Method and system for optimizing grinding and polishing process parameters of train axle
By optimizing the grinding and polishing process parameters of train axles through grey correlation analysis and the CRITIC objective weighting method, and combining it with robotic automatic grinding and polishing integrated equipment, the problem of difficult control of grinding and polishing quality was solved, the surface roughness and material removal depth were optimized, and the grinding and polishing quality and efficiency were improved.
Patent Information
- Application Number
- CN202510927898.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-04
- Publication Date
- 2025-10-10
AI Technical Summary
In the existing technology, the grinding and polishing quality is difficult to control and various processing requirements are difficult to meet. Especially in the grinding and polishing process of train axles, it is difficult to optimize the surface roughness and material removal depth at the same time.
The grey correlation analysis method and CRITIC objective weighting method are used, combined with robotic automatic grinding and polishing integrated equipment, to optimize the grinding and polishing process parameters. By combining the grinding head mesh size, feed speed, spindle speed and grinding and polishing force, multi-objective optimization of surface roughness and material removal depth is achieved.
It achieves efficient and low-loss grinding and polishing of train axle surface roughness within a specific range, improves grinding and polishing quality and processing efficiency, and reduces labor intensity and dust impact.
Smart Images
Figure CN120755738A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of process optimization, and provides a train axle grinding and polishing process parameter optimization method and system. BACKGROUND
[0002] The axle of a high-speed train is an important component for bearing the weight and load of the train body, and its reliability directly relates to the driving safety of the train. During the assembly of the axle, the axle shoulder and the locomotive hub are matched with each other, so that the axle shoulder is repeatedly stressed and stress concentration exists, and the burrs on the outer surface of the axle affect the assembly performance of the axle. Therefore, grinding and polishing is a key process in the production line of the axle, and the grinding and polishing quality directly affects the fatigue characteristics of the axle. Therefore, in view of the problems of difficult control of grinding and polishing quality and difficult satisfaction of various processing requirements, it is urgent to develop a grinding and polishing process parameter optimization method for the axle of a train. SUMMARY
[0003] The present application provides a train axle grinding and polishing process parameter optimization method and system to solve the defects of difficult control of grinding and polishing quality and difficult satisfaction of various processing requirements in the prior art. The present application can achieve that the axle reaches a specific surface roughness range while reducing the material removal depth, and has important guiding significance and practical application value for high-quality, efficient and low-loss grinding and polishing of the surface of the axle.
[0004] The present application provides a train axle grinding and polishing process parameter optimization method, which comprises: determining a multi-objective optimization system of grinding and polishing process parameters of a train axle; the multi-objective optimization system is obtained by combining multiple grinding and polishing process parameters, so that the multi-optimization target of the axle grinding and polishing satisfies the comprehensive processing target; the multi-optimization target of the axle grinding and polishing comprises the surface roughness and the material removal depth of the axle grinding and polishing; based on the multi-objective optimization system, a gray correlation analysis method is used to analyze the gray correlation degree between the grinding and polishing process parameter combination and the multi-optimization target of the axle grinding and polishing; the weight of the multi-optimization target of the axle grinding and polishing is determined; and the grinding and polishing process parameter combination optimization result of the train axle is determined according to the weight and the gray correlation analysis result.
[0005] According to the train axle grinding and polishing process parameter optimization method provided by the present application, the grinding and polishing test is performed by using an axle robot automatic grinding and polishing integrated equipment.
[0006] According to the train axle grinding and polishing process parameter optimization method provided by the present application, the grinding and polishing process parameters comprise the grinding head pitch, the feed speed, the spindle speed and the grinding and polishing force; and the target range of the surface roughness of the axle grinding and polishing is 0.2-0.4 μm.
[0007] According to the train axle polishing process parameter optimization method provided by the application, before the sampling gray correlation analysis method is used to analyze the gray correlation degree between the polishing process parameter combination and the train axle polishing multi-optimization target based on the multi-objective optimization system, the target data of the train axle polishing multi-optimization target is subjected to dimensionless processing to obtain dimensionless data, and the gray correlation degree is analyzed according to the dimensionless data.
[0008] According to the train axle polishing process parameter optimization method provided by the application, the gray correlation degree between the polishing process parameter combination and the train axle polishing multi-optimization target is analyzed based on the multi-objective optimization system and the sampling gray correlation analysis method, and the method comprises the following steps.
[0009] According to the train axle polishing process parameter optimization method provided by the application, the weight of the train axle polishing multi-optimization target is determined, and the method comprises the following steps.
[0010] The application further provides a train axle polishing process parameter optimization system, which comprises the following modules.
[0011] The application further provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor.
[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for optimizing the grinding and polishing process parameters of a train axle as described in any one of the above is implemented.
[0013] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described methods for optimizing grinding and polishing process parameters of a train axle.
[0014] The present invention provides a method and system for optimizing the grinding and polishing process parameters of a train axle. The method includes: determining a multi-objective optimization system for the grinding and polishing process parameters of the train axle; the multi-objective optimization system is to combine multiple grinding and polishing process parameters so that the multiple optimization targets of axle grinding and polishing meet the comprehensive processing target; the multiple optimization targets of axle grinding and polishing include the surface roughness and material removal depth of axle grinding and polishing; based on the multi-objective optimization system, a sampling grayscale correlation analysis method is used to analyze the grayscale correlation between the grinding and polishing process parameter combination and the multiple optimization targets of axle grinding and polishing; the weights of the multiple optimization targets of axle grinding and polishing are determined; and based on the weights and grayscale correlation analysis results, the optimization results of the grinding and polishing process parameter combination of the train axle are determined. The present invention can achieve a specific surface roughness range for the axle while reducing the material removal depth, and has important guiding significance and practical application value for high-quality, high-efficiency and low-loss grinding and polishing of the axle surface. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0016] Figure 1 It is a flow chart of the method for optimizing the grinding and polishing process parameters of a train axle provided by the present invention.
[0017] Figure 2 This is one of the specific flow diagrams of the method for optimizing the grinding and polishing process parameters of a train axle provided by the present invention.
[0018] Figure 3 It is a structural schematic diagram of the axle robot automatic grinding and polishing integrated equipment provided by the present invention.
[0019] Figure 4 This is the second specific flow diagram of the method for optimizing the grinding and polishing process parameters of a train axle provided by the present invention.
[0020] Figure 5 It is a schematic diagram of a multi-objective optimization system for the grinding and polishing process parameters of a train axle provided by the present invention.
[0021] Figure 6 It is a flow chart of determining the weights of multiple optimization objectives for axle grinding and polishing provided by the present invention.
[0022] Figure 7 It is a structural schematic diagram of the grinding and polishing process parameter optimization system for train axles provided by the present invention.
[0023] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION
[0024] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.
[0025] In the production of high-speed and subway trains, axle quality directly impacts train safety and reliability. Axles are key components of train bogies, bearing not only the weight of the vehicle but also various dynamic loads during operation. Therefore, improving axle surface quality and fatigue strength is a crucial task in the manufacturing process. Grinding, as the final step in axle machining, has a direct impact on axle surface roughness and material removal depth.
[0026] Please refer to Figure 1 , Figure 1 A schematic flow chart of the method for optimizing the grinding and polishing process parameters of a train axle provided by the present invention.
[0027] Please refer to Figure 2 , Figure 2 This is one of the specific flow diagrams of the method for optimizing the grinding and polishing process parameters of a train axle provided by the present invention.
[0028] The present invention provides a method for optimizing grinding and polishing process parameters of a train axle, comprising: 101: A multi-objective optimization system for determining the grinding and polishing process parameters for train axles. The multi-objective optimization system combines multiple grinding and polishing process parameters to ensure that the multiple optimization objectives for axle grinding and polishing meet the overall processing objectives. The multiple optimization objectives for axle grinding and polishing include surface roughness and material removal depth. 102: Based on the multi-objective optimization system, the sampling gray correlation analysis method is used to analyze the gray correlation between the grinding and polishing process parameter combination and the multi-optimization objectives of axle grinding and polishing; 103: Determine the weights of multiple optimization objectives for axle grinding and polishing; 104: Based on the weight and grayscale correlation analysis results, determine the optimization results of the grinding and polishing process parameters combination of the train axle.
[0029] Industrial robots have high processing efficiency, large workspace, good accessibility, and strong versatility. Integrating robot grinding and polishing equipment into the axle full-automatic production line is an effective solution for automatic grinding and polishing of train axles. Train axle grinding and polishing requires removing surface processing texture and residual defects, strictly controlling the grinding and polishing surface roughness, and reducing the grinding and polishing material removal depth, while improving the material removal uniformity. The selection of train axle robot grinding and polishing process parameters will directly affect the surface roughness and material removal depth results, therefore, in view of the problems of difficult control of grinding and polishing quality and difficult satisfaction of various processing requirements, the present application provides a grinding and polishing process parameter optimization method for train axles, based on the self-built EA4T axle robot automatic grinding and polishing integrated equipment, the grey correlation analysis method is used for multi-objective optimization of EA4T axle grinding and polishing process parameters, and then the optimal process parameter combination of EA4T axle robot grinding and polishing is obtained. First, the EA4T axle robot grinding and polishing orthogonal test is carried out, and the grinding and polishing allowable parameter range is determined according to the test results; secondly, the multi-objective optimization system of EA4T axle grinding and polishing process parameters is determined, the target data of the axle grinding and polishing multi-optimization target is dimensionless processed and the grey correlation coefficient is calculated; finally, according to the weighted (weight of the axle grinding and polishing multi-optimization target) result of the grey correlation coefficient, the process parameters corresponding to the maximum grey correlation degree are output as the optimal grinding and polishing process parameter combination of the EA4T axle, so that the axle grinding and polishing multi-optimization target meets the comprehensive processing target (termination condition). The optimization method has the characteristics of strong universality, simple calculation process, high reliability, etc., and the EA4T axle can achieve a specific surface roughness range while reducing the material removal depth by using the method, which has important guiding significance and practical application value for high-quality, high-efficiency and low-loss grinding and polishing of the EA4T axle surface.
[0030] Of course, in addition to the existing surface roughness and material removal depth, other optimization targets such as grinding efficiency, grinding tool wear rate, and processing energy consumption can also be introduced. A multi-objective comprehensive optimization system is formed, and the balance between multiple targets is realized through weight distribution or multi-objective optimization algorithm (such as Pareto optimization).
[0031] The influence of grinding process on the surface roughness and material removal depth of train axles is a complex and important problem. Through in-depth research and continuous optimization, the present application can provide higher quality and more reliable axles for high-speed trains and subway trains, and contribute to the development of railway transportation.
[0032] As a preferred embodiment, the method uses axle robot automatic grinding and polishing integrated equipment for grinding and polishing test.
[0033] Please refer to Figure 3 , Figure 3 The structure diagram of the axle robot automatic grinding and polishing integrated equipment provided by the present application.
[0034] In this embodiment, an EA4T axle robot automatic grinding and polishing integrated equipment is developed by integrating modules such as axle clamping, constant force control, trajectory planning, automatic tool changing, and comprehensive control. The Taguchi method is used to design a four-factor, four-level orthogonal test for the EA4T axle robot grinding and polishing. The EA4T axle robot automatic grinding and polishing integrated equipment consists of a robot 1, a base 2, a constant force controller 3, a spindle motor 4, a grinding head 5, a tool changer 6, a clamping fixture 7, and a control system 8. The EA4T axle A is clamped at both ends and stably supported at the lower end by the clamping fixture 7. The robot 1 is mounted on the base 2. The constant force controller 3 and the spindle motor 4 are fixed together at the end of the sixth axis of the robot 1. The rotation of the spindle motor 4 drives the grinding head 5 to rotate at high speed, realizing the full-surface grinding and polishing of the EA4T axle A. The control system 8 is used to implement grinding and polishing trajectory planning and processing program execution, and control the grinding head 5 to automatically change operations at the tool changer 6.
[0035] Please refer to Figure 4 , Figure 4 This is the second specific flow diagram of the method for optimizing the grinding and polishing process parameters of a train axle provided by the present invention.
[0036] Please refer to Figure 5 , Figure 5 Schematic diagram of the multi-objective optimization system for the grinding and polishing process parameters of train axles provided by the present invention.
[0037] As a preferred embodiment, the grinding and polishing process parameters include grinding head grit, feed speed, spindle speed and grinding and polishing force; the target range of the surface roughness of the axle grinding and polishing is 0.2-0.4 μm.
[0038] Grinding process is a key link in the manufacturing process, and the selection of its parameters has a direct impact on the surface roughness and processing stress of the workpiece. In order to improve the quality of the workpiece and reduce the processing stress, in this embodiment, the technical indicator requirement of the surface roughness of EA4T axle grinding and polishing is 0.2-0.4μm, and the preliminary selected EA4T axle robot grinding and polishing orthogonal test parameter levels are shown in Table 1. A grinding head mesh size 120#, 240#, 320#, 400#, B feed speed 20mm / s-50mm / s, C spindle speed 750r / min-3000r / min, D grinding and polishing force 15N-30N. According to the orthogonal test variance and signal-to-noise ratio calculation results, the mean signal-to-noise ratio of the 400# grinding head at the surface roughness of 0.3μm is the largest, and the grinding head mesh size A of EA4T axle grinding and polishing is selected as 400#. In the EA4T axle allowable grinding and polishing parameter range, 64 parameter combinations of six levels of feed speed, spindle speed, and grinding and polishing force are selected at equal intervals as input. Set the initial value of the gray correlation degree. =0, input the grinding and polishing process parameter combination B1, C1, D1.
[0039] Table 1 EA4T axle robot grinding and polishing orthogonal test parameter level table The gray correlation analysis method is used to optimize the EA4T axle robot grinding and polishing process parameters, and the optimization criterion is that the larger the gray correlation degree, the more the grinding and polishing process parameter combination can meet the multi-objective quality requirement. According to the comprehensive machining target of the EA4T axle to achieve the target roughness range of 0.2-0.4μm and reduce the material removal depth, the midpoint Ra=0.3μm in the surface roughness interval is selected as the optimal surface roughness target. The surface roughness data is processed as the distance between the surface roughness value and 0.3μm .
[0040] , Among them, is the surface roughness value input in the optimization process.
[0041] According to the EA4T axle robot grinding and polishing orthogonal test results, the material removal depth reaches the maximum value at the middle position of a single track, so the maximum material removal depth at this position is taken as the material removal depth target. The EA4T axle grinding and polishing requires the surface roughness to reach the target range, and the material removal depth to be as small as possible, so the surface roughness target value and the material removal depth h have the characteristics of being small.
[0042] Based on the multi-objective optimization system of gray correlation analysis (GRA), V a is the feed speed, n is the spindle speed, F n is the grinding force, R a is the surface roughness, h is the material removal depth, W 1 and W 2 are weight coefficients, and GRG is the gray correlation degree.
[0043] As a preferred embodiment, based on the multi-objective optimization system, before the gray correlation analysis method is used to analyze the correlation degree of the grinding and polishing process parameter combination and the axle grinding and polishing multi-optimization target, it also includes: performing dimensionless processing on the axle grinding and polishing multi-optimization target to obtain dimensionless processed data, so as to perform gray correlation degree analysis according to the dimensionless processed data.
[0044] In this embodiment, due to the different physical meanings and dimensions of the surface roughness and material removal depth data, the target data of the polished surface roughness and material removal depth of the EA4T axle need to be dimensionless when performing grey correlation analysis.
[0045] , in, is the data obtained after dimensionless processing; The data to be processed; i is the data sequence number, indivual; k To optimize the target sequence number, indivual.
[0046] As a preferred embodiment, based on a multi-objective optimization system, a sampling grayscale correlation analysis method is used to analyze the grayscale correlation between the grinding and polishing process parameter combination and the axle grinding and polishing multiple optimization targets, including: based on the multi-objective optimization system, according to the dimensionless processed data, calculating the grayscale correlation coefficient of the axle grinding and polishing multiple optimization targets under the grinding and polishing process parameter combination; according to the grayscale correlation coefficient, calculating the grayscale correlation of the axle grinding and polishing multiple optimization targets under the grinding and polishing process parameter combination.
[0047] In this embodiment, after target data preprocessing is complete, the correlation coefficient between each target sequence and the reference sequence is calculated. A larger coefficient indicates a higher correlation between the grinding and polishing process parameters and the multi-objective optimization system. Based on the multi-objective optimization system for the grinding and polishing process parameters of the EA4T train axle, the grayscale correlation coefficient of the axle grinding and polishing multi-optimization objectives for each grinding and polishing process parameter combination is calculated using dimensionless data.
[0048] , in, is the dimensionless i Under the combination of grinding and polishing process parameters k Grey correlation coefficient of the optimization target data; is the resolution coefficient, , usually take ; The second-level minimum difference , the maximum difference between the two levels , is the series of parameters for each grinding and polishing process X i Each point on the curve and the optimization target sequence X o The absolute difference of each point on the curve.
[0049] The grey correlation coefficient can only reflect the similarity of two sequences at a certain point, and the grey correlation degree is the weighted sum of the grey correlation coefficients of the same grinding and polishing process parameter combination for each optimization target. According to the grey correlation coefficient, the grey correlation degree of the grinding and polishing process parameter combination under the axle grinding and polishing multi-optimization target is calculated, so as to facilitate the centralized and dispersed information and overall comparison.
[0050] , wherein, is the grey correlation degree calculation result corresponding to the first i grinding and polishing process parameter combination; is the response weight of the first k optimization target.
[0051] Of course, the present application can also combine the grey correlation analysis method with other optimization algorithms (such as genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, etc.) to form a hybrid optimization algorithm. For example, after the grey correlation analysis method determines the preliminary optimization direction, the genetic algorithm is used to further optimize the parameter combination to obtain a more optimal grinding and polishing process parameter.
[0052] The present application can also introduce deep learning technology, such as neural network, to model and predict the surface roughness and material removal depth during grinding and polishing. Through training a large amount of experimental data, the neural network can learn the complex nonlinear relationship between the grinding and polishing parameters and the processing quality, so as to provide more accurate target data for the grey correlation analysis and further improve the optimization accuracy.
[0053] Please refer to Figure 6 , Figure 6 is a flowchart provided by the present application for determining the weight of the axle grinding and polishing multi-optimization target.
[0054] As a preferred embodiment, the weight of the axle grinding and polishing multi-optimization target is determined, comprising: using the CRITIC objective weighting method, according to the dimensionless data, calculating the optimization target variability and the optimization target conflict, and according to the variability calculation result and the conflict calculation result, calculating the weight of the axle grinding and polishing multi-optimization target.
[0055] In this embodiment, the CRITIC objective weighting method is used to determine the weight of each optimization target of the EA4T axle grinding and polishing. The CRITIC objective weighting method can take into account the differences between the optimization targets while considering the correlation between the optimization targets, and the weighting process is based on the objective nature of the sample data. Within the allowable grinding and polishing process parameter range, 16 sets of process parameter combinations are selected as sample data of the optimization target value. The CRITIC method target data dimensionless method is the same as the grey correlation analysis method.
[0056] The standard deviation of the sample data is used to represent the optimization target variability: , wherein, is the standard deviation of the sample data of the k th optimization objective, is the sample size, is the sample mean of the k th optimization objective.
[0057] The correlation coefficient is used to represent the conflict index between optimization objectives: , wherein, is the correlation coefficient between two different indicators x and y , is the conflict index of the k th optimization objective, is the number of indicators.
[0058] Thus, the weight is calculated by the CRITIC objective weighting method: , wherein, is the information amount of the k th optimization objective, is the weight of the k th optimization objective.
[0059] The weights of surface roughness and material removal depth calculated according to the equidistant selection of 25 sets of polishing process parameter combination sample data are [0.325 0.557], respectively.
[0060] For the input EA4T axle robot polishing allowable parameter range, the four sets of optimal solutions with the largest gray correlation degree can be obtained, as shown in Table 2. By comparing the gray correlation degree results obtained by multi-objective optimization, the process parameter combination corresponding to the maximum gray correlation degree is output as the optimal process parameter combination of EA4T axle robot polishing. Thus, the optimal process parameter combination of EA4T axle robot polishing is grinding head mesh 400#, feed speed 48-50 mm / s, spindle speed 760-770 rpm, and polishing force 16 N.
[0061] Table 2 Optimal process parameter combination table of EA4T axle robot polishing In the actual polishing process, key parameters such as surface roughness, material removal depth, and polishing force can be monitored in real time. By establishing a real-time feedback control system, the polishing process parameters can be dynamically adjusted according to the monitoring data to achieve adaptive optimization control.
[0062] Of course, machine learning algorithms can also be combined to provide intelligent diagnosis and early warning of abnormalities during the grinding and polishing process. For example, if an abnormally high surface roughness or excessive material removal depth is detected, process parameters can be adjusted or processing can be suspended in a timely manner to avoid processing defects.
[0063] Compared with the prior art, the present invention has the following beneficial effects: (1) The present invention provides a multi-objective process parameter optimization method for EA4T axle robot grinding and polishing, and independently builds an integrated robot grinding and polishing equipment for EA4T axle automatic grinding and polishing, which changes the status quo of traditional manual grinding and polishing with high labor intensity, low processing efficiency, and dust that affects health, and effectively improves the automation level of EA4T axle grinding and polishing.
[0064] (2) Aiming at the limitations of the optimization objectives of the traditional grinding and polishing process of EA4T axles, the present invention creatively improves the grinding and polishing multi-objective optimization system, fully considers the data variability and conflict characteristics, effectively considers the inherent properties of the sample data, and ensures good optimization effects.
[0065] (3) This paper has completed the development of a multi-objective optimization calculation method for EA4T axle robot grinding and polishing, obtained the optimal grinding and polishing process parameter domain under multiple objectives, and achieved the quality requirements of achieving the target surface roughness range while reducing the material removal depth, which has certain practical engineering application value.
[0066] The following describes the system for optimizing the grinding and polishing process parameters of a train axle provided by the present invention. The system for optimizing the grinding and polishing process parameters of a train axle described below and the method for optimizing the grinding and polishing process parameters of a train axle described above can be referenced to each other.
[0067] Please refer to Figure 7 , Figure 7 This is a structural schematic diagram of the train axle grinding and polishing process parameter optimization system provided by the present invention.
[0068] The present invention also provides a system for optimizing the grinding and polishing process parameters of train axles, comprising: a system determination module 701, for determining a multi-objective optimization system for the grinding and polishing process parameters of train axles; the multi-objective optimization system is a system for combining multiple grinding and polishing process parameters so that the axle grinding and polishing multiple optimization targets meet the comprehensive processing targets; the axle grinding and polishing multiple optimization targets include the surface roughness and material removal depth of the axle grinding and polishing; an analysis module 702, for analyzing the grayscale correlation between the grinding and polishing process parameter combination and the axle grinding and polishing multiple optimization targets based on the multi-objective optimization system and the sampling grayscale correlation analysis method; a weight determination module 703, for determining the weight of the axle grinding and polishing multiple optimization targets; a result determination module 704, for determining the optimization result of the grinding and polishing process parameter combination of the train axle according to the weight and the grayscale correlation analysis result.
[0069] As a preferred embodiment, the grinding and polishing test is performed using an axle robot automatic grinding and polishing integrated equipment.
[0070] As a preferred embodiment, the grinding and polishing process parameters include grinding head grit, feed speed, spindle speed and grinding and polishing force; the target range of the surface roughness of the axle grinding and polishing is 0.2-0.4 μm.
[0071] As a preferred embodiment, based on the multi-objective optimization system, the sampling grayscale correlation analysis method analyzes the correlation between the grinding and polishing process parameter combination and the axle grinding and polishing multi-optimization objectives, and also includes: dimensionless processing of the target data of the axle grinding and polishing multi-optimization objectives to obtain the dimensionless processed data, and perform grayscale correlation analysis based on the dimensionless processed data.
[0072] As a preferred embodiment, the analysis module 702 is specifically used to: calculate the grayscale correlation coefficient of the multiple optimization targets of axle grinding and polishing under the combination of grinding and polishing process parameters based on the multi-objective optimization system and the dimensionless processed data; calculate the grayscale correlation degree of the multiple optimization targets of axle grinding and polishing under the combination of grinding and polishing process parameters based on the grayscale correlation coefficient.
[0073] As a preferred embodiment, the weight determination module 703 is specifically used to: adopt the CRITIC objective weighting method, perform optimization target variability calculation and optimization target conflict calculation based on the dimensionless processed data, and calculate the weights of multiple optimization targets of axle grinding and polishing based on the variability calculation results and the conflict calculation results.
[0074] Figure 8 The following is a schematic diagram of the structure of an electronic device, such as Figure 8 As shown, the electronic device may include: a processor 801, a communications interface 802, a memory 803, and a communications bus 804, wherein the processor 801, the communications interface 802, and the memory 803 communicate with each other via the communications bus 804. The processor 801 may call logic instructions in the memory 803 to execute a method for optimizing grinding and polishing process parameters for a train axle. The method includes: determining a multi-objective optimization system for the grinding and polishing process parameters of the train axle; the multi-objective optimization system combines multiple grinding and polishing process parameters so that the multiple optimization objectives of axle grinding and polishing meet the comprehensive processing objectives; the multiple optimization objectives of axle grinding and polishing include surface roughness and material removal depth of axle grinding and polishing; based on the multi-objective optimization system, using a sampling grayscale correlation analysis method to analyze the grayscale correlation between the grinding and polishing process parameter combination and the multiple optimization objectives of axle grinding and polishing; determining weights for the multiple optimization objectives of axle grinding and polishing; and determining an optimization result of the grinding and polishing process parameter combination for the train axle based on the weights and the grayscale correlation analysis results.
[0075] Further, the logic instructions in the memory 803 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the parts that contribute to the related art essentially or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the method of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.
[0076] The embodiment of the present application discloses a computer program product, the computer program product comprises a computer program stored on a non-transitory computer readable storage medium, the computer program comprises program instructions, when the program instructions are executed by a computer, the computer can execute the train wheel grinding and polishing process parameter optimization method provided by each method embodiment, the method comprises: determining a multi-objective optimization system of the train wheel grinding and polishing process parameters; the multi-objective optimization system is obtained by combining a plurality of grinding and polishing process parameters, so that the multi-optimization target of the train wheel grinding and polishing meets the comprehensive machining target; the multi-optimization target of the train wheel grinding and polishing comprises the surface roughness and the material removal depth of the train wheel grinding and polishing; based on the multi-objective optimization system, the gray correlation analysis method is used to analyze the gray correlation degree between the grinding and polishing process parameter combination and the multi-optimization target of the train wheel grinding and polishing; the weight of the multi-optimization target of the train wheel grinding and polishing is determined; according to the weight and the gray correlation analysis result, the grinding and polishing process parameter combination optimization result of the train wheel is determined.
[0077] On the other hand, the embodiment of the present application also provides a non-transitory computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the train wheel grinding and polishing process parameter optimization method provided by each embodiment, the method comprises: determining a multi-objective optimization system of the train wheel grinding and polishing process parameters; the multi-objective optimization system is obtained by combining a plurality of grinding and polishing process parameters, so that the multi-optimization target of the train wheel grinding and polishing meets the comprehensive machining target; the multi-optimization target of the train wheel grinding and polishing comprises the surface roughness and the material removal depth of the train wheel grinding and polishing; based on the multi-objective optimization system, the gray correlation analysis method is used to analyze the gray correlation degree between the grinding and polishing process parameter combination and the multi-optimization target of the train wheel grinding and polishing; the weight of the multi-optimization target of the train wheel grinding and polishing is determined; according to the weight and the gray correlation analysis result, the grinding and polishing process parameter combination optimization result of the train wheel is determined.
[0078] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.
[0079] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.
[0080] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for optimizing grinding and polishing process parameters of a train axle, characterized in that: include: A multi-objective optimization system for determining the grinding and polishing process parameters of train axles; The multi-objective optimization system is to make the axle grinding and polishing multi-optimization objectives meet the comprehensive processing objectives by combining multiple grinding and polishing process parameters; The multi-optimization objectives of axle grinding and polishing include surface roughness and material removal depth of axle grinding and polishing; Based on the multi-objective optimization system, a sampling grayscale correlation analysis method is used to analyze the grayscale correlation between the grinding and polishing process parameter combination and the axle grinding and polishing multi-optimization objectives; Determining weights of multiple optimization objectives for axle grinding and polishing; According to the weight and grayscale correlation analysis results, the optimization result of the grinding and polishing process parameter combination of the train axle is determined.
2. The method for optimizing the grinding and polishing process parameters of a train axle according to claim 1, characterized in that: The method adopts axle robot automatic grinding and polishing integrated equipment to perform grinding and polishing tests.
3. The method for optimizing the grinding and polishing process parameters of a train axle according to claim 2, characterized in that: The grinding and polishing process parameters include grinding head grit, feed speed, spindle speed and grinding and polishing force; the target range of the surface roughness of the axle grinding and polishing is 0.2-0.4 μm.
4. The method for optimizing grinding and polishing process parameters of a train axle according to any one of claims 1 to 3, characterized in that: Before analyzing the correlation between the grinding and polishing process parameter combination and the axle grinding and polishing multi-optimization objectives using the sampling grayscale correlation analysis method based on the multi-objective optimization system, the method further includes: The target data of the axle grinding and polishing multi-optimization targets are dimensionally non-converted to obtain dimensionally non-converted data, and grayscale correlation analysis is performed based on the dimensionally non-converted data.
5. The method for optimizing grinding and polishing process parameters of a train axle according to claim 4, characterized in that: The sampling grayscale correlation analysis method based on the multi-objective optimization system analyzes the grayscale correlation between the grinding and polishing process parameter combination and the axle grinding and polishing multi-optimization objectives, including: Based on the multi-objective optimization system and the dimensionless processed data, the grayscale correlation coefficient of the axle grinding and polishing multi-optimization objectives under the grinding and polishing process parameter combination is calculated; According to the grayscale correlation coefficient, the grayscale correlation of the axle grinding and polishing multi-optimization objectives under the grinding and polishing process parameter combination is calculated.
6. The method for optimizing grinding and polishing process parameters of a train axle according to claim 4, characterized in that: Determining the weights of the axle grinding and polishing multiple optimization objectives includes: The CRITIC objective weighting method is used to calculate the variability of optimization targets and the conflict of optimization targets based on the dimensionless processed data, and the weights of the multiple optimization targets of axle grinding and polishing are calculated based on the variability calculation results and the conflict calculation results.
7. A system for optimizing grinding and polishing process parameters for train axles, characterized in that: include: System determination module, a multi-objective optimization system for determining the grinding and polishing process parameters of train axles; The multi-objective optimization system is to make the axle grinding and polishing multi-optimization objectives meet the comprehensive processing objectives by combining multiple grinding and polishing process parameters; The multi-optimization objectives of axle grinding and polishing include surface roughness and material removal depth of axle grinding and polishing; An analysis module, configured to analyze the grayscale correlation between the grinding and polishing process parameter combination and the axle grinding and polishing multi-optimization objectives using a sampling grayscale correlation analysis method based on the multi-objective optimization system; A weight determination module, used to determine the weights of the axle grinding and polishing multiple optimization objectives; The result determination module is used to determine the optimization result of the grinding and polishing process parameter combination of the train axle according to the weight and grayscale correlation analysis results.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the program, the method for optimizing the grinding and polishing process parameters of a train axle as described in any one of claims 1 to 6 is implemented.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for optimizing the grinding and polishing process parameters of a train axle as claimed in any one of claims 1 to 6 is implemented.
10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for optimizing the grinding and polishing process parameters of a train axle as claimed in any one of claims 1 to 6 is implemented.