear processing raw materials; dividing the K groups of gear parameter information into groups according to the multiple groups of gears with the same performance to obtain multiple groups of gear specification information; performing optimal milling according to the multiple groups of gear specification information and the multiple standard material specification information to obtain multiple groups of plate milling strategies; and adopting the multiple groups of plate milling strategies to perform batch milling manufacturing of the K functional gears.

[0007] The second aspect of the present application provides a manufacturing process optimization system for wind turbine gears, the system comprising: a design information interaction unit, used to interactively obtain target design information of a wind turbine gearbox, wherein the target design information comprises K groups of gear parameter information and K groups of gear performance information, the K groups of gear parameter information and the K groups of gear performance information are based on K functional gear association mappings, K is a positive integer; an analysis module construction unit, used to pre-construct a performance deviation analysis module; a performance deviation analysis unit, used to synchronize the K groups of gear performance information to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance. Gears; a processing raw material calling unit, used to call processing raw materials according to the multiple groups of gears with the same performance, and obtain multiple gear processing raw materials; a specification information calling unit, used to interactively obtain multiple standard material specification information of the multiple gear processing raw materials; a gear specification calling unit, used to group the K groups of gear parameter information according to the multiple groups of gears with the same performance, and obtain multiple groups of gear specification information; a milling strategy optimization unit, used to perform optimal milling according to the multiple groups of gear specification information and the multiple standard material specification information, and obtain multiple groups of plate milling strategies; a batch milling execution unit, used to adopt the multiple groups of plate milling strategies to perform batch milling process processing of the K functional gears.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: The method provided in the embodiment of the present application obtains target design information of a wind turbine gearbox through interaction, wherein the target design information includes K groups of gear parameter information and K groups of gear performance information, and the K groups of gear parameter information and the K groups of gear performance information are based on K functional gear association mappings, where K is a positive integer; a performance deviation analysis module is pre-constructed; the K groups of gear performance information are synchronized to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance; the processing raw materials are called according to the multiple groups of gears with the same performance to obtain multiple gear processing raw materials; multiple standard material specification information of the multiple gear processing raw materials is interactively obtained; the K groups of gear parameter information are grouped according to the multiple groups of gears with the same performance to obtain multiple groups of gear specification information; optimal milling is performed according to the multiple groups of gear specification information and the multiple standard material specification information to obtain multiple groups of plate milling strategies; and the multiple groups of plate milling strategies are adopted to perform batch milling manufacturing of the K functional gears. The technical effect of carrying out gear adaptation processing of multiple specifications and parameters of blanks based on the gear structure of the wind turbine box is achieved, which reduces the waste of processing raw materials and reduces production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1A schematic diagram of the process flow of the wind turbine gear manufacturing process optimization method provided in this application; Figure 2 A schematic diagram of the process of obtaining gear specification information in the method for optimizing the manufacturing process of wind turbine gears provided in this application; Figure 3 A schematic diagram of the structure of the wind turbine gear manufacturing process optimization system provided in this application.

[0010] Explanation of the accompanying drawings: design information interaction unit 1, analysis module construction unit 2, performance deviation analysis unit 3, processing raw material calling unit 4, specification information calling unit 5, gear specification calling unit 6, milling strategy optimization unit 7, batch milling execution unit 8. DETAILED DESCRIPTION

[0011] The present application provides a method and system for optimizing the manufacturing process of wind turbine gears, which is used to solve the technical problem that the prior art generally uses batch processing of gears with the same design parameters on the blank for wind turbine gears, which causes waste of processing materials and leads to high production costs. The invention achieves the technical effect of adapting the processing of multi-specification parameter gears of the blank based on the gear structure of the wind turbine box, reducing the waste of processing materials and reducing production costs.

[0012] The acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with relevant regulations.

[0013] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them. Example

[0014] like Figure 1 As shown, the present application provides a method for optimizing the manufacturing process of a wind turbine gear, the method comprising: A100: interactively obtaining target design information of a wind turbine gearbox, wherein the target design information includes K groups of gear parameter information and K groups of gear performance information, and the K groups of gear parameter information and the K groups of gear performance information are based on K functional gear association mappings, where K is a positive integer; Specifically, in this embodiment, the wind turbine gearbox is a plurality of types of wind turbine gearboxes currently produced by manufacturers, based on which there are a plurality of types of gears in the plurality of types of wind turbine gearboxes.

[0015] Based on this, this embodiment interactively obtains design parameter information of various models of wind turbine gearboxes currently in production, and splits the obtained design parameters according to the gear monomer design parameters to obtain the target design information, wherein the target design information includes K groups of gear parameter information and K groups of gear performance information of K functional gears, wherein the gear parameter information includes but is not limited to the module, the number of teeth, and the pitch circle diameter, and the gear performance information includes i performance parameters corresponding to i performance indicators, and exemplarily, the gear performance indicators include performance indicators such as density, cutting performance, thermal stability, fatigue life and strength.

[0016] The gear performance information can be used as a screening constraint to select gear blanks with matching performance information and thickness specifications from existing gear blanks, and then process corresponding functional gears in combination with the gear parameter information.

[0017] A200: Pre-built performance deviation analysis module; In one embodiment, a performance deviation analysis module is pre-built, and step A200 of the method provided in the present application further includes: A210: The performance deviation analysis module includes a performance similarity analyzer and a performance deviation summarizer; A220: Pre-construct a similarity analysis calculation formula, which is as follows: ; in, is the similarity index of the two sets of gear performance information, The first Item performance parameter value, For similar gear performance information Item performance parameter value, is the total number of gear performance indicators, and the gear performance indicators of standard gear performance information and similar gear performance information are consistent; A230: construct the performance similarity analyzer based on the KNN model, and synchronize the similarity analysis calculation formula to the performance similarity analyzer; A240: preset a performance deviation summary threshold, and synchronize the performance deviation summary threshold to the performance deviation summarizer.

[0018] Specifically, in this embodiment, the performance deviation analysis module is used to quickly, accurately and scientifically calculate the similarity of the two functional gears under the condition of obtaining the gear performance information of the two functional gears, so as to determine whether the two functional gears can be processed with the same gear blank.

[0019] The performance deviation analysis module includes a performance similarity analyzer and a performance deviation summarizer. The performance similarity analyzer is used to perform similarity calculations on two functional gears. The performance deviation summarizer is a data comparison engine that can perform data comparisons based on predefined parameters. In this embodiment, the performance deviation summary threshold is used as a predefined parameter to set the comparison benchmark of the data comparison engine (performance deviation summarizer) so that the performance deviation summarizer can be used to determine whether two functional gears can be processed using the same gear blank based on the calculation results of the performance similarity analyzer.

[0020] A similarity analysis calculation formula is pre-built, and the similarity analysis calculation formula is as follows: ; in, is the similarity index of the two sets of gear performance information, The first Item performance parameter value, For similar gear performance information Item performance parameter value, is the total number of gear performance indicators, and the gear performance indicators of standard gear performance information and similar gear performance information are consistent; The performance similarity analyzer is constructed based on the KNN model, and the similarity analysis calculation formula is synchronized to the performance similarity analyzer.

[0021] A performance deviation summary threshold is preset. When the performance similarity indexes of two or more functional gears are at the same performance deviation summary threshold, it is considered that the two or more functional gears can be processed using gear blanks of the same specifications. In this embodiment, the performance deviation summary threshold is synchronized to the performance deviation summarizer.

[0022] This embodiment constructs a performance deviation analysis module to provide an effective processing method for subsequent scientific judgment of the performance design similarity of functional gears and grouping functional gears based on performance design.

[0023] A300: Synchronizing the K groups of gear performance information to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance; In one embodiment, the performance information of the K groups of gears is synchronized to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance. The method step A300 provided in the present application also includes: A310: randomly selecting based on the K groups of gear performance information to obtain the standard gear performance information; A320: constructing K-1 groups of performance deviation data sets based on K-1 groups of gear performance information and the standard gear performance information, and synchronizing them one by one to the performance similarity analyzer of the performance deviation analysis module to perform performance deviation analysis, and obtaining K-1 performance deviation indexes; A330: defining the standard performance deviation index of the standard gear performance information as 1, and synchronizing the standard performance deviation index and the K-1 performance deviation indexes to the performance deviation summarizer for serialization processing to obtain a performance deviation sequence; A340: calling the performance deviation summary threshold to perform data classification of the performance deviation sequence to obtain the multiple groups of gears with the same performance; A350: Summarize the K groups of gear performance information based on the multiple groups of gears with the same performance to obtain multiple groups of parameter information with the same performance.

[0024] Specifically, in this embodiment, a group of gear performance information is randomly selected from the K groups of gear performance information as the standard gear performance information, and the K functional gears are classified by judging the similarity between the remaining K-1 groups of gear performance information and the standard gear performance information.

[0025] Specifically, this embodiment constructs K-1 groups of performance deviation data sets based on K-1 groups of gear performance information and the standard gear performance information, and each group of performance deviation data sets includes standard gear performance information and a group of gear performance information.

[0026] K-1 groups of performance deviation data groups are synchronized one by one to the performance similarity analyzer of the performance deviation analysis module to perform performance deviation analysis to obtain K-1 performance deviation indexes.

[0027] The standard performance deviation index of the standard gear performance information is defined as 1, and the standard performance deviation index and the K-1 performance deviation indices are synchronized to the performance deviation inductor. First, the serialization process is completed by sorting the performance deviation indices from large to small to obtain a performance deviation sequence. In the performance deviation sequence, the functional gear corresponding to the performance deviation data group whose performance deviation index is closer to 1 is closer to the performance requirement of the gear blank for the functional gear corresponding to the standard gear performance information.

[0028] The performance deviation summary threshold is used as a grading threshold to obtain multi-level performance deviations, and the interval distance between two adjacent levels of performance deviations is the performance deviation summary threshold.

[0029] Based on the obtained multi-level performance deviations, intuitive data grading of the performance deviation sequence is performed to obtain the multiple groups of gears with the same performance. It should be understood that the gear performance information of several functional gears in each group of gears with the same performance is similar, and gear blanks with the same performance information can be used for gear processing, that is, the processing of these several functional gears is carried out on the same gear blank.

[0030] This embodiment performs mapping and summarizing of the K groups of gear performance information based on the multiple groups of gears with the same performance to obtain multiple groups of parameter information with the same performance. This embodiment classifies functional gears based on the similarity of gear performance information, and obtains multiple groups of gear performance information of each group of functional gears with similar performance, providing a high-availability reference for subsequent gear blank selection and calling.

[0031] A400: calling processing raw materials according to the plurality of groups of gears with the same performance to obtain a plurality of gear processing raw materials; In one embodiment, the processing raw materials are called according to the plurality of groups of gears with the same performance to obtain a plurality of gear processing raw materials. The method step A400 provided in the present application further includes: A410: Based on the standard gear performance information, the performance index is called to obtain Gear performance indicators; A420: obtaining a first set of same performance parameter information from the multiple sets of same performance parameter information; A430: Based on The gear performance index is used to split and reorganize the first group of performance parameter information to obtain Group performance parameters; A440: The performance parameters of the group are called to obtain the performance extreme value. Performance extremes; A450: pre-building a processing raw material information database, wherein the processing raw material information database stores multiple sets of sample processing raw materials, sample performance index sets, and sample material specifications; A460: The processing material information library is traversed by using the performance extreme value as the screening constraint to obtain a first gear processing material, wherein each performance index in the sample performance index set of the first gear processing material is better than the Performance extremes; A470: And so on, to obtain the various gear processing raw materials mentioned above.

[0032] Specifically, in this embodiment, the performance index is called based on the standard gear performance information to obtain multiple performance indexes constituting the standard gear performance information, totaling Gear performance indicators.

[0033] A first group of same performance parameter information is obtained by calling the multiple groups of same performance parameter information, wherein the first group of same performance parameter information specifically includes G groups of same performance parameter information of G functional gears.

[0034] Based on the The gear performance index is used to split and reorganize the first group of performance parameter information to obtain The performance parameter indicators of each group of performance parameters are consistent, and each group of performance parameters is G. The group performance parameters are serialized from large to small to call the performance extreme value (maximum value) and obtain An extreme performance value.

[0035] The processed raw material is the gear blank, and each sample processed raw material has a corresponding sample performance index set including i performance parameters and a sample material specification characterizing the size of the unused gear blank steel plate.

[0036] A plurality of sets of sample processing raw materials - sample performance indicator sets - sample material specifications are obtained, and the obtained data are stored in a pre-built processing raw material information library for storage management.

[0037] As mentioned The processing material information library is traversed by using the performance extreme value as the screening constraint to obtain a first gear processing material, wherein each performance index in the sample performance index set of the first gear processing material is only slightly The performance extreme value is obtained by analogy, and the various gear processing raw materials are obtained.

[0038] This embodiment achieves the technical effect of obtaining a variety of gear processing raw materials suitable for the production of multiple groups of gears with the same performance by performing gear analysis with similar performance, and achieves the technical effect of reducing the number of gear ingredient types required for gear processing, reducing the complexity of production and processing, and reducing the dependence of gear blank selection on manual experience.

[0039] A500: interactively obtaining multiple standard material specification information of the multiple gear processing raw materials; Specifically, in this embodiment, the gear processing raw material is the gear blank, and the standard material specification information is the length and width parameters of a complete regular quadrilateral gear blank. To facilitate mass production, gear blanks often have standardized length and width parameters. Therefore, this embodiment directly interacts with gear blank manufacturers or the Internet to obtain a variety of sample material specifications of a variety of sample processing raw materials, and then after obtaining the various gear processing raw materials, the various standard material specification information is obtained by mapping and calling the processing raw material information library.

[0040] A600: Divide the K groups of gear parameter information into groups according to the multiple groups of gears with the same performance, and obtain multiple groups of gear specification information; In one embodiment, Figure 2 As shown, the K groups of gear parameter information are divided into groups according to the multiple groups of gears with the same performance to obtain multiple groups of gear specification information. The method step A600 provided in the present application also includes: A610: Based on the K groups of gear parameter information, a production log is called to obtain K groups of historical milling allowance constraint sets, wherein each group of historical milling constraints has historical milling efficiency and historical milling scrap rate identifiers; A620: preset milling weight configuration, wherein the milling weight configuration includes a milling efficiency weight and a scrap rate weight; A630: performing weighted calculation on the K groups of historical milling allowance constraint sets based on the milling weight configuration to obtain K groups of historical milling coefficient sets; A640: Serialize the K groups of historical milling coefficient sets and perform extreme value calls to obtain K extreme values ​​of milling allowances; A650: Use the K milling allowance extreme values ​​to map and replace the multiple sets of gear specification information to obtain multiple sets of gear allowance parameters.

[0041] Specifically, in this embodiment, the milling allowance is the diameter parameter of the gear disc steel plate of the most basic initial shape when manufacturing the gear cut out from the gear stock at the beginning of functional gear processing. The milling allowance is larger than the outer diameter of the functional gear actually processed.

[0042] It should be understood that the larger the milling allowance, the greater the tolerance for errors in the gear machining process. At the same time, the gear machining efficiency and machining costs also increase.

[0043] Based on this, this embodiment calls the gear production log of the same design parameters according to the K groups of gear parameter information to obtain K groups of historical milling allowance constraint sets, and each group of historical milling constraints includes multiple gear historical milling allowances. It should be understood that in this embodiment, the milling allowance is the diameter parameter of the gear disk steel plate of the most basic initial shape when manufacturing the gear cut from the gear blank at the beginning of functional gear processing. Each gear historical milling allowance has a historical milling efficiency and a historical milling scrap rate identifier, and the milling scrap rate is the production control situation of the gear under different milling allowances.

[0044] The milling weight configuration is preset, and the milling weight configuration includes a milling efficiency weight and a scrap rate weight. This embodiment does not limit the specific weight assignment. In actual applications, the numerical value setting can be focused on the user's production of finished products and production efficiency requirements.

[0045] Based on the milling weight configuration, the K groups of historical milling allowance constraint sets are weightedly calculated to obtain K groups of historical milling coefficient sets, wherein each group of historical milling coefficient sets includes multiple historical milling coefficients, and the multiple historical milling coefficients correspond to the multiple gear historical milling allowances in the previous evaluation. The K groups of historical milling coefficient sets are serialized and extreme value calls are performed to obtain K milling allowance extreme values, and the milling allowance extreme value is the optimal solution for the gear milling diameter that balances the gear processing scrap rate and the production speed.

[0046] The K milling allowance extreme values ​​are used to map and replace the multiple sets of gear specification information to obtain multiple sets of gear allowance parameters, each set of gear allowance parameters is multiple gear disc diameter information of a circular pancake-shaped gear disc obtained by milling multiple functional gears that are processed with the same gear blank.

[0047] This embodiment achieves the technical effect of obtaining multiple sets of gear allowances with balanced production efficiency and production quality control by performing gear plate allowance analysis, thereby providing a reference for generating cutting strategies for subsequent gear blank cutting process steps.

[0048] A700: performing optimal milling according to the multiple sets of gear specification information and the multiple sets of standard material specification information to obtain multiple sets of plate milling strategies; In one embodiment, optimal milling is performed according to the multiple sets of gear specification information and the multiple standard material specification information to obtain multiple sets of plate milling strategies. The method step A700 provided in the present application also includes: A710: mapping and calling a first set of gear margin parameters and first standard material specification information from the plurality of sets of gear margin parameters and the plurality of standard material specification information, wherein the first set of gear margin parameters is mapped to M functional gears, where M is a positive integer less than K; A720: Perform two-dimensional modeling based on the first set of gear margin parameters and the first standard material specifications to obtain M first gear models and a first standard blank model; A730: interactively obtain M gear processing benefits of the M functional gears; A740: Taking the M first gear models as optimization benchmarks and the M gear processing benefits as milling strategy evaluation benchmarks, performing optimization milling on the first standard blank model to obtain a first plate milling strategy; A750: And so on, to obtain the multiple sets of plate milling strategies.

[0049] In one embodiment, the M first gear models are used as optimization benchmarks, the M gear processing benefits are used as milling strategy evaluation benchmarks, and optimization milling is performed on the first standard blank model to obtain a first plate milling strategy. The method step A740 provided in the present application also includes: A741: Sequencing the M first gear models according to the M gear processing benefits to obtain a first gear sequence; A742: obtaining a first benefit gear based on the first gear sequence call; A743: performing drop fitting filling of the M first gear models and the first benefit gear with the first standard blank model as a constraint to obtain a first filling result; A744: obtaining a second benefit gear based on the first gear sequence call; A745: using the second benefit gear to traverse the first filling result to obtain a second filling result; A746: And so on, until the Mth benefit gear of the first gear sequence is used to traverse the M-1th filling result to obtain the first plate milling strategy, wherein the first plate milling strategy includes M groups of milling circle center coordinates.

[0050] Specifically, in this embodiment, since the plate milling strategy method for obtaining the gear blank of any group of gears with the same performance among multiple groups of gears with the same performance is consistent, this embodiment calls the first group of gear margin parameters and the first standard material specification information from the multiple groups of gear margin parameters and the multiple standard material specification information mappings, and the first group of gear margin parameters is mapped to M functional gears, where M is a positive integer less than K.

[0051] Taking the analysis and determination of the first sheet metal milling strategy based on the first set of gear allowance parameters and the first standard material specification information as an example, detailed parameters of the sheet metal milling strategy generation method are performed.

[0052] Two-dimensional modeling is performed based on the first set of gear margin parameters and the first standard material specifications to obtain M first gear models with different gear plate diameters and a first standard blank model.

[0053] The M gear processing benefits of the M functional gears are interactively obtained, and the gear processing benefit is the sales unit price of a single gear.

[0054] The M first gear models are serialized according to the M gear processing benefits to obtain a first gear sequence, and a first benefit gear is obtained based on the first gear sequence. The first benefit gear is the functional gear with the greatest economic value.

[0055] In the constrained size range of the first standard blank model, the M first gear models are first filled in. The M first gear models are in unspecified positions in the first standard blank model. Based on software simulation, the first standard blank model space is made vertical. The M first gear models naturally fall to the bottom of the first standard blank model, and then the gear models corresponding to an unspecified number of first benefit gears are filled into the first standard blank model. Through the falling simulation, the space of each gear model in the first standard blank model is continuously displaced and compressed until the gear model of the first benefit gear can no longer be placed, thereby obtaining the first filling result.

[0056] The same drop fitting method is used to obtain the second benefit gear based on the first gear sequence call; the second benefit gear is used to traverse the first filling result to fill the second benefit gear that meets the remaining plate area required for filling, and obtain the second filling result. And so on, until the Mth benefit gear of the first gear sequence is used to traverse the M-1th filling result, and the first plate milling strategy is obtained. The first plate milling strategy includes M groups of milling circle center coordinates, each group of milling circle center coordinates is a plurality of gear disk circle center coordinates when a functional gear is milling a gear disk, and so on, the plurality of groups of plate milling strategies are obtained.

[0057] This embodiment adopts drop fitting to generate a gear disc milling plan with the maximum economic benefit on the surface of a gear blank, thereby achieving the technical effect of improving the utilization rate of the milling plan for the gear blank.

[0058] A800: Adopt the multiple sets of plate milling strategies to perform batch milling process of the K functional gears.

[0059] Specifically, in this embodiment, after the gear blank is positioned and clamped, the corresponding plate milling strategy among the multiple groups of plate milling strategies is used to locate the milling circle center, and the corresponding gear disc milling allowance is used to perform milling processing on the gear blank, and the gear discs obtained by processing the K functional gears are classified for batch processing in the subsequent refined processing process.

[0060] This implementation achieves the technical effect of performing multi-specification parameter gear adaptation processing on the blank based on the gear structure of the wind turbine box, while reducing the waste of processing raw materials and lowering the production cost.

[0061] Embodiment 2 Based on the same inventive concept as the method for optimizing the manufacturing process of wind turbine gears in the aforementioned embodiment, Figure 3 As shown, the present application provides a manufacturing process optimization system for wind turbine gears, wherein the system comprises: A design information interaction unit 1, used for interactively obtaining target design information of a wind turbine gearbox, wherein the target design information includes K groups of gear parameter information and K groups of gear performance information, and the K groups of gear parameter information and the K groups of gear performance information are based on K functional gear association mappings, where K is a positive integer; An analysis module construction unit 2, used for pre-constructing a performance deviation analysis module; The performance deviation analysis unit 3 is used to synchronize the performance information of the K groups of gears to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears and obtain multiple groups of gears with the same performance; A processing raw material calling unit 4 is used to call processing raw materials according to the plurality of groups of gears with the same performance, and obtain a plurality of gear processing raw materials; A specification information calling unit 5, used for interactively obtaining a plurality of standard material specification information of the plurality of gear processing raw materials; A gear specification calling unit 6 is used to divide the K groups of gear parameter information into groups according to the multiple groups of gears with the same performance, so as to obtain multiple groups of gear specification information; A milling strategy optimization unit 7, used for performing milling optimization according to the multiple sets of gear specification information and the multiple sets of standard material specification information to obtain multiple sets of plate milling strategies; The batch milling execution unit 8 is used to adopt the multiple sets of plate milling strategies to perform batch milling process processing on the K functional gears.

[0062] In one embodiment, the analysis module construction unit 2 further includes: The performance deviation analysis module includes a performance similarity analyzer and a performance deviation summarizer; A similarity analysis calculation formula is pre-built, and the similarity analysis calculation formula is as follows: ; in, is the similarity index of the two sets of gear performance information, The first Item performance parameter value, For similar gear performance information Item performance parameter value, is the total number of gear performance indicators, and the gear performance indicators of standard gear performance information and similar gear performance information are consistent; Constructing the performance similarity analyzer based on the KNN model, and synchronizing the similarity analysis calculation formula to the performance similarity analyzer; A performance deviation summary threshold is preset, and the performance deviation summary threshold is synchronized to the performance deviation summarizer.

[0063] In one embodiment, the performance deviation analysis unit 3 further includes: Randomly select based on the K groups of gear performance information to obtain the standard gear performance information; Constructing K-1 groups of performance deviation data sets based on K-1 groups of gear performance information and the standard gear performance information, and synchronizing them one by one to the performance similarity analyzer of the performance deviation analysis module to perform performance deviation analysis, and obtaining K-1 performance deviation indexes; The standard performance deviation index of the standard gear performance information is defined as 1, and the standard performance deviation index and the K-1 performance deviation indexes are synchronized to the performance deviation summarizer for serialization processing to obtain a performance deviation sequence; Calling the performance deviation summary threshold to perform data classification of the performance deviation sequence to obtain the multiple groups of gears with the same performance; The performance information of the K groups of gears with the same performance is summarized and processed according to the multiple groups of gears with the same performance to obtain multiple groups of parameter information with the same performance.

[0064] In one embodiment, the processing raw material calling unit 4 further includes: Based on the standard gear performance information, the performance index is called to obtain Gear performance indicators; Obtaining a first set of same performance parameter information from the plurality of sets of same performance parameter information; Based on the The gear performance index is used to split and reorganize the first group of performance parameter information to obtain Group performance parameters; Regarding the The performance parameters of the group are called to obtain the performance extreme value. Performance extremes; Pre-constructing a processing raw material information database, wherein the processing raw material information database stores multiple sets of sample processing raw materials - sample performance indicator sets - sample material specifications; As mentioned The processing material information library is traversed by using the performance extreme value as the screening constraint to obtain a first gear processing material, wherein each performance index in the sample performance index set of the first gear processing material is better than the Performance extremes; And so on, the various gear processing raw materials are obtained.

[0065] In one embodiment, the gear specification calling unit 5 further includes: Based on the K groups of gear parameter information, a production log is called to obtain K groups of historical milling allowance constraint sets, wherein each group of historical milling constraints has historical milling efficiency and historical milling scrap rate identifiers; Preset milling weight configuration, wherein the milling weight configuration includes a milling efficiency weight and a scrap rate weight; Performing weighted calculation on the K groups of historical milling allowance constraint sets based on the milling weight configuration to obtain K groups of historical milling coefficient sets; Serializing the K groups of historical milling coefficient sets and performing extreme value calls to obtain K extreme values ​​of milling allowances; The K milling allowance extreme values ​​are used to map and replace the multiple sets of gear specification information to obtain multiple sets of gear allowance parameters.

[0066] In one embodiment, the milling strategy optimization unit 6 further includes: Mapping and calling a first set of gear margin parameters and first standard material specification information from the plurality of sets of gear margin parameters and the plurality of standard material specification information, wherein the first set of gear margin parameters is mapped to M functional gears, where M is a positive integer less than K; Perform two-dimensional modeling based on the first set of gear margin parameters and the first standard material specification to obtain M first gear models and a first standard blank model; Interactively obtaining M gear processing benefits of the M functional gears; Taking the M first gear models as optimization benchmarks and the M gear processing benefits as milling strategy evaluation benchmarks, performing optimization milling on the first standard blank model to obtain a first plate milling strategy; By analogy, the multiple sets of plate milling strategies are obtained.

[0067] In one embodiment, the milling strategy optimization unit 6 further includes: Sequencing the M first gear models according to the M gear processing benefits to obtain a first gear sequence; Obtaining a first benefit gear based on the first gear sequence call; Performing drop fitting filling of the M first gear models and the first benefit gear with the first standard blank model as a constraint to obtain a first filling result; Obtaining a second benefit gear based on the first gear sequence call; Using the second benefit gear to traverse the first filling result to obtain a second filling result; And so on, until the M-th benefit gear of the first gear sequence is used to traverse the M-1th filling result, the first plate milling strategy is obtained, wherein the first plate milling strategy includes M groups of milling circle center coordinates.

[0068] Any of the methods or steps described above may be stored as computer instructions or programs in various types of computer memories, and the computer instructions or programs may be recognized by various types of computer processors to implement any of the methods or steps described above.

[0069] Based on the above specific embodiments of the present invention, any improvements and modifications made to the present invention by those skilled in the art without departing from the principles of the present invention shall fall within the patent protection scope of the present invention.

Claims

1. A method for optimizing the manufacturing process of wind turbine gears, characterized in that: The method comprises: Interactively obtain target design information of a wind turbine gearbox, wherein the target design information includes K groups of gear parameter information and K groups of gear performance information, and the K groups of gear parameter information and the K groups of gear performance information are based on K functional gear association mappings, where K is a positive integer; Pre-built performance deviation analysis module; Synchronizing the K groups of gear performance information to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance; Calling processing raw materials according to the plurality of groups of gears with the same performance to obtain a variety of gear processing raw materials; Interactively obtain multiple standard material specification information of the multiple gear processing raw materials; Divide the K groups of gear parameter information into groups according to the multiple groups of gears with the same performance, and obtain multiple groups of gear specification information; Perform optimal milling according to the multiple sets of gear specification information and the multiple sets of standard material specification information to obtain multiple sets of plate milling strategies; The multiple sets of plate milling strategies are used to perform batch milling process processing on the K functional gears.

2. The method according to claim 1, characterized in that A performance deviation analysis module is pre-built, and the method further comprises: The performance deviation analysis module includes a performance similarity analyzer and a performance deviation summarizer; A similarity analysis calculation formula is pre-built, and the similarity analysis calculation formula is as follows: ; in, is the similarity index of the two sets of gear performance information, The first Item performance parameter value, For similar gear performance information Item performance parameter value, is the total number of gear performance indicators, and the gear performance indicators of standard gear performance information and similar gear performance information are consistent; Constructing the performance similarity analyzer based on the KNN model, and synchronizing the similarity analysis calculation formula to the performance similarity analyzer; A performance deviation summary threshold is preset, and the performance deviation summary threshold is synchronized to the performance deviation summarizer.

3. The method according to claim 2, characterized in that The performance information of the K groups of gears is synchronized to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance. The method further includes: Randomly select based on the K groups of gear performance information to obtain the standard gear performance information; Constructing K-1 groups of performance deviation data sets based on K-1 groups of gear performance information and the standard gear performance information, and synchronizing them one by one to the performance similarity analyzer of the performance deviation analysis module to perform performance deviation analysis, and obtaining K-1 performance deviation indexes; The standard performance deviation index of the standard gear performance information is defined as 1, and the standard performance deviation index and the K-1 performance deviation indexes are synchronized to the performance deviation summarizer for serialization processing to obtain a performance deviation sequence; Calling the performance deviation summary threshold to perform data classification of the performance deviation sequence to obtain the multiple groups of gears with the same performance; The performance information of the K groups of gears with the same performance is summarized and processed according to the multiple groups of gears with the same performance to obtain multiple groups of parameter information with the same performance.

4. The method according to claim 3, characterized in that The raw materials for processing are called according to the plurality of groups of gears with the same performance to obtain a plurality of raw materials for gear processing, and the method further comprises: Based on the standard gear performance information, the performance index is called to obtain Gear performance indicators; Obtaining a first set of same performance parameter information from the plurality of sets of same performance parameter information; Based on the The gear performance index is used to split and reorganize the first group of performance parameter information to obtain Group performance parameters; Regarding the The performance parameters of the group are called to obtain the performance extreme value. Performance extremes; Pre-constructing a processing raw material information database, wherein the processing raw material information database stores multiple sets of sample processing raw materials - sample performance indicator sets - sample material specifications; As mentioned The processing material information library is traversed by using the performance extreme value as the screening constraint to obtain a first gear processing material, wherein each performance index in the sample performance index set of the first gear processing material is better than the Performance extremes; And so on, the various gear processing raw materials are obtained.

5. The method according to claim 1, characterized in that The K groups of gear parameter information are divided into groups according to the multiple groups of gears with the same performance to obtain multiple groups of gear specification information. The method further includes: Based on the K groups of gear parameter information, a production log is called to obtain K groups of historical milling allowance constraint sets, wherein each group of historical milling constraints has historical milling efficiency and historical milling scrap rate identifiers; Preset milling weight configuration, wherein the milling weight configuration includes a milling efficiency weight and a scrap rate weight; Performing weighted calculation on the K groups of historical milling allowance constraint sets based on the milling weight configuration to obtain K groups of historical milling coefficient sets; Serializing the K groups of historical milling coefficient sets and performing extreme value calls to obtain K extreme values ​​of milling allowances; The K milling allowance extreme values ​​are used to map and replace the multiple sets of gear specification information to obtain multiple sets of gear allowance parameters.

6. The method according to claim 5, characterized in that Optimal milling is performed according to the multiple sets of gear specification information and the multiple standard material specification information to obtain multiple sets of plate milling strategies, and the method further includes: Mapping and calling a first set of gear margin parameters and first standard material specification information from the plurality of sets of gear margin parameters and the plurality of standard material specification information, wherein the first set of gear margin parameters is mapped to M functional gears, where M is a positive integer less than K; Perform two-dimensional modeling based on the first set of gear margin parameters and the first standard material specification to obtain M first gear models and a first standard blank model; Interactively obtaining M gear processing benefits of the M functional gears; Taking the M first gear models as optimization benchmarks and the M gear processing benefits as milling strategy evaluation benchmarks, performing optimization milling on the first standard blank model to obtain a first plate milling strategy; By analogy, the multiple sets of plate milling strategies are obtained.

7. The method according to claim 6, characterized in that Taking the M first gear models as optimization benchmarks, taking the M gear processing benefits as milling strategy evaluation benchmarks, performing optimization milling on the first standard blank model to obtain a first plate milling strategy, the method further includes: Sequencing the M first gear models according to the M gear processing benefits to obtain a first gear sequence; Obtaining a first benefit gear based on the first gear sequence call; Performing drop fitting filling of the M first gear models and the first benefit gear with the first standard blank model as a constraint to obtain a first filling result; Obtaining a second benefit gear based on the first gear sequence call; Using the second benefit gear to traverse the first filling result to obtain a second filling result; And so on, until the M-th benefit gear of the first gear sequence is used to traverse the M-1th filling result, the first plate milling strategy is obtained, wherein the first plate milling strategy includes M groups of milling circle center coordinates.

8. The manufacturing process optimization system for wind turbine gears is characterized by: The system comprises: A design information interaction unit, used for interactively obtaining target design information of a wind turbine gearbox, wherein the target design information includes K groups of gear parameter information and K groups of gear performance information, and the K groups of gear parameter information and the K groups of gear performance information are based on K functional gear association mappings, where K is a positive integer; An analysis module building unit, used to pre-build a performance deviation analysis module; A performance deviation analysis unit, used for synchronizing the performance information of the K groups of gears to the performance deviation analysis module for performance deviation analysis, so as to divide the processing raw materials of the K functional gears to obtain multiple groups of gears with the same performance; A processing raw material calling unit, used to call processing raw materials according to the plurality of groups of gears with the same performance, and obtain a variety of gear processing raw materials; A specification information calling unit, used for interactively obtaining a plurality of standard material specification information of the plurality of gear processing raw materials; A gear specification calling unit, used for dividing the K groups of gear parameter information into groups according to the multiple groups of gears with the same performance, and obtaining multiple groups of gear specification information; A milling strategy optimization unit, used to perform milling optimization according to the multiple sets of gear specification information and the multiple sets of standard material specification information to obtain multiple sets of plate milling strategies; The batch milling execution unit is used to adopt the multiple sets of plate milling strategies to perform batch milling process processing on the K functional gears.

Images