Spindle precision design evaluation method and system based on big data

Abstract

The present invention relates to the technical field of mechanical spindle design, and in particular to a spindle precision design evaluation method and system based on big data, the method comprising: constructing an original design scheme according to the spindle precision evaluation standard of the spindle to be set; establishing a scheme design database, retrieving historical design schemes similar to the spindle precision evaluation standard in the scheme design database, and generating an iterative calculation group; using the iterative calculation group as a benchmark, combining the original design scheme to establish a scheme iterative comparison model, and generating an optimized design scheme for the spindle to be set; evaluating and verifying the optimized design scheme according to the spindle precision evaluation standard, and generating a spindle design scheme based on the evaluation and verification results. Through the present invention, the problems of insufficient data utilization, limited optimization capability, and lack of dynamic evaluation in the traditional spindle design method are effectively solved, the accuracy and efficiency of spindle design are significantly improved, and the trial and error cost in the design process is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical spindle design, and in particular to a spindle precision design evaluation method and system based on big data. Background Art

[0002] With the continuous development of the machining industry, the spindle, as the core component of high-precision CNC machine tools, has a design and performance that directly determines the machining accuracy, production efficiency and reliability of the machine tools. In the spindle design process, how to optimize the key design parameters of the spindle to meet high-precision requirements based on complex and changing application scenarios and machining requirements has always been a core issue of concern to the industry.

[0003] Traditional spindle design methods usually rely on engineering experience or trial and error. This method is not only inefficient, but also fails to fully tap the potential value of historical design data, resulting in limited effectiveness and reliability of optimized design.

[0004] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention

[0005] The present invention provides a spindle precision design evaluation method and system based on big data, which can effectively solve the problems in the background technology.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is:

[0007] A spindle precision design evaluation method based on big data, the method comprising:

[0008] Construct an original design plan based on the spindle accuracy evaluation standard of the spindle to be installed;

[0009] Establishing a scheme design database, searching the scheme design database for historical design schemes similar to the spindle precision evaluation standard, and generating an iterative calculation group;

[0010] Taking the iterative calculation group as a benchmark and combining it with the original design scheme, a scheme iterative comparison model is established to generate an optimized design scheme for the main shaft to be set;

[0011] The optimized design solution is evaluated and verified according to the spindle accuracy evaluation standard, and a spindle design solution is generated based on the evaluation and verification results.

[0012] Furthermore, a scheme iteration comparison model is established in combination with the original design scheme, including:

[0013] Extracting design parameters related to the historical design scheme and the spindle precision evaluation standard to form a historical design parameter set;

[0014] Selecting a plurality of design parameter combinations from the historical design parameter set, and combining the design parameter combinations of the original design solution to construct an iterative calculation group;

[0015] Designing an iterative calculation method based on the spindle accuracy evaluation standard, calculating the iterative index of each design parameter combination in the iterative calculation group by the iterative calculation method, and sorting the design parameter combinations according to the iterative index;

[0016] The iteration index is combined with the original design solution, and a comparison iteration calculation group is trained to generate the solution iteration comparison model.

[0017] Furthermore, the design parameter combinations are sorted according to the iteration index, including:

[0018] Decoding each of the design parameter combinations in the iterative calculation group to generate iterative design codons, and weighting the iterative design codons to generate weighted iterative codons;

[0019] Substituting the weighted iterative codon into the iterative calculation method, performing parameter excellence evaluation on the design parameter combination, and integrating to generate an excellent evaluation value;

[0020] According to the excellent evaluation value, comparing the iteration index of the design parameter combination corresponding to the solution proportion calculation in the iteration calculation group;

[0021] The design parameter combinations are sorted according to the iteration index, and the design parameter combination with the highest iteration index is selected from the same type.

[0022] Furthermore, the integration generates excellent evaluation values, including:

[0023] Classifying the evaluation index of the design parameter combination into a plurality of evaluation index dimensions, and assigning a weight coefficient to each of the evaluation index dimensions according to the spindle accuracy evaluation standard;

[0024] Parsing the iteratively designed codons, mapping each of the iteratively designed codons to a plurality of evaluation index dimensions to form a parameter index mapping table, and performing weight addition through the parameter index mapping table to obtain weighted iterative codons;

[0025] Substituting the weighted iterative codon into the iterative calculation method, performing single-dimensional excellence calculation on the performance of each design parameter combination in each evaluation index dimension, and generating a local excellence value;

[0026] Performing weighted integration on the local excellence values ​​of each of the design parameter combinations, and generating a multi-dimensional evaluation value according to the weight coefficients of the evaluation index dimensions;

[0027] Based on the multi-dimensional evaluation values, the interactive impact of the parameters in the design parameter combination is verified, and the local evaluation results are adjusted and optimized to finally generate excellent evaluation values.

[0028] Further, a main shaft design scheme is generated based on the evaluation and verification results, including:

[0029] Extracting key design parameters from the optimization design scheme, and comparing and analyzing the key design parameters with the spindle accuracy evaluation standard item by item to generate comparative analysis results;

[0030] Based on the comparative analysis results, quantify the influence of the key design parameters on the spindle accuracy, and generate a parameter deviation analysis report, wherein the parameter deviation analysis report includes compliance parameters and parameters that need to be adjusted;

[0031] Based on the parameter deviation analysis report, a spindle design correction scheme is generated, wherein the spindle design correction scheme includes correction values ​​of the parameters to be adjusted in the optimization design scheme and performance prediction results of the adjustment;

[0032] The spindle design revision scheme is compared with the original design scheme, the spindle design revision scheme is verified by the spindle accuracy evaluation standard, and a final spindle design scheme is output.

[0033] Furthermore, a spindle design correction plan is generated, including:

[0034] Based on the parameter deviation analysis report, the parameters to be adjusted in the optimization design scheme that do not meet the spindle accuracy assessment standard are prioritized;

[0035] According to the priority classification, the initial value of the parameter to be adjusted is adjusted based on the spindle accuracy evaluation standard to generate a candidate set of correction parameters;

[0036] Performing multi-objective verification on the correction parameter candidate set, screening the design correction values ​​that meet the spindle accuracy evaluation standard, and integrating the design correction values ​​with the compliance parameters to generate a correction design parameter set;

[0037] The spindle performance index is predicted based on the modified design parameter set, the prediction result is compared with the spindle accuracy evaluation standard to verify the rationality of the modified design parameter set, and a spindle design correction plan is generated.

[0038] Further, an iterative calculation group is generated, including:

[0039] Filter out historical design schemes that match the spindle accuracy evaluation standard of the spindle to be set from the scheme design database;

[0040] Analyze the historical design scheme, extract the historical spindle design parameters related to the spindle accuracy evaluation standard, preset parameter combination rules, and generate multiple groups of parameter combinations to be designed through parameter perturbation;

[0041] Performing a preliminary fitness evaluation on the generated parameter combinations to be designed, performing a quantitative score on each group of parameter combinations to be designed according to the key indicators in the spindle accuracy evaluation standard, and eliminating the parameter combinations with the lowest and highest initial fitness values;

[0042] The parameter combinations to be designed that have passed the preliminary fitness evaluation are integrated to generate the iterative calculation group.

[0043] Furthermore, multiple sets of parameter combinations to be designed are generated through parameter perturbation, including:

[0044] Based on the mean and standard deviation of the historical spindle design parameters and in combination with the spindle accuracy evaluation standard, a disturbance range of each of the historical spindle design parameters is set, wherein the disturbance range includes parameter limits of positive offset and negative offset;

[0045] Randomly perturb the historical spindle design parameters within the perturbation range to generate an initial parameter perturbation set;

[0046] Performing multi-dimensional cross-combination on the parameters in the initial parameter disturbance set to form a plurality of different disturbance parameter combinations;

[0047] Compare and analyze the disturbance parameter combination with the spindle accuracy evaluation standard, eliminate the disturbance parameter combination that does not meet the constraint conditions, and perform multiple rounds of disturbance optimization again;

[0048] The disturbance parameter combination that meets the spindle accuracy evaluation standard after the multiple rounds of disturbance optimization is classified into a set of parameters to be designed.

[0049] A spindle precision design evaluation system based on big data, the system comprising:

[0050] The original design module builds the original design plan according to the spindle accuracy evaluation standard of the spindle to be set;

[0051] Iterative calculation module, establishes a scheme design database, retrieves historical design schemes similar to the spindle accuracy evaluation standard in the scheme design database, and generates an iterative calculation group;

[0052] The optimization design module uses the iterative calculation group as a benchmark and combines the original design scheme to establish a scheme iterative comparison model to generate an optimized design scheme for the spindle to be set;

[0053] The scheme generation module evaluates and verifies the optimized design scheme according to the spindle accuracy evaluation standard, and generates the spindle design scheme based on the evaluation and verification results.

[0054] Furthermore, the optimization design module includes:

[0055] A parameter extraction unit extracts design parameters related to historical design schemes and spindle accuracy evaluation standards to form a historical design parameter set;

[0056] The calculation construction unit selects multiple design parameter combinations from the historical design parameter set, combines the design parameter combinations of the original design scheme, and constructs an iterative calculation group;

[0057] A combination sorting unit designs an iterative calculation method based on the spindle accuracy evaluation standard, calculates the iterative index of each design parameter combination in the iterative calculation group through the iterative calculation method, and sorts the design parameter combinations according to the iterative index;

[0058] The model training unit combines the iteration index with the original design solution and compares the iteration comparison model generated by the iteration calculation group training.

[0059] The technical solution of the present invention can achieve the following technical effects:

[0060] It solves the problems of insufficient data utilization, limited optimization capabilities and lack of dynamic evaluation in traditional spindle design methods, significantly improves the accuracy and efficiency of spindle design, and reduces the trial and error costs in the design process; enhances the utilization rate of design data, realizes the automation and intelligence of high-precision spindle design, and meets the high-precision requirements of spindles in the field of high-end manufacturing.

[0061] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A flowchart for designing an evaluation method for spindle accuracy based on big data;

[0064] Figure 2 It is a structural diagram of the scheme iteration comparison model;

[0065] Figure 3 Schematic diagram of the process for generating excellent evaluation values;

[0066] Figure 4 A schematic diagram of the process for generating a spindle design solution;

[0067] Figure 5 It is a structural diagram of the iterative computing group. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0069] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0070] Embodiment 1

[0071] like Figure 1 As shown, the present application provides a spindle precision design evaluation method based on big data, the method comprising:

[0072] S10: constructing an original design scheme according to the spindle accuracy evaluation standard of the spindle to be set;

[0073] S20: establishing a scheme design database, searching the scheme design database for historical design schemes similar to the spindle accuracy evaluation standard, and generating an iterative calculation group;

[0074] S30: Taking the iterative calculation group as a benchmark, a scheme iterative comparison model is established in combination with the original design scheme to generate an optimized design scheme for the main axis to be set;

[0075] S40: Evaluate and verify the optimized design solution according to the spindle accuracy evaluation standard, and generate a spindle design solution based on the evaluation and verification results.

[0076] Specifically, according to the application scenario and precision requirements of the spindle to be installed, the initial design parameters of the spindle are defined and an original design scheme is generated, including dimensional parameters (such as spindle diameter and length), material property parameters (such as material type and hardness) and performance parameters (such as rotational accuracy and dynamic stability). The original design scheme is used as the initial input scheme for the spindle design; a large number of verified spindle design schemes are collected and integrated to form a scheme design database. Each design scheme in the scheme design database includes historical design schemes related to the spindle, precision evaluation results and actual application performance data. These schemes are classified and labeled through big data storage and retrieval technology; historical design schemes similar to the spindle precision evaluation standard of the spindle to be installed are retrieved from the scheme design database, and they are screened according to the similarity of design parameters to finally form an iterative calculation group; based on the iterative calculation group, the iterative calculation group and the original design scheme are extracted. Parameters are obtained and standardized. An iterative calculation method is designed based on the spindle accuracy evaluation standard. The iterative index is calculated for each parameter combination in the iterative calculation group. The design parameter combinations are sorted according to the iterative index, and the parameter combinations with high iterative index are screened out. The iterative index is compared and analyzed with the original design scheme, and a scheme iterative comparison model is trained to generate the scheme. The high iterative index parameter combination in the scheme iterative comparison model is used as a candidate scheme, and the parameter combination is further adjusted through optimization methods such as genetic algorithms to generate an optimized design scheme for the spindle to be designed. The optimized design scheme includes the adjusted key design parameters and their corresponding predicted performance values. Based on the evaluation and verification results of the optimized design scheme, the parameters that do not meet the spindle accuracy evaluation standard are corrected, and a spindle design correction scheme is generated. The correction scheme is finally verified to ensure that the spindle accuracy evaluation standard is met, and the final spindle design scheme and its performance report are output.

[0077] The technical solution of the present invention solves the problems of insufficient data utilization, limited optimization capability and lack of dynamic evaluation in traditional spindle design methods, significantly improves the accuracy and efficiency of spindle design, and reduces the trial and error costs in the design process.

[0078] Further, if Figure 2 As shown, a scheme iteration comparison model is established in combination with the original design scheme, including:

[0079] Extract the design parameters related to the historical design scheme and the spindle accuracy evaluation standard to form a historical design parameter set;

[0080] Select multiple design parameter combinations from the historical design parameter set, combine them with the design parameter combinations of the original design scheme, and construct an iterative calculation group;

[0081] An iterative calculation method is designed based on the spindle accuracy evaluation standard. The iterative calculation method is used to calculate the iterative index of each design parameter combination in the iterative calculation group, and the design parameter combinations are sorted according to the iterative index.

[0082] The iteration index is combined with the original design scheme, and the iteration comparison model of the scheme generated by the iteration calculation group training is compared.

[0083] As a preferred embodiment of the above, historical design schemes related to the spindle accuracy evaluation standard of the spindle to be set are retrieved from the scheme design database, and these historical design schemes contain multi-dimensional design parameters, such as size parameters, material parameters, dynamic performance parameters, and processing accuracy parameters. These parameters closely related to the spindle accuracy are extracted to form a historical design parameter set; design parameter combinations are selected and an iterative calculation group is constructed. From the historical design parameter set, multiple groups of design parameter combinations are selected, and the parameter combination closest to the spindle accuracy evaluation standard is preferentially selected to ensure that the selected design parameter combination has diversity in range and distribution to enhance the adaptability of the iterative calculation group, and the selected historical design parameter combination is integrated with the design parameter combination of the original design scheme, and multiple groups of new design parameter combinations are generated through parameter perturbation to construct an iterative calculation group; according to the spindle accuracy evaluation standard, the iterative calculation group is designed The method is used to calculate the iteration index of each design parameter combination in the iteration calculation group, and a comprehensive fitness function is constructed based on the key indicators of the spindle accuracy evaluation standard (such as circular runout accuracy, thermal expansion compensation performance, dynamic stiffness, etc.). According to the importance of the evaluation standard, weights are assigned to the key indicators in the fitness function, and each group of design parameters is substituted into the fitness function to calculate its iteration index; according to the calculated iteration index, the design parameter combinations in the iteration calculation group are sorted, and the parameter combinations with high iteration indexes are screened out. The parameter combinations with similar iteration indexes are sorted according to the secondary evaluation standard (such as dynamic performance priority or material performance priority); the sorted high iteration index parameter combinations are compared and analyzed with the parameter set of the original design scheme, and the iterative calculation group is trained by machine learning methods (such as regression analysis or neural network) to generate a scheme iteration comparison model.

[0084] Furthermore, the design parameter combinations are ranked according to the iteration index, including:

[0085] Decoding each design parameter combination in the iterative calculation group to generate iterative design codons, and weighting the iterative design codons to generate weighted iterative codons;

[0086] Substitute the weighted iterative codons into the iterative calculation method, evaluate the parameter excellence of the design parameter combination, and integrate to generate an excellent evaluation value;

[0087] According to the excellent evaluation value, compare the iteration index of the design parameter combination corresponding to the solution proportion in the iteration calculation group;

[0088] The design parameter combinations are sorted according to the iteration index, and the design parameter combination with the highest iteration index is selected among the same type.

[0089] As a preferred embodiment of the above embodiment, key parameters in the design parameter combination are extracted, such as spindle diameter, length, material properties (such as density, elastic modulus), dynamic performance parameters (such as rotation accuracy, dynamic balance level), and thermal stability parameters (such as thermal expansion coefficient). After each design parameter is standardized, it is converted into a codon structure, for example, a numerical sequence is assigned by dimension, so that each parameter codon can clearly reflect its physical meaning (such as "diameter-material-stiffness" is mapped to a DMK sequence), and the generated iterative design codon can uniquely encode each design parameter combination; according to the spindle accuracy evaluation standard, weights are assigned to each parameter in the iterative design codon, for example, the circular runout accuracy accounts for 40% of the weight, the dynamic performance (such as maximum speed, dynamic balance) accounts for 30% of the weight, the thermal stability accounts for 20% of the weight, and other design parameters (such as material properties) account for 10% of the weight. Through weighted processing, the iterative design codon is recalculated to generate a weighted iterative codon, which can more accurately reflect the contribution of different parameters to the spindle design target. The weighted iteration code is substituted into the iteration calculation method to evaluate the parameter excellence of the design parameter combination. The excellence of each design parameter combination in a single evaluation dimension such as circular runout accuracy, dynamic performance, and thermal stability is evaluated, and the single-dimensional excellence value is calculated. The single-dimensional excellence values ​​are weighted and integrated according to the weight coefficient to generate an overall excellent evaluation value. The excellent evaluation value can quantify the comprehensive performance of each design parameter combination in the spindle precision design. According to the excellent evaluation value, the proportion of the schemes in the iteration calculation group is compared, and the iteration index of each design parameter combination is calculated. For the design parameter combination with a higher excellent evaluation value, a higher proportion weight is given. The iteration index is normalized by the weighted proportion so as to uniformly rank the comprehensive performance of different parameter combinations. The design parameter combination with a higher iteration index has a stronger optimization potential and adaptability. According to the calculated iteration index, the design parameter combinations in the iteration calculation group are ranked, and the parameter combination with the highest iteration index is selected as the representative parameter combination.

[0090] Further, if Figure 3 As shown, the integration generates excellent assessment values, including:

[0091] Classify the evaluation indicators of the design parameter combination into multiple evaluation indicator dimensions, and assign a weight coefficient to each evaluation indicator dimension according to the spindle accuracy evaluation standard;

[0092] Analyze the iterative design codons, map each iterative design codon to multiple evaluation index dimensions, form a parameter index mapping table, and perform weight addition through the parameter index mapping table to obtain weighted iterative codons;

[0093] Substitute the weighted iterative codon into the iterative calculation method, perform single-dimensional excellence calculation on the performance of each design parameter combination in each evaluation index dimension, and generate a local excellence value;

[0094] The local excellence values ​​of each design parameter combination are weighted and integrated, and a multi-dimensional evaluation value is generated according to the weight coefficient of the evaluation index dimension;

[0095] Based on multi-dimensional evaluation values, the interactive impact of parameters in the design parameter combination is verified, and the local evaluation results are adjusted and optimized to ultimately generate excellent evaluation values.

[0096] As a preferred embodiment of the above, according to the spindle precision evaluation standard, the evaluation index of the design parameter combination can be divided into the following dimensional examples, such as precision index, dynamic performance index, thermal stability index, material performance index, and processing reliability index. According to the requirements of the spindle precision evaluation standard, a weight coefficient is assigned to each evaluation index dimension; the iterative design codon is parsed, and its design parameters are mapped to multiple evaluation index dimensions to form a parameter index mapping table. For example, an iterative design codon may include the following parameters: spindle diameter, material, rotation speed, and thermal expansion coefficient, which are mapped as follows: the precision index is affected by the diameter and material, the dynamic performance index is affected by the diameter and rotation speed, and the thermal stability index is affected by the thermal expansion coefficient and material. After the mapping is completed, the weights are added to generate a weighted iterative codon; the weighted iterative codon is substituted into the iterative calculation method to perform a single-dimensional analysis on the performance of each design parameter combination in each evaluation index dimension. The single-dimensional excellence value is used to quantify the performance of the design parameter combination in each evaluation dimension; the single-dimensional excellence value of each design parameter combination is weighted and integrated according to the weight to generate a multi-dimensional evaluation value, which comprehensively reflects the overall performance of the design parameter combination in each evaluation indicator dimension; based on the generated multi-dimensional evaluation value, the parameters in the design parameter combination are verified for interaction effects, such as verifying whether the synergistic effect of the spindle diameter and the material elastic modulus affects the circular runout accuracy. If the interaction verification result shows that a certain parameter has a negative impact on the overall performance (such as the material elastic modulus causes the thermal expansion to exceed the standard), the parameter is optimized and adjusted, the single-dimensional excellence value is recalculated, and the multi-dimensional evaluation value is updated; after completing the interaction impact verification and optimization adjustment, an excellent evaluation value is finally generated, which represents the overall excellence and optimization potential of the design parameter combination. The excellent evaluation value will serve as the core basis for the calculation of the iteration index and the ranking of parameter combinations.

[0097] Further, if Figure 4 As shown, a main axis design solution is generated based on the evaluation and verification results, including:

[0098] Extract the key design parameters in the optimized design scheme, and compare and analyze the key design parameters with the spindle accuracy evaluation standards item by item to generate comparative analysis results;

[0099] Based on the comparative analysis results, the influence of key design parameters on spindle accuracy is quantified, and a parameter deviation analysis report is generated. The parameter deviation analysis report includes the compliant parameters and the parameters that need to be adjusted.

[0100] Generate a spindle design correction plan based on the parameter deviation analysis report. The spindle design correction plan includes the correction values ​​of the parameters to be adjusted in the optimization design plan and the performance prediction results of the adjustment;

[0101] The spindle design revision plan is compared with the original design plan, the spindle design revision plan is verified through the spindle accuracy evaluation standard, and the final spindle design plan is output.

[0102] As a preferred embodiment of the above embodiment, key design parameters directly related to the spindle accuracy evaluation standard are extracted from the optimized design scheme. These parameters include but are not limited to dimensional parameters (such as spindle diameter and length), performance parameters (such as circular runout accuracy, dynamic balance level, thermal expansion) and material property parameters (such as density and elastic modulus). The extracted key design parameters are compared and analyzed item by item to evaluate whether they meet the requirements of the spindle accuracy evaluation standard, and a comparative analysis result is generated, including compliant parameters that meet the spindle accuracy evaluation standard and parameters that need to be adjusted that have deviations and need further optimization; based on the comparative analysis results, the parameters that need to be adjusted are quantitatively analyzed to generate a parameter deviation analysis report. The parameter deviation analysis report includes calculating the deviation amount of the parameters that need to be adjusted relative to the spindle accuracy evaluation standard, and quantifying the degree of influence of the parameters that need to be adjusted on the overall performance of the spindle accuracy in combination with their weights in the design scheme. The parameter deviation analysis report clearly points out the design parameters that need to be optimized The optimized parts and their optimization priorities are as follows; for the parameters to be adjusted listed in the parameter deviation analysis report, according to the spindle accuracy evaluation standard, the parameters to be adjusted are optimized and calculated, and their values ​​are corrected to meet the accuracy standard. The corrected parameters to be adjusted and the compliant parameters are integrated to regenerate a complete set of corrected design parameters. Based on the corrected design parameter set, the performance indicators of the adjusted spindle are predicted to ensure that the optimized parameters meet the spindle accuracy design requirements. The spindle design correction plan includes the optimized values ​​of the parameters to be adjusted and the corresponding performance prediction results. The generated spindle design correction plan is compared with the original design plan, and the correction plan is verified by the spindle accuracy evaluation standard. The verification content includes whether the corrected parameters fully meet the spindle accuracy evaluation standard and whether the overall performance of the corrected plan is better than the original design plan. The verification results confirm the feasibility and reliability of the correction plan, and provide a basis for the output of the final design plan. After the correction plan is verified, the final spindle design plan is output.

[0103] Further, a spindle design correction plan is generated, including:

[0104] Based on the parameter deviation analysis report, prioritize the parameters that need to be adjusted in the optimized design scheme that do not meet the spindle accuracy assessment standards;

[0105] According to the priority classification, the initial values ​​of the parameters to be adjusted are adjusted based on the spindle accuracy evaluation standard to generate a candidate set of correction parameters;

[0106] Perform multi-objective verification on the candidate set of correction parameters, select the design correction values ​​that meet the spindle accuracy evaluation standards, and integrate the design correction values ​​with the compliance parameters to generate a set of correction design parameters;

[0107] The spindle performance indicators are predicted based on the modified design parameter set, the prediction results are compared with the spindle accuracy evaluation criteria to verify the rationality of the modified design parameter set, and a spindle design correction plan is generated.

[0108] As a preferred embodiment of the above, based on the parameter deviation analysis report, the parameters to be adjusted in the optimization design scheme that do not meet the spindle accuracy evaluation standard are prioritized and classified, and the classification basis includes the weight of the direct impact of the parameters on the spindle accuracy, the degree of deviation and the difficulty of adjustment, and the key parameters that have a greater impact on the accuracy and a lower correction difficulty are adjusted first; according to the priority classification of the parameters to be adjusted, their initial values ​​are adjusted based on the spindle accuracy evaluation standard to generate a candidate set of correction parameters, and multiple groups of correction values ​​are generated by perturbation. Adjustment rules are defined in combination with historical design data, such as adjusting the elastic modulus of the spindle material to reduce thermal expansion or optimize the dynamic balance level, so as to form an initial structure of the candidate set of correction parameters; by constructing a multi-objective verification model, each group of correction values ​​is verified from multiple dimensions such as accuracy targets (such as circular runout accuracy), dynamic performance targets (such as maximum speed) and thermal stability targets (such as thermal expansion), and the screening rules ensure that the correction values ​​not only meet the spindle accuracy evaluation standards, but also meet the comprehensive performance indicators. Achieve the optimal balance, such as eliminating correction values ​​that have limited improvement on accuracy or have a negative impact on other performance indicators, and retaining positive correction values ​​to generate the final corrected design parameter set; the corrected design parameter set is integrated by the screened design correction values ​​and the compliant parameters in the original plan, as the basis for generating the spindle design correction plan, based on the corrected design parameter set, the overall performance indicators of the spindle are predicted through the performance prediction model, such as verifying whether the corrected circular runout accuracy meets the expected requirements, whether the dynamic performance and thermal expansion are kept within a reasonable range, and the prediction results are further compared with the evaluation criteria to verify the rationality and adaptability of the corrected design parameter set; integrate the corrected design parameter set, performance prediction results, and comparative analysis results before and after correction to generate a spindle design correction plan, which details the adjusted key parameter values, the optimization effect of the overall performance, and the differences in the design before and after correction, providing a clear decision-making basis for design optimization.

[0109] Further, if Figure 5 As shown, an iterative calculation group is generated, including:

[0110] Select historical design schemes that match the spindle accuracy evaluation standard of the spindle to be set from the scheme design database;

[0111] Analyze historical design schemes, extract historical spindle design parameters related to spindle accuracy evaluation standards, preset parameter combination rules, and generate multiple sets of parameter combinations to be designed through parameter perturbations;

[0112] Perform a preliminary fitness evaluation on the generated parameter combinations to be designed, and quantify the scores of each parameter combination to be designed according to the key indicators in the spindle accuracy evaluation standard, and eliminate the parameter combinations with the lowest and highest initial fitness values;

[0113] The parameter combinations to be designed that have passed the preliminary fitness evaluation are integrated to generate an iterative calculation group.

[0114] As a preferred embodiment of the above, through the scheme design database, based on the spindle accuracy evaluation standard, the historical design schemes similar to the spindle to be set are screened, and the screening is carried out according to the key indicator matching rules, such as spindle accuracy (circular runout accuracy, coaxiality), dynamic performance (maximum speed, dynamic balance level) and thermal stability (thermal expansion), etc., to ensure that the screened historical design schemes are highly relevant to the spindle to be set in terms of application scenarios and design goals; the screened historical design schemes are analyzed to extract historical design parameters related to the spindle accuracy evaluation standard, and the extracted parameter set provides a basis for generating new parameter combinations to be designed; based on the historical design parameter set, according to the preset parameter combination rules, the parameter perturbation method is applied to generate multiple groups of parameter combinations to be designed, and in the historical design parameters, the historical design parameters are extracted to form a new set of parameters to be designed. Within the reasonable range of historical design parameters, positive and negative disturbances are performed based on the parameter change trend, and multi-dimensional cross-combinations are performed between different parameter dimensions to ensure the diversity and coverage of parameter combinations; the generated parameter combination to be designed is matched and evaluated with the spindle accuracy evaluation standard, and the adaptability of the parameter combination to the spindle accuracy requirements is measured by quantifying the fitness value. The fitness evaluation is based on key indicators (such as circular runout accuracy, dynamic performance and thermal stability), and the fitness value is calculated in combination with the standard requirements. Parameter combinations with too high or too low fitness values ​​are eliminated to avoid falling into local optimal solutions at an early stage, while improving the global optimization potential of parameter combinations; the parameter combinations that have passed the preliminary fitness evaluation are integrated to generate an iterative calculation group, and the integrated iterative calculation group is used as the input for subsequent iterative calculations.

[0115] Furthermore, multiple sets of parameter combinations to be designed are generated through parameter perturbation, including:

[0116] Based on the mean and standard deviation of the historical spindle design parameters and in combination with the spindle accuracy evaluation standard, the disturbance range of each historical spindle design parameter is set, and the disturbance range includes the parameter limits of positive and negative offsets;

[0117] Perform random perturbations on the historical spindle design parameters within the perturbation range to generate an initial parameter perturbation set;

[0118] Perform multi-dimensional cross-combination on the parameters in the initial parameter perturbation set to form multiple different perturbation parameter combinations;

[0119] Compare and analyze the disturbance parameter combinations with the spindle accuracy evaluation criteria, eliminate the disturbance parameter combinations that do not meet the constraints, and perform multiple rounds of disturbance optimization again;

[0120] The perturbation parameter combinations that meet the spindle accuracy evaluation criteria after multiple rounds of perturbation optimization are classified into the parameter set to be designed.

[0121] As a preferred embodiment of the above, based on the mean and standard deviation of the historical spindle design parameters and in combination with the spindle accuracy evaluation standard, the disturbance range of each design parameter is set. The setting of the disturbance range is based on the limit values ​​of the positive offset and the negative offset and the distribution characteristics of the historical data to set the upper and lower limits of the parameter disturbance. Within the set disturbance range, an initial parameter disturbance set is generated based on a random disturbance algorithm. The random disturbance algorithm uses a specific probability distribution (such as normal distribution or uniform distribution) to control the distribution trend of the disturbance, so that the generated parameter set has uniformity and coverage. By combining the disturbance values ​​of different design parameter dimensions, multiple groups of disturbance parameter combinations are generated. The cross-combination follows the principle of multi-dimensional coverage, so that each disturbance parameter combination has uniformity and coverage. The dynamic parameters can be effectively matched with other parameters in the multi-dimensional parameter space, thereby maximizing the diversity of disturbance parameter combinations; the generated disturbance parameter combinations are compared and analyzed with the spindle accuracy evaluation standards, and the disturbance parameter combinations that do not meet the standards are eliminated through the multi-dimensional constraint condition filtering mechanism; multiple rounds of disturbance optimization are performed on the retained disturbance parameter combinations. In each round of optimization, the disturbance range is dynamically adjusted and further screening is performed to improve the adaptability of the parameter combination. The optimized disturbance parameter combination can better meet the design goals while avoiding the risk of local optimality; the disturbance parameter combinations that meet the spindle accuracy evaluation standards after multiple rounds of optimization are classified into the set of parameters to be designed as the input for subsequent iterative calculations.

[0122] Embodiment 2

[0123] Based on the same inventive concept as the spindle precision design evaluation method based on big data in the aforementioned embodiment, the present invention further provides a spindle precision design evaluation system based on big data, the system comprising:

[0124] The original design module builds the original design plan according to the spindle accuracy evaluation standard of the spindle to be set;

[0125] Iterative calculation module, establishes a scheme design database, retrieves historical design schemes similar to the spindle accuracy evaluation standard in the scheme design database, and generates an iterative calculation group;

[0126] The optimization design module uses the iterative calculation group as a benchmark and combines the original design scheme to establish a scheme iterative comparison model to generate an optimized design scheme for the spindle to be set;

[0127] The scheme generation module evaluates and verifies the optimized design scheme according to the spindle accuracy evaluation standard, and generates the spindle design scheme based on the evaluation and verification results.

[0128] The above-mentioned adjustment system in the present invention can effectively realize a spindle accuracy design evaluation method based on big data, and the technical effects that can be achieved are as described in the above-mentioned embodiments and will not be repeated here.

[0129] Specifically, the optimization design module includes:

[0130] A parameter extraction unit extracts design parameters related to historical design schemes and spindle accuracy evaluation standards to form a historical design parameter set;

[0131] The calculation construction unit selects multiple design parameter combinations from the historical design parameter set, combines the design parameter combinations of the original design scheme, and constructs an iterative calculation group;

[0132] A combination sorting unit designs an iterative calculation method based on the spindle accuracy evaluation standard, calculates the iterative index of each design parameter combination in the iterative calculation group through the iterative calculation method, and sorts the design parameter combinations according to the iterative index;

[0133] The model training unit combines the iteration index with the original design solution and compares the iteration comparison model generated by the iteration calculation group training.

[0134] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.

[0135] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined therein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A spindle precision design evaluation method based on big data, characterized in that: The method comprises: Construct an original design plan based on the spindle accuracy evaluation standard of the spindle to be installed; Establishing a scheme design database, searching the scheme design database for historical design schemes similar to the spindle precision evaluation standard, and generating an iterative calculation group; Taking the iterative calculation group as a benchmark and combining it with the original design scheme, a scheme iterative comparison model is established to generate an optimized design scheme for the main shaft to be set; Evaluate and verify the optimized design scheme according to the spindle accuracy evaluation standard, and generate a spindle design scheme based on the evaluation and verification results; Combined with the original design scheme, a scheme iteration comparison model is established, including: Extracting design parameters related to the historical design scheme and the spindle precision evaluation standard to form a historical design parameter set; Selecting a plurality of design parameter combinations from the historical design parameter set, and combining the design parameter combinations of the original design solution to construct an iterative calculation group; Designing an iterative calculation method based on the spindle accuracy evaluation standard, calculating the iterative index of each design parameter combination in the iterative calculation group by the iterative calculation method, and sorting the design parameter combinations according to the iterative index; Combining the iteration index with the original design solution, and training a comparison iteration calculation group to generate the solution iteration comparison model; Sorting the design parameter combinations according to the iteration index includes: Decoding each of the design parameter combinations in the iterative calculation group to generate iterative design codons, and weighting the iterative design codons to generate weighted iterative codons; Substituting the weighted iterative codon into the iterative calculation method, performing parameter excellence evaluation on the design parameter combination, and integrating to generate an excellent evaluation value; According to the excellent evaluation value, comparing the iteration index of the design parameter combination corresponding to the solution proportion calculation in the iteration calculation group; The design parameter combinations are sorted according to the iteration index, and the design parameter combination with the highest iteration index is selected from the same type.

2. The spindle precision design evaluation method based on big data according to claim 1 is characterized in that: Integration generates excellent assessment value, including: Classifying the evaluation index of the design parameter combination into a plurality of evaluation index dimensions, and assigning a weight coefficient to each of the evaluation index dimensions according to the spindle accuracy evaluation standard; Parsing the iteratively designed codons, mapping each of the iteratively designed codons to a plurality of evaluation index dimensions to form a parameter index mapping table, and performing weight addition through the parameter index mapping table to obtain weighted iterative codons; Substituting the weighted iterative codon into the iterative calculation method, performing a single-dimensional excellence calculation on the performance of each design parameter combination in each evaluation index dimension, and generating a local excellence value; Performing weighted integration on the local excellence values ​​of each of the design parameter combinations, and generating a multi-dimensional evaluation value according to the weight coefficients of the evaluation index dimensions; Based on the multi-dimensional evaluation values, the interactive impact of the parameters in the design parameter combination is verified, and the local evaluation results are adjusted and optimized to finally generate excellent evaluation values.

3. The spindle precision design evaluation method based on big data according to claim 1 is characterized in that: Generate a spindle design solution based on the results of the evaluation and verification, including: Extracting key design parameters from the optimization design scheme, and comparing and analyzing the key design parameters with the spindle accuracy evaluation standard item by item to generate comparative analysis results; Based on the comparative analysis results, quantify the influence of the key design parameters on the spindle accuracy, and generate a parameter deviation analysis report, wherein the parameter deviation analysis report includes compliance parameters and parameters that need to be adjusted; Based on the parameter deviation analysis report, a spindle design correction scheme is generated, wherein the spindle design correction scheme includes correction values ​​of the parameters to be adjusted in the optimization design scheme and performance prediction results of the adjustment; The spindle design revision scheme is compared with the original design scheme, the spindle design revision scheme is verified by the spindle accuracy evaluation standard, and a final spindle design scheme is output.

4. The spindle precision design evaluation method based on big data according to claim 3 is characterized in that: Generate spindle design revisions including: Based on the parameter deviation analysis report, the parameters to be adjusted in the optimization design scheme that do not meet the spindle accuracy assessment standard are prioritized; According to the priority classification, the initial value of the parameter to be adjusted is adjusted based on the spindle accuracy evaluation standard to generate a candidate set of correction parameters; Performing multi-objective verification on the correction parameter candidate set, screening the design correction values ​​that meet the spindle accuracy evaluation standard, and integrating the design correction values ​​with the compliance parameters to generate a correction design parameter set; The spindle performance index is predicted based on the modified design parameter set, the prediction result is compared with the spindle accuracy evaluation standard to verify the rationality of the modified design parameter set, and a spindle design correction plan is generated.

5. The spindle precision design evaluation method based on big data according to claim 1 is characterized in that: Generate an iterative calculation group, including: Filter out historical design schemes that match the spindle accuracy evaluation standard of the spindle to be set from the scheme design database; Analyze the historical design scheme, extract the historical spindle design parameters related to the spindle accuracy evaluation standard, preset parameter combination rules, and generate multiple groups of parameter combinations to be designed through parameter perturbation; Performing a preliminary fitness evaluation on the generated parameter combinations to be designed, performing a quantitative score on each group of parameter combinations to be designed according to the key indicators in the spindle accuracy evaluation standard, and eliminating the parameter combinations with the lowest and highest initial fitness values; The parameter combinations to be designed that have passed the preliminary fitness evaluation are integrated to generate the iterative calculation group.

6. The spindle precision design evaluation method based on big data according to claim 5 is characterized in that: Generate multiple sets of design parameter combinations through parameter perturbation, including: Based on the mean and standard deviation of the historical spindle design parameters and in combination with the spindle accuracy evaluation standard, a disturbance range of each of the historical spindle design parameters is set, wherein the disturbance range includes parameter limits of positive offset and negative offset; Randomly perturb the historical spindle design parameters within the perturbation range to generate an initial parameter perturbation set; Performing multi-dimensional cross-combination on the parameters in the initial parameter disturbance set to form a plurality of different disturbance parameter combinations; Compare and analyze the disturbance parameter combination with the spindle accuracy evaluation standard, eliminate the disturbance parameter combination that does not meet the constraint conditions, and perform multiple rounds of disturbance optimization again; The disturbance parameter combination that meets the spindle accuracy evaluation standard after the multiple rounds of disturbance optimization is classified into a set of parameters to be designed.

7. A spindle precision design evaluation system based on big data, characterized in that: Using the spindle precision design evaluation method based on big data as claimed in claim 1, the system comprises: The original design module builds the original design plan according to the spindle accuracy evaluation standard of the spindle to be set; Iterative calculation module, establishes a scheme design database, retrieves historical design schemes similar to the spindle accuracy evaluation standard in the scheme design database, and generates an iterative calculation group; The optimization design module uses the iterative calculation group as a benchmark and combines the original design scheme to establish a scheme iterative comparison model to generate an optimized design scheme for the spindle to be set; The scheme generation module evaluates and verifies the optimized design scheme according to the spindle accuracy evaluation standard, and generates the spindle design scheme based on the evaluation and verification results; The optimization design module includes: A parameter extraction unit extracts design parameters related to historical design schemes and spindle accuracy evaluation standards to form a historical design parameter set; The calculation construction unit selects multiple design parameter combinations from the historical design parameter set, combines the design parameter combinations of the original design scheme, and constructs an iterative calculation group; A combination sorting unit designs an iterative calculation method based on the spindle accuracy evaluation standard, calculates the iterative index of each design parameter combination in the iterative calculation group through the iterative calculation method, and sorts the design parameter combinations according to the iterative index; The model training unit combines the iteration index with the original design solution and compares the iteration comparison model generated by the iteration calculation group training.

Images