Agricultural machine thin-wall part forming process based on multi-objective optimization

Abstract

The invention discloses an agricultural machine thin-wall part forming process based on multi-objective optimization. The agricultural machine thin-wall part forming process comprises the following steps that 1, agricultural machine thin-wall part forming basic parameters and multi-objective optimization indexes are determined; 2, an agricultural machine thin-wall part forming multi-physics field coupling numerical simulation model is constructed; 3, constructing a multi-objective optimization model based on an improved intelligent algorithm; step 4, determining a Pareto optimal solution and process parameters; and 5, batched forming and quality monitoring of the agricultural machine thin-wall parts are carried out. According to the technology, by building a multi-objective optimization model and combining numerical simulation and experimental verification, collaborative optimization of forming precision, mechanical properties and production economy is achieved, the forming quality and production efficiency of the agricultural machine thin-wall part are improved, and the production cost and resource consumption are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural machinery parts manufacturing, in particular to an agricultural machinery thin-walled part forming process based on multi-objective optimization, which is suitable for efficient and high-quality forming manufacturing of various agricultural machinery thin-walled structural parts, can significantly improve the mechanical properties, forming precision and production economy of agricultural machinery thin-walled parts, and reduce production cost and resource consumption. BACKGROUND

[0002] As a key component of agricultural machinery equipment, the forming quality of agricultural machinery thin-walled parts directly affects the overall performance, reliability and service life of agricultural machinery. With the development of agricultural mechanization towards high precision, high efficiency and light weight, higher requirements are put forward for the forming precision (such as dimensional tolerance, geometric error), mechanical properties (such as tensile strength, yield strength, fatigue life) and production economy (such as material utilization rate, forming cycle, energy consumption) of agricultural machinery thin-walled parts.

[0003] Currently, the commonly used forming processes for agricultural machinery thin-walled parts mainly include stamping forming, casting forming, injection molding (for non-metal thin-walled parts) and hydraulic forming. However, these traditional forming processes have many problems in practical application:

[0004] Single-objective optimization limitation: Existing process parameter design mainly optimizes a single target (such as forming pass rate or production efficiency), ignoring the coupling relationship between multiple targets. For example, excessive increase in pressing pressure to improve forming precision may lead to increased mold wear, increased energy consumption, and increased risk of thin-walled part cracking; if only material utilization rate is pursued and process steps are simplified, it is easy to lead to insufficient mechanical properties of thin-walled parts, which cannot meet the high-strength working condition requirements of agricultural machinery operation.

[0005] Process parameters rely on experience: The determination of process parameters mainly relies on the accumulation of engineers' experience, lacking scientific quantitative analysis and optimization methods. Different materials (such as high-strength steel, aluminum alloy) and different structures (such as complex curved surface, multi-joint thin-walled) of agricultural machinery thin-walled parts have large differences in material flow law, stress and strain distribution during forming process. Empirical parameter design is easy to lead to poor process stability and large product quality fluctuations in batch production.

[0006] Multi-physical field coupling problem is not solved: The forming process of agricultural machinery thin-walled parts involves the coupling of force field, temperature field, displacement field and other multi-physical fields. Traditional processes do not fully consider the influence of multi-field coupling on forming quality. For example, local high temperature in stamping forming easily leads to a decrease in material plasticity, causing wrinkles or cracks in thin-walled parts; uneven pressure distribution in hydraulic forming will lead to wall thickness deviation of thin-walled parts exceeding the design requirements, affecting the subsequent assembly and use performance.

[0007] The trade-off between production economy and forming quality is prominent: traditional processes often require increasing production costs (such as using high-precision molds and extending the forming cycle) to improve forming quality, or sacrificing forming quality to reduce costs, making it difficult to achieve synergistic optimization between the two. For example, using low-specification sheet metal to reduce material costs requires multiple stamping processes to ensure accuracy, leading to a decrease in production efficiency; if a one-time forming process is adopted to pursue high-efficiency production, dimensional deviations are likely to occur, increasing the scrap rate.

[0008] Therefore, in view of the shortcomings of the existing forming process for thin-walled parts of agricultural machinery, it is urgent to develop a forming process based on multi-objective optimization. Through scientific optimization models and parameter design methods, a multi-objective synergistic optimization of forming accuracy, mechanical properties and production economy can be achieved, so as to meet the needs of modern agricultural machinery for high-quality, low-cost and high-efficiency manufacturing of thin-walled parts. Summary of the Invention

[0009] To address the problems existing in the prior art, this invention provides a multi-objective optimization-based forming process for thin-walled agricultural machinery parts. The aim is to overcome the limitations of single-objective optimization, empirical parameter design, unresolved multi-physics coupling issues, and the prominent contradiction between economic efficiency and quality in existing forming processes. This process, through the construction of a multi-objective optimization model and the combination of numerical simulation and experimental verification, achieves synergistic optimization of forming accuracy, mechanical properties, and production economy, thereby improving the forming quality and production efficiency of thin-walled agricultural machinery parts while reducing production costs and resource consumption.

[0010] To achieve the above objectives, the technical solution adopted by the present invention is: a forming process for thin-walled agricultural machinery parts based on multi-objective optimization, comprising the following steps:

[0011] Step 1: Determine the basic parameters and multi-objective optimization indicators for forming thin-walled parts for agricultural machinery;

[0012] Step 2: Construct a multi-physics coupled numerical simulation model for the forming of thin-walled agricultural machinery parts;

[0013] Step 3: Construct a multi-objective optimization model based on improved intelligent algorithms;

[0014] Step 4: Pareto optimal solution decision and process parameter determination;

[0015] Step 5: Mass production and quality control of thin-walled parts for agricultural machinery.

[0016] Furthermore, step 1 specifically includes:

[0017] 1.1 Basic Parameter Acquisition: Based on the design requirements of the thin-walled agricultural machinery part to be formed, such as structural dimensions, wall thickness, and material type, determine the forming process type, such as stamping, hydroforming, or casting, and collect basic parameters, including:

[0018] Material parameters: elastic modulus, Poisson's ratio, yield strength, tensile strength, plastic strain rate, and coefficient of thermal expansion, which are specific to temperature-sensitive materials;

[0019] Structural parameters: maximum wall thickness, minimum wall thickness, radius of curvature of curved surfaces, rib height and spacing, and opening size and location of thin-walled parts;

[0020] Initial process parameters: molding temperature, molding pressure, molding speed, holding time, mold clearance, and pouring temperature;

[0021] 1.2 Determination of Multi-Objective Optimization Indicators: Based on the usage requirements and production demands of thin-walled agricultural machinery components, multi-objective optimization indicators were determined, including:

[0022] Forming accuracy indicators: dimensional tolerances, form and position errors, and wall thickness deviation rate;

[0023] Mechanical performance indicators: tensile strength, yield strength, fatigue life, hardness;

[0024] Production economic indicators: material utilization rate, forming cycle, energy consumption per unit product, and scrap rate.

[0025] Furthermore, step 2 specifically involves the following steps:

[0026] 2.1 Geometric Model Establishment: Based on the three-dimensional design drawings of thin-walled agricultural machinery parts, geometric models of the thin-walled parts and forming molds are established using CAD software. The models are simplified to reduce the amount of numerical simulation calculations.

[0027] 2.2 Mesh Generation and Boundary Condition Setting:

[0028] The geometric model was imported into CAE software, and adaptive mesh generation technology was used to refine the mesh in the stress and strain concentration areas during the forming process of thin-walled parts to ensure simulation accuracy.

[0029] Set boundary conditions: Define the contact relationship between the mold and the thin-walled part, the motion constraints of the forming equipment, and the temperature boundaries according to the forming process type;

[0030] 2.3 Construction of Multiphysics Coupling Equations:

[0031] Force field equations: Based on the theory of elastoplastic mechanics, stress balance equations are established during the forming process of thin-walled parts, taking into account the effects of plastic flow and strain hardening of materials;

[0032] Temperature field equation: Considering the heat generated by friction, heat generated by plastic deformation and heat conduction during the forming process, a heat conduction equation is established;

[0033] Displacement field equation: Combining the coupling effect of force field and temperature field, the displacement equation of thin-walled part is established to solve the displacement change of each node during the forming process and predict the forming shape and dimensional deviation of thin-walled part;

[0034] 2.4 Numerical Simulation Solution and Result Analysis: Run the multiphysics coupled numerical simulation model to obtain data such as stress distribution, strain distribution, temperature distribution, displacement distribution, and dimensional deviation and wall thickness deviation of the thin-walled part during the forming process; analyze the satisfaction of multi-objective optimization indicators under the initial process parameters, and identify the key process parameters that affect the forming quality and economy.

[0035] Furthermore, step 3 specifically includes:

[0036] 3.1 Determine the optimization variables and constraints:

[0037] Optimization variables: The key process parameters identified in step 2.4 are used as optimization variables. For example, in stamping, the optimization variables are stamping pressure P (MPa), stamping speed v (mm / s), die clearance d (mm), and forming temperature T (℃). Constraints: Based on the design standards and actual production of thin-walled agricultural machinery parts, the constraint range of the optimization variables is set, and the constraint threshold of the multi-objective optimization index is set.

[0038] 3.2 Establishing a multi-objective optimization objective function:

[0039] Forming accuracy objective function: With the objectives of minimizing dimensional tolerance, minimizing form and position error, and minimizing wall thickness deviation rate, a comprehensive objective function for forming accuracy, f1(X), is constructed, where X = is the optimization variable vector;

[0040]

[0041] In the formula: ΔL is the deviation between the actual length and the design length L0, Δφ is the deviation between the actual form and position error and the allowable form and position error φ0, Δt is the deviation between the actual wall thickness deviation and the allowable wall thickness deviation t0, and ω1, ω2, ω3 are weighting coefficients (satisfying ω1+ω2+ω3=1), which are determined by the analytic hierarchy process (AHP).

[0042] Mechanical performance objective function: With the goals of maximizing tensile strength, maximizing yield strength, and maximizing fatigue life, a comprehensive mechanical performance objective function f2(X) is constructed.

[0043]

[0044] In the formula: σb is the actual tensile strength, σb0 is the design tensile strength, σs is the actual yield strength, σs0 is the design yield strength, N is the actual fatigue life, N0 is the design fatigue life, and α1, α2, α3 are weighting coefficients that satisfy α1+α2+α3=1, which are determined according to the operating conditions of thin-walled parts of agricultural machinery.

[0045] Production economic objective function: With the goals of maximizing material utilization, minimizing forming cycle, minimizing unit product energy consumption, and minimizing scrap rate, a comprehensive production economic objective function f3(X) is constructed.

[0046]

[0047] In the formula: η is the actual material utilization rate, η0 is the target material utilization rate, t is the actual forming cycle, t0 is the target forming cycle, E is the actual unit product energy consumption, E0 is the target unit product energy consumption, γ is the actual scrap rate, γ0 is the target scrap rate, and β1, β2, β3, β4 are weighting coefficients that satisfy β1+β2+β3+β4=1, which are determined according to the enterprise's production cost and efficiency requirements;

[0048] 3.3 Improved Intelligent Algorithm Selection and Model Optimization:

[0049] The improved non-dominated sorting genetic algorithm NSGA-II or the improved particle swarm optimization algorithm PSO are selected as multi-objective optimization algorithms. By introducing adaptive crossover mutation operators or dynamic adjustment strategies for inertial weights, the convergence speed and global optimization ability of the algorithms are improved.

[0050] The multiphysics coupled numerical simulation model established in step 2 is used as the fitness function of the optimization model. The optimization variables are input and the multi-objective optimization index value is output.

[0051] An improved intelligent algorithm is run to iteratively optimize the multi-objective optimization model and generate the Pareto optimal solution set.

[0052] Furthermore, step 4 specifically involves:

[0053] 4.1 Pareto optimal solution selection: The combination of process parameters in the Pareto optimal solution set is comprehensively evaluated using the fuzzy hierarchical analysis method or the Technique for Order Preference by Similarity to Ideal Solution method.

[0054] Construct an evaluation index system: use the comprehensive objective function value of forming accuracy, mechanical properties, and production economy as the evaluation index;

[0055] Determine the weights of the indicators: Determine the weights of each evaluation indicator using expert scoring or entropy weighting methods;

[0056] Calculate the comprehensive evaluation value of each Pareto optimal solution, and select the process parameter combination with the highest comprehensive evaluation value as the optimal process parameter;

[0057] 4.2 Optimal process parameter verification:

[0058] Numerical simulation verification: Input the optimal process parameters into the multiphysics coupled numerical simulation model established in step 2 to verify whether the forming accuracy, mechanical properties, and production economy indicators meet the design requirements.

[0059] Experimental verification: Based on the optimal process parameters, forming experiments of thin-walled parts for agricultural machinery were conducted, and dimensional data, mechanical property data, and production economic data of the experimental parts were collected.

[0060] Error analysis: Compare the experimental results with the numerical simulation results to analyze the causes of errors. If the error exceeds the allowable range, return to step 3 to adjust and optimize the model parameters, and re-optimize until the experimental results meet the design requirements.

[0061] Furthermore, step 5 specifically includes:

[0062] 5.1 Batch forming process implementation: Based on the optimal process parameters determined in step 4, debug the forming equipment, set the equipment parameters, and carry out batch production of thin-walled agricultural machinery parts;

[0063] 5.2 Real-time quality monitoring:

[0064] Online monitoring: A machine vision inspection system is used to monitor the size and appearance defects of thin-walled parts in real time; an infrared thermometer is used to monitor temperature changes during the forming process; and a pressure sensor is used to monitor forming pressure fluctuations.

[0065] Offline inspection: Periodically sample thin-walled parts from mass production for mechanical property testing and dimensional accuracy inspection, and record the inspection data;

[0066] 5.3 Dynamic adjustment of process parameters: If quality abnormalities are found through online monitoring or offline testing, the cause of the abnormality is analyzed and the optimal process parameters are fine-tuned according to the abnormality to ensure the stability of product quality during mass production.

[0067] The beneficial effects of this invention are:

[0068] 1. This invention, by constructing a multi-objective optimization model, incorporates forming accuracy, mechanical properties, and production economy into a unified optimization framework, overcoming the limitations of traditional single-objective optimization and achieving synergistic improvement of all three. For example, by optimizing stamping process parameters, the dimensional tolerance of thin-walled agricultural machinery parts can be controlled within ±0.05mm, tensile strength can be increased by 15%-20%, material utilization rate can be increased by 8%-12%, forming cycle can be shortened by 10%-15%, and energy consumption per unit product can be reduced by 5%-8%.

[0069] 2. This invention combines multi-physics coupling numerical simulation with improved intelligent algorithms to replace the traditional experience-based process parameter design method. It can accurately predict the impact of multi-physics coupling on forming quality during the forming process, quantify the mapping relationship between key process parameters and optimization indicators, improve the scientificity and accuracy of process parameter design, reduce reliance on engineers' experience, and reduce process debugging cycle and cost.

[0070] 3. This invention establishes a numerical simulation model that couples force field, temperature field, and displacement field, fully considering the influence of multi-field coupling on forming quality. It can accurately predict the stress-strain distribution, temperature distribution, and dimensional deviation during the forming process of thin-walled parts, effectively avoiding defects such as wrinkling, cracking, and uneven wall thickness caused by multi-field coupling, and improving the stability of forming quality.

[0071] 4. By optimizing process parameters, this invention improves forming quality, increases material utilization, reduces forming cycle and energy consumption, and decreases scrap rate, significantly reducing the production cost of thin-walled agricultural machinery parts (by 10%-15%). Simultaneously, high-quality thin-walled parts enhance the reliability and service life of agricultural machinery, strengthen the market competitiveness of agricultural machinery products, and align with the modern agricultural machinery development trend of lightweighting, high efficiency, and low cost.

[0072] 5. The process method of this invention is applicable to the forming of thin-walled agricultural machinery parts made of different materials (such as high-strength steel, aluminum alloy, and magnesium alloy) and different structures (such as complex curved surfaces, multi-ribbed thin-walled parts, and perforated thin-walled parts). The numerical simulation model and optimization parameters can be adjusted according to the specific forming process type (such as stamping, hydraulic, and casting), and it has strong versatility and scalability. In addition, the optimization accuracy and quality monitoring capability of the process can be further improved by introducing more advanced intelligent algorithms (such as deep learning and reinforcement learning) or monitoring technologies (such as the Internet of Things and big data analysis). Detailed Implementation

[0073] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below through embodiments. However, it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the scope of the invention.

[0074] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention.

[0075] To make the technical solution of the present invention clearer and easier to understand, the following describes the specific implementation of the present invention in detail using the example of "stamping of thin-walled agricultural machinery gearbox housing (material: 6061 aluminum alloy, structural dimensions: length 300mm × width 200mm × height 150mm, design wall thickness 3mm)".

[0076] (I) Step 1: Determine the basic parameters and multi-objective optimization index

[0077] 1.1 Basic Parameter Acquisition:

[0078] Material parameters (6061 aluminum alloy): elastic modulus 69 GPa, Poisson's ratio 0.33, yield strength 275 MPa, tensile strength 310 MPa, plastic strain rate 0.2, coefficient of thermal expansion 23.1×10^-6 / ℃;

[0079] Structural parameters: maximum wall thickness 3.2mm, minimum wall thickness 2.8mm, surface curvature radius 10mm, rib height 8mm, spacing 20mm, opening size φ15mm (2 openings);

[0080] Initial process parameters: stamping pressure 120MPa, stamping speed 50mm / s, die clearance 3.1mm, forming temperature 25℃.

[0081] 1.2 Determination of Multi-Objective Optimization Indicators:

[0082] Forming accuracy indicators: dimensional tolerance ≤ ±0.08mm (deviation of length 300mm, width 200mm, height 150mm), flatness ≤ 0.05mm / m, wall thickness deviation rate ≤ 5% (design wall thickness 3mm, maximum allowable wall thickness deviation 0.15mm);

[0083] Mechanical performance indicators: tensile strength ≥300MPa, yield strength ≥260MPa, fatigue life ≥10^5 cycles (stress amplitude 150MPa, room temperature environment), Brinell hardness ≥95HB.

[0084] Production economic indicators: material utilization rate ≥ 88% (raw materials are 6061 aluminum alloy sheets of 320mm×220mm×3mm), forming cycle ≤ 30s / piece, unit product energy consumption ≤ 0.5kW·h / piece, scrap rate ≤ 2%.

[0085] (II) Step 2: Constructing a multiphysics coupled numerical simulation model

[0086] 2.1 Geometric Model Establishment:

[0087] A three-dimensional geometric model of the thin-walled part of the agricultural machinery gearbox housing and the stamping die was created using SolidWorks 2023 software. The thin-walled part model retains key structures (ribs, openings) and ignores irrelevant small holes with a diameter ≤2mm and non-functional chamfers with a radius ≤1mm. The die model includes an upper die (punch) and a lower die (cavity). The cavity size of the cavity is determined based on the design dimensions of the thin-walled part and the material springback (the springback rate of 6061 aluminum alloy stamping is approximately 0.5%-1%), with a springback compensation allowance of 0.02mm.

[0088] 2.2 Mesh Generation and Boundary Condition Setting:

[0089] The geometric model was imported into ABAQUS 2022 software, and the thin-walled part was meshed using quadrilateral reduced integral elements (C3D8R). The mesh size was set to 1mm in stress and strain concentration areas (rib roots, opening edges, and rounded corners), and 3mm in other areas, with a total of approximately 85,000 elements. The mold was meshed using rigid elements (R3D4) with a mesh size of 5mm, and a total of approximately 32,000 elements.

[0090] Boundary condition settings: Define the friction type between the mold and the thin-walled part as Coulomb friction, with a friction coefficient of 0.12 (using extreme pressure stamping lubricant); set the downward speed of the upper mold to 50 mm / s in the initial process parameters, and fix the lower mold; set the ambient temperature to 25℃, and ensure that the initial temperature of the mold is consistent with the ambient temperature, ignoring the heat exchange between the mold and the environment during the forming process (short-time forming, heat loss ≤3%).

[0091] 2.3 Construction of Multiphysics Coupling Equations:

[0092] Force field equations: Based on J2 flow theory and considering the plastic hardening characteristics of 6061 aluminum alloy, the Swift hardening model is used to describe the stress-strain relationship of the material. The hardening equation is as follows:

[0093] σ=K(ε0+ε p ) n

[0094] Where K = 450 MPa, ε0 = 0.005, n = 0.18 (obtained through material tensile testing); the stress balance equation is:

[0095] Where σ is the stress tensor and ρ is the material density (2700 kg / m³). 3 ), b is the volume force, and u is the acceleration vector;

[0096] Temperature field equation: Considering heat generated by friction and heat generated by plastic deformation, the heat conduction equation is as follows: Where c is the specific heat capacity (900 J / (kg·℃)), k is the thermal conductivity (160 W / (m·℃)), q_f is the frictional heat generation rate (q_f = \mu P v, \mu is the coefficient of friction, P is the contact pressure, v is the relative sliding speed), and q_p is the heat generation rate of plastic deformation (

[0097] β = 0.9 (where β is the heat conversion efficiency);

[0098] Displacement field equation: Considering the coupling effect of the force field and the temperature field, and taking into account the thermal expansion effect, the displacement equation is ε = ε e +ε p +ε T Where εvarepsilon is elastic strain, εvarepsilon is plastic strain, and εvarepsilon is thermal strain (εt). T =αΔT, where α is the coefficient of thermal expansion).

[0099] 2.4 Numerical Simulation Solution and Result Analysis:

[0100] Run the ABAQUS / Explicit solver, setting the simulation time to 0.6 seconds (corresponding to a 20mm upward and downward distance of the upper die, meeting the forming requirements of thin-walled parts). After the solution is complete, extract the key result data:

[0101] Forming accuracy: Length deviation +0.12mm, width deviation -0.10mm, height deviation +0.09mm (all exceeding the target requirement of ±0.08mm); flatness 0.07mm / m (exceeding the target requirement of 0.05mm / m); maximum wall thickness deviation 0.21mm, wall thickness deviation rate 7% (exceeding the target requirement of 5%).

[0102] Mechanical properties: The average equivalent stress of the thin-walled component is 285 MPa. Based on the stress-strength relationship, the tensile strength is approximately 290 MPa (lower than the target requirement of 300 MPa), and the yield strength is approximately 250 MPa (lower than the target requirement of 260 MPa).

[0103] Production economy: Material utilization rate is about 82% (due to the width of edge waste after forming reaching 15mm, exceeding expectations), forming cycle is 28s (meets the requirement of ≤30s), and unit product energy consumption is 0.58kW·h / piece (exceeds the requirement of 0.5kW·h / piece).

[0104] Key process parameter identification: Through parameter sensitivity analysis (changing a single parameter and observing the rate of change of the index), stamping pressure (affecting stress distribution and wall thickness deviation), forming temperature (affecting material plasticity and springback), and die clearance (affecting dimensional accuracy and frictional heat generation) were identified as key optimization variables. The impact rate of stamping speed on the index was ≤5%, so it was not included in the optimization variables for the time being.

[0105] (III) Step 3: Construct a multi-objective optimization model based on the improved NSGA-II

[0106] 3.1 Determine the optimization variables and constraints:

[0107] Optimization variables: stamping pressure P (50-200MPa), forming temperature T (25-300℃), die clearance d (3.0-3.2mm);

[0108] Constraints: P_in[50,200]MPa, T_in[25,300]℃, d_in[3.0,3.2]mm; simultaneously meet the forming accuracy index (dimensional tolerance ≤ ±0.08mm, flatness ≤ 0.05mm / m, wall thickness deviation rate ≤ 5%), mechanical performance index (tensile strength ≥ 300MPa, yield strength ≥ 260MPa), and production economy index (material utilization rate ≥ 88%, unit product energy consumption ≤ 0.5kW·h / piece).

[0109] 3.2 Establishing a multi-objective optimization objective function:

[0110] Forming accuracy objective function: Where \Delta L is the actual dimensional deviation (taking the maximum value of the length, width, and height deviations), \Delta\phi is the actual flatness, and \Delta t_r is the actual wall thickness deviation rate; \omega_1 = 0.4, \omega_2 = 0.3, \omega_3 = 0.3 (the weights were determined by inviting 5 agricultural machinery manufacturing experts to score using the AHP method).

[0111] Objective function for mechanical properties: Where σb is the actual tensile strength, σs is the actual yield strength, and N is the actual fatigue life; α1 = 0.4, α2 = 0.3, α3 = 0.3 (based on the alternating load conditions borne by the gearbox housing, tensile strength has the greatest impact on service life);

[0112] Production economic objective function:

[0113]

[0114] Where α is the actual material utilization rate, t is the actual forming cycle (s), E is the actual unit product energy consumption (kW·h / piece), and gamma is the actual scrap rate; α1 = 0.3, α2 = 0.2, α3 = 0.3, α4 = 0.2 (enterprises pay more attention to material utilization rate and energy consumption cost).

[0115] 3.3 Improved NSGA-II Algorithm Optimization:

[0116] Algorithm improvements: An adaptive crossover operator (the crossover probability P_c is dynamically adjusted according to the population diversity, P_c = 0.9 when the diversity is low and P_c = 0.6 when the diversity is high) and a polynomial mutation operator (mutation probability P_m = 1 / n, where n is the number of optimization variables and the variable length is set to 0.05) are introduced to improve the algorithm's global optimization ability.

[0117] Algorithm parameter settings: Population size is set to 100, number of iterations is set to 50, initial crossover probability is 0.7, and mutation probability is 0.33;

[0118] Optimization solution: The ABAQUS numerical simulation model is coupled with the improved NSGA-II algorithm through a Python script. In each iteration, the optimization variables are input, ABAQUS is called to solve the problem and output the objective function value. After 50 iterations, a Pareto optimal solution set containing 28 solutions is generated.

[0119] (iv) Step 4: Pareto optimal solution decision and process parameter determination

[0120] 4.1 Pareto optimal solution selection:

[0121] The TOPSIS method was used to screen the optimal Pareto solution:

[0122] Construct a standardized decision matrix: Standardize the three objective function values ​​of the 28 Pareto optimal solutions to eliminate the influence of dimensions;

[0123] Determine the positive ideal solution (f_1 = 0.85, f_2 = 1.05, f_3 = 0.92) and the negative ideal solution (f_1 = 1.2, f_2 = 0.95, f_3 = 0.8);

[0124] Calculate the Euclidean distance between each solution and the positive and negative ideal solutions, determine the relative closeness, and select the process parameter combination with the highest relative closeness (0.86): stamping pressure P = 165 MPa, forming temperature T = 180℃, and die clearance d = 3.08 mm.

[0125] 4.2 Optimal process parameter verification:

[0126] Numerical simulation verification: The optimal process parameters were input into the ABAQUS model. The simulation results showed that the maximum dimensional deviation was +0.06 mm, the flatness was 0.04 mm / m, and the wall thickness deviation rate was 4.2% (forming accuracy met the standard); the tensile strength was 308 MPa, the yield strength was 265 MPa, and the fatigue life was 1.08 × 10^5 cycles (mechanical properties met the standard); the material utilization rate was 89.5%, the forming cycle was 27 s, and the energy consumption per unit product was 0.46 kW·h / piece (production economy met the standard).

[0127] Experimental verification: A 1600kN hydraulic punch press was used to conduct a stamping experiment according to the optimal process parameters, and 10 samples were produced.

[0128] Dimensional inspection: The dimensions of the sample were inspected using a coordinate measuring machine (accuracy ±0.001mm). The length deviation was +0.065mm, the width deviation was -0.058mm, the height deviation was +0.052mm, the flatness was 0.045mm / m, the wall thickness deviation rate was 4.5%, and the error with the simulation result was ≤8% (within the allowable range).

[0129] Mechanical property testing: Tensile tests were conducted on the samples according to GB / T 228.1-2021 standard, with a tensile strength of 305 MPa and a yield strength of 262 MPa; fatigue tests were conducted according to GB / T 3075-2008 standard, with a fatigue life of 1.05 × 10^5 cycles, and the error between the results and the simulation results was ≤5%.

[0130] Production economic statistics: material utilization rate 89.2% (scrap width reduced to 10mm), forming cycle 27.5s, unit product energy consumption 0.47kW·h / piece, scrap rate 1.8% (1 out of 10 samples was unqualified due to surface scratches), all of which meet the design requirements.

[0131] (V) Step 5: Mass production and quality control of thin-walled parts for agricultural machinery

[0132] 5.1 Implementation of batch forming process:

[0133] In the agricultural machinery parts production workshop, two 1600kN hydraulic punch presses (model YH27-1600) are used for batch production according to the optimal process parameters (P=165MPa, T=180℃, d=3.08mm), with a production scale of 500 pieces / batch. Before production, the mold is preheated (temperature rises to 180℃, preheating is done using electric heating rods, preheating time is 30min). The raw material is 6061 aluminum alloy sheet with a thickness of 320mm×220mm×3mm, and 550 sheets are used in each batch (with a 10% margin).

[0134] 5.2 Real-time quality monitoring:

[0135] Online monitoring: An industrial camera (20 megapixel resolution, 30fps) and an image recognition system (based on OpenCV, with a recognition accuracy of ±0.01mm) are installed at the punch press exit to detect dimensional deviations and appearance defects (cracks, wrinkles, dents) of the sample in real time, with a recognition accuracy of ≥98%; a pressure sensor (accuracy ±1MPa) is installed in the mold contact area to monitor the stamping pressure fluctuation in real time, triggering an alarm when the pressure deviation exceeds ±5MPa; an infrared thermometer (accuracy ±2℃) is used to monitor the temperature of the formed sample to ensure that the temperature is stable within the range of 175-185℃.

[0136] Offline inspection: For every 50 samples produced, one sample is randomly selected for offline inspection. The dimensional accuracy is checked using a coordinate measuring machine, the tensile test is performed using a universal testing machine (accuracy ±1%), and the fatigue life test is performed using a fatigue testing machine (accuracy ±2%). The inspection data is recorded and a quality report is generated.

[0137] 5.3 Dynamic adjustment of process parameters:

[0138] When the 300th piece was produced, online monitoring revealed that the sample length deviation had increased to +0.10mm (exceeding the allowable range). Analysis indicated that the mold had experienced slight wear due to prolonged use (the cavity size increased by 0.03mm). Based on the wear condition, the stamping pressure was adjusted to 170MPa (an increase of 5MPa to compensate for pressure loss caused by mold wear). After adjustment, the sample length deviation returned to +0.07mm (meeting requirements). When the 450th piece was produced, the energy consumption per unit increased to 0.52kW·h / piece. Analysis indicated that lubricant consumption led to an increased coefficient of friction. After replenishing lubricant, the energy consumption decreased to 0.48kW·h / piece. After the final 500 pieces were produced, the scrap rate was 1.6% (8 pieces were defective, including 5 with appearance defects and 3 with dimensional errors), all meeting production requirements.

[0139] This embodiment takes the stamping forming of a thin-walled part of a 6061 aluminum alloy agricultural machinery gearbox housing as an example. Through steps such as basic parameter acquisition, multi-physics coupled numerical simulation, improved NSGA-II multi-objective optimization, Pareto optimal solution decision-making, batch forming, and quality monitoring, the optimal process parameters were finally determined to be a stamping pressure of 165 MPa, a forming temperature of 180℃, and a die clearance of 3.08 mm. The implementation results show that this process can control the dimensional tolerance of the thin-walled part within ±0.08 mm, achieve a tensile strength ≥300 MPa, a material utilization rate ≥88%, a unit product energy consumption ≤0.5 kW·h / piece, and a scrap rate ≤2%, fully meeting the high-quality and economical production requirements of thin-walled agricultural machinery parts, and verifying the feasibility and superiority of the process of this invention.

[0140] 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 or improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-objective optimization based forming process for thin-walled components of farm machinery, characterized in that, The method comprises the following steps: Step 1: determining the forming basic parameters of the agricultural machinery thin-walled part and the multi-objective optimization index; Step 2: constructing a multi-physical field coupling numerical simulation model for the forming of the agricultural machinery thin-walled part; Step 3: constructing a multi-objective optimization model based on an improved intelligent algorithm; Step 4: determining the Pareto optimal solution and the process parameters; Step 5: batch forming and quality monitoring of the agricultural machinery thin-walled part.

2. The multi-objective optimization based forming process of thin-walled agricultural machine component according to claim 1, wherein, In step 1, specifically: 1.1 basic parameter acquisition: according to the design requirements of the to-be-formed agricultural machinery thin-walled part, such as structural size, wall thickness, material type, determining the forming process type, such as stamping forming, hydraulic forming, casting forming, and collecting basic parameters, including: Material parameters: elastic modulus, Poisson's ratio, yield strength, tensile strength, plastic strain rate, and thermal expansion coefficient of the material, which are for temperature-sensitive materials; Structural parameters: maximum wall thickness, minimum wall thickness, curvature radius of the thin-walled part, rib height and spacing, and hole size and position; Initial process parameters: forming temperature, forming pressure, forming speed, holding time, die gap, and pouring temperature; 1.2 multi-objective optimization index determination: combining the use requirements and production requirements of the agricultural machinery thin-walled part, the multi-objective optimization index is determined, including: Forming accuracy index: size tolerance, geometric error, and wall thickness deviation rate; Mechanical property index: tensile strength, yield strength, fatigue life, and hardness; Production economy index: material utilization rate, forming cycle, unit product energy consumption, and scrap rate.

3. The multi-objective optimization based forming process of thin-walled agricultural machine component as claimed in claim 1 wherein, The specific steps of step 2 are as follows: 2.1 geometric model establishment: based on the three-dimensional design drawing of the agricultural machinery thin-walled part, the geometric model of the thin-walled part and the forming die is established by using CAD software, the model is simplified to reduce the numerical simulation calculation amount; 2.2 mesh division and boundary condition setting: Import the geometric model into the CAE software, use adaptive mesh division technology to encrypt the mesh in the stress and strain concentration area during the forming process of the thin-walled part, and ensure the simulation accuracy; Set the boundary conditions: according to the forming process type, define the contact relationship between the die and the thin-walled part, the motion constraint of the forming equipment, and the temperature boundary; 2.3 construction of multi-physical field coupling equation: Force field equation: based on the theory of elastic-plastic mechanics, the stress balance equation in the forming process of the thin-walled part is established, considering the plastic flow and strain hardening effect of the material; Temperature field equation: considering the friction heat, plastic deformation heat and heat conduction in the forming process, the heat conduction equation is established; Displacement field equation: combined with the coupling effect of force field and temperature field, the displacement equation of the thin-walled part is established, the displacement change of each node in the forming process is solved, and the forming shape and size deviation of the thin-walled part are predicted; 2.4 numerical simulation solution and result analysis: run the multi-physical field coupling numerical simulation model, obtain the stress distribution, strain distribution, temperature distribution, displacement distribution of the thin-walled part in the forming process, and the size deviation, wall thickness deviation after forming; analyze the satisfaction of the multi-objective optimization index under the initial process parameters, and identify the key process parameters affecting the forming quality and economy.

4. The multi-objective optimization based forming process of thin-walled agricultural machine component as claimed in claim 1 wherein, The specific steps of step 3 are as follows: 3.1 determining optimization variables and constraint conditions: Optimization variables: the key process parameters identified in step 2.4 are used as optimization variables, for example: in punch forming, the optimization variables are punch pressure P, unit: MPa, punch speed v, unit: mm / s, die gap d, unit: mm, forming temperature T, unit: ℃; constraint conditions: according to the design standards and production practice of agricultural machinery thin-walled parts, the constraint range of optimization variables is set, and the constraint threshold of multi-objective optimization index is set; 3.2 Establishing a multi-objective optimization objective function: Forming accuracy objective function: taking the minimization of size tolerance, the minimization of shape and position error, and the minimization of wall thickness deviation rate as the goal, a forming accuracy comprehensive objective function f1(X) is constructed, wherein X=is the optimization variable vector; In the formula: ΔL is the deviation of actual length and design length L0, Δφ is the deviation of actual shape and position error and allowable shape and position error φ0, Δt is the deviation of actual wall thickness deviation and allowable wall thickness deviation t0, ω1, ω2, ω3 are weight coefficients (satisfying ω1+ω2+ω3=1), which are determined by the analytic hierarchy process AHP; Mechanical property objective function: taking the maximization of tensile strength, the maximization of yield strength, and the maximization of fatigue life as the goal, a mechanical property comprehensive objective function f2(X) is constructed; In the formula: σb is the actual tensile strength, σb0 is the design tensile strength, σs is the actual yield strength, σs0 is the design yield strength, N is the actual fatigue life, N0 is the design fatigue life, α1, α2, α3 are weight coefficients satisfying α1+α2+α3=1, which are determined according to the working conditions of agricultural machinery thin-walled parts; Production economy objective function: taking the maximization of material utilization rate, the minimization of forming cycle, the minimization of unit product energy consumption, and the minimization of scrap rate as the goal, a production economy comprehensive objective function f3(X) is constructed; In the formula: η is the actual material utilization rate, η0 is the target material utilization rate, t is the actual forming cycle, t0 is the target forming cycle, E is the actual unit product energy consumption, E0 is the target unit product energy consumption, γ is the actual scrap rate, γ0 is the target scrap rate, β1, β2, β3, β4 are weight coefficients satisfying β1+β2+β3+β4=1, which are determined according to the production cost and efficiency requirements of enterprises; 3.3 Improved intelligent algorithm selection and model optimization: Selecting improved non-dominated sorting genetic algorithm NSGA-II or improved particle swarm optimization algorithm PSO as the multi-objective optimization algorithm, the convergence speed and global optimization ability of the algorithm are improved by introducing adaptive crossover mutation operator or inertia weight dynamic adjustment strategy; The multi-physical field coupling numerical simulation model established in step 2 is used as the fitness function of the optimization model, the optimization variables are input, and the multi-objective optimization index values are output; Run the improved intelligent algorithm to iteratively optimize the multi-objective optimization model and generate a Pareto optimal solution set.

5. The multi-objective optimization based forming process of thin-walled agricultural machine component as claimed in claim 1 wherein, The step 4 is specifically: 4.1 Pareto optimal solution screening: using fuzzy analytic hierarchy process or Technique for Order Preference by Similarity to Ideal Solution method to comprehensively evaluate each process parameter combination in the Pareto optimal solution set; Constructing evaluation index system: taking the comprehensive objective function value of forming accuracy, mechanical properties and production economy as the evaluation index; Determining index weight: determining the weight of each evaluation index through expert scoring method or entropy weight method; Calculating the comprehensive evaluation value of each Pareto optimal solution, and screening the process parameter combination with the highest comprehensive evaluation value as the optimal process parameter; 4.2 Optimal process parameter verification: Numerical simulation verification: input the optimal process parameters into the multi-physical field coupling numerical simulation model established in step 2 to verify whether the forming accuracy, mechanical properties and production economy indicators meet the design requirements; Experimental verification: according to the optimal process parameters, perform the forming experiment of agricultural machinery thin-walled parts, collect the size data, mechanical property data and production economy data of the experimental parts; Error analysis: compare the experimental results with the numerical simulation results, analyze the error causes, if the error exceeds the allowable range, return to step 3 to adjust and optimize the model parameters, and re-optimize until the experimental results meet the design requirements.

6. A multi-objective optimization based forming process for thin-walled components of farm machinery as claimed in claim 1 wherein, The step 5 is specifically: 5.1 Batch forming process implementation: according to the optimal process parameters determined in step 4, debug the forming equipment, set the equipment parameters, and perform batch production of agricultural machinery thin-walled parts; 5.2 Real-time quality monitoring: Online monitoring: using machine vision detection system to monitor the size and appearance defects of thin-walled parts in real time, using infrared thermometer to monitor the temperature change in the forming process, using pressure sensor to monitor the forming pressure fluctuation; Offline detection: periodically extract the thin-walled parts produced in batch, perform mechanical property test and size accuracy test, and record the test data; 5.3 Dynamic adjustment of process parameters: if the online monitoring or offline detection finds quality abnormalities, analyze the abnormal reasons, and adjust the optimal process parameters according to the abnormal conditions to ensure the stability of product quality in batch production process.

Images