An intelligent simulation analysis method and system for overloaded gear machining

Abstract

The present invention relates to the technical field of intelligent simulation analysis, and particularly to an intelligent simulation analysis method and system for heavy-duty gear machining. The method includes the following steps: collecting gear heat treatment machining data; performing gear heat treatment simulation based on the gear heat treatment machining data to generate gear heat treatment simulation data; performing quantitative distribution analysis of gear heat treatment strain response based on the gear heat treatment simulation data to generate gear heat treatment strain response quantitative distribution data; analyzing the fitting data of heat treatment strain response performance-demand indicators through a preset gear heat treatment strain demand indicator and the gear heat treatment strain response quantitative distribution data; and performing processing parameter analysis of strain response demand based on the fitting data of heat treatment strain response performance-demand indicators to generate processing parameters of strain response demand. The present invention realizes intelligent heat treatment machining with higher efficiency and accuracy through simulation analysis of the heat treatment machining of heavy-duty gears.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent simulation analysis, and particularly to an intelligent simulation analysis method and system for heavy-duty gear machining. Background Art

[0002] In the field of modern construction machinery, the gear system, as a key transmission component, is widely used in various heavy-duty and high-load mechanical equipment. Due to its extremely high load-bearing capacity requirements, the machining quality of heavy-duty gears directly affects the performance and service life of the equipment. There are many problems in traditional heavy-duty gear machining methods. Especially during the heat treatment process, the heat treatment quality and strain behavior control of gears are often affected by changes in the machining environment and process parameters, resulting in unstable gear performance, and even defects such as heat treatment deformation and residual stress, which in turn affect the load-bearing capacity and working life of the gears. However, the existing heavy-duty gear machining methods that rely on empirical formulas and fixed process parameters for heat treatment control can no longer meet the requirements of modern industry for machining accuracy and efficiency. The real-time monitoring and adjustment of the temperature field and strain field are difficult, resulting in uncontrollable deformation during the machining process, thus affecting the machining quality of the final gears. In addition, the technology often lacks intelligent feedback adjustment means for the dynamic changes during the gear heat treatment process, leading to problems such as high energy consumption, low efficiency, and insufficient accuracy during the machining process. Summary of the Invention

[0003] Based on this, the present invention provides an intelligent simulation analysis method and system for heavy-duty gear machining to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent simulation analysis method for heavy-duty gear machining includes the following steps:

[0005] Step S1: Use a distributed sensor network to perform real-time monitoring and processing of heat treatment processing signals for heavy-duty gear heat treatment operations, generating gear heat treatment processing data; perform gear heat treatment simulation processing based on the gear heat treatment processing data, generating gear heat treatment simulation data; perform timing, temperature, and strain analysis of gear heat treatment processing based on the gear heat treatment simulation data, generating gear heat treatment timing-temperature-strain data;

[0006] Step S2: Perform gear heat treatment strain reaction quantitative distribution analysis based on the gear heat treatment timing-temperature-strain data, generating gear heat treatment strain reaction quantitative distribution data;

[0007] Step S3: Perform demand index fitting processing on the heat treatment strain reaction based on the preset gear heat treatment strain demand index and the gear heat treatment strain reaction quantification distribution data to generate heat treatment strain reaction performance-demand index fitting data; perform analysis on the processing parameters required for the strain reaction based on the heat treatment strain reaction performance-demand index fitting data to generate the processing parameters required for the strain reaction.

[0008] Step S4: Perform demand processing simulation analysis on the strain reaction based on the processing parameters required for the strain reaction to generate demand processing simulation data for the strain reaction; perform analysis on the residual heat of the simulated response processing based on the demand processing simulation data for the strain reaction to generate data on the residual heat of the simulated response processing.

[0009] Step S5: Perform safety detection and adjustment processing on the processing parameters required for the strain reaction using the data on the residual heat of the simulated response processing to obtain the safe processing parameters required for the strain reaction; perform intelligent optimization and iteration processing on the processing parameters based on the safe processing parameters required for the strain reaction to generate optimized processing parameters required for the strain reaction; perform intelligent processing parameter feedback operations for the heat treatment of heavy-duty gears through the optimized processing parameters required for the strain reaction.

[0010] Further, step S1 includes the following steps:

[0011] Step S11: Use a distributed sensor network to perform real-time monitoring and processing of the heat treatment processing signals during the heat treatment processing of heavy-duty gears to generate gear heat treatment processing data.

[0012] Step S12: Perform gear heat treatment simulation processing based on the gear heat treatment processing data to generate gear heat treatment simulation data.

[0013] Step S13: Perform analysis on the temperature field distribution of gear heat treatment based on the gear heat treatment simulation data to generate gear heat treatment temperature field distribution data.

[0014] Step S14: Perform analysis on the strain behavior of gear heat treatment based on the gear heat treatment simulation data to generate gear heat treatment strain behavior data.

[0015] Step S15: Perform analysis on the timing, temperature, and strain of gear heat treatment processing based on the gear heat treatment temperature field distribution data and the gear heat treatment strain behavior data to generate gear heat treatment timing-temperature-strain data.

[0016] Further, step S2 includes the following steps:

[0017] Step S21: Analyze the strain influence factors of gear heat treatment based on the gear heat treatment timing-temperature-strain data to generate gear heat treatment strain influence factors.

[0018] Step S22: Use the gear heat treatment strain reaction quantification evaluation algorithm to conduct a quantification evaluation process of the strain reaction under the influence of time sequence and temperature of gear heat treatment on the gear heat treatment strain influence factors, and generate gear heat treatment strain reaction quantification data;

[0019] Step S23: Conduct a distribution mapping process of the gear heat treatment strain reaction quantification based on the gear heat treatment strain reaction quantification data, and generate gear heat treatment strain reaction quantification distribution data.

[0020] Furthermore, the gear heat treatment strain influence factors described in step S21 include the gear heat treatment strain elastic modulus factor, the gear heat treatment strain expansion factor, and the gear heat treatment strain tensile strength factor.

[0021] Furthermore, the gear heat treatment strain reaction quantification evaluation algorithm described in step S22 is as follows:

[0022] ;

[0023] In the formula, is expressed as, represents the continuous reaction time of the heat treatment, represents the reaction temperature data of the gear heat treatment, represents the end reaction time of the heat treatment, represents the start reaction time of the heat treatment, represents the quantification information of the relationship between the gear heat treatment strain elastic modulus factor and temperature, represents the temperature change rate of the gear heat treatment, represents the quantification information of the relationship between the gear heat treatment strain expansion factor and temperature, represents the quantification information of the relationship between the gear heat treatment strain tensile strength factor and temperature, represents the initial reaction temperature data of the gear heat treatment, represents the temperature-dependent heat treatment reaction effect data varying with temperature, represents the temperature change difference between the start and the end.

[0024] Furthermore, step S3 includes the following steps:

[0025] Step S31: Conduct a spatial clustering analysis of the heat treatment strain reaction based on the gear heat treatment strain reaction quantification distribution data, and generate heat treatment strain reaction spatial clustering data;

[0026] Step S32: Conduct a performance grouping process of the heat treatment strain reaction based on the heat treatment strain reaction characteristic spatial clustering data, and generate heat treatment strain reaction performance group data;

[0027] Step S33: Based on the preset gear heat treatment strain requirement index and the heat treatment strain response performance group data, perform demand index fitting processing for each strain response performance group to generate heat treatment strain response performance - demand index fitting data;

[0028] Step S34: Analyze the processing parameters required for strain response according to the heat treatment strain response performance - demand index fitting data to generate the processing parameters required for strain response.

[0029] Further, step S4 includes the following steps:

[0030] Step S41: Based on the processing parameters required for strain response, perform demand processing simulation analysis of strain response to generate demand processing simulation data for strain response;

[0031] Step S42: According to the gear heat treatment temperature field distribution data, perform temperature transfer distribution analysis of gear heat treatment to generate gear heat treatment temperature transfer distribution data;

[0032] Step S43: According to the gear heat treatment temperature transfer distribution data and the demand processing simulation data for strain response, perform simulated response heat gradient distribution analysis to generate simulated response heat gradient distribution data;

[0033] Step S44: Through the simulated response heat gradient distribution data, perform simulated response processing residual heat analysis to generate simulated response processing residual heat data.

[0034] Further, step S5 includes the following steps:

[0035] Step S51: Through the simulated response processing residual heat data, perform safety detection and adjustment processing on the processing parameters required for strain response, including: when the simulated response processing residual heat data is greater than the preset abnormal deformation threshold of processing residual heat, execute step S511; or, when the simulated response processing residual heat data is not greater than the preset abnormal deformation threshold of processing residual heat, execute step S512;

[0036] Step S511: Mark the processing parameters required for strain response corresponding to the simulated response processing residual heat data as abnormal strain response processing parameters with residual heat, and perform correction and adjustment of the processing parameters required for strain response with abnormal deformation of residual heat to obtain the corrected strain response processing parameters with abnormal residual heat, and feedback the corrected strain response processing parameters with abnormal residual heat to step S34 for abnormal correction and adjustment operation of the processing parameters required for strain response;

[0037] Step S512: Mark the strain reaction demand processing parameters corresponding to the analog response processed residual heat data as strain reaction demand safe processing parameters;

[0038] Step S52: Perform intelligent optimization iteration processing on the processing parameters based on the strain reaction demand safe processing parameters to generate strain reaction demand optimized processing parameters;

[0039] Step S53: Execute the intelligent processing parameter feedback operation of heavy-duty gear heat treatment through the strain reaction demand optimized processing parameters.

[0040] Furthermore, Step S52 includes the following steps:

[0041] Step S521: Perform data integration modeling processing according to the strain reaction demand safe processing parameters and the corresponding analog response processed residual heat data to generate a strain reaction demand safe processing parameter - residual heat data model;

[0042] Step S522: Perform simulation analysis of the hardened layer processing of the residual heat based on the gear heat treatment strain reaction quantification distribution data and the strain reaction demand safe processing parameter - residual heat data model to generate residual heat hardened layer processing simulation data;

[0043] Step S523: Analyze the hardened layer processing benefit characteristics of the residual heat hardened layer processing simulation data to generate residual heat hardened layer processing benefit characteristic data;

[0044] Step S524: Use the residual heat hardened layer processing benefit characteristic data as the processing parameter optimization coefficient, and perform intelligent optimization iteration processing on the strain reaction demand safe processing parameters through the processing parameter optimization coefficient to generate strain reaction demand optimized processing parameters.

[0045] This specification provides an intelligent simulation analysis system for heavy-duty gear processing, which is used to execute the intelligent simulation analysis method for heavy-duty gear processing as described above. This intelligent simulation analysis system for heavy-duty gear processing includes:

[0046] Gear heat treatment simulation analysis module, which is used to use a distributed sensor network to perform real-time monitoring and processing of heat treatment processing signals for heavy-duty gear heat treatment processing operations to generate gear heat treatment processing data; perform gear heat treatment simulation processing based on the gear heat treatment processing data to generate gear heat treatment simulation data; perform timing, temperature, and strain analysis of gear heat treatment processing based on the gear heat treatment simulation data to generate gear heat treatment timing - temperature - strain data;

[0047] Gear heat treatment strain response analysis module, which is used to conduct quantitative distribution analysis of gear heat treatment strain response based on gear heat treatment time-sequence - temperature - strain data, and generate quantitative distribution data of gear heat treatment strain response;

[0048] Strain response requirement machining parameter analysis module, which is used to perform fitting processing of requirement indicators for heat treatment strain response through preset gear heat treatment strain requirement indicators and quantitative distribution data of gear heat treatment strain response, and generate fitting data of heat treatment strain response performance - requirement indicators; conduct analysis of machining parameters for strain response requirements based on the fitting data of heat treatment strain response performance - requirement indicators, and generate machining parameters for strain response requirements;

[0049] Simulation response machining residual heat analysis module, which is used to conduct demand machining simulation analysis of strain response based on machining parameters for strain response requirements, and generate demand machining simulation data of strain response; conduct analysis of simulation response machining residual heat based on the demand machining simulation data of strain response, and generate simulation response machining residual heat data;

[0050] Machining parameter intelligent optimization iteration module, which is used to perform safety detection and adjustment processing of machining parameters for strain response requirements with the machining parameters for strain response requirements through simulation response machining residual heat data to obtain safe machining parameters for strain response requirements; conduct intelligent optimization iteration processing of machining parameters based on the safe machining parameters for strain response requirements, and generate optimized machining parameters for strain response requirements; execute intelligent machining parameter feedback operation for heavy-duty gear heat treatment through the optimized machining parameters for strain response requirements.

[0051] The beneficial effects of this application are as follows. By introducing a distributed sensor network to monitor the heat treatment process of heavy-duty gears in real time, the present invention can accurately obtain various key parameters during the processing, such as temperature, strain and other data, and conduct a more refined simulation analysis of the gear heat treatment process. Through heat treatment simulation based on these processing data, the temperature field and strain field distributions during the processing can be accurately reproduced, revealing potential strain and temperature changes during the heat treatment process and predicting processing defects in advance. In addition, by further combining time series, temperature and strain analysis, the correlations between temperature, strain and time series at each moment during the processing are comprehensively analyzed, providing comprehensive theoretical support for subsequent processing optimization, ensuring the effective control of the gear heat treatment quality, and significantly improving the processing accuracy and stability. Through the strain response quantitative distribution analysis based on the gear heat treatment time series-temperature-strain data, the strain response characteristics during the heat treatment process can be further refined and its distribution can be quantified. The core of this process is to identify the key factors affecting the gear heat treatment quality, such as strain elastic modulus, strain expansion factor, strain tensile strength factor, etc., through the analysis of the gear heat treatment strain influence factors, so as to comprehensively evaluate various strain responses during the gear heat treatment process. Through the quantitative evaluation of these influence factors, the strain behavior of the gear material at different temperatures and times can be accurately captured and its distribution mapping can be carried out. This method can not only accurately describe the strain response characteristics during the gear heat treatment process, but also provide a quantitative basis for subsequent processing optimization, optimize processing parameters, reduce the negative impact of strain response on gear performance, and thus improve the quality and reliability of gear processing. By fitting the demand index with the gear heat treatment strain response quantitative distribution data, the actual performance of the strain response during the heat treatment process can be accurately matched with the preset strain demand index, so as to ensure that the heat treatment process meets the specific performance requirements of the gear material. Through spatial clustering analysis and strain response performance grouping, the behavior characteristics of gear heat treatment strain under different working conditions are refined, helping to identify the key factors that have a greater impact on gear performance and further quantifying their impact on gear performance. By fitting these influencing factors with the demand index, processing parameters are formulated to ensure that the strain behavior of the gear during the processing is consistent with the performance requirements. Through the analysis of the processing parameters required for the strain response, highly accurate control of the processing process can be achieved, the heat treatment process can be optimized, the overall quality and stability of the gear can be improved, and its service life can be extended. Based on the processing parameters required for the strain response, demand processing simulation analysis can accurately predict the change trend of the strain response under different processing conditions, providing data support for the adjustment during the actual processing. Through the temperature transfer distribution analysis, the influence of temperature changes on material properties during the gear heat treatment process can be deeply understood, the temperature control strategy can be further optimized, and the negative impact of temperature fluctuations on processing quality can be reduced.The simulated response heat gradient distribution analysis can reveal the heat transfer and distribution rules during the processing, thereby helping to predict the residual heat generated during processing and its impact on the gear structure. The simulated response processing residual heat analysis provides a scientific basis for the adjustment of processing parameters, ensuring that the residual heat generation is minimized while ensuring the quality of the gear, avoiding thermal strain and deformation problems during processing, improving the accuracy and stability of gear processing, and further optimizing the processing efficiency and quality. The safe detection and adjustment of the simulated response processing residual heat data can effectively avoid the material deformation problem caused by abnormal residual heat during the heat treatment process. By performing dynamic detection according to the preset threshold, when the residual heat data exceeds the threshold, the correction process is immediately started, the abnormal processing parameters are marked and adjusted, thereby preventing the gear deformation or damage caused by uneven heat distribution, ensuring that the temperature control during the processing is within a reasonable range, and thus ensuring the accuracy and quality of the gear. Through the safe adjustment and intelligent optimization of the processing parameters required by the strain response, accurate processing process optimization can be achieved. Intelligent optimization iteration based on safe processing parameters not only improves the processing efficiency, but also achieves the best heat treatment effect, reduces energy consumption, and reduces process costs by continuously optimizing the processing parameters. The optimized processing parameters are fed back to the processing system to form a closed-loop control system, ensuring that each round of heat treatment process can be adjusted and improved based on real-time data. Through this efficient feedback mechanism, the heat treatment process of the gear has been continuously improved, thereby improving the overall performance and service life of the gear and reducing potential risks in the production process.

[0052] Therefore, the intelligent simulation analysis method of heavy-duty gear processing of the present invention simulates and analyzes the heat treatment of heavy-duty gears, obtains processing data in real time, and conducts a comprehensive analysis of timing, temperature and strain, so as to accurately capture the slight changes in the gear processing process, accurately analyze the strain response of each distribution of heavy-duty gears to temperature changes, and ensure that the deformation in the processing process can be pre-controlled, meet the requirements of modern industry for processing accuracy and efficiency, and achieve the processing quality requirements of gears. In addition, based on the intelligent feedback adjustment mechanism, it can respond to the dynamic changes in the heat treatment process of the gear in real time, automatically optimize the processing parameters, and through continuous optimization of the processing parameters, the processing parameters maintain the cracking, deformation and other problems of the gear heat treatment processing, and ensure that the processing parameters can achieve the goal of the surface hardening layer of the gear, which not only improves production efficiency and reduces energy consumption, but also can achieve more precise control under different working conditions, thereby ensuring the efficiency and accuracy of the processing process, so as to provide an efficient, accurate and energy-saving heavy-duty gear processing method, and meet the needs of modern industry for high-precision and high-efficiency processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1Schematic diagram of the step process of an intelligent simulation analysis method for heavy-duty gear machining according to the present invention;

[0054] Figure 2 For Figure 1 Schematic diagram of the detailed implementation steps of step S3 in

[0055] Figure 3 For Figure 1 Schematic diagram of the detailed implementation steps of step S4 in

[0056] The realization of the object of the present invention, functional features and advantages will be further described in conjunction with embodiments with reference to the accompanying drawings. Specific embodiments

[0057] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0058] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0059] It should be understood that although the terms "first", "second", etc. may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0060] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides an intelligent simulation analysis method for heavy-duty gear machining, including the following steps:

[0061] Step S1: Use a distributed sensor network to perform real-time monitoring and processing of heat treatment processing signals for heavy-duty gear heat treatment processing operations to generate gear heat treatment processing data; perform gear heat treatment simulation processing based on the gear heat treatment processing data to generate gear heat treatment simulation data; perform timing, temperature, and strain analysis of gear heat treatment processing based on the gear heat treatment simulation data to generate gear heat treatment timing-temperature-strain data;

[0062] In the embodiments of the present invention, during the heat treatment process of heavy-duty gears, a set of distributed sensor networks are first deployed. The types of sensors include temperature sensors (such as thermocouple-type sensors), strain sensors (such as fiber optic sensors or resistance strain gauges), and acceleration sensors (such as piezoelectric acceleration sensors). These sensors are evenly arranged on the gear surface and key areas (such as tooth surfaces, tooth roots, and key contact surfaces). The sensors monitor and collect signals generated during the processing in real time, including temperature changes (for example, temperature range: 100°C to 1000°C), strain changes (strain range: -0.01% to 0.05%), and vibration and other parameters, in order to obtain gear heat treatment processing data. Based on the gear heat treatment processing data, data simulation is carried out using heat treatment simulation software (such as ANSYS or ABAQUS). The software is used to create a geometric model of the gear, define its material properties and geometric dimensions, and input external environmental parameters. A multi-physics coupling model is established, and numerical calculations are carried out by combining the heat conduction equation, fluid mechanics equation, and mechanical strain model. During the simulation process, the thermal loads, external fluid convection, and radiation cooling effects that the gear undergoes during different heating, holding, and cooling stages are considered. The gear heat treatment simulation data generated by the simulation results, including the temperature field, strain field, and the thermal stress conditions that occur during the heating and cooling processes, provide a basis for further analysis. Based on the gear heat treatment simulation data, temperature field distribution analysis is carried out. The finite element method (FEM) is used to establish a three-dimensional temperature field model in the simulation software, and the temperature distribution at different time nodes during the heating, holding, and cooling processes of the gear is analyzed. During the simulation process, the heat source distribution (such as the uniform temperature distribution inside the heating furnace), the thermal conductivity of the gear (such as the thermal conductivity of steel is 45 W / m·K), the specific heat capacity (such as the specific heat capacity of steel is 500 J / kg·K), and the thermal convection and radiation effects during the cooling process are considered. Through numerical calculations, the temperature field distribution data of each region at different time nodes are generated. Based on the temperature field distribution data, gear heat treatment strain behavior analysis is carried out. According to the temperature field distribution, the thermal stress formula and elastic deformation theory are applied, and combined with the temperature changes generated during the heat treatment process of the gear, strain analysis is carried out. The finite element method is used to analyze the influence of thermal stress on the gear during the heating and cooling processes, predict the maximum strain values at different parts of the gear (such as the maximum strain on the tooth surface is 0.02%), and further calculate its strain distribution. The generated strain behavior data can provide the internal and external stress distributions of the gear during the heat treatment process, and help evaluate the deformation problems that occur during the processing. According to the gear heat treatment temperature field distribution data and the gear heat treatment strain behavior data, the timing, temperature, and strain analysis of the gear heat treatment process are carried out, and the principal component analysis (PCA) method is used to analyze the temperature and strain data at different time nodes in order to extract key characteristic patterns.For example, the PCA model calculates the covariance matrix of temperature and strain data and extracts the first two principal components. The first principal component represents the influence of temperature change on strain, and the second principal component represents the coupling relationship between temperature and strain. Further, regression analysis (such as linear regression or polynomial regression) is used to analyze the relationship between temperature and strain data, and the specific functional relationship between temperature and strain is obtained. Time series-temperature-strain data is generated to provide a basis for optimizing the processing technology and parameter adjustment. Through this data, the influence of temperature change on strain during gear heat treatment can be accurately predicted and used for subsequent process optimization.

[0063] Step S2: Based on the time series-temperature-strain data of gear heat treatment, perform a quantitative distribution analysis of gear heat treatment strain response to generate gear heat treatment strain response quantitative distribution data;

[0064] In the embodiments of the present invention, based on the time-sequence - temperature - strain data of gear heat treatment, the strain influence factors during gear heat treatment are analyzed. Statistical analysis methods (such as correlation analysis and regression analysis) are used to conduct a detailed study on the relationship among temperature, strain, and gear material. During the analysis process, first, the temperature, strain data, and material properties (such as elastic modulus, expansion coefficient, strain tensile strength, etc.) at each time node during gear heat treatment are extracted. By calculating the temperature change rate, temperature gradient during heating and cooling processes, etc., the key factors affecting strain are identified. By calculating the correlation between these factors, the strain influence factor data of gear heat treatment is generated. The gear heat treatment strain response quantification evaluation algorithm is used to perform the strain response quantification evaluation processing of the gear heat treatment strain influence factors under the influence of time sequence and temperature of gear heat treatment. A self-developed gear heat treatment strain response quantification evaluation algorithm is adopted. By inputting the temperature field, strain field, and their influence factors (such as expansion coefficient, temperature gradient, elastic modulus, strain tensile strength, etc.), the strain response of the gear under different processing conditions is calculated. The algorithm will calculate the strain distribution based on these inputs and generate strain response quantification data, which reflects the strain degree that occurs during the actual processing of the gear and its impact on the heat treatment quality. Through this algorithm, the influence of different temperature fields and the involved time on the strain effect of gear heat treatment can be evaluated more accurately. Distribution mapping processing of strain response quantification is performed according to the gear heat treatment strain response quantification data. Through spatial analysis and data visualization techniques, a distribution map of the strain response during gear heat treatment is generated. The gear is divided into multiple small regions (for example, each gear tooth surface is divided into 5 regions, and each region is 20 mm × 20 mm). For each region, the strain data at each time point in the heat treatment simulation results are used for mapping, and color identification is performed according to the magnitude of the strain value. The generated strain response quantification distribution map visually shows the strain degree of each part of the gear during heat treatment. For example, the strain response of the tooth surface region during heat treatment is 0.015%, and that of the tooth root region is 0.02%. This distribution map provides a visual basis and can quantify the distribution information of the strain response, providing effective support for optimizing the heat treatment process and avoiding excessive local deformation.

[0065] Step S3: Through the preset gear heat treatment strain requirement index and the gear heat treatment strain response quantification distribution data, perform the fitting processing of the requirement index of the heat treatment strain response to generate the heat treatment strain response performance - requirement index fitting data; according to the heat treatment strain response performance - requirement index fitting data, perform the analysis of the processing parameters required for the strain response to generate the processing parameters required for the strain response.

[0066] In the embodiments of the present invention, spatial clustering analysis of the heat treatment strain response is performed according to the quantified distribution data of the gear heat treatment strain response, and the strain response data of different regions of the gear is classified by using a spatial clustering analysis algorithm. The K-means clustering algorithm or the DBSCAN algorithm is used for data classification. In this process, first, the strain data of the gear is divided into several regions. For the strain data of each region, clustering processing is performed according to its strain magnitude and pattern. The initial center points of the K-means clustering algorithm can be randomly selected as 5 points. The algorithm calculates the distance from each data point to these center points and performs iterative updates until the clustering result converges. The clustering result divides the strain data into multiple subsets, and each subset represents a similar strain response pattern. The generated spatial clustering data of the heat treatment strain response provides a basis for subsequent strain performance grouping. Based on the spatial clustering data of the heat treatment strain response, heat treatment strain response performance grouping processing is performed. For the strain characteristic data after each spatial clustering, its performance under different temperatures and process parameters is analyzed. By comparing the strain changes under different temperatures and cooling rates, the strain characteristic pattern of this region can be determined and compared with the strain responses of other regions. Through clustering analysis, similar strain response characteristics are classified into the same group. Heat treatment strain response performance group data is generated, and the strain characteristics within each group are relatively consistent, facilitating subsequent targeted demand index fitting processing. According to the strain performance group data and combined with the preset gear heat treatment strain demand index, strain response performance-demand index fitting processing is performed. The data of each strain performance group is compared with these preset strain demand indexes. If the strain response in the tooth root region exceeds the maximum allowable strain, the process parameters need to be adjusted (such as reducing the heating temperature or changing the cooling rate). The strain response characteristics of each group are optimized by mathematical fitting methods (such as the least squares method or genetic algorithm) to ensure that they meet the preset demand indexes, and heat treatment strain response performance-demand index fitting data is generated. According to the heat treatment strain response performance-demand index fitting data, the processing parameters for the strain response demand are analyzed. By analyzing the processing parameters of each strain performance group under different strain demands, the processing parameters of each group are determined. These parameters will be used for the next processing simulation and optimization. Through these processing parameters, it is ensured that the gear achieves the minimum deformation and stress distribution during the heat treatment process, meets the quality requirements, and improves the production efficiency.

[0067] Step S4: Based on the processing parameters for the strain response demand, perform demand processing simulation analysis of the strain response to generate strain response demand processing simulation data; perform simulation response processing residual heat analysis according to the strain response demand processing simulation data to generate simulation response processing residual heat data;

[0068] In the embodiments of the present invention, a demand processing simulation analysis of strain response is carried out based on processing parameters of strain response requirements. Using CAE (Computer Aided Engineering) simulation software, such as Simulia or COMSOL, a demand processing simulation analysis of strain response is carried out for the gear heat treatment process. In the software, a three-dimensional geometric model of the gear is established, and the temperature range, cooling rate, and other relevant process parameters are set according to the processing parameters. During the simulation process, through the finite element analysis (FEA) method, changes in various indicators during the strain response process are simulated, such as thermal deformation, thermal stress, and strain distribution. The simulation results will predict the strain behavior of the gear under specific process conditions and give the deformation and thermal stress distribution. This simulation result provides a basis for the subsequent adjustment of processing parameters to ensure that the strain during the processing is controlled within the allowable range. According to the simulation data and the gear heat treatment temperature field distribution data, a temperature transfer distribution analysis is carried out. By establishing a finite element model of the temperature field, the geometric model of the gear is coupled with the temperature field to simulate the heat transfer process inside the gear. Assuming that the initial temperature of the gear is room temperature, during the heating process, the heat provided by the external heat source is transferred from the gear surface to the inside, and the temperature gradually rises. In the simulation, considering the thermal conductivity, specific heat capacity of the gear material, and boundary conditions, such as the temperature of the heating furnace being 900 °C, analyze how heat is transferred in each region of the gear. The generated temperature transfer distribution data can show the temperature distribution of each point inside the gear. This data reveals the heat transfer law in different regions of the gear, which can help optimize the temperature control during cooling and heating and improve the consistency and uniformity of heat treatment. Based on the temperature transfer distribution data, the change in the heat gradient is further analyzed. By combining the thermal stress and strain data during the gear processing, the simulated response heat gradient distribution data is calculated and generated. The heat gradient refers to the temperature difference between different regions of the gear, which directly affects the thermal stress distribution of the gear. Using finite element analysis, by simulating the change in the heat gradient, the generated simulated response heat gradient distribution data reveals the stress and strain response of the gear under different cooling rates, provides guidance for the control of heat distribution during the processing, and helps ensure the uniform distribution of thermal stress and strain during the processing. According to the simulated response heat gradient distribution data, the problem of residual heat during the processing is analyzed. During the heat treatment process, due to the temperature gradient difference in different regions, residual heat will be generated inside the gear, resulting in uneven thermal stress and deformation problems. For example, assume that during the gear heating process, due to too large a temperature gradient, the root region of the tooth fails to reach the target temperature completely, while the temperature of the tooth surface region is too high, resulting in large thermal deformation of the tooth surface. By calculating the residual heat distribution in different regions inside the gear, the simulated response processing residual heat data is obtained. This data shows the difference in residual heat between the tooth surface and the tooth root. The residual heat in the tooth surface region is 15 J / g, while that in the tooth root region is 5 J / g.Further adjust the temperature control during the heating and cooling processes based on these data to avoid excessive temperature differences, reduce the influence of residual heat, and ultimately optimize the machining quality of the gears.

[0069] Step S5: Perform safety detection and adjustment processing on the strain response demand machining parameters by simulating the response to the machining residual heat data to obtain the strain response demand safe machining parameters; perform intelligent optimization and iteration processing on the machining parameters based on the strain response demand safe machining parameters to generate the strain response demand optimized machining parameters; execute the intelligent machining parameter feedback operation for the heavy-duty gear heat treatment through the strain response demand optimized machining parameters.

[0070] In the embodiments of the present invention, the safety detection and adjustment of the processing parameters required for the strain response during the gear heat treatment process are carried out according to the simulated response processing residual heat data. A preset abnormal deformation threshold of the processing residual heat is set. For example, the threshold is set to a residual heat of 30 J / g. When the simulated response processing residual heat data is greater than this threshold, it indicates that there is a relatively significant residual heat during the heat treatment process, resulting in abnormal deformation or unqualified processing. Abnormal correction is performed on the processing parameters required for the strain response. Conversely, when the simulated response processing residual heat data is less than or equal to the preset threshold, the processing parameters required for the strain response are marked as safe processing parameters and no adjustment is made. When the simulated response processing residual heat data is greater than the preset abnormal deformation threshold of the processing residual heat, correction adjustment for the abnormal deformation of the residual heat is performed on the relevant processing parameters required for the strain response. The processing parameters required for the strain response corresponding to the simulated response processing residual heat data are marked as the processing parameters required for the abnormal strain response of the residual heat. These parameters include heating temperature, cooling rate, time period, etc. In this case, the purpose of correcting these parameters is to reduce the generation of residual heat and avoid thermal stress and non-uniform deformation. The adjusted processing parameters required for the strain response will be returned to step S3 for further abnormal correction adjustment operations until the output simulated response processing residual heat data is not greater than the preset abnormal deformation threshold of the processing residual heat, thereby ensuring that the strain control and heat distribution during the processing reach an ideal state. When the simulated response processing residual heat data is less than or equal to the preset abnormal deformation threshold of the processing residual heat, the processing parameters required for the strain response are marked as the processing parameters required for the safe strain response, which means that these processing parameters can be used in actual production without causing abnormal thermal stress or deformation problems. In this case, no further adjustment is required and production can be directly carried out through these parameters. Based on the processing parameters required for the safe strain response, enter the intelligent optimization iteration processing stage of the processing parameters. In this stage, machine learning algorithms (such as support vector machine SVM or reinforcement learning) are applied to further optimize the processing parameters required for the safe strain response. Assume that the safe processing parameters are: heating temperature 880°C, cooling rate 1.5°C / min. After optimization processing, the generated processing parameters required for the optimized strain response are: heating temperature 875°C, cooling rate 1.4°C / min. During this optimization process, the algorithm will comprehensively consider multiple factors, such as processing accuracy, time efficiency, energy efficiency, etc., to generate a set of optimized processing parameters. For example, the optimized heating temperature and cooling rate will be able to minimize thermal deformation and thermal stress, while improving production efficiency and reducing energy consumption. Intelligent processing parameter feedback operations for the heat treatment of heavy-duty gears are carried out according to the processing parameters required for the optimized strain response. In this stage, the optimized processing parameters will be fed back to the heat treatment equipment on the production line, and the control parameters of the equipment, such as temperature setting, cooling rate, heating duration, etc., will be adjusted in real time.For example, in the actual operation of heat treatment of heavy-duty gears, the heating temperature of the equipment will be automatically adjusted to 875 °C, and the cooling rate will be adjusted to 1.4 °C / min to ensure that the strain response during the processing meets the preset safety and quality standards.

[0071] Furthermore, step S1 includes the following steps:

[0072] Step S11: Use a distributed sensor network to monitor and process the heat treatment processing signals of the heavy-duty gear heat treatment operation in real time to generate gear heat treatment processing data;

[0073] Step S12: Perform gear heat treatment simulation processing based on the gear heat treatment processing data to generate gear heat treatment simulation data;

[0074] Step S13: Analyze the temperature field distribution of gear heat treatment according to the gear heat treatment simulation data to generate gear heat treatment temperature field distribution data;

[0075] Step S14: Analyze the strain behavior of gear heat treatment according to the gear heat treatment simulation data to generate gear heat treatment strain behavior data;

[0076] Step S15: Perform timing, temperature, and strain analysis of gear heat treatment processing based on the gear heat treatment temperature field distribution data and the gear heat treatment strain behavior data to generate gear heat treatment timing-temperature-strain data.

[0077] In the embodiments of the present invention, during the heat treatment process of heavy-duty gears, a set of distributed sensor networks is first deployed. The types of sensors include temperature sensors (such as thermocouple sensors), strain sensors (such as fiber optic sensors or resistance strain gauges), and acceleration sensors (such as piezoelectric acceleration sensors). These sensors are evenly arranged on the gear surface and key areas (such as tooth surfaces, tooth roots, and key contact surfaces). For example, 6 temperature sensors, 3 strain sensors, and 2 acceleration sensors are arranged in the tooth surface and tooth root areas of the gear. The sensors monitor and collect signals generated during the processing in real time, including temperature changes (for example, temperature range: 100°C to 1000°C), strain changes (strain range: -0.01% to 0.05%), and vibration and other parameters. All data is transmitted to the central processing unit (CPU) through a wireless network. The central processing unit filters, denoises, and cleans the received raw data, and uses a band-pass filter (such as 2 Hz to 500 Hz) to remove high-frequency noise and low-frequency fluctuations. After processing, gear heat treatment processing data is generated and stored in a database for subsequent analysis use to ensure the accuracy and integrity of the data. Based on the gear heat treatment processing data, data simulation and simulation are carried out using heat treatment simulation software (such as ANSYS or ABAQUS). The software is used to create a geometric model of the gear, define its material properties (for example, the thermal conductivity of alloy steel material is 45 W / m·K, and the specific heat capacity is 500 J / kg·K), and geometric dimensions (such as gear diameter 200 mm, thickness 20 mm), and input external environment parameters (such as ambient temperature is 25°C, and the cooling medium is water). A multi-physical field coupling model is established, and numerical calculations are carried out by combining the heat conduction equation, fluid mechanics equation, and mechanical strain model. During the simulation process, the thermal loads, external fluid convection, and radiation cooling effects borne by the gear during different heating, holding, and cooling stages are considered. The simulation results generate gear heat treatment simulation data, including temperature fields, strain fields, and thermal stress conditions occurring during heating and cooling, providing a basis for further analysis. Based on the gear heat treatment simulation data, temperature field distribution analysis is carried out. The finite element method (FEM) is used to establish a three-dimensional temperature field model in the simulation software, and the temperature distribution at different time nodes during the heating, holding, and cooling processes of the gear is analyzed. For example, during the heating process, assume the heating temperature is 950°C, the holding time is 30 minutes, and the cooling time is 15 minutes. During the simulation process, the heat source distribution (such as the internal temperature of the heating furnace is evenly distributed), the thermal conductivity of the gear (such as the thermal conductivity of steel is 45 W / m·K), the specific heat capacity (such as the specific heat capacity of steel is 500 J / kg·K), and the thermal convection and radiation effects during the cooling process are considered.Through numerical calculation, temperature field distribution data of each region (such as gear tooth roots, tooth surfaces, etc.) at different time nodes are generated (for example, the tooth root temperature is 850 °C and the tooth surface temperature is 900 °C), providing data support for subsequent strain analysis and optimization of processing parameters. Based on the temperature field distribution data, the strain behavior analysis of gear heat treatment is carried out. According to the temperature field distribution, applying the thermal stress formula and the elastic deformation theory, combined with the temperature changes generated during the gear heat treatment process, strain analysis is carried out. For example, assuming that when the gear is heated to 950 °C, the maximum thermal stress is 300 MPa, according to the material elastic modulus of strain (such as the elastic modulus of steel is 210 GPa), the strain changes on the gear surface and inside are calculated through the strain formula. The finite element method is used to analyze the influence of thermal stress on the gear during the heating and cooling processes, predict the maximum strain values of different parts of the gear (such as the maximum strain on the tooth surface is 0.02%), and further calculate its strain distribution. The generated strain behavior data can provide the internal and external stress distribution of the gear during the heat treatment process, helping to evaluate the deformation problems that occur during the processing. According to the gear heat treatment temperature field distribution data and the gear heat treatment strain behavior data, the timing, temperature, and strain analysis of gear heat treatment processing are carried out. The principal component analysis (PCA) method is used to analyze the temperature and strain data at different time nodes to extract key characteristic patterns. For example, the PCA model extracts the first two principal components by calculating the covariance matrix of temperature and strain data. The first principal component represents the influence of temperature change on strain, and the second principal component represents the coupling relationship between temperature and strain. During the analysis process, the set principal component threshold is 95% of the explained variance ratio, and the first two principal components are selected for calculation. Further, regression analysis (such as linear regression or polynomial regression) is used to analyze the relationship between temperature and strain data, and the specific functional relationship between temperature and strain is obtained. Generate time series-temperature-strain data (such as at time node 50 seconds, when the temperature is 600 °C, the strain is 0.01%), providing a basis for optimizing the processing technology and parameter adjustment. Through this data, the influence of temperature change on strain during the gear heat treatment process can be accurately predicted and used for subsequent process optimization.

[0078] Further, step S2 includes the following steps:

[0079] Step S21: Analyze the gear heat treatment strain influence factors based on the gear heat treatment time series-temperature-strain data to generate gear heat treatment strain influence factors;

[0080] Step S22: Use the gear heat treatment strain response quantification evaluation algorithm to perform strain response quantification evaluation processing on the gear heat treatment strain influence factors under the influence of time series and temperature of gear heat treatment to generate gear heat treatment strain response quantification data;

[0081] Step S23: Perform distribution mapping processing of gear heat treatment strain response quantification based on the gear heat treatment strain response quantification data, and generate gear heat treatment strain response quantification distribution data.

[0082] In the embodiment of the present invention, based on the gear heat treatment time-sequence-temperature-strain data, the analysis of the strain influence factors during the gear heat treatment process is carried out. Statistical analysis methods (such as correlation analysis, regression analysis) are used to conduct a detailed study on the relationship between temperature, strain, and gear material. During the analysis process, first, the temperature, strain data, and material properties (such as elastic modulus, expansion coefficient, strain tensile strength, etc.) at each time node during the gear heat treatment process are extracted. By calculating the temperature change rate, temperature gradient during the heating and cooling processes, etc., the key factors affecting the strain are identified. For example, the expansion coefficient of the gear (such as the expansion coefficient of steel is 12×10 -6( / °C), elastic modulus (for example, the elastic modulus of steel is 210 GPa), temperature change rate (for example, the heating rate from room temperature to 900 °C is 5 °C / min), and temperature gradient (for example, the temperature difference between the tooth root and tooth surface during heating is 100 °C) are important factors affecting strain. By calculating the correlations between these factors, data on the influencing factors of gear heat treatment strain are generated. For example, the influence of the temperature change rate on strain is 0.4, the influence of the expansion coefficient on strain is 0.3, the influence of the elastic modulus is 0.2, and the influence of the temperature gradient is 0.1. The gear heat treatment strain response quantification evaluation algorithm is used to perform quantification evaluation processing on the influencing factors of gear heat treatment strain under the influence of time sequence and temperature during gear heat treatment. Using a self-developed gear heat treatment strain response quantification evaluation algorithm, by inputting the temperature field, strain field, and their influencing factors (such as expansion coefficient, temperature gradient, elastic modulus, strain tensile strength, etc.), the strain response of the gear under different processing conditions is calculated. For example, during the process of heating the gear to 900 °C, the strain response model of the gear will consider the temperature change rate (such as a heating rate of 5 °C / min), material properties (such as the elastic modulus of steel being 210 GPa), and strain field data. The algorithm will calculate the strain distribution based on these inputs and generate strain response quantification data. For example, the strain response in the tooth root area is 0.02%, and the strain response in the tooth surface area is 0.015%. These quantification data represent the strain degree of each area of the gear during heat treatment and output a comprehensive evaluation value (such as the gear strain index being 0.18), which reflects the strain degree that occurs in the gear during the actual processing and its impact on the quality of heat treatment. Through this algorithm, the influence of different temperature fields and time involved on the strain effect of gear heat treatment can be evaluated more precisely. Distribution mapping processing of strain response quantification is carried out according to the gear heat treatment strain response quantification data. Through spatial analysis and data visualization techniques, a distribution map of the strain response during gear heat treatment is generated. First, the gear is divided into multiple small areas (for example, each gear tooth surface is divided into 5 areas, each area being 20 mm × 20 mm). For each area, the strain data at each time point in the heat treatment simulation results are used for mapping, and color identification is carried out according to the magnitude of the strain value. For example, 0.02% strain is mapped to red, 0.01% strain is mapped to yellow, and 0.005% strain is mapped to green. The generated distribution map of strain response quantification visually shows the strain degree of each part of the gear during heat treatment. For example, the strain response in the tooth surface area during heat treatment is 0.015%, and the tooth root area is 0.02%. This distribution map provides a visual basis and can quantify the distribution information of the strain response, providing effective support for optimizing the heat treatment process and avoiding excessive local deformation.

[0083] Further, the gear heat treatment strain influence factors described in step S21 include the gear heat treatment strain elastic modulus factor, the gear heat treatment strain expansion factor, and the gear heat treatment strain tensile strength factor.

[0084] Further, the gear heat treatment strain response quantification evaluation algorithm described in step S22 is as follows:

[0085] ;

[0086] In the formula, is expressed as, represents the continuous reaction time of the heat treatment, represents the reaction temperature data of the gear heat treatment, represents the end reaction time of the heat treatment, represents the start reaction time of the heat treatment, represents the quantification information of the relationship between the gear heat treatment strain elastic modulus factor and temperature, represents the temperature change rate of the gear heat treatment, represents the quantification information of the relationship between the gear heat treatment strain expansion factor and temperature, represents the quantification information of the relationship between the gear heat treatment strain tensile strength factor and temperature, represents the actual reaction temperature data of the gear heat treatment, represents the temperature-dependent heat treatment reaction effect data varying with temperature, represents the temperature change difference between the start and the end.

[0087] The gear heat treatment strain response quantification evaluation algorithm in the present invention. This gear heat treatment strain response quantification evaluation algorithm accurately simulates the strain response of the gear during the heat treatment process by establishing a comprehensive evaluation model based on temperature, strain, and material properties. Each parameter in the formula represents different physical characteristics and key factors in the heat treatment process. Specifically, in the algorithm Represents the quantified value of the strain response of the gear at a given time and reaction temperature. This value reflects the degree of deformation experienced by the gear during the heat treatment process, taking into account the cumulative effect from the start to the end of the heat treatment. Among them, the strain elastic modulus factor at different temperatures describes the ability of the gear material to respond to external loads at different temperatures. Through its relationship with temperature, it can provide the algorithm with quantified information on the changes in material properties of the gear during the heat treatment process. The temperature change rate is used to describe the speed of temperature change during the heat treatment process, which has an important impact on the deformation and stress of the gear. The expansion factor of the gear at different temperatures depicts the expansion effect of temperature change on the size and structure of the gear. The tensile strength factor of the gear material at different temperatures is a key factor in measuring the stress-bearing capacity of the material during the heat treatment process. Another key term in this formula is the heat treatment reaction effect data of the gear that changes with temperature at different temperatures. It can capture the variation laws of heat treatment reactions (such as hardening, tempering, etc.) under different temperature conditions and quantify them as temperature-dependent effects. The range of the inner integral is from the initial temperature at the start of the heat treatment to the current temperature, reflecting the long-term cumulative effect of temperature change on the heat treatment effect. Through this algorithm, the strain response of the gear during the entire heat treatment process and its impact on quality can be accurately calculated. Especially in the heat treatment process, how to predict strain based on changes in factors such as temperature and time, so as to optimize the heat treatment process and prevent gear deformation or insufficient strength caused by temperature non-uniformity or thermal gradient problems. This algorithm based on multi-physics field coupling can provide detailed analysis of each stage during the heat treatment process, providing a scientific basis for accurately controlling the process parameters of gear heat treatment and optimizing the process design, ultimately improving the performance and quality of the gear. By establishing a quantified model of the strain response during the heat treatment process, the trend of strain change of the gear during the heat treatment process can be accurately evaluated, and the complex relationships between factors such as temperature, strain, and tensile strength can be precisely quantified. The core advantage of this algorithm lies in its high physical modeling foundation. Through the dynamic coupling of multiple key parameters such as the temperature change rate, strain elastic modulus, and expansion factor, it provides a multi-dimensional and adjustable strain evaluation framework. The integration of the algorithm enables real-time and accurate calculation of the strain problems that occur during the gear heat treatment process, timely discovery and correction of thermal deformation caused by temperature non-uniformity or temperature gradient, and avoidance of quality problems during the processing.

[0088] Further, step S3 includes the following steps:

[0089] Step S31: Conduct spatial clustering analysis of the heat treatment strain response based on the quantified distribution data of the gear heat treatment strain response to generate spatial clustering data of the heat treatment strain response;

[0090] In the embodiments of the present invention, spatial clustering analysis of heat treatment strain response is performed based on the quantified distribution data of gear heat treatment strain response, and a spatial clustering analysis algorithm is used to classify the strain response data of different regions of the gear. Specifically, the K-means clustering algorithm or the DBSCAN algorithm is used for data classification. In this process, first, the strain data of the gear is divided into several regions. For example, the tooth surface, tooth root, and other key regions of the gear (such as each region has a size of 20 mm × 20 mm). For the strain data of each region (for example, the tooth surface strain response is 0.015%, and the tooth root strain response is 0.02%), clustering processing is performed according to its strain magnitude and pattern. The initial center points of the K-means clustering algorithm can randomly select 5 points (for example, representing strain responses of 0.01%, 0.02%, 0.03%, 0.05%, and 0.07% respectively). The algorithm calculates the distance from each data point to these center points and performs iterative updates until the clustering result converges. Finally, the clustering result divides the strain data into multiple subsets, and each subset represents a similar strain response pattern. For example, the tooth surface region is grouped into one group, the tooth root region is grouped into another group, and other regions are classified according to the characteristics of the strain response. The generated spatial clustering data of heat treatment strain response provides a basis for subsequent strain performance grouping.

[0091] Step S32: Perform heat treatment strain response performance grouping processing based on the spatial clustering data of heat treatment strain response characteristics to generate heat treatment strain response performance group data;

[0092] In the embodiments of the present invention, based on the spatial clustering data of heat treatment strain response, heat treatment strain response performance grouping processing is performed. For each strain characteristic data after spatial clustering (for example, the strain value of a certain type of aggregated data is between 0.015% and 0.03%, representing the tooth surface region), its performance under different temperatures and process parameters is analyzed. Taking the tooth surface region as an example, assuming that its temperature range during the heating process is 600°C to 900°C and the cooling rate is 2°C / min, analyze the strain response performance of this region under different process parameters. In this process, by comparing the strain changes under different temperatures and cooling rates, the strain characteristic pattern of this region can be determined and compared with the strain responses of other regions. Through clustering analysis, similar strain response characteristics are divided into the same group (for example, the tooth surface region with a temperature change range of 600°C to 900°C is grouped into one group). Heat treatment strain response performance group data is generated, and the strain characteristics within each group are relatively consistent, facilitating subsequent targeted demand index fitting processing.

[0093] Step S33: Based on the preset gear heat treatment strain requirement indicators and the heat treatment strain response performance group data, perform the fitting process of the requirement indicators for each strain response performance group to generate the heat treatment strain response performance - requirement indicator fitting data;

[0094] In the embodiment of the present invention, according to the strain performance group data and in combination with the preset gear heat treatment strain requirement indicators, perform the fitting process of the strain response performance - requirement indicators. Assume that the preset strain requirement indicators include the maximum allowable strain (for example, the maximum allowable strain in the tooth surface area is 0.02%) and the strain distribution uniformity in the tooth root area (for example, the maximum difference in tooth root strain distribution is 0.005%). Compare the data of each strain performance group with these preset strain requirement indicators. For example, for the tooth surface area, its strain response is 0.015%, which meets the preset maximum allowable strain (0.02%). If the strain response in the tooth root area is 0.025%, exceeding the allowable maximum strain, it is necessary to adjust the process parameters (such as reducing the heating temperature or changing the cooling rate). Optimize the strain response characteristics of each group through mathematical fitting methods (such as the least - squares method or genetic algorithm) to ensure that it meets the preset requirement indicators and generate the heat treatment strain response performance - requirement indicator fitting data.

[0095] Step S34: Analyze the processing parameters required for the strain response according to the heat treatment strain response performance - requirement indicator fitting data to generate the processing parameters required for the strain response;

[0096] In the embodiment of the present invention, according to the heat treatment strain response performance - requirement indicator fitting data, analyze the processing parameters required for the strain response. By analyzing the processing parameters of each strain performance group under different strain requirements, determine the processing parameters of each group. Assume that the optimal processing parameters for the tooth surface area are a heating temperature of 850 °C and a cooling rate of 2 °C / min, and the processing parameters for the tooth root area are a heating temperature of 900 °C and a cooling rate of 1 °C / min to obtain the processing parameters required for the strain response. These parameters will be used for the next processing simulation and optimization. Through these processing parameters, ensure that the gear realizes the minimum deformation and stress distribution during the heat treatment process, meets the quality requirements, and improves production efficiency.

[0097] Further, step S4 includes the following steps:

[0098] Step S41: Based on the processing parameters required for the strain response, perform the simulation analysis of the processing required for the strain response to generate the simulation data of the processing required for the strain response;

[0099] In the embodiments of the present invention, a demand processing simulation analysis of strain response is carried out based on the processing parameters of strain response requirements. Using CAE (Computer Aided Engineering) simulation software, such as Simulia or COMSOL, a demand processing simulation analysis of strain response is carried out for the gear heat treatment process. First, a three-dimensional geometric model of the gear is established in the software, and the temperature range, cooling rate and other related process parameters are set according to the processing parameters. For example, assume the processing parameters are: heating temperature 850°C, cooling rate 2°C / min. During the simulation process, through the finite element analysis (FEA) method, the changes of various indicators in the strain response process are simulated, such as thermal deformation, thermal stress and strain distribution. The simulation results will predict the strain behavior of the gear under specific process conditions and give the deformation and thermal stress distribution. For example, the simulation shows that during the heating process of the gear, the temperature in the tooth surface area rises relatively fast, resulting in an increase in strain, while the strain in the tooth root area is relatively small. This simulation result provides a basis for the subsequent adjustment of processing parameters to ensure that the strain during the processing is controlled within the allowable range.

[0100] Step S42: Perform a temperature transfer distribution analysis of gear heat treatment according to the gear heat treatment temperature field distribution data, and generate gear heat treatment temperature transfer distribution data;

[0101] In the embodiments of the present invention, a temperature transfer distribution analysis is carried out according to the simulation data and the gear heat treatment temperature field distribution data. First, by establishing a finite element model of the temperature field, the geometric model of the gear is coupled with the temperature field to simulate the heat transfer process inside the gear. Assume the initial temperature of the gear is room temperature (20°C). During the heating process, the heat provided by the external heat source is transferred to the inside through the gear surface, and the temperature gradually rises. In the simulation, considering the thermal conductivity, specific heat capacity of the gear material and boundary conditions, such as the temperature of the heating furnace is 900°C, analyze how the heat is transferred in each area of the gear. The generated temperature transfer distribution data can show the temperature distribution of each point inside the gear. For example, the temperature in the tooth surface area is 850°C, and the temperature in the tooth root area is 780°C. This data reveals the heat transfer law of different areas of the gear, which can help optimize the temperature control during cooling and heating, and improve the consistency and uniformity of heat treatment.

[0102] Step S43: Perform a simulated response heat gradient distribution analysis according to the gear heat treatment temperature transfer distribution data and the strain response demand processing simulation data, and generate simulated response heat gradient distribution data;

[0103] In the embodiments of the present invention, based on the temperature transfer distribution data, the change of the heat gradient is further analyzed. By combining the thermal stress and strain data in the gear processing process, the simulated response heat gradient distribution data is calculated and generated. The heat gradient refers to the temperature difference between different regions of the gear, which directly affects the thermal stress distribution of the gear. Assume that during the cooling process, the temperature of the gear surface rapidly drops from 850 °C to 300 °C, while the internal temperature drops more slowly, resulting in an obvious temperature gradient. Using finite element analysis, by simulating the change of the heat gradient, the generated simulated response heat gradient distribution data reveals the stress and strain responses of the gear at different cooling rates. For example, when the cooling rate is 1 °C / min, the temperature difference between the tooth surface and the tooth root of the gear is 50 °C; while when the cooling rate is 3 °C / min, the temperature difference between the tooth surface and the tooth root increases to 80 °C. This data can provide guidance for the control of the heat distribution during the processing, helping to ensure the uniform distribution of thermal stress and strain during the processing.

[0104] Step S44: Perform a simulated response analysis of the machining residual heat through the simulated response heat gradient distribution data to generate simulated response machining residual heat data.

[0105] In the embodiments of the present invention, based on the simulated response heat gradient distribution data, the problem of residual heat during the processing is analyzed. During the heat treatment process, due to the temperature gradient difference in different regions, residual heat will be generated inside the gear, resulting in uneven thermal stress and deformation problems. For example, assume that during the gear heating process, due to the excessive temperature gradient, the tooth root region fails to reach the target temperature completely, while the temperature of the tooth surface region is too high, resulting in large thermal deformation of the tooth surface. By calculating the residual heat distribution in different regions inside the gear, the simulated response machining residual heat data is obtained. This data shows the difference in residual heat between the tooth surface and the tooth root. The residual heat in the tooth surface region is 15 J / g, while that in the tooth root region is 5 J / g. Analyzing this data is used to identify the deformation problems caused by uneven heat, such as the higher residual heat in the tooth surface region causing the gear to bend or warp. According to these data, further adjust the temperature control during the heating and cooling processes, avoid excessive temperature differences, reduce the influence of residual heat, and finally optimize the machining quality of the gear.

[0106] Furthermore, step S5 includes the following steps:

[0107] Step S51: Perform a safety detection and adjustment process on the strain response required machining parameters through the simulated response machining residual heat data, including: when the simulated response machining residual heat data is greater than the preset machining residual heat abnormal deformation threshold, execute step S511; or, when the simulated response machining residual heat data is not greater than the preset machining residual heat abnormal deformation threshold, execute step S512;

[0108] Step S511: Mark the strain reaction demand processing parameter corresponding to the simulated response processed residual heat data as the residual heat abnormal strain reaction demand processing parameter, and perform correction adjustment of the strain reaction demand processing parameter for the residual heat abnormal deformation of the residual heat abnormal strain reaction demand processing parameter, so as to obtain the strain reaction demand processing parameter corrected for residual heat abnormality, and feedback the strain reaction demand processing parameter corrected for residual heat abnormality to step S34 for abnormal correction adjustment operation of the strain reaction demand processing parameter;

[0109] Step S512: Mark the strain reaction demand processing parameter corresponding to the simulated response processed residual heat data as the strain reaction demand safety processing parameter;

[0110] Step S52: Perform intelligent optimization iteration processing on the processing parameter based on the strain reaction demand safety processing parameter to generate the optimized processing parameter for the strain reaction demand;

[0111] Step S53: Execute the intelligent processing parameter feedback operation of the heavy-duty gear heat treatment through the optimized processing parameter for the strain reaction demand.

[0112] In the embodiments of the present invention, the safety detection and adjustment of the processing parameters required for the strain response during the gear heat treatment process are carried out according to the simulated response of the residual heat data of the processing. Specifically, during implementation, first, a preset abnormal deformation threshold of the processing residual heat is set. For example, the threshold is set to a residual heat of 30 J / g. When the simulated response of the processing residual heat data is greater than this threshold, it indicates that there is a relatively significant residual heat during the heat treatment process, resulting in abnormal deformation or unqualified processing. At this time, the system executes step S511 to perform abnormal correction on the processing parameters required for the strain response. Conversely, when the simulated response of the processing residual heat data is less than or equal to the preset threshold, step S512 is executed to mark the processing parameters required for the strain response as safe processing parameters without adjustment. When the simulated response of the processing residual heat data is greater than the preset abnormal deformation threshold of the processing residual heat, correction and adjustment of the abnormal deformation of the residual heat are performed on the relevant processing parameters required for the strain response. The processing parameters required for the strain response corresponding to the simulated response of the processing residual heat data are marked as the processing parameters required for the abnormal strain response of the residual heat. These parameters include heating temperature, cooling rate, time period, etc. In this case, the purpose of correcting these parameters is to reduce the generation of residual heat and avoid thermal stress and non-uniform deformation. For example, assume the original processing parameters are: heating temperature 920°C, cooling rate 2°C / min. After calculation and adjustment, the adjusted processing parameters are: heating temperature 880°C, cooling rate 1.5°C / min. The optimized cooling rate and temperature will help reduce the residual heat generated during the processing. The adjusted processing parameters required for the strain response will return to step S34 for further abnormal correction and adjustment operations, and the corresponding steps after step S34 will be re-executed until the output simulated response of the processing residual heat data is not greater than the preset abnormal deformation threshold of the processing residual heat, thereby ensuring that the strain control and heat distribution during the processing reach an ideal state. When the simulated response of the processing residual heat data is less than or equal to the preset abnormal deformation threshold of the processing residual heat, the processing parameters required for the strain response are marked as the safe processing parameters required for the strain response, which means that these processing parameters can be used in actual production without causing abnormal thermal stress or deformation problems. In this case, no further adjustment is required, and production can be directly carried out using these parameters. For example, if the simulated response of the processing residual heat data is 25 J / g, lower than the threshold of 30 J / g, it indicates that the heat treatment process of the gear is within a safe range, and production can continue according to the original parameters without additional adjustment. Based on the safe processing parameters required for the strain response, enter the intelligent optimization and iteration processing stage of the processing parameters. In this stage, machine learning algorithms (such as support vector machine SVM or reinforcement learning) are applied to further optimize the safe processing parameters required for the strain response.Assume that the safe processing parameters are: heating temperature 880 °C, cooling rate 1.5 °C / min. After optimization, the optimized processing parameters required for the strain reaction are: heating temperature 875 °C, cooling rate 1.4 °C / min. During this optimization process, the algorithm comprehensively considers multiple factors, such as processing accuracy, time efficiency, energy efficiency, etc., to generate a set of optimized processing parameters. For example, the optimized heating temperature and cooling rate can minimize thermal deformation and thermal stress to the greatest extent, while improving production efficiency and reducing energy consumption. Perform intelligent processing parameter feedback operations for the heat treatment of heavy-duty gears according to the optimized processing parameters required by the root strain reaction. At this stage, the optimized processing parameters will be fed back to the heat treatment equipment on the production line, and the control parameters of the equipment, such as temperature setting, cooling rate, heating duration, etc., will be adjusted in real time. For example, in the actual operation of the heat treatment of heavy-duty gears, the heating temperature of the equipment will be automatically adjusted to 875 °C, and the cooling rate will be adjusted to 1.4 °C / min to ensure that the strain reaction during the processing meets the preset safety and quality standards.

[0113] Further, step S52 includes the following steps:

[0114] Step S521: Perform data integration modeling processing based on the safe processing parameters required by the strain reaction and the corresponding simulated response processing residual heat data to generate a safe processing parameter-residual heat data model required by the strain reaction;

[0115] Step S522: Perform simulation analysis of the hardened layer processing of the residual heat based on the strain reaction quantification distribution data of the gear heat treatment and the safe processing parameter-residual heat data model required by the strain reaction to generate simulated data for the hardened layer processing of the residual heat;

[0116] Step S523: Analyze the benefit characteristics of the hardened layer processing of the residual heat for the simulated data of the hardened layer processing of the residual heat to generate benefit characteristic data for the hardened layer processing of the residual heat;

[0117] Step S524: Use the benefit characteristic data of the hardened layer processing of the residual heat as the processing parameter optimization coefficient, and perform intelligent optimization iteration processing on the safe processing parameters required by the strain reaction through the processing parameter optimization coefficient to generate optimized processing parameters required by the strain reaction.

[0118] In the embodiments of the present invention, the data integration modeling technology is adopted to integrate the strain response demand safety processing parameters and their corresponding residual heat data. First, the processing parameters under different heat treatment conditions are collected, such as heating temperature, cooling rate, heating time, etc., and a complete data set is established by combining the residual heat data generated during the gear processing. Then, the support vector machine (SVM) or decision tree algorithm is used for modeling. In the SVM modeling process, the Gaussian kernel function (RBF) is selected, the penalty parameter C is adjusted to be between 1.0 and 10.0, and the maximum number of iterations is set to 1000 times. The best support vectors are selected through cross-validation. Through this modeling process, the relationship between the distribution of residual heat and processing parameters during the gear heat treatment under different processing conditions can be predicted, thus providing data support for the subsequent optimization of the heat treatment process. According to the strain response demand safety processing parameter-residual heat data model, the residual heat hardened layer processing simulation analysis is carried out. Using simulation software (such as ANSYS or COMSOL), combined with the physical characteristics of the hardened layer effect, the quality changes of the hardened layer under different processing parameters (such as heating time, temperature, and cooling rate) are simulated. In the simulation of the hardened layer effect, the heating temperature is set to 850°C, the cooling rate is 1.5°C / min, and the depth (0.8 mm to 1.5 mm), hardness (HRC58 to HRC62), and uniformity (uniform hardened layer distribution of 0.8 to 1.2 mm) of the hardened layer are simulated. The simulation results will provide key data for the uniformity and quality of the gear hardened layer, and reveal the influence of heat treatment on the gear hardened layer under different processing conditions, providing a basis for the subsequent optimization plan. Based on the residual heat hardened layer processing simulation data, the hardened layer processing benefit characteristic analysis is carried out. Through characteristic analysis algorithms, such as clustering analysis or principal component analysis (PCA), the key factors affecting the hardened layer quality are extracted. When using PCA, data dimensionality reduction processing is performed on the characteristics of the hardened layer, such as hardness, thickness, and uniformity. The number of principal components is set to 2, and 95% of the variance is maintained. After standardizing all input data (mean is 0, variance is 1), the quality characteristic data of the hardened layer is transformed into a new feature space, and the principal components that can best represent the hardened layer performance are extracted. Through characteristic analysis, the key factors affecting the hardened layer quality are identified, providing guidance for the subsequent optimization of the processing plan. Using the hardened layer processing benefit characteristic data as the coefficient for optimizing the processing parameters, the intelligent optimization iteration processing of the processing parameters is carried out. Machine learning algorithms such as neural networks or gradient boosting decision trees (GBDT) are used to optimize the processing parameters, and the constraint function of the model is designed based on the simulated response processing residual heat data corresponding to the strain response demand safety processing parameters not being greater than the preset processing residual heat abnormal deformation threshold. The neural network adopts a 3-layer structure, with 64 neurons in each layer, the activation function is selected as ReLU, the learning rate is 0.001, and the number of training times is 100 times; the batch size is set to 32.The Gradient Boosting Decision Tree (GBDT) uses a maximum tree depth of 5, a learning rate of 0.1, and 100 weak learners in the form of trees. Using these algorithms, the hardened layer machining benefit feature data is converted into optimization coefficients, and then the safe machining parameters for strain response requirements are optimized. Through the optimized machining parameters (such as the temperature adjusted to 900°C and the cooling rate of 1.0°C / min), the machining effect is ensured to be optimal, and it is guaranteed that no deformation or breakage of the gear will occur during the heat treatment machining.

[0119] This specification provides an intelligent simulation analysis system for heavy-duty gear machining, which is used to execute the intelligent simulation analysis method for heavy-duty gear machining as described above. The intelligent simulation analysis system for heavy-duty gear machining includes:

[0120] A gear heat treatment simulation and analysis module, which is used to use a distributed sensor network to monitor and process the heat treatment machining signals of heavy-duty gear heat treatment operations in real time, and generate gear heat treatment machining data; perform gear heat treatment simulation processing based on the gear heat treatment machining data to generate gear heat treatment simulation data; perform time series, temperature, and strain analysis of gear heat treatment machining based on the gear heat treatment simulation data to generate gear heat treatment time series-temperature-strain data;

[0121] A gear heat treatment strain response analysis module, which is used to perform a quantitative distribution analysis of the gear heat treatment strain response based on the gear heat treatment time series-temperature-strain data to generate gear heat treatment strain response quantitative distribution data;

[0122] A strain response requirement machining parameter analysis module, which is used to perform a fitting process of the requirement index of the heat treatment strain response through a preset gear heat treatment strain requirement index and the gear heat treatment strain response quantitative distribution data to generate heat treatment strain response performance-requirement index fitting data; perform strain response requirement machining parameter analysis based on the heat treatment strain response performance-requirement index fitting data to generate strain response requirement machining parameters;

[0123] A simulated response machining residual heat analysis module, which is used to perform a demand machining simulation analysis of the strain response based on the strain response requirement machining parameters to generate strain response demand machining simulation data; perform a simulated response machining residual heat analysis based on the strain response demand machining simulation data to generate simulated response machining residual heat data;

[0124] The intelligent optimization iteration module for processing parameters is used to perform safety detection and adjustment processing on the strain response demand processing parameters by simulating the response of the residual heat data of the processed parts, so as to obtain the safe processing parameters of the strain response demand; perform intelligent optimization iteration processing on the processing parameters based on the safe processing parameters of the strain response demand to generate the optimized processing parameters of the strain response demand; and execute the intelligent processing parameter feedback operation of the heavy-duty gear heat treatment through the optimized processing parameters of the strain response demand.

[0125] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be encompassed within the present invention.

[0126] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent simulation analysis method for heavy-duty gear machining, characterized in that, It includes the following steps: Step S1: Use a distributed sensor network to perform real-time monitoring and processing of heat treatment processing signals for heavy-duty gear heat treatment processing operations, generating gear heat treatment processing data; perform gear heat treatment simulation processing based on the gear heat treatment processing data, generating gear heat treatment simulation data; perform timing, temperature, and strain analysis of gear heat treatment processing based on the gear heat treatment simulation data, generating gear heat treatment timing-temperature-strain data; Step S2: Perform gear heat treatment strain reaction quantitative distribution analysis based on the gear heat treatment timing-temperature-strain data, generating gear heat treatment strain reaction quantitative distribution data; Step S3: Perform demand index fitting processing of heat treatment strain reaction through a preset gear heat treatment strain demand index and gear heat treatment strain reaction quantitative distribution data, generating heat treatment strain reaction performance-demand index fitting data; perform strain reaction demand processing parameter analysis based on the heat treatment strain reaction performance-demand index fitting data, generating strain reaction demand processing parameters; Step S4: Perform demand processing simulation analysis of strain reaction based on the strain reaction demand processing parameters, generating strain reaction demand processing simulation data; perform simulated response processing residual heat analysis based on the strain reaction demand processing simulation data, generating simulated response processing residual heat data; Step S5: Perform safety detection and adjustment processing of the strain reaction demand processing parameters through the simulated response processing residual heat data to obtain strain reaction demand safety processing parameters; perform intelligent optimization and iteration processing of the processing parameters based on the strain reaction demand safety processing parameters, generating strain reaction demand optimized processing parameters; perform intelligent processing parameter feedback operations for heavy-duty gear heat treatment through the strain reaction demand optimized processing parameters.

2. The intelligent simulation analysis method for heavy-duty gear machining according to claim 1, wherein Step S1 includes the following steps: Step S11: Use a distributed sensor network to perform real-time monitoring and processing of heat treatment processing signals for heavy-duty gear heat treatment processing operations, generating gear heat treatment processing data; Step S12: Perform gear heat treatment simulation processing based on the gear heat treatment processing data, generating gear heat treatment simulation data; Step S13: Perform gear heat treatment temperature field distribution analysis based on the gear heat treatment simulation data, generating gear heat treatment temperature field distribution data; Step S14: Perform gear heat treatment strain behavior analysis based on the gear heat treatment simulation data, generating gear heat treatment strain behavior data; Step S15: Perform timing, temperature, and strain analysis of gear heat treatment processing based on the gear heat treatment temperature field distribution data and the gear heat treatment strain behavior data, generating gear heat treatment timing-temperature-strain data.

3. The intelligent simulation analysis method for heavy-duty gear machining according to claim 1, wherein Step S2 includes the following steps: Step S21: Perform gear heat treatment strain influence factor analysis based on the gear heat treatment timing-temperature-strain data, generating gear heat treatment strain influence factors; Step S22: Use the gear heat treatment strain reaction quantitative evaluation algorithm to perform strain reaction quantitative evaluation processing of the gear heat treatment strain influence factors under the influence of timing and temperature of gear heat treatment, generating gear heat treatment strain reaction quantitative data; Step S23: Perform distribution mapping processing on the gear heat treatment strain response quantification data to generate gear heat treatment strain response quantification distribution data.

4. The intelligent simulation analysis method for heavy-duty gear machining according to claim 3, characterized in that The gear heat treatment strain influence factors described in Step S21 include the gear heat treatment strain elastic modulus factor, the gear heat treatment strain expansion factor, and the gear heat treatment strain tensile strength factor.

5. The intelligent simulation analysis method for heavy-duty gear machining according to claim 4, characterized in that, The gear heat treatment strain response quantification evaluation algorithm described in Step S22 is as follows: ； In the formula, is expressed as which represents the continuous reaction time of heat treatment, which represents the reaction temperature data of gear heat treatment, which represents the end reaction time of heat treatment, which represents the starting reaction time of heat treatment, which represents the quantified information on the relationship between the strain elastic modulus factor and temperature of gear heat treatment, which represents the temperature change rate of gear heat treatment, which represents the quantified information on the relationship between the strain expansion factor and temperature of gear heat treatment, which represents the quantified information on the relationship between the strain tensile strength factor and temperature of gear heat treatment, which represents the initial reaction temperature data of gear heat treatment, which represents the temperature-dependent heat treatment reaction effect data varying with temperature, which represents the temperature change difference between the start and the end.

6. The intelligent simulation analysis method for heavy-duty gear machining according to claim 1, wherein Step S3 includes the following steps: Step S31: Perform spatial clustering analysis of the heat treatment strain response based on the gear heat treatment strain response quantification distribution data to generate heat treatment strain response spatial clustering data; Step S32: Perform heat treatment strain response performance grouping processing based on the heat treatment strain response feature spatial clustering data to generate heat treatment strain response performance group data; Step S33: Perform demand index fitting processing for each strain response performance group based on the preset gear heat treatment strain demand index and the heat treatment strain response performance group data to generate heat treatment strain response performance-demand index fitting data; Step S34: Perform strain response demand processing parameter analysis based on the heat treatment strain response performance-demand index fitting data to generate strain response demand processing parameters.

7. The intelligent simulation analysis method for heavy-duty gear machining according to claim 2, wherein Step S4 includes the following steps: Step S41: Perform demand processing simulation analysis of the strain response based on the strain response demand processing parameters to generate strain response demand processing simulation data; Step S42: Perform temperature transfer distribution analysis of the gear heat treatment based on the gear heat treatment temperature field distribution data to generate gear heat treatment temperature transfer distribution data; Step S43: Perform simulated response heat gradient distribution analysis based on the gear heat treatment temperature transfer distribution data and the strain response demand processing simulation data to generate simulated response heat gradient distribution data; Step S44: Perform simulated response processing residual heat analysis through the simulated response heat gradient distribution data to generate simulated response processing residual heat data.

8. The intelligent simulation analysis method for heavy-duty gear machining according to claim 6, characterized in that Step S5 includes the following steps: Step S51: Perform safety detection and adjustment processing on the strain response demand processing parameters through the simulated response processing residual heat data, including: when the simulated response processing residual heat data is greater than the preset processing residual heat abnormal deformation threshold, execute Step S511; or, when the simulated response processing residual heat data is not greater than the preset processing residual heat abnormal deformation threshold, execute Step S512; Step S511: Mark the strain response demand processing parameters corresponding to the simulated response processing residual heat data as residual heat abnormal strain response demand processing parameters, and perform strain response demand processing parameter correction adjustment for the residual heat abnormal deformation of the residual heat abnormal strain response demand processing parameters to obtain the residual heat abnormal corrected strain response demand processing parameters, and feedback the residual heat abnormal corrected strain response demand processing parameters to Step S34 for abnormal correction adjustment operation of the strain response demand processing parameters; Step S512: Mark the strain response demand processing parameters corresponding to the simulated response residual heat data as strain response demand safe processing parameters; Step S52: Perform intelligent optimization iteration processing on the processing parameters based on the strain response demand safe processing parameters to generate strain response demand optimized processing parameters; Step S53: Execute the intelligent processing parameter feedback operation of heavy-duty gear heat treatment through the strain response demand optimized processing parameters.

9. The intelligent simulation analysis method for heavy-duty gear machining according to claim 8, characterized in that Step S52 includes the following steps: Step S521: Perform data integration modeling processing according to the strain response demand safe processing parameters and the corresponding simulated response residual heat data to generate a strain response demand safe processing parameter - residual heat data model; Step S522: Perform simulated analysis of hardened layer machining of residual heat based on the gear heat treatment strain response quantization distribution data and the strain response demand safe processing parameter - residual heat data model to generate simulated residual heat hardened layer machining data; Step S523: Analyze the hardened layer machining benefit characteristics of the simulated residual heat hardened layer machining data to generate simulated residual heat hardened layer machining benefit characteristic data; Step S524: Use the simulated residual heat hardened layer machining benefit characteristic data as the processing parameter optimization coefficient, and perform intelligent optimization iteration processing on the strain response demand safe processing parameters through the processing parameter optimization coefficient to generate strain response demand optimized processing parameters.

10. An intelligent simulation analysis system for overloaded gear machining, characterized in that, An intelligent simulation analysis method for performing heavy-duty gear machining as described in claim 1, the intelligent simulation analysis system for heavy-duty gear machining includes: A gear heat treatment simulation analysis module, configured to use a distributed sensor network to perform real-time monitoring and processing of heat treatment processing signals for heavy-duty gear heat treatment operations to generate gear heat treatment processing data; perform gear heat treatment simulation processing based on the gear heat treatment processing data to generate gear heat treatment simulation data; perform timing, temperature, and strain analysis of gear heat treatment processing based on the gear heat treatment simulation data to generate gear heat treatment timing - temperature - strain data; A gear heat treatment strain response analysis module, configured to perform gear heat treatment strain response quantization distribution analysis based on the gear heat treatment timing - temperature - strain data to generate gear heat treatment strain response quantization distribution data; A strain response demand processing parameter analysis module, configured to perform demand index fitting processing of heat treatment strain response through a preset gear heat treatment strain demand index and the gear heat treatment strain response quantization distribution data to generate heat treatment strain response performance - demand index fitting data; perform strain response demand processing parameter analysis based on the heat treatment strain response performance - demand index fitting data to generate strain response demand processing parameters; A simulated response machining residual heat analysis module, configured to perform demand machining simulation analysis of strain response based on the strain response demand processing parameters to generate strain response demand machining simulation data; perform simulated response machining residual heat analysis based on the strain response demand machining simulation data to generate simulated response machining residual heat data; The intelligent optimization iteration module for processing parameters is used to perform safety detection and adjustment processing on the strain response demand processing parameters by simulating the response of the residual heat data of the processed parts, so as to obtain the safe processing parameters for the strain response demand; perform intelligent optimization iteration processing on the processing parameters based on the safe processing parameters for the strain response demand to generate the optimized processing parameters for the strain response demand; and execute the intelligent processing parameter feedback operation of the heavy-duty gear heat treatment through the optimized processing parameters for the strain response demand.

Images