Modification parameter configuration method of large-module involute gear for forming gears
Through genetic algorithms and historical design data, the prediction model is constructed and gear displacement parameters are optimized, which solves the problems of low efficiency and difficulty in automation of traditional design methods, realizes the intelligence and automation of gear design, and improves the reliability and efficiency of design.
Patent Information
- Application Number
- CN202411110622.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-14
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-08-14
AI Technical Summary
Traditional gear design methods are inefficient and error-prone, making it difficult to find the global optimal solution to gear design within a reasonable time, especially in the face of complex design parameters and optimization goals, and the prior art is difficult to realize intelligent automation design of gear displacement parameters.
By collecting the basic parameters of large-module involute gears, setting the initial range of displacement parameters, designing optimization objective functions, and using genetic algorithms to perform multi-objective optimization, combining historical design data to build a displacement parameter prediction model, and performing multiple aspects Verify to ensure the scientificity and effectiveness of the design.
It improves gear design efficiency, optimizes parameter settings, ensures design reliability and intelligent prediction, realizes intelligent and automated design of gear displacement parameters, and improves the overall performance of gears.
Smart Images

Figure CN118643620B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of gear manufacturing, and more specifically to a method for configuring displacement parameters of a large-module involute gear facing a formed gear. Background Art
[0002] Large-module involute gears are widely used in heavy machinery, wind power generation, ship propulsion systems and other fields because of their ability to transmit high power and high torque. However, with the increasing demand for industrial applications, the design and manufacture of gears are also facing higher requirements, including improving the load-bearing capacity of gears, extending service life, and improving transmission efficiency. This requires that gear design must find an optimal balance between multiple goals to ensure that the gears can still operate stably and reliably under complex working conditions.
[0003] Traditional gear design methods often rely on experience and manual calculations, which are inefficient and prone to errors. Especially when faced with complex design parameters and optimization goals, traditional methods are difficult to find the global optimal solution within a reasonable time.
[0004] With the rapid development of computer technology and artificial intelligence, it has become a trend to use computer-aided design (CAD) and computer-aided engineering (CAE) to optimize gear design.
[0005] For example, the Chinese patent with the publication number CN102954178A discloses a method for calculating the processing parameters of non-zero-pitch cone integrated displacement bevel gears. According to the parameters given in the product design drawing, in the process part, only the pitch circle diameter, pitch circle module, pitch circle tooth angle and pitch circle theoretical arc tooth thickness need to be calculated; the processing parameters of the bevel gear with non-zero-pitch cone integrated displacement tooth shape are determined according to the four parameters of pitch circle diameter, pitch circle module, pitch circle tooth angle and pitch circle theoretical arc tooth thickness. Using the calculation method of the invention, the calculation speed and accuracy are greatly improved, and the repeated calculation process is reduced; process technicians can conveniently, quickly and accurately calculate the machine tool adjustment parameters required for non-zero-pitch cone integrated displacement bevel gears.
[0006] In gear design, the selection of displacement parameters is crucial. Displacement parameters directly affect the meshing characteristics, strength and life of the gear. In order to optimize the displacement parameters, designers need to consider a large number of factors, including the basic geometric parameters of the gear. However, there are complex nonlinear relationships between these factors, which increases the difficulty of optimization design. In addition, today's industrial production requires product automation, so the design of displacement parameters also needs to follow the principles of intelligent automation. Summary of the invention
[0007] In order to solve the above problems, an embodiment of the present invention provides a large-module involute gear displacement parameter configuration method for a formed gear, comprising:
[0008] Obtain historical design data through design, build a displacement parameter prediction integrated model through integration, input basic parameters into the displacement parameter prediction integrated model to automatically output displacement parameters;
[0009] The design includes:
[0010] Collect the basic parameters of large-module involute gears; set the initial range of displacement parameters based on preliminary analysis; design the optimization objective function, and use genetic algorithms to perform multi-objective optimization on the displacement parameters to obtain the optimal solution; verify the optimal solution, introduce nonlinear functions, and verify again. After verification, output the activation code to activate the integration;
[0011] The integration includes:
[0012] Construct an initialized displacement parameter prediction model; collect historical design data; use the historical design data to train the initialized displacement parameter prediction model to obtain a displacement parameter prediction integrated model.
[0013] The optimization objective function includes a gear strength function, a transmission efficiency function and a gear life function; the gear strength function includes a bending strength function and a contact strength function;
[0014] Gear strength function:
[0015] ; ;
[0016] In the formula, is the bending strength function, is the tooth force, is the load factor, is the speed coefficient, is the meshing coefficient, is the width coefficient, is the tooth width, is the tooth form coefficient, is the contact strength function, is the contact coefficient, is the elastic coefficient;
[0017] Transmission efficiency function :
[0018] ;
[0019] In the formula, is the power loss, is the input power;
[0020] Gear life function :
[0021] ;
[0022] In the formula, is the basic rated load, is the equivalent load.
[0023] Furthermore, the method of performing multi-objective optimization on displacement parameters using a genetic algorithm includes:
[0024] S1: Generate an initial population, each individual represents a set of displacement parameters, the main body of the displacement parameters is the displacement coefficient, which is defined as the standardized value of the gear tooth profile offset ,The displacement parameters include displacement coefficient and initial angle, and the population size is set to a fixed value by default;
[0025] S2: Define the fitness function and evaluate the fitness of each individual according to the optimization objective function;
[0026] S3: individuals are selected for mating using roulette wheel selection or tournament selection method based on fitness values;
[0027] S4: Perform a crossover operation on the selected individuals, including a single-point crossover operation and a multi-point crossover operation, to generate new individuals;
[0028] S5: Perform mutation operation on the new individuals generated after crossover to increase the diversity of the population. The mutation operation randomly adjusts the displacement coefficient or initial angle.
[0029] S6: The selected individuals, the new individuals generated by the crossover operation and the new individuals generated by the mutation operation form a new population;
[0030] S7: Repeat S2 to S6 until the predetermined number of generations or fitness function converges, at which time the individual with the highest fitness is selected as the optimal solution.
[0031] Furthermore, the method for verifying the optimal solution includes finite element analysis, multi-body dynamics simulation and fatigue life analysis; finite element analysis verifies the stress and deformation of the gear under the working load to determine whether there is stress concentration or deformation; multi-body dynamics simulation simulates the dynamic characteristics of the gear transmission process to evaluate whether the transmission efficiency and meshing performance meet the standards; fatigue life analysis is based on the fatigue characteristics of the gear material to predict whether the service life of the gear under different working conditions meets the standards.
[0032] Furthermore, the nonlinear function is introduced to describe the displacement coefficient by a nonlinear function. The law of change with the change of gear tooth profile.
[0033] Furthermore, the construction framework of the initialized displacement parameter prediction model is based on a neural network algorithm.
[0034] Furthermore, the historical design data includes basic design parameters and displacement parameters corresponding to the basic parameters; and the training method of the initialized displacement parameter prediction model includes:
[0035] The basic parameters in each group of historical design data are used as the input of the displacement parameter prediction model, and the displacement parameters are used as the output. The actual displacement parameters corresponding to the basic parameters in each group of historical design data are used as the prediction targets, and the training target is to minimize the sum of the first prediction accuracies of all predicted displacement parameters. The displacement parameter prediction model is trained until the sum of the first prediction accuracies converges and the training is stopped.
[0036] Furthermore, it also includes:
[0037] Collect material characteristics and working environment;
[0038] Input material properties and working environment into the pre-built influencing factor prediction model and output the influencing factor;
[0039] The displacement parameter prediction model is initialized by training historical design data and influencing factors to obtain the displacement parameter prediction integrated model.
[0040] Furthermore, the material properties include heat treatment information, mechanical properties and chemical composition; the working environment includes lubrication conditions and load conditions; and the method for constructing the influencing factor prediction model includes:
[0041] Convert each set of material properties and working environment into the form of a first eigenvector, where the elements of the first eigenvector include heat treatment information, mechanical properties, chemical composition, lubrication conditions, and load conditions;
[0042] The set of all first eigenvectors is used as the input of the impact factor prediction model, the impact factor prediction model takes the impact factor predicted for each group of first eigenvectors as the output, takes the actual impact factor corresponding to each group of first eigenvectors as the prediction target, and takes minimizing the sum of the second prediction accuracies of all predicted impact factors as the training target; the impact factor prediction model is trained until the sum of the second prediction accuracies reaches convergence and the training is stopped; the impact factor prediction model is a regression model or a decision tree model.
[0043] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for configuring displacement parameters of a large-module involute gear for a formed gear is implemented.
[0044] A computer-readable storage medium stores a computer program, and when the computer program is executed, the method for configuring the displacement parameters of a large-module involute gear for a formed gear is implemented.
[0045] The technical effects and advantages of the large-module involute gear displacement parameter configuration method for formed gears provided by the present invention are as follows:
[0046] Technical effect: The present invention collects basic parameters of large-module involute gears, sets the initial range of displacement parameters, designs optimization objective functions, uses genetic algorithms to perform multi-objective optimization of displacement parameters, obtains the optimal solution, and verifies it in many aspects, thereby ensuring the scientificity and effectiveness of the displacement parameter optimization process; integrates and collects historical design data, constructs an initialized displacement parameter prediction model, and trains the model with historical design data, ultimately obtaining a displacement parameter prediction integrated model, thereby making the displacement parameter prediction process more intelligent and automated.
[0047] Advantages: The present invention has significant advantages in improving design efficiency, optimizing parameter setting, ensuring design reliability and realizing intelligent prediction, and provides a comprehensive and effective solution for the displacement parameter design of large-module involute gears. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 The design and integration flow chart of the displacement parameter prediction integrated model in Example 1;
[0049] Figure 2 It is another design and integration flow chart of the displacement parameter prediction integrated model in Example 2;
[0050] Figure 3 is a schematic diagram of an electronic device of the present invention;
[0051] Figure 4 Schematic diagram of the storage medium of the present invention. DETAILED DESCRIPTION
[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0053] Example 1
[0054] See also Figure 1As shown, the method for configuring displacement parameters of large-module involute gears for formed gears described in this embodiment includes: obtaining historical design data through design, constructing a displacement parameter prediction integrated model through integration, and inputting basic parameters into the displacement parameter prediction integrated model to automatically output the displacement parameters.
[0055] The design includes:
[0056] Collect the basic parameters of large-module involute gears; set the initial range of displacement parameters based on preliminary analysis; design the optimization objective function, and use genetic algorithm to perform multi-objective optimization on the displacement parameters to obtain the optimal solution; verify the optimal solution, introduce nonlinear functions, and verify again. After verification, output the activation code to activate the integration.
[0057] The integration includes:
[0058] Collect historical design data; construct an initialized displacement parameter prediction model; use the historical design data to train the initialized displacement parameter prediction model to obtain a displacement parameter prediction integrated model.
[0059] The basic parameters include module, number of teeth, pitch circle diameter, pressure angle and tooth width; the module is obtained by dividing the pitch circle diameter of the gear by the number of teeth; the module determines the size and strength of the gear, and a larger module is suitable for applications with large loads and low speeds. The module affects the pitch circle diameter, tooth height, tooth thickness and other geometric parameters of the gear, thereby affecting the meshing performance and manufacturing accuracy of the gear; the number of teeth affects the pitch circle diameter of the gear and the center distance of the gear, and different combinations of the number of teeth will affect the meshing angle and transmission efficiency of the gear; according to the application and design requirements, a non-standard pressure angle may be selected to optimize the transmission performance, and the pressure angle affects the gear The meshing characteristics of the gear include the gear's load-bearing capacity and meshing impact. A larger pressure angle can increase the gear's load-bearing capacity, but it will increase the gear's sliding and friction losses. The tooth width affects the gear's load-bearing capacity and stiffness. A wider tooth width can increase the gear's load-bearing capacity, but it will also increase the gear's weight and manufacturing difficulty. The tooth width is related to the gear's friction and lubrication properties, affecting the gear's transmission efficiency and life. The pitch circle diameter determines the gear's installation size and center distance, affecting the gear's overall layout and space occupancy. The pitch circle diameter directly affects the gear's tooth root bending stress and tooth surface contact stress, thereby affecting the gear's strength and life.
[0060] The main body of the displacement parameter is the displacement coefficient. The initial range of the displacement parameter is to set the initial value of the displacement coefficient. The displacement coefficient is defined as the standardized value of the gear tooth profile offset. The preliminary definition of the calculation formula is:
[0061] ;
[0062] In the formula, is the tooth profile offset, obtained based on experience and preliminary analysis, where the preliminary analysis refers to relevant standards such as ISO and AGMA. is the default value; is the modulus.
[0063] The initial range of displacement parameters is set to provide a starting point for displacement parameter optimization, ensure that the optimization process is carried out within a reasonable range, and improve the optimization efficiency and effect.
[0064] The optimization objective function includes a gear strength function, a transmission efficiency function and a gear life function; the gear strength function includes a bending strength function and a contact strength function; the design expression of the optimization objective function includes.
[0065] Bending strength function :
[0066] ;
[0067] In the formula, is the tooth force, is the load factor, is the speed coefficient, is the meshing coefficient, is the width coefficient, is the tooth width, is the tooth form coefficient.
[0068] Contact Strength Function :
[0069] ;
[0070] In the formula, is the contact coefficient, is the elastic coefficient.
[0071] Transmission efficiency function :
[0072] ;
[0073] In the formula, is the power loss, is the input power.
[0074] Gear life function :
[0075] ;
[0076] In the formula, is the basic rated load, is the equivalent load.
[0077] It is particularly noted that the purpose of multi-objective optimization is to find the best combination of displacement parameters and improve the comprehensive performance of gears, and the optimization objective function is the evaluation criterion. In computer software settings, similar function settings require advance framework design.
[0078] The method for multi-objective optimization of displacement parameters using genetic algorithm comprises:
[0079] S1: Generate an initial population. Each individual represents a set of displacement parameters, including displacement coefficient and initial angle. The size of the population is set to a fixed value by default, such as 50.
[0080] S2: Define the fitness function and evaluate the fitness of each individual according to the optimization objective function. The comprehensive calculation method includes:
[0081]
[0082] In the formula, , and All are weights; is the initial angle.
[0083] S3: Individuals are selected for mating using either roulette wheel selection or tournament selection method based on their fitness values.
[0084] S4: Perform a crossover operation on the selected individuals, including a single-point crossover operation and a multi-point crossover operation, to generate new individuals.
[0085] S5: Perform mutation operation on the new individuals generated after crossover to increase the diversity of the population. The mutation operation can randomly adjust the displacement coefficient or initial angle.
[0086] S6: The selected individuals, the new individuals generated by the crossover operation and the new individuals generated by the mutation operation form a new population.
[0087] S7: Repeat S2 to S6 until a predetermined number of generations, such as 100 generations, or the fitness function converges, and then select the individual with the highest fitness as the optimal solution. The optimal solution at this time is the optimal displacement parameter.
[0088] A specific example of using genetic algorithm to perform multi-objective optimization on displacement parameters:
[0089] A high-end engineering machinery company wants to design a large-module involute gear for heavy lifting equipment to improve its load-bearing capacity and service life. Engineers decided to use genetic algorithms to optimize the gear displacement parameters. The following are the specific steps for using genetic algorithms:
[0090] Initial population generation:
[0091] Engineers first determined the basic parameter ranges for gear design, including module, pressure angle, tooth top height coefficient, and displacement coefficient. Using these parameter ranges, 100 different gear displacement parameter combinations were randomly generated. Each set of parameters is called an individual, and all individuals constitute the initial population.
[0092] Fitness evaluation:
[0093] Finite element analysis is performed for each gear designed individually to calculate its bending strength and contact strength under maximum working load. Based on the strength and efficiency of the gear, the fitness value of each individual is calculated. The higher the fitness value, the more superior the displacement parameters of this group.
[0094] choose:
[0095] According to the fitness value, the roulette wheel selection method is used to select individuals with high fitness as parents to provide genetic material for the next generation.
[0096] cross:
[0097] Perform a crossover operation on the selected parent individuals to generate new individuals (offspring). For example, select the displacement parameters of two parent individuals and mix them to generate a new combination of displacement parameters.
[0098] Mutations:
[0099] In order to increase the diversity of the population, the displacement parameters of some offspring individuals are randomly mutated, such as randomly adjusting the value of a displacement parameter.
[0100] Iteration:
[0101] Repeat the above selection, crossover and mutation steps to generate multiple generations of offspring. Each generation will gradually optimize the gear shift parameters based on fitness evaluation.
[0102] Termination conditions:
[0103] After 50 iterations, engineers found that the fitness value had reached a stable level and further optimization would only improve the performance, so the algorithm was terminated.
[0104] Result output:
[0105] Finally, the set of displacement parameters with the highest adaptability was selected as the optimal solution. The engineers used this set of displacement parameters to design a large-module involute gear, which, after testing, showed excellent load-bearing capacity and service life, meeting the design requirements of heavy lifting equipment.
[0106] The optimization objective function comprehensively considers the strength, efficiency, life and manufacturing feasibility of the gear. The genetic algorithm can be used to effectively explore the optimal displacement parameters, improve the gear performance, and provide an effect reference for subsequent training data. Since the displacement parameters have an impact on the overall gear structure and the formed gear itself, the genetic algorithm does not require specific information about the problem, such as the objective function gradient, etc. It has low requirements on the problem form, has global search capabilities, and is not easy to stay at the local optimal solution. It is very beneficial to solving the Pareto frontier solution of the displacement parameters. The Pareto frontier solution here is a mathematical term, which is simply translated as the optimal solution. In the face of the efficiency-first principle in industrial design, the genetic algorithm is easy to implement and its high efficiency is more suitable.
[0107] The method for verifying the optimal solution includes finite element analysis, multi-body dynamics simulation and fatigue life analysis; finite element analysis verifies the stress and deformation of the gear under the working load to determine whether there is stress concentration or excessive deformation; multi-body dynamics simulation simulates the dynamic characteristics of the gear transmission process to evaluate whether the transmission efficiency and meshing performance meet the standards; fatigue life analysis is based on the fatigue characteristics of the gear material to predict whether the service life of the gear under different working conditions meets the standards; verification (such as finite element analysis, multi-body dynamics simulation and fatigue life analysis) is used to ensure that the optimal solution meets the design requirements and ensure the reliability and practicality of the design.
[0108] A specific example of the verification method is:
[0109] An engineering machinery company designed a new large-module involute gear for heavy cranes. They used a genetic algorithm to obtain the optimal combination of displacement parameters, and then verified the gear through finite element analysis (FEA).
[0110] Steps include:
[0111] Use CAD software to create a 3D model of the gear and import it into the finite element analysis software.
[0112] The gear model is meshed with small elements, ensuring that the mesh is fine enough to capture areas of stress concentration.
[0113] Apply the actual loads and boundary conditions that gears are subject to during operation, including torque, speed, and contact forces.
[0114] Run a finite element analysis to calculate the stresses and deformations of the gears under load.
[0115] Observe the stress distribution and deformation of the gear, and focus on checking whether there are areas of stress concentration or excessive deformation.
[0116] After verifying the finite element analysis results, engineers performed multibody dynamics simulation on the gear transmission system to evaluate its dynamic characteristics and transmission performance.
[0117] Steps include:
[0118] Model the gear transmission system in multibody dynamics simulation software, including gears, shafts, bearings, and other related components.
[0119] Input the gear geometry, mass properties and displacement parameters, and set the operating conditions of the transmission system, such as speed, load, etc.
[0120] Perform dynamic simulation to simulate the meshing, transmission and vibration of gears during operation.
[0121] Evaluate the dynamic response of gear transmission systems, including transmission efficiency, meshing performance, vibration and noise levels.
[0122] To ensure the reliability of gears in long-term use, engineers conduct fatigue life analysis on the gears.
[0123] Steps include:
[0124] Collect fatigue property data of gear materials, including fatigue limit and SN curve, etc.
[0125] Define the load spectrum of the gear under actual working conditions and consider the variable loads under different working conditions.
[0126] Based on the stress results of finite element analysis, the stress range of the gear under each load cycle is calculated.
[0127] Use fatigue life analysis software to input stress cycles and material fatigue properties to predict the fatigue life of gears under different working conditions.
[0128] Based on the fatigue life analysis results, the reliability of the gears within their expected service life is evaluated.
[0129] The nonlinear function is introduced to further improve the gear meshing performance and processing feasibility, and the displacement coefficient is described by the nonlinear function. The law of change with the change of gear tooth profile, nonlinear displacement coefficient The nonlinear function of is described as:
[0130] ;
[0131] In the formula, is the initial displacement coefficient, is the tooth profile angle, and To adjust the parameters.
[0132] It is particularly noted that: by introducing nonlinear functions, a coupling effect can be formed with the genetic algorithm. After the introduction of nonlinear functions, the genetic algorithm can "search" the solution space more deeply during the optimization process, and improve the possibility of the global optimal solution. The nonlinear deformation increases the nonlinear relationship between the decision variables and the objective function, which facilitates the genetic algorithm to explore a wider space by eliminating excellent individuals. The nonlinear term can enhance the differences between individuals, which is beneficial to the important "selection" and "crossover" operations in the genetic algorithm. At the same time, it expands the decision space to a certain extent, increases the possibility of genetic variation, and prevents the algorithm from staying in the suboptimal solution. Re-verification will ensure the comprehensive optimization of the final design, thereby achieving the conditions for activating integration.
[0133] The historical design data includes basic design parameters and corresponding displacement parameters; the performance index includes the value of the optimization objective function.
[0134] The construction framework of the initialized displacement parameter prediction model is based on a neural network algorithm.
[0135] The training method of the initialized displacement parameter prediction model includes:
[0136] The basic parameters in each set of historical design data are used as the input of the displacement parameter prediction model, and the displacement parameters are used as the output. The actual displacement parameters corresponding to the basic parameters in each set of historical design data are used as the prediction targets, and minimizing the sum of the first prediction accuracies of all predicted displacement parameters is used as the training target.
[0137] Among them, the calculation formula for the first prediction accuracy is: ,in, is the first prediction accuracy, is the predicted displacement parameter corresponding to the i-th group of basic parameters, is the displacement parameter corresponding to the i-th group of basic parameters; i is the group number of the historical design data; the displacement parameter prediction model is trained until the sum of the first prediction accuracies reaches convergence and the training is stopped.
[0138] By constructing an initial model and using historical design data to train the initialized displacement parameter prediction model, a displacement parameter prediction integrated model is obtained. After uploading the displacement parameter prediction integrated model to the backend server, the displacement parameters can be automatically output based on the basic parameters.
[0139] The displacement parameter prediction integrated model is obtained by integrating one or more trained displacement parameter prediction models, and the methods for integrating the multiple trained displacement parameter prediction models include integrated learning, graph model integration, meta-learning and other integration methods; the displacement parameter prediction model is a machine learning model constructed based on primary historical design data, which can make displacement parameter predictions, but the prediction ability is limited, and there may be large errors in the prediction of new data. Different models have different prediction effects in different data ranges. Through integration, the strengths of each model can be fully utilized. Compared with a single model, the integrated model has stronger prediction ability and is more stable in a wider data range.
[0140] Example 2
[0141] like Figure 2 As shown, this embodiment further improves the design on the basis of embodiment 1. The material properties and working environment have a certain influence on the optimization objective function. If no improvement is made, it may cause a certain misjudgment in the prediction of the displacement parameters. However, because the influence of material properties and working environment on the displacement parameters is far less than that of the basic parameters, it may only cause the model to have a tendency to misjudgment during integration. Therefore, it will be used as an influencing factor of the training data for evaluation. Based on this, the large-module involute gear displacement parameter configuration method for formed gears also includes:
[0142] Collect material properties and working environment.
[0143] Input material properties and working environment into the pre-built impact factor prediction model and output the impact factor.
[0144] The displacement parameter prediction model initialized by training historical design data and influencing factors is obtained by the displacement parameter prediction integrated model.
[0145] The material properties include heat treatment information, mechanical properties and chemical composition. The material properties can be obtained through the production database of the gear manufacturer; heat treatment information such as heat treatment type, hardness and microstructure changes; mechanical properties such as tensile strength, yield strength, fracture toughness and fatigue limit; chemical composition such as the content of elements such as carbon, silicon, manganese, sulfur and phosphorus.
[0146] The working environment includes lubrication conditions and load conditions. The working environment can be obtained under laboratory conditions; the lubrication conditions include lubrication type, lubrication frequency and lubricant type, among which lubrication types include grease and synthetic oil; the lubrication frequency is represented by a numerical feature, and the unit is times / hour; the lubricant type includes mineral oil and synthetic oil; the load conditions include workload, impact load and load distribution; the workload is represented by a numerical feature, and the unit is N; the impact load is represented by a numerical feature, and the unit is N; the load distribution is represented by a numerical feature, and can be represented by statistical indicators such as mean and variance.
[0147] The influencing factors include strength factor, efficiency factor and life factor, and the range of the influencing factors is (0, 1) by default; the strength factor reflects the influence of gear material and working environment on gear strength, and the closer the value is to 1, the more favorable the material and environment are for the strength of the gear; the efficiency factor reflects the influence of lubrication conditions and workload on gear transmission efficiency, and the closer the value is to 1, the higher the efficiency; the life factor reflects the influence of material properties and working environment on gear fatigue life, and the closer the value is to 1, the longer the gear life.
[0148] The method for constructing the impact factor prediction model includes:
[0149] Each set of material properties and working environment is converted into the form of a first eigenvector, and the elements in the first eigenvector include heat treatment information, mechanical properties, chemical composition, lubrication conditions and load conditions.
[0150] The set of all first eigenvectors is used as the input of the impact factor prediction model. The impact factor prediction model takes the impact factor predicted for each group of first eigenvectors as output, takes the actual impact factor corresponding to each group of first eigenvectors as the prediction target, and takes minimizing the sum of the second prediction accuracies of all predicted impact factors as the training target.
[0151] Among them, the calculation formula for the second prediction accuracy is: ,in is the second prediction accuracy, For the The predicted influencing factors of the group material properties corresponding to the working environment, For the The actual influencing factors corresponding to the material properties and working environment; is the group number of the first feature vector; the impact factor prediction model is trained until the sum of the second prediction accuracy reaches convergence and the training is stopped; the impact factor prediction model is any one of a regression model and a decision tree.
[0152] It should be noted that: due to the large number and complexity of influencing factors, the black box effect of the influencing factor prediction model can be used to eliminate the complicated factors for quantitative processing, directly and automatically output the influencing factors, prevent prediction misjudgments, and make the results more accurate.
[0153] Example 3
[0154] See also Figure 3As shown, the present application also provides an electronic device 500. The electronic device 500 may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are run by one or more processors, the method for configuring the large modulus involute gear displacement parameters for the formed gear as described above may be executed.
[0155] The system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device 500 may include a bus 501, one or more CPUs 502, a ROM 503, a RAM 504, a communication port 505 connected to a network, an input / output 506, a hard disk 507, etc. The storage device in the electronic device 500, such as the ROM 503 or the hard disk 507, may store the large-module involute gear displacement parameter configuration method for forming gears provided in the present application. Furthermore, the electronic device 500 may also include a user interface 508. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.
[0156] Example 4
[0157] See also Figure 4 As shown, the present application discloses a computer-readable storage medium. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the large-module involute gear displacement parameter configuration method for forming gears according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache), etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.
[0158] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
[0159] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A large-module involute gear displacement parameter configuration method for forming gears, characterized in that: include: Obtain historical design data through design, build a displacement parameter prediction integrated model through integration, input basic parameters into the displacement parameter prediction integrated model to automatically output displacement parameters; The design includes: Collect the basic parameters of large-module involute gears; set the initial range of displacement parameters based on preliminary analysis; design the optimization objective function, and use genetic algorithms to perform multi-objective optimization on the displacement parameters to obtain the optimal solution; verify the optimal solution, introduce nonlinear functions, and verify again. After verification, output the activation code to activate the integration; The integration includes: Construct an initialized displacement parameter prediction model; collect historical design data; use the historical design data to train the initialized displacement parameter prediction model to obtain a displacement parameter prediction integrated model for gear maintenance; The optimization objective function includes a gear strength function, a transmission efficiency function and a gear life function; the gear strength function includes a bending strength function and a contact strength function; Gear strength function: ; ; In the formula, is the bending strength function, is the tooth force, is the load factor, is the speed coefficient, is the meshing coefficient, is the width coefficient, is the tooth width, is the tooth form coefficient, is the contact strength function, is the contact coefficient, is the elastic coefficient; m is the modulus; Transmission efficiency function : ; In the formula, is the power loss, is the input power; Gear life function : ; In the formula, is the basic rated load, is the equivalent load.
2. The method for configuring the displacement parameters of a large-module involute gear for a formed gear according to claim 1, characterized in that: The method for multi-objective optimization of displacement parameters using genetic algorithm comprises: S1: Generate an initial population, each individual represents a set of displacement parameters, the displacement parameters include displacement coefficient and initial angle, the displacement coefficient is the standardized value of the gear tooth profile offset , the size of the population is a preset fixed value; S2: Define the fitness function and evaluate the fitness of each individual according to the optimization objective function; S3: individuals are selected for mating using roulette wheel selection or tournament selection method based on fitness values; S4: Perform a crossover operation on the selected individuals, including a single-point crossover operation and a multi-point crossover operation, to generate new individuals; S5: Perform mutation operation on the new individuals generated after crossover to increase the diversity of the population. The mutation operation randomly adjusts the displacement coefficient or initial angle. S6: The selected individuals, the new individuals generated by the crossover operation and the new individuals generated by the mutation operation form a new population; S7: Repeat S2 to S6 until the predetermined number of generations or fitness function converges, at which time the individual with the highest fitness is selected as the optimal solution.
3. The method for configuring the displacement parameters of a large-module involute gear for a formed gear according to claim 2, characterized in that: The method for verifying the optimal solution includes finite element analysis, multi-body dynamics simulation and fatigue life analysis; finite element analysis verifies the stress and deformation of the gear under the working load to determine whether there is stress concentration or deformation; multi-body dynamics simulation simulates the dynamic characteristics of the gear transmission process to evaluate whether the transmission efficiency and meshing performance meet the standards; fatigue life analysis is based on the fatigue characteristics of the gear material to predict whether the service life of the gear under different working conditions meets the standards.
4. The method for configuring the displacement parameters of a large-module involute gear for a formed gear according to claim 2, characterized in that: The nonlinear function is introduced to describe the displacement coefficient by a nonlinear function. The law of change with the change of gear tooth profile.
5. The method for configuring the displacement parameters of large-module involute gears for forming gears according to claim 1, characterized in that: The construction framework of the initialized displacement parameter prediction model is based on a neural network algorithm.
6. The method for configuring the displacement parameters of a large-module involute gear for a formed gear according to claim 5, characterized in that: The historical design data includes basic design parameters and displacement parameters corresponding to the basic parameters; The training method of the initialized displacement parameter prediction model includes: The basic parameters in each set of historical design data are used as inputs of the displacement parameter prediction model, the displacement parameters are used as outputs, the actual displacement parameters corresponding to the basic parameters in each set of historical design data are used as prediction targets, and minimizing the sum of the first prediction accuracies of all predicted displacement parameters is used as a training target; The displacement parameter prediction model is trained until the sum of the first prediction accuracy reaches convergence and then the training is stopped.
7. The large-module involute gear displacement parameter configuration method for forming gears according to claim 1, characterized in that: Also includes: Collect the material properties and working environment of large modulus involute gears; Input material properties and working environment into the pre-built influencing factor prediction model and output the influencing factor; The displacement parameter prediction model is initialized by training historical design data and influencing factors to obtain the displacement parameter prediction integrated model.
8. The method for configuring the displacement parameters of a large-module involute gear for a formed gear according to claim 7, characterized in that: The material properties include heat treatment information, mechanical properties and chemical composition; the working environment includes lubrication conditions and load conditions; the method for constructing the influencing factor prediction model includes: Convert each set of material properties and working environment into the form of a first eigenvector, where the elements of the first eigenvector include heat treatment information, mechanical properties, chemical composition, lubrication conditions, and load conditions; The set of all first eigenvectors is used as the input of the impact factor prediction model, the impact factor prediction model takes the impact factor predicted for each group of first eigenvectors as the output, takes the actual impact factor corresponding to each group of first eigenvectors as the prediction target, and takes minimizing the sum of the second prediction accuracies of all predicted impact factors as the training target; the impact factor prediction model is trained until the sum of the second prediction accuracies reaches convergence and the training is stopped; the impact factor prediction model is a regression model or a decision tree model.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method for configuring the displacement parameters of a large-module involute gear for a formed gear as described in any one of claims 1 to 8 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method for configuring the displacement parameters of a large-module involute gear for a formed gear as described in any one of claims 1 to 8 is implemented.
