A forging quality control method and system for a high-strength, high-inertia flexible flywheel

Abstract

The present invention relates to a forging quality control method and system of a high-strength large-inertia flexible flywheel, comprising first stamping the parts of the high-strength large-inertia flexible flywheel, then quenching and tempering the stamped parts, the quenching temperature is 800-850°C, the tempering temperature is 400-450°C, and the quenching and tempering heat treatment is performed before assembly, and the method also includes: M1. In the forging process of the high-strength large-inertia flexible flywheel, the forging process parameter data information and forging quality data information of the flexible flywheel are collected, and normalized to obtain the forging process parameter data information and forging quality data information of the processed flexible flywheel. The present invention not only controls and adjusts the forging process of the flexible flying disc in real time, improves the forging quality of the flexible flying disc, but also can adaptively adjust the forging process parameters of the flexible flying disc during the forging process, and improves the forging efficiency of the flexible flying disc.

Description

Technical Field

[0001] The invention relates to the technical field of forging a large-inertia flexible flywheel, and in particular to a forging quality control method and system for a high-strength large-inertia flexible flywheel. Background Art

[0002] Automation technology refers to the use of computers, robots and other advanced technologies to automate workflows and business processes. Automation technology has been widely used in various industries, and with the continuous development of science and technology, automation technology is also constantly improving and evolving. The rise of artificial intelligence and the integration of automation technology Artificial intelligence (AI) is currently one of the main drivers of automation technology. By using machine learning and deep learning algorithms, artificial intelligence can simulate and surpass human intelligence, thereby achieving a higher level of automation.

[0003] In the manufacturing industry, artificial intelligence can be used for autonomous learning and decision-making of robots. How to control and adjust the forging quality of high-strength and large-inertia flexible flywheels has become a problem that we urgently need to solve. Summary of the invention

[0004] In view of the above problems, the present invention provides a forging quality control method and system for a high-strength and large-inertia flexible flywheel, which not only performs real-time control and adjustment on the forging process of the flexible flying disc to improve the forging quality of the flexible flying disc, but also can adaptively adjust the forging process parameters of the flexible flying disc during the forging process to improve the forging efficiency of the flexible flying disc.

[0005] In order to achieve the above-mentioned purpose and other related purposes, the technical solution provided by the present invention is as follows:

[0006] A forging quality control method for a high-strength, high-inertia flexible flywheel comprises: first stamping the parts of the high-strength, high-inertia flexible flywheel, then quenching and tempering the stamped parts, the quenching temperature is 800-850°C, the tempering temperature is 400-450°C, and then assembling after the quenching and tempering heat treatment, the method also comprises:

[0007] M1. In the forging process of the high-strength and high-inertia flexible flywheel, the forging process parameter data information and forging quality data information of the flexible flywheel are collected and normalized to obtain the forging process parameter data information and forging quality data information of the processed flexible flywheel;

[0008] M2. Based on the forging process parameter data information and forging quality data information of the processed flexible flywheel, a flexible flywheel clustering model based on the Spearman rank correlation coefficient is constructed, and the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated to obtain the relationship matrix data information between the forging process parameters and the forging quality of the flexible flywheel;

[0009] M3. Based on the relationship matrix data information between the forging process parameters and forging quality of the flexible flywheel, the forging process parameters of the flexible flywheel are optimized by using an artificial bee colony optimization algorithm integrating multidimensional scaling analysis to obtain the optimized forging process parameter data information of the flexible flywheel;

[0010] M4. Based on the optimized forging process parameter data information of the flexible flywheel, a forging feasibility evaluation function P of the flexible flywheel is established to evaluate the feasibility of forging the flexible flywheel, and output the forging feasibility evaluation data information of the flexible flywheel.

[0011] Furthermore, in step M2, the construction of the flexible flywheel clustering model based on the Spearman rank correlation coefficient and the calculation of the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel include:

[0012] M21. Based on the forging process parameter data information and forging quality data information of the processed flexible flywheel, a function F of the Spearman rank correlation coefficient of the flexible flywheel is established.

[0013]

[0014] Among them, x i is the forging process parameter data information of the processed flexible flywheel, y i is the forging quality data information of the processed flexible flywheel, x 0 is the mean data information of the forging process parameters of the processed flexible flywheel, y 0 is the mean data information of the forging quality of the processed flexible flywheel, f is the rank function of the flexible flywheel forging process parameters, g is the rank function of the flexible flywheel forging quality, the Spearman rank correlation coefficient of the flexible flywheel forging process and quality is calculated, and the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality is obtained;

[0015] M22. Based on the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality, a cluster analysis function G of the forging process and quality of the flexible flywheel is constructed.

[0016]

[0017] Among them, z is the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality, α1 , α 2 and α 3 It is the determining factor of the relationship between the forging process and quality of the flexible flywheel;

[0018] M23. Based on the cluster analysis function G of the forging process and quality of the flexible flywheel, the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated to obtain the relationship matrix data information between the forging process parameters and the forging quality of the flexible flywheel.

[0019] Furthermore, the relationship between the flexible flywheel forging process and quality is determined by the factor α 1 , α 2 and α 3 The constraints are:

[0020]

[0021] Furthermore, the mean data information x of the forging process parameters of the processed flexible flywheel 0 for,

[0022]

[0023] Mean data information y of the forging quality of the treated flexible flywheel 0 for,

[0024]

[0025] The order function f of the flexible flywheel forging process parameters is:

[0026]

[0027] The order function g of the forging quality of the flexible flywheel is:

[0028]

[0029] Among them, μ i is the weight coefficient of the forging process parameters of the flexible flywheel, η i is the weight coefficient of the forging quality of the flexible flywheel, x i is the forging process parameter data information of the processed flexible flywheel, y i It is the forging quality data information of the processed flexible flywheel.

[0030] Furthermore, in step M3, the optimization of the forging process parameters of the flexible flywheel by using an artificial bee colony optimization algorithm integrated with multi-dimensional scaling analysis includes:

[0031] M31. Based on the relationship matrix data information of the forging process parameters and forging quality of the flexible flywheel, the artificial bee colony is initialized, the maximum number of iterations is determined, and the data information of the initialized artificial bee colony is obtained;

[0032] M32. Based on the data information of the initialized artificial bee colony, a multidimensional scaling analysis algorithm is used to perform dimensionality reduction processing on the data of the artificial bee colony to obtain the processed data information of the artificial bee colony;

[0033] M33. Based on the processed data information of the artificial bee colony, construct the individual fitness function S of the flexible flywheel artificial bee colony,

[0034]

[0035] Among them, a is the data information of the artificial bee colony after processing, ρ 1 , 2 and ρ 3 The fitness adjustment factor of the artificial bee colony is used to calculate the fitness value of the individuals in the artificial bee colony to obtain the fitness value data information of the individuals in the artificial bee colony;

[0036] M34. Based on the fitness value data information of the individuals of the artificial bee colony, establish the target optimization function R of the artificial bee colony,

[0037]

[0038] Among them, b is the fitness value data information of the individuals in the artificial bee colony, θ 1 ,θ 2 and θ 3 Taking the target optimization factor of the artificial bee colony as the target optimization factor, the forging process parameters of the flexible flywheel are optimized, and the optimized forging process parameter data information of the flexible flywheel is obtained.

[0039] Furthermore, in step M32, the dimensionality reduction processing of the artificial bee colony data using a multidimensional scaling analysis algorithm includes:

[0040] M321. Based on the data information of the initialized artificial bee colony, construct a similarity function W of the artificial bee colony,

[0041]

[0042] Among them, c is the data information of the initialized artificial bee colony, δ 1 and δ 2 is the gradient difference factor of the artificial bee colony, characterizes the similarity matrix of the artificial bee colony, and obtains the similarity matrix data information of the artificial bee colony;

[0043] M322. Based on the similarity matrix data information of the artificial bee colony, construct a dot matrix g of the low-dimensional space of the artificial bee colony,

[0044]

[0045] Among them, h is the similarity matrix data information of the artificial bee colony;

[0046] M323. Based on the lattice g of the low-dimensional space of the artificial bee colony, perform dimensionality reduction processing on the data of the artificial bee colony to obtain data information of the processed artificial bee colony.

[0047] Furthermore, the fitness adjustment factor ρ of the artificial bee colony 1 , 2 and ρ 3 The constraints are:

[0048]

[0049] The target optimization factor θ of the artificial bee colony 1 ,θ 2 and θ 3 The constraint function H is,

[0050]

[0051] The value range of H is (1,2).

[0052] Furthermore, the forging feasibility evaluation function P of the flexible flywheel is:

[0053]

[0054] Among them, r is the optimized forging process parameter data information of the flexible flywheel, γ 1 , γ 2 and γ 3 It is an adaptive feedback adjustment factor of the flexible flywheel, and a preset threshold is set. If the forging feasibility evaluation data information of the flexible flywheel is greater than the preset threshold, the forging requirements are met; if the forging feasibility evaluation data information of the flexible flywheel is less than the preset threshold, the forging requirements are not met.

[0055] Furthermore, the adaptive feedback adjustment factor γ of the flexible flywheel 1 , γ 2 and γ 3 The constraints are:

[0056]

[0057] In order to achieve the above-mentioned objectives and other related objectives, the present invention also provides a forging quality control system for a high-strength, large-inertia flexible flywheel, comprising a computer device programmed or configured to execute any one of the steps of the forging quality control method for a high-strength, large-inertia flexible flywheel.

[0058] The present invention has the following positive effects:

[0059] 1. The present invention constructs a flexible flywheel clustering model based on the Spearman rank correlation coefficient, calculates the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel, and optimizes the forging process parameters of the flexible flywheel in combination with an artificial bee colony optimization algorithm that integrates multidimensional scaling analysis. It not only controls and adjusts the forging process of the flexible flying disc in real time to improve the forging quality of the flexible flying disc, but also can adaptively adjust the forging process parameters of the flexible flying disc during the forging process to improve the forging efficiency of the flexible flying disc.

[0060] 2. The present invention establishes a forging feasibility evaluation function P of the flexible flywheel to accurately evaluate the forging quality of the flexible flywheel, thereby reducing the defective rate of the flexible flywheel. At the same time, it can reduce manual participation, thereby improving work efficiency and productivity and reducing labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0062] Figure 2 A schematic diagram of a process for constructing a flexible flywheel clustering model based on the Spearman rank correlation coefficient according to the present invention;

[0063] Figure 3 It is a flow chart of the artificial bee colony optimization algorithm using fusion multidimensional scaling analysis of the present invention;

[0064] Figure 4 It is a schematic diagram of the flow of the multidimensional scaling analysis algorithm of the present invention;

[0065] Figure 5 It is a structural schematic diagram of a flexible flywheel with large inertia according to the present invention;

[0066] Figure 6 It is a schematic diagram of the detection line structure of the large inertia flexible flywheel of the present invention.

[0067] Explanation of the numbers in the figure: 1-connecting plate, 2-flexible disk, 3-starting gear ring, 4-flywheel detection equipment, 5-flywheel conveyor line. DETAILED DESCRIPTION

[0068] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0069] Example 1: Figure 1 or Figure 5 As shown, a forging quality control method for a high-strength, high-inertia flexible flywheel comprises stamping the parts of the high-strength, high-inertia flexible flywheel first, and then quenching and tempering the stamped parts, the quenching temperature is 800-850°C, the tempering temperature is 400-450°C, and the quenching and tempering heat treatments are followed by assembly, the connecting plates 1 are evenly distributed on the edge of the flexible disk 2, the connecting plates 1 and the starting gear ring 3 are welded into an integrated structure, the flywheel is placed on a flywheel conveyor line 5, and is tested by a flywheel testing device 4, and the method further comprises:

[0070] M1. In the forging process of the high-strength and high-inertia flexible flywheel, the forging process parameter data information and forging quality data information of the flexible flywheel are collected and normalized to obtain the forging process parameter data information and forging quality data information of the processed flexible flywheel;

[0071] M2. Based on the forging process parameter data information and forging quality data information of the processed flexible flywheel, a flexible flywheel clustering model based on the Spearman rank correlation coefficient is constructed, and the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated to obtain the relationship matrix data information between the forging process parameters and the forging quality of the flexible flywheel;

[0072] M3. Based on the relationship matrix data information between the forging process parameters and forging quality of the flexible flywheel, the forging process parameters of the flexible flywheel are optimized by using an artificial bee colony optimization algorithm integrating multidimensional scaling analysis to obtain the optimized forging process parameter data information of the flexible flywheel;

[0073] M4. Based on the optimized forging process parameter data information of the flexible flywheel, a forging feasibility evaluation function P of the flexible flywheel is established to evaluate the feasibility of forging the flexible flywheel, and output the forging feasibility evaluation data information of the flexible flywheel.

[0074] In this embodiment, if Figure 2 As shown, in step M2, the flexible flywheel clustering model based on the Spearman rank correlation coefficient is constructed, and the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated, including:

[0075] M21. Based on the forging process parameter data information and forging quality data information of the processed flexible flywheel, a function F of the Spearman rank correlation coefficient of the flexible flywheel is established.

[0076]

[0077] Among them, x i is the forging process parameter data information of the processed flexible flywheel, y i is the forging quality data information of the processed flexible flywheel, x 0 is the mean data information of the forging process parameters of the processed flexible flywheel, y 0 is the mean data information of the forging quality of the processed flexible flywheel, f is the rank function of the flexible flywheel forging process parameters, g is the rank function of the flexible flywheel forging quality, the Spearman rank correlation coefficient of the flexible flywheel forging process and quality is calculated, and the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality is obtained;

[0078] M22. Based on the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality, a cluster analysis function G of the forging process and quality of the flexible flywheel is constructed.

[0079]

[0080] Among them, z is the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality, α 1 , α 2 and α 3 It is the determining factor of the relationship between the forging process and quality of the flexible flywheel;

[0081] M23. Based on the cluster analysis function G of the forging process and quality of the flexible flywheel, the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated to obtain the relationship matrix data information between the forging process parameters and the forging quality of the flexible flywheel.

[0082] In this embodiment, the relationship between the flexible flywheel forging process and quality is determined by the factor α 1 , α 2 and α 3 The constraints are:

[0083]

[0084] In this embodiment, the mean data information x of the forging process parameters of the processed flexible flywheel 0 for,

[0085]

[0086] The mean data information y0 of the forging quality of the processed flexible flywheel is,

[0087]

[0088] The order function f of the flexible flywheel forging process parameters is:

[0089]

[0090] The order function g of the forging quality of the flexible flywheel is:

[0091]

[0092] Among them, μ i is the weight coefficient of the forging process parameters of the flexible flywheel, η i is the weight coefficient of the forging quality of the flexible flywheel, x i is the forging process parameter data information of the processed flexible flywheel, y i It is the forging quality data information of the processed flexible flywheel.

[0093] Embodiment 2: Based on the processing quality control method of a high-strength and large-inertia flexible flywheel in Embodiment 1, the present invention is further illustrated and described below.

[0094] like Figure 1 or Figure 5 As shown, a forging quality control method for a high-strength, large-inertia flexible flywheel comprises stamping the parts of the high-strength, large-inertia flexible flywheel first, and then quenching and tempering the stamped parts, the quenching temperature is 800-850°C, the tempering temperature is 400-450°C, and the quenching and tempering heat treatment is followed by assembly, the connecting plates 1 are evenly distributed on the edge of the flexible disk 2, the connecting plates 1 and the starting gear ring 3 are welded into an integrated structure, the flywheel is placed on a flywheel conveyor line 5, and is tested by a flywheel testing device 4, and the method further comprises:

[0095] M1. In the forging process of the high-strength and high-inertia flexible flywheel, the forging process parameter data information and forging quality data information of the flexible flywheel are collected and normalized to obtain the forging process parameter data information and forging quality data information of the processed flexible flywheel;

[0096] M2. Based on the forging process parameter data information and forging quality data information of the processed flexible flywheel, a flexible flywheel clustering model based on the Spearman rank correlation coefficient is constructed, and the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated to obtain the relationship matrix data information between the forging process parameters and the forging quality of the flexible flywheel;

[0097] M3. Based on the relationship matrix data information between the forging process parameters and forging quality of the flexible flywheel, the forging process parameters of the flexible flywheel are optimized by using an artificial bee colony optimization algorithm integrating multidimensional scaling analysis to obtain the optimized forging process parameter data information of the flexible flywheel;

[0098] M4. Based on the optimized forging process parameter data information of the flexible flywheel, a forging feasibility evaluation function P of the flexible flywheel is established to evaluate the feasibility of forging the flexible flywheel, and output the forging feasibility evaluation data information of the flexible flywheel.

[0099] In this embodiment, if Figure 3 As shown, in step M3, the optimization of the forging process parameters of the flexible flywheel by using the artificial bee colony optimization algorithm integrated with multi-dimensional scaling analysis includes:

[0100] M31. Based on the relationship matrix data information of the forging process parameters and forging quality of the flexible flywheel, the artificial bee colony is initialized, the maximum number of iterations is determined, and the data information of the initialized artificial bee colony is obtained;

[0101] M32. Based on the data information of the initialized artificial bee colony, a multidimensional scaling analysis algorithm is used to perform dimensionality reduction processing on the data of the artificial bee colony to obtain the processed data information of the artificial bee colony;

[0102] M33. Based on the processed data information of the artificial bee colony, construct the individual fitness function S of the flexible flywheel artificial bee colony,

[0103]

[0104] Among them, a is the data information of the artificial bee colony after processing, ρ 1 , 2 and ρ 3 The fitness adjustment factor of the artificial bee colony is used to calculate the fitness value of the individuals in the artificial bee colony to obtain the fitness value data information of the individuals in the artificial bee colony;

[0105] M34. Based on the fitness value data information of the individuals of the artificial bee colony, establish the target optimization function R of the artificial bee colony,

[0106]

[0107] Among them, b is the fitness value data information of the individuals in the artificial bee colony, θ 1 ,θ 2 and θ 3 Taking the target optimization factor of the artificial bee colony as the target optimization factor, the forging process parameters of the flexible flywheel are optimized, and the optimized forging process parameter data information of the flexible flywheel is obtained.

[0108] In this embodiment, if Figure 4 As shown, in step M32, the use of a multidimensional scaling analysis algorithm to perform dimensionality reduction processing on the data of the artificial bee colony includes:

[0109] M321. Based on the data information of the initialized artificial bee colony, construct a similarity function W of the artificial bee colony,

[0110]

[0111] Among them, c is the data information of the initialized artificial bee colony, δ 1 and δ 2 is the gradient difference factor of the artificial bee colony, characterizes the similarity matrix of the artificial bee colony, and obtains the similarity matrix data information of the artificial bee colony;

[0112] M322. Based on the similarity matrix data information of the artificial bee colony, construct a dot matrix g of the low-dimensional space of the artificial bee colony,

[0113]

[0114] Among them, h is the similarity matrix data information of the artificial bee colony;

[0115] M323. Based on the lattice g of the low-dimensional space of the artificial bee colony, perform dimensionality reduction processing on the data of the artificial bee colony to obtain data information of the processed artificial bee colony.

[0116] In this embodiment, the fitness adjustment factor ρ of the artificial bee colony is 1 , 2 and ρ 3 The constraints are:

[0117]

[0118] The target optimization factor θ of the artificial bee colony 1 ,θ 2 and θ 3 The constraint function H is,

[0119]

[0120] The value range of H is (1,2).

[0121] In this embodiment, the forging feasibility evaluation function P of the flexible flywheel is:

[0122]

[0123] Among them, r is the optimized forging process parameter data information of the flexible flywheel, γ 1 , γ2 and γ 3 It is an adaptive feedback adjustment factor of the flexible flywheel, and a preset threshold is set. If the forging feasibility evaluation data information of the flexible flywheel is greater than the preset threshold, the forging requirements are met; if the forging feasibility evaluation data information of the flexible flywheel is less than the preset threshold, the forging requirements are not met.

[0124] In this embodiment, the adaptive feedback adjustment factor γ of the flexible flywheel 1 , γ 2 and γ 3 The constraints are:

[0125]

[0126] In this embodiment, the present invention provides a forging quality control system for a high-strength, high-inertia flexible flywheel, comprising a computer device programmed or configured to execute any one of the steps of the forging quality control method for a high-strength, high-inertia flexible flywheel.

[0127] In this embodiment, the present invention provides a computer-readable storage medium storing a computer program programmed or configured to execute any one of the improved methods for controlling forging quality of a high-strength, large-inertia flexible flywheel.

[0128] Any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0129] In summary, the present invention not only controls and adjusts the forging process of the flexible flying disc in real time to improve the forging quality of the flexible flying disc, but also can adaptively adjust the forging process parameters of the flexible flying disc during the forging process to improve the forging efficiency of the flexible flying disc.

[0130] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A forging quality control method for a high-strength, high-inertia flexible flywheel, comprising stamping the parts of the high-strength, high-inertia flexible flywheel, and then quenching and tempering the stamped parts, the quenching temperature is 800-850°C, the tempering temperature is 400-450°C, and the quenching and tempering heat treatment is followed by assembly, characterized in that: The method further comprises: M1. In the forging process of the high-strength and high-inertia flexible flywheel, the forging process parameter data information and forging quality data information of the flexible flywheel are collected and normalized to obtain the forging process parameter data information and forging quality data information of the processed flexible flywheel; M2. Based on the forging process parameter data information and forging quality data information of the processed flexible flywheel, a flexible flywheel clustering model based on the Spearman rank correlation coefficient is constructed, and the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated to obtain the relationship matrix data information between the forging process parameters and the forging quality of the flexible flywheel; M3. Based on the relationship matrix data information between the forging process parameters and forging quality of the flexible flywheel, the forging process parameters of the flexible flywheel are optimized by using an artificial bee colony optimization algorithm integrating multidimensional scaling analysis to obtain the optimized forging process parameter data information of the flexible flywheel; M4. Based on the optimized forging process parameter data information of the flexible flywheel, a forging feasibility evaluation function P of the flexible flywheel is established to evaluate the feasibility of forging the flexible flywheel, and output the forging feasibility evaluation data information of the flexible flywheel.

2. According to the forging quality control method of a high-strength and large-inertia flexible flywheel according to claim 1, in step M2, constructing a flexible flywheel clustering model based on the Spearman rank correlation coefficient and calculating the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel comprises: M21. Based on the forging process parameter data information and forging quality data information of the processed flexible flywheel, a function F of the Spearman rank correlation coefficient of the flexible flywheel is established. Among them, x i is the forging process parameter data information of the processed flexible flywheel, y i is the forging quality data information of the processed flexible flywheel, x0 is the mean data information of the forging process parameters of the processed flexible flywheel, y0 is the mean data information of the forging quality of the processed flexible flywheel, f is the rank function of the forging process parameters of the flexible flywheel, g is the rank function of the forging quality of the flexible flywheel, the Spearman rank correlation coefficient of the forging process and quality of the flexible flywheel is calculated, and the Spearman rank correlation coefficient data information of the forging process and quality of the flexible flywheel is obtained; M22. Based on the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality, a cluster analysis function G of the forging process and quality of the flexible flywheel is constructed. Among them, z is the Spearman rank correlation coefficient data information of the flexible flywheel forging process and quality, α1, α2 and α3 are the relationship determining factors between the flexible flywheel forging process and quality; M23. Based on the cluster analysis function G of the forging process and quality of the flexible flywheel, the relationship matrix between the forging process parameters and the forging quality of the flexible flywheel is calculated to obtain the relationship matrix data information between the forging process parameters and the forging quality of the flexible flywheel.

3. The forging quality control method of a high-strength, large-inertia flexible flywheel according to claim 2 is characterized in that: The constraints of the factors α1, α2 and α3 determining the relationship between the flexible flywheel forging process and quality are:

4. The forging quality control method of a high-strength, large-inertia flexible flywheel according to claim 2 is characterized in that: The mean data information x0 of the forging process parameters of the processed flexible flywheel is, The mean data information y0 of the forging quality of the processed flexible flywheel is, The order function f of the flexible flywheel forging process parameters is: The order function g of the forging quality of the flexible flywheel is: Among them, μ i is the weight coefficient of the forging process parameters of the flexible flywheel, η i is the weight coefficient of the forging quality of the flexible flywheel, x i is the forging process parameter data information of the processed flexible flywheel, y i It is the forging quality data information of the processed flexible flywheel.

5. The forging quality control method of a high-strength and large-inertia flexible flywheel according to claim 1 is characterized in that: In step M3, the optimization of the forging process parameters of the flexible flywheel by using an artificial bee colony optimization algorithm integrated with multidimensional scaling analysis includes: M31. Based on the relationship matrix data information of the forging process parameters and forging quality of the flexible flywheel, the artificial bee colony is initialized, the maximum number of iterations is determined, and the data information of the initialized artificial bee colony is obtained; M32. Based on the data information of the initialized artificial bee colony, a multidimensional scaling analysis algorithm is used to perform dimensionality reduction processing on the data of the artificial bee colony to obtain the processed data information of the artificial bee colony; M33. Based on the processed data information of the artificial bee colony, construct the individual fitness function S of the flexible flywheel artificial bee colony, Among them, a is the data information of the artificial bee colony after processing, ρ1, ρ2 and ρ3 are the fitness adjustment factors of the artificial bee colony, and the fitness values ​​of the individuals of the artificial bee colony are calculated to obtain the fitness value data information of the individuals of the artificial bee colony; M34. Based on the fitness value data information of the individuals of the artificial bee colony, establish the target optimization function R of the artificial bee colony, Among them, b is the fitness value data information of the individuals in the artificial bee colony, θ1, θ2 and θ3 are the target optimization factors of the artificial bee colony, and the forging process parameters of the flexible flywheel are optimized to obtain the optimized forging process parameter data information of the flexible flywheel.

6. The forging quality control method of a high-strength and high-inertia flexible flywheel according to claim 5 is characterized in that: In step M32, the dimensionality reduction processing of the artificial bee colony data using a multidimensional scaling analysis algorithm includes: M321. Based on the data information of the initialized artificial bee colony, construct a similarity function W of the artificial bee colony, Among them, c is the data information of the initialized artificial bee colony, δ1 and δ2 are the gradient difference factors of the artificial bee colony, and the similarity matrix of the artificial bee colony is characterized to obtain the similarity matrix data information of the artificial bee colony; M322. Based on the similarity matrix data information of the artificial bee colony, construct a dot matrix g of the low-dimensional space of the artificial bee colony, Among them, h is the similarity matrix data information of the artificial bee colony; M323. Based on the lattice g of the low-dimensional space of the artificial bee colony, perform dimensionality reduction processing on the data of the artificial bee colony to obtain data information of the processed artificial bee colony.

7. The forging quality control method of a high-strength and large-inertia flexible flywheel according to claim 5, characterized in that: The constraints of the fitness adjustment factors ρ1, ρ2 and ρ3 of the artificial bee colony are: The constraint function H of the target optimization factors θ1, θ2 and θ3 of the artificial bee colony is, The value range of H is (1,2).

8. The forging quality control method of a high-strength and large-inertia flexible flywheel according to claim 1 is characterized in that: The forging feasibility evaluation function P of the flexible flywheel is: Among them, r is the optimized forging process parameter data information of the flexible flywheel, γ1, γ2 and γ3 are the adaptive feedback adjustment factors of the flexible flywheel, and a preset threshold is set. If the forging feasibility evaluation data information of the flexible flywheel is greater than the preset threshold, the forging requirements are met; if the forging feasibility evaluation data information of the flexible flywheel is less than the preset threshold, the forging requirements are not met.

9. The forging quality control method of a high-strength, large-inertia flexible flywheel according to claim 8, characterized in that: The constraints of the adaptive feedback adjustment factors γ1, γ2 and γ3 of the flexible flywheel are:

10. A forging quality control system for a high-strength, large-inertia flexible flywheel, comprising a computer device, characterized in that: The computer device is programmed or configured to execute the steps of the forging quality control method for a high-strength and large-inertia flexible flywheel as claimed in any one of claims 1 to 9.

Images