Aluminum profile extrusion process energy consumption optimization method based on digital twinning

Abstract

The invention relates to an aluminum profile extrusion process energy consumption optimization method based on digital twinning, and the method comprises the steps: building a digital twinning model of an aluminum profile extrusion process, setting the range of extrusion process parameters, importing preset process parameters into the model for simulation, and extracting a quality index and an energy consumption index. The process parameters are optimized through a multi-objective optimization algorithm; the optimized parameters are imported into the model for simulation again, and results before and after optimization are compared to judge whether optimization is achieved or not. If the product quality is qualified and the energy consumption is optimal, applying optimization parameters to actual production; otherwise, continuing to optimize until the preset requirement is met. Through a digital twinning means, the strength and the workload of finding the optimal energy consumption process parameters in the aluminum profile extrusion process only through repeated manual physical experiments are reduced, energy conservation and emission reduction in the aluminum profile extrusion process are achieved, and meanwhile the production efficiency of an enterprise is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption optimization in aluminum profile processing, and specifically to an energy consumption optimization method for an aluminum profile extrusion process based on digital twins. Background Art

[0002] As global energy shortages and environmental pollution become increasingly serious, the manufacturing industry faces huge challenges in energy conservation and emission reduction. Aluminum extrusion is an important processing technology widely used in the fields of construction, transportation, electronics, etc., and its energy consumption in the production process has attracted much attention. However, the aluminum extrusion manufacturing process is affected by process parameters and consumes a lot of energy. Its production process is a high-energy consumption and high-emission manufacturing process, which leads to increased production costs for manufacturers. Traditional aluminum extrusion processes often rely on experience and manual repeated experiments to determine the optimal process parameters, with high energy consumption and low production efficiency.

[0003] In recent years, with the rapid development of digital technology, the application of digital twin technology in the field of industrial manufacturing has gradually emerged. Digital twin technology achieves accurate simulation and real-time monitoring of the actual production process through the deep integration of virtual models and physical equipment. It can not only simulate the changes of various process parameters in the production process, but also obtain key indicators of product quality and energy consumption through virtual experiments, providing data support for the optimization of process parameters.

[0004] In the field of aluminum extrusion, the application of digital twin technology can effectively reduce the number of physical experiments, reduce experimental costs, and improve production efficiency. However, most of the current research based on digital twin technology focuses on optimizing product quality, and relatively little research and optimization of energy consumption. In particular, in the aluminum extrusion process, how to minimize energy consumption through digital twin means is still a technical problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of the present invention is to provide a method for optimizing energy consumption in an aluminum profile extrusion process based on digital twins, to construct a digital twin model of the aluminum profile extrusion process, to optimize process parameters using a multi-objective optimization algorithm based on the simulation results of product quality and energy consumption, and to improve production efficiency.

[0006] According to one main aspect of the present invention, a method for optimizing energy consumption in an aluminum profile extrusion process based on digital twin is provided, comprising one or a combination of the following steps:

[0007] Step 1: Build a digital twin model of the aluminum profile extrusion process;

[0008] Step 2, setting the range of various process parameters for aluminum profile extrusion, wherein the process parameters include extrusion temperature T, extrusion speed V, hydraulic system pressure Ph, electrical system power Pe, die geometry G, and raw material characteristic parameter M;

[0009] Step 3: Import the preset aluminum profile extrusion process parameters into the digital twin model, simulate the aluminum profile extrusion forming process, and extract the quality index value Q(Pi) and the energy consumption index value E(Pi) from the simulation results of the digital twin model;

[0010] Step 4, using the quality index values ​​and energy consumption index values ​​obtained in step 3) as constraints, optimizing the aluminum profile extrusion process parameters using a multi-objective optimization algorithm;

[0011] Step 5: Import the optimized aluminum profile extrusion process parameters into the digital twin model, simulate the aluminum profile extrusion forming process again, and extract the quality index values ​​and energy consumption index values;

[0012] Step 6, compare the aluminum profile extrusion process parameters and product quality indicators before and after optimization to determine whether the product quality is qualified and whether the energy consumption is optimal; if the product quality is qualified and the energy consumption is optimal, the optimized aluminum profile extrusion process parameters are applied to actual production; otherwise, the quality index values ​​and energy consumption index values ​​obtained in step 5 are used as constraints, and the aluminum profile extrusion process parameters are optimized using the multi-objective optimization algorithm described in step 4, and steps 5 and 6 are repeated until the product quality is qualified and the energy consumption is optimal.

[0013] In the above scheme, by building an aluminum profile extrusion process model based on digital twin, the digital simulation and optimization of the extrusion process is realized, which can accurately simulate the process parameters such as temperature, speed, hydraulic system pressure, etc. in actual production. This allows the production process to be quickly iterated in a virtual environment, which can greatly reduce the cost and time loss in traditional experimental methods, while avoiding possible material waste in production.

[0014] Setting a reasonable range of process parameters is the basis for ensuring the optimization effect. By limiting these parameters within a certain range, the feasibility of optimization can be ensured, and the parameters can be prevented from exceeding the operating limits of the actual equipment, thereby ensuring safety and product quality.

[0015] By importing process parameters into the digital twin model for simulation, the real extrusion process can be simulated and the corresponding quality indicators and energy consumption indicators can be quickly obtained. The simulation results provide a data basis for subsequent optimization, so that each parameter and its impact on quality and energy consumption can be quantified.

[0016] Moreover, through the multi-objective optimization algorithm, the balance between quality and energy consumption can be considered at the same time, and energy consumption can be reduced as much as possible while maintaining product quality in line with requirements. This optimization method can effectively solve the limitations of single objectives in traditional optimization, such as only pursuing minimum energy consumption or maximum quality, and ensure the comprehensive benefits of production. Using a multi-strategy improved multi-objective particle swarm optimization algorithm based on non-dominated sorting, crowding distance calculation strategy, and survival of the fittest selection strategy, the optimal solution that meets multiple constraints can be quickly found.

[0017] In some embodiments, as a further preferred solution, the digital twin model includes:

[0018] A hydraulic system model, used to simulate the working process of the hydraulic components of the aluminum extrusion press. The hydraulic system model accurately describes the behavior of the hydraulic circuit, including pumps, valves, pipes and actuators;

[0019] Mechanical system models, used to simulate the motion mechanism of extrusion equipment;

[0020] Electrical system model, used to analyze the power consumption and operating efficiency of motors and control circuits in extrusion equipment, and further optimize power distribution;

[0021] Extrusion simulation model, used to model and simulate the plastic deformation process of aluminum profiles and predict the material flow behavior under different temperature and pressure conditions;

[0022] The product quality detection model combines data from multiple sensors to monitor the morphological changes of the product during the extrusion process in real time to ensure product quality indicators.

[0023] As a further preferred solution, the optimized process parameters are updated to the production equipment in real time through the cloud-based digital twin platform to achieve automated adjustment and energy consumption monitoring.

[0024] As a further preferred solution, the quality indicators include strength, hardness, plasticity, and toughness, and the energy consumption indicator is the power consumption of the hydraulic pump of the hydraulic system.

[0025] In some embodiments, as a further preferred solution, the multi-objective optimization algorithm is a multi-objective particle swarm optimization algorithm based on a multi-strategy improvement of non-dominated sorting, crowding distance calculation strategy and survival of the fittest selection strategy, including one or a combination of the following steps:

[0026] Initialize the particle group, each particle represents a set of aluminum profile extrusion process parameter combinations Pi = [Ti, Vi, Phi, Pei, Gi, Mi], where Ti represents the extrusion temperature in the parameter combination represented by the i-th particle, Vi represents the extrusion speed used in the i-th particle, Phi represents the working pressure of the hydraulic system in the i-th particle, Pei represents the power of the electrical system in the i-th particle, Gi represents the die geometry parameters in the i-th particle, and Mi represents the raw material characteristic parameters used in the i-th particle;

[0027] The initial position Xi and velocity Vi of each particle are randomly generated and meet the upper and lower limit constraints of the process parameters;

[0028] In each iteration, the digital twin model is used to simulate and calculate the energy consumption E(Pi) and quality index Q(Pi) of each particle Pi. The fitness of each particle is determined by its objective function value;

[0029] The particle's position and velocity are updated using the following formula:

[0030]

[0031] In the formula, is the velocity of particle i at the tth iteration,

[0032] is the position of particle i at the tth iteration,

[0033] ω: Inertia weight, ranging from [0.4, 0.9], controls the balance between large-scale search and local optimization. Larger ω values ​​(close to 0.9) encourage global search and can help the algorithm escape from the local optimal solution; smaller ω values ​​(close to 0.4) encourage local search and help converge to the optimal solution.

[0034] c1=c2=2.0: learning factor, c1 controls the degree to which the individual follows its own historical best position, and c2 controls the degree to which the individual follows the group's best position. c1=c2=2.0 is a more conservative and effective choice because it balances the influence of individuals and groups and helps stabilize convergence.

[0035] r1, r2: random numbers, ranging from [0,1],

[0036] P besr : The historical optimal position of particle i,

[0037] G besr : The optimal position among all particles;

[0038] For each particle group, non-dominated sorting is performed based on the dual objectives of energy consumption and quality, and the particle dominance relationship satisfies the condition: if particle Pi is not worse than Pj in all objectives and is better than Pj in at least one objective, then Pi dominates Pj, that is:

[0039] P i Dominate And Q(P i )≥Q min ) or (E(P i ) <E(P j ) and Q(P i )>Q(P j ))

[0040] For each particle Pi, calculate the number ni of particles it is dominated by:

[0041]

[0042] Among them, Ⅱ is the indicator function, when Pj dominates Pi, Ⅱ = 1, otherwise Ⅱ = 0;

[0043] The particles with a dominance number of 0 form the first layer of non-dominated solutions. These solutions are removed from the particle set, and the dominance numbers of the remaining particles are calculated to form the second layer of non-dominated solutions. This process is repeated until all particles are classified;

[0044] Calculate the crowding distance of each particle in the non-dominated layer to ensure diversity;

[0045] Particles are selected to enter the next generation based on non-dominated sorting and crowding distance, with priority given to solutions with low energy consumption and satisfying quality constraints;

[0046] For each non-dominated layer, the solution with a large crowding distance is selected first to increase the diversity of solutions. If the number of solutions in the solution set exceeds the requirement, the solution with lower energy consumption is selected by comparing the energy consumption values.

[0047] Based on the convergence conditions, it is determined whether the optimization process is completed and the optimal aluminum profile extrusion process parameters are output.

[0048] As a further preferred solution, the convergence and termination conditions include:

[0049] The improvement rate of energy consumption during the optimization process is lower than the preset threshold v;

[0050] Reach the maximum number of iterations Tmax;

[0051] The Pareto front is stable and has no significant changes.

[0052] As a further preferred solution, the multi-objective optimization algorithm introduces global search and local search mechanisms to accelerate convergence, combines fuzzy logic control and neural networks to assist decision-making in the optimization process, and dynamically adjusts ω, c1, and c2 according to the convergence state of the particle swarm.

[0053] Global search and local search mechanisms are introduced into the algorithm to improve the convergence speed of the algorithm and the quality of the solution. During the search process, fuzzy logic control and neural networks are combined to assist in decision-making on the search behavior of the particle swarm. According to the current convergence state of the particle swarm, the inertia weight, learning factor and search range are dynamically adjusted to ensure that the particle swarm explores a larger range of solution space with a higher global search capability in the early stage of optimization, and gradually transitions to local search in the later stage of optimization, accurately optimizing the details of the solution, thereby improving the optimization efficiency and global convergence.

[0054] As a further preferred solution, the multi-objective optimization algorithm takes minimizing the energy consumption of the aluminum profile extrusion process as the main goal.

[0055] According to another main aspect of the present invention, a system for executing a method for optimizing energy consumption of an aluminum profile extrusion process based on digital twin is provided, comprising:

[0056] Process parameter setting module, used to set the range of aluminum profile extrusion process parameters;

[0057] The digital twin model module will import the set aluminum profile extrusion process parameters, simulate the extrusion process, and generate simulation results, including energy consumption indicators and product quality indicators;

[0058] Optimization module, which uses multi-objective optimization algorithm to optimize the aluminum profile extrusion process parameters;

[0059] The feedback module is used to import the optimized process parameters into the digital twin model for re-simulation, generate new energy consumption and quality indicators, and compare them with the results before optimization;

[0060] The control module is used to judge whether the product quality is qualified and whether the energy consumption reaches the optimization target according to the results of the feedback module. If the conditions are met, the optimized process parameters are output and applied to actual production. Otherwise, the process parameters are continuously optimized until the predetermined energy consumption and quality requirements are met.

[0061] By integrating multiple functional modules, intelligent energy consumption optimization of the aluminum extrusion process is achieved. It ensures the lowest energy consumption while meeting quality requirements, thereby significantly improving energy efficiency and reducing production costs. This process not only reduces energy consumption, but also reduces the workload of the equipment, prolongs the service life of the equipment, and helps achieve green manufacturing and sustainable development goals.

[0062] Based on another main aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed, the energy consumption optimization method of the aluminum profile extrusion process based on digital twin is implemented.

[0063] Based on another main aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the energy consumption optimization method for the aluminum profile extrusion process based on digital twin is implemented.

[0064] Advantages and beneficial effects of the present invention:

[0065] The present invention realizes the digital simulation of the aluminum profile extrusion process by constructing a digital twin model of aluminum profile extrusion equipment, extrusion process and product quality inspection; proposes to optimize the aluminum profile extrusion process parameters according to the quality index values ​​and energy consumption index values ​​of the digital twin model simulation results by using a multi-strategy improved multi-objective particle swarm optimization algorithm based on non-dominated sorting, crowding distance calculation strategy and survival of the fittest selection strategy, so as to achieve the optimal energy consumption in the aluminum profile extrusion process.

[0066] Through digital twin technology, the present invention reduces the repeated experiments and manual intervention required in traditional physical experiments to find the optimal energy consumption parameters. This not only greatly reduces the cost and intensity of the experiment, but also significantly shortens the research and development cycle, so that the energy-saving effect of the aluminum profile extrusion process can be fully reflected. In addition, with the help of the combination of digital twin technology and optimization algorithms, enterprises can find the optimal process parameters faster and more accurately, and ultimately achieve energy conservation and emission reduction, reduce resource waste, and further improve production efficiency and product consistency. This digital and intelligent technological innovation not only brings significant economic benefits to enterprises, but also provides technical support for the sustainable development of the aluminum profile industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying creative labor, other drawings obtained based on these drawings still belong to the scope of the present invention.

[0068] Figure 1 It is a schematic diagram of the process of the present invention;

[0069] Figure 2 It is a schematic diagram of the multi-objective optimization algorithm flow of the present invention. DETAILED DESCRIPTION

[0070] The preferred embodiments of the present invention will be described in detail below so that the purpose, features and advantages of the present invention can be more clearly understood. It should be understood that the following embodiments are not intended to limit the scope of the present invention, but are only intended to illustrate the essential spirit of the technical solution of the present invention.

[0071] In the following description, certain specific details are set forth for the purpose of illustrating the various disclosed embodiments to provide a thorough understanding of the various disclosed embodiments. However, those skilled in the relevant art will recognize that the embodiments may be practiced without one or more of these specific details. In other cases, well-known devices, structures, and techniques associated with the present application may not be shown or described in detail to avoid unnecessarily obscuring the description of the embodiments.

[0072] References throughout the specification to "one embodiment" or "an embodiment" indicate that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of "in one embodiment" or "in an embodiment" in various places throughout the specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any manner in one or more embodiments.

[0073] Example

[0074] like Figure 1 Shown is a flow chart of a method for optimizing energy consumption in an aluminum profile extrusion process based on digital twins provided in one embodiment of the present invention.

[0075] like Figure 2 The figure shows a flow chart of a multi-objective particle swarm optimization algorithm based on a non-dominated sorting, crowding distance calculation strategy and survival of the fittest selection strategy provided by an embodiment of the present invention.

[0076] 1. Construction of digital twin model

[0077] In this invention, the digital twin model is the core component, which accurately simulates the aluminum profile extrusion process by integrating multiple subsystems including hydraulic system model, mechanical system model, electrical system model, extrusion simulation model and product quality inspection model. The model is constructed based on advanced physical modeling and simulation technology, ensuring the accuracy and reliability of the simulation results.

[0078] 1.1 Hydraulic system model, used to simulate the working process of the hydraulic components of the aluminum extruder. The system model accurately describes the behavior of the hydraulic circuit, including pumps, valves, pipelines and actuators; the hydraulic system is the key driving system in the aluminum profile extrusion process, responsible for providing the pressure and power required for the extrusion process. In order to accurately model the hydraulic system, the behavior of the hydraulic system is determined by the fluid dynamics equations, which are used to describe the pressure drop, flow rate and other parameters of the liquid when it flows in the hydraulic pipeline.

[0079] 1.2 Mechanical system model, used to simulate the motion mechanism of the extrusion equipment, and simulate the mechanical transmission and motion characteristics of the aluminum profile extrusion equipment. The following aspects are mainly considered:

[0080] The motion and mechanical characteristics of the device are described by Newton-Euler equations;

[0081] Coulomb friction model or viscous friction model is used to simulate the friction loss of extrusion equipment during movement;

[0082] The plastic deformation theory is used to analyze the forces and deformation characteristics of aluminum profiles during the extrusion process, and to predict the working state of the equipment under different loads.

[0083] 1.3 Electrical system model, used to analyze the power consumption and operating efficiency of motors and control circuits in extrusion equipment, and further optimize power distribution;

[0084] The motor in the extrusion equipment is modeled using the motor's torque balance equation and power equation to simulate the relationship between its output power, torque and speed.

[0085] 1.4 Extrusion simulation model, which is used to model and simulate the plastic deformation process of aluminum profiles and predict the material flow behavior under different temperature and pressure conditions; the extrusion simulation model is the core part of the entire digital twin model, mainly involving the following contents:

[0086] Based on the stress-strain relationship in plastic mechanics, the deformation behavior of aluminum at different temperatures and pressures is simulated, and the plastic flow theory and Navier-Stokes equation are used to describe the fluidity of the material;

[0087] The flow behavior of aluminum profiles is numerically solved by the finite element method (FEM) to predict the material flow, temperature field, stress field and deformation under different extrusion conditions;

[0088] The coupled temperature field and stress field equations are used to simulate the effect of temperature change on material flow during the extrusion process.

[0089] 1.5 Product quality detection model, combined with a variety of sensor data to monitor the morphological changes of products in real time during the extrusion process, through the virtual test bench in the simulation environment, to conduct virtual tests on strength, hardness, toughness, etc., to predict the final physical properties of the product and ensure product quality indicators.

[0090] 1.6 Digital simulation: After modeling is completed, use numerical simulation tools (such as Ansys, MATLAB Simulink, COMSOL, etc.) to digitally simulate the hydraulic system, mechanical system, and electrical system, and compare and verify with actual production data. Extract the quality index value Q(Pi) and energy consumption index value E(Pi) from the simulation results of the digital twin model.

[0091] 2. Multi-objective optimization algorithm

[0092] After the simulation is completed, the aluminum profile extrusion process parameters are optimized according to the quality index values ​​and energy consumption index values ​​of the digital twin model simulation results using a multi-objective particle swarm optimization algorithm improved by multiple strategies based on non-dominated sorting, crowding distance calculation strategy and survival of the fittest selection strategy to achieve the optimal energy consumption of the aluminum profile extrusion process.

[0093] 2.1 Improvement strategy of multi-objective particle swarm optimization algorithm (MOPSO)

[0094] MOPSO is a classic optimization algorithm that finds the optimal solution to a problem by simulating the group behavior of particles. It is particularly effective in multi-objective optimization and can handle the simultaneous optimization of multiple conflicting objectives. For the present invention, the two objectives are:

[0095] Minimize energy consumption: that is, reduce the energy consumption required in the aluminum profile extrusion process by optimizing parameters;

[0096] Maximizing quality: that is, ensuring key quality indicators such as product strength and toughness while reducing energy consumption.

[0097] Among them, minimizing the energy consumption in the aluminum profile extrusion process is the main goal.

[0098] In multi-objective optimization, the Pareto front is an effective way to describe the trade-offs between multiple optimization objectives. In this optimization process, improvements are made through three core strategies: non-dominated sorting, crowding distance calculation, and survival of the fittest selection strategy.

[0099] 2.2 Non-dominated sorting

[0100] Non-dominated sorting is the process of classifying a population of particles according to whether they are dominated or not. The algorithm divides all particles into several layers, the first layer is non-dominated solutions, that is, solutions on the Pareto front, the second layer is solutions that are only dominated by the first layer solutions, and so on.

[0101] For each particle group, non-dominated sorting is performed based on the dual objectives of energy consumption and quality, and the particle dominance relationship satisfies the condition: if particle Pi is not worse than Pj in all objectives and is better than Pj in at least one objective, then Pi dominates Pj, that is:

[0102] Pi Domination and Q(Pi)≥Qmin) or (E(Pi)=E(Pj) ​​and Q(Pi)>Q(Pj))

[0103] Let ni be the number of times dominated by other particles, initialized to 0

[0104] Let Si be the set of all particles dominated by Pi

[0105] For each particle Pi, calculate the number ni of particles it is dominated by:

[0106]

[0107] Among them, Ⅱ is the indicator function, when Pj dominates Pi, Ⅱ = 1, otherwise Ⅱ = 0;

[0108] The particles with dominance number ni of 0 form the first layer of non-dominated solutions, which are removed from the particle set and added to the Pareto front;

[0109] For each particle Pi that belongs to the first-level non-dominated solution, find all the particles in the particle set Si that it dominates and perform the following operations on these particles:

[0110] For each particle Pj∈Si dominated by Pi, its domination count is reduced by one, that is, nj=nj-1.

[0111] If nj=0, Pj is added to the second-level non-dominated solutions.

[0112] This process is repeated until all particles are assigned to a layer.

[0113] Through this process, all particles are stratified, with the first layer being the optimal Pareto front and subsequent layers representing successively suboptimal solutions.

[0114] 2.3 Crowding distance calculation

[0115] The crowding distance is used to evaluate the distribution of solutions on the Pareto front. Its purpose is to maintain the diversity of the Pareto solution set and prevent particles from concentrating in a local area of ​​the front.

[0116] The crowding distance D(Pi) calculates the spatial sparsity around each particle.

[0117] For each particle Pi on the Pareto front, initialize its crowding distance to 0. Sort the particles for each objective function and find the minimum and maximum values. The crowding distances of the solutions with the minimum and maximum objective function values ​​on the Pareto front are set to infinity because they are located at the boundary and are often the solutions that need to be retained.

[0118] For the particle in the middle, the crowding distance is calculated as:

[0119]

[0120] Among them, f m (P i+1 ) and f m (P i-1 ) are the particles P on the target m. i+1 and P i-1 The objective function value of and is the objective function f m The maximum and minimum values ​​of .

[0121] A particle with a larger crowding distance indicates that it is located in a sparse area of ​​the frontier and is preferred for retention; a particle with a smaller crowding distance is more likely to be eliminated.

[0122] 2.4 Survival of the fittest selection strategy

[0123] At the end of each iteration, the solutions in the current population are compared with the solutions in the historical population, and the best solution is selected to enter the next generation.

[0124] Combining non-dominated sorting and crowding distance, the survival of the fittest selection strategy ensures that the solutions with the lowest energy consumption and meeting the quality standards are retained, the inferior solutions are gradually eliminated, and the optimal solutions on the Pareto front are retained.

[0125] For each non-dominated layer, solutions with large crowding distance are selected first to increase the diversity of solutions. If the number of solutions in the solution set exceeds the requirement, solutions with lower energy consumption are selected first by comparing the energy consumption values.

[0126] 2.5 Strategies to Accelerate Convergence

[0127] 2.51 Global and Local Search Mechanisms

[0128] Global search and local search are two search mechanisms in particle swarm optimization algorithm:

[0129] Global search: In the early stages of optimization, the algorithm needs a larger exploration range to avoid falling into the local optimum. Global search increases the search range of particles in the solution space through a larger inertia weight ω, thereby improving the exploration ability.

[0130] Local search: As the optimization proceeds, the inertia weight ω is gradually reduced so that particles focus more on the vicinity of the current optimal solution, thereby improving the ability to refine the optimal solution and enhancing the algorithm's development capabilities.

[0131] The dynamic adjustment strategy of the inertia weight ω is carried out according to the following formula:

[0132]

[0133] Where, ω(t): inertia weight of the tth generation,

[0134] ω max and ω min : The maximum and minimum values ​​of the inertia weight are 0.9 and 0.4 respectively,

[0135] t: current iteration number,

[0136] T max : Maximum number of iterations.

[0137] In this way, the inertia weight gradually decreases with the number of iterations, thus achieving a smooth transition from global search to local search. This dynamic adjustment can effectively improve the convergence speed and avoid falling into the local optimum.

[0138] 2.52 Introduction of fuzzy logic control and neural network assisted decision making

[0139] In order to further optimize the convergence speed, fuzzy logic control and neural network are combined to dynamically adjust the parameters in the algorithm.

[0140] Fuzzy rules are set according to the key indicators in the aluminum extrusion process. The fuzzy controller adjusts the weight of global and local search at each iteration according to these rules to ensure that the appropriate search intensity is maintained at all stages. Fuzzy logic control adjusts according to the distribution state and convergence trend of the current solution by fuzzifying the input variables and reasoning according to the rule base. When the convergence speed is slow, increase ω or adjust the learning factor to enhance the global search; when the convergence speed is fast and the diversity is low, reduce ω to strengthen the local search.

[0141] The neural network can judge the different states in the optimization process based on the training data and output appropriate parameter adjustment suggestions. During the optimization process, the neural network outputs adjustment suggestions for ω, c1, and c2 in real time based on the current particle distribution and convergence state, thereby accelerating convergence.

[0142] During the optimization process, the fuzzy controller and the neural network work together. The fuzzy controller evaluates the current optimization status in real time and adjusts the optimization direction through rules; the neural network fine-tunes the optimization parameters based on the learned historical data.

[0143] 2.6 Multi-objective optimization process and calculation

[0144] Initialize the particle group, each particle represents a set of aluminum profile extrusion process parameter combinations Pi = [Ti, Vi, Phi, Pei, Gi, Mi], where Ti represents the extrusion temperature in the parameter combination represented by the i-th particle, Vi represents the extrusion speed used in the i-th particle, Phi represents the working pressure of the hydraulic system in the i-th particle, Pei represents the power of the electrical system in the i-th particle, Gi represents the die geometry parameters in the i-th particle, and Mi represents the raw material characteristic parameters used in the i-th particle;

[0145] The initial position Xi and velocity Vi of each particle are randomly generated and meet the upper and lower limit constraints of the process parameters;

[0146] In each iteration, the digital twin model is used to simulate and calculate the energy consumption E(Pi) and quality index Q(Pi) of each particle Pi. The fitness of each particle is determined by its objective function value;

[0147] The particle's position and velocity are updated using the following formula:

[0148]

[0149] In the formula, is the velocity of particle i at the tth iteration,

[0150] is the position of particle i at the tth iteration,

[0151] ω: Inertia weight, ranging from [0.4, 0.9], controls the balance between large-scale search and local optimization. Larger ω values ​​(close to 0.9) encourage global search and can help the algorithm escape from the local optimal solution; smaller ω values ​​(close to 0.4) encourage local search and help converge to the optimal solution.

[0152] c1=c2=2.0: learning factor, c1 controls the degree to which the individual follows its own historical best position, and c2 controls the degree to which the individual follows the group's best position. Choosing c1=c2=2.0 is a more conservative and effective choice because it balances the influence of individuals and groups and helps stabilize convergence.

[0153] r1, r2: random numbers, ranging from [0,1],

[0154] P besr : The historical optimal position of particle i,

[0155] G best : The optimal position among all particles;

[0156] For each particle group, non-dominated sorting is performed based on the dual objectives of energy consumption and quality, and the particle dominance relationship satisfies the condition: if particle Pi is not worse than Pj in all objectives and is better than Pj in at least one objective, then Pi dominates Pj, that is:

[0157] P i Dominate And Q(P i )≥Q min ) or (E(P i ) <E(P j ) and Q(P i )>Q(P j ))

[0158] For each particle Pi, calculate the number ni of particles it is dominated by:

[0159]

[0160] Among them, Ⅱ is the indicator function, when Pj dominates Pi, Ⅱ = 1, otherwise Ⅱ = 0;

[0161] The particles with a dominance number of 0 form the first layer of non-dominated solutions. These solutions are removed from the particle set, and the dominance numbers of the remaining particles are calculated to form the second layer of non-dominated solutions. This process is repeated until all particles are classified;

[0162] Calculate the crowding distance of each particle in the non-dominated layer to ensure diversity;

[0163] Particles are selected to enter the next generation based on non-dominated sorting and crowding distance, with priority given to solutions with low energy consumption and satisfying quality constraints;

[0164] For each non-dominated layer, the solution with a large crowding distance is selected first to increase the diversity of solutions. If the number of solutions in the solution set exceeds the requirement, the solution with lower energy consumption is selected by comparing the energy consumption values.

[0165] Based on the convergence conditions, it is determined whether the optimization process is completed and the optimal aluminum profile extrusion process parameters are output.

[0166] As a further preferred solution, the convergence and termination conditions include:

[0167] The improvement rate of energy consumption during the optimization process is lower than the preset threshold ∈;

[0168] If the rate of change of the optimal energy consumption value in consecutive G generations If it is less than the set threshold ∈, it is considered to have converged.

[0169] When the number of algorithm iterations reaches the maximum number of iterations Tmax, the optimization process is terminated;

[0170] The Pareto front is stable and has no significant changes. The stability distance of the Pareto front solution set is calculated.

[0171]

[0172] Where N is the number of Pareto front solutions,

[0173] and and are the Pareto front solutions of the tth and t+1th generations respectively.

[0174] If the continuous G generation D Pareto If the stability distance is lower than the set Pareto frontier threshold δ, it is considered to have converged.

[0175] The matters not described in detail in the present invention are all known technologies to those skilled in the art.

[0176] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for optimizing energy consumption in aluminum profile extrusion process based on digital twin, characterized in that: The method includes one or a combination of the following steps: Step 1: Build a digital twin model of the aluminum profile extrusion process; Step 2, setting the range of various process parameters for aluminum profile extrusion, wherein the process parameters include extrusion temperature T, extrusion speed V, hydraulic system pressure Ph, electrical system power Pe, die geometry G, and raw material characteristic parameter M; Step 3: Import the preset aluminum profile extrusion process parameters into the digital twin model, simulate the aluminum profile extrusion forming process, and extract the quality index value Q(Pi) and the energy consumption index value E(Pi) from the simulation results of the digital twin model; Step 4, using the quality index values ​​and energy consumption index values ​​obtained in step 3) as constraints, optimizing the aluminum profile extrusion process parameters using a multi-objective optimization algorithm; Step 5: Import the optimized aluminum profile extrusion process parameters into the digital twin model, simulate the aluminum profile extrusion forming process again, and extract the quality index values ​​and energy consumption index values; Step 6, compare the aluminum profile extrusion process parameters and product quality indicators before and after optimization to determine whether the product quality is qualified and whether the energy consumption is optimal; If the product quality is qualified and the energy consumption is optimal, the optimized aluminum profile extrusion process parameters are applied to actual production. Otherwise, the quality index values ​​and energy consumption index values ​​obtained in step 5 are used as constraints, and the aluminum profile extrusion process parameters are optimized using the multi-objective optimization algorithm described in step 4, and steps 5 and 6 are repeated until the product quality is qualified and the energy consumption is optimal.

2. The method for optimizing energy consumption in aluminum profile extrusion process based on digital twin according to claim 1, characterized in that: The digital twin model includes: A hydraulic system model, used to simulate the working process of the hydraulic components of the aluminum extrusion press. The hydraulic system model accurately describes the behavior of the hydraulic circuit, including pumps, valves, pipes and actuators; Mechanical system models, used to simulate the motion mechanism of extrusion equipment; Electrical system model, used to analyze the power consumption and operating efficiency of motors and control circuits in extrusion equipment, and further optimize power distribution; Extrusion simulation model, used to model and simulate the plastic deformation process of aluminum profiles; The product quality detection model combines data from multiple sensors to monitor the morphological changes of the product during the extrusion process in real time.

3. The method for optimizing energy consumption in aluminum profile extrusion process based on digital twin according to claim 1, characterized in that: The quality indicators include strength, hardness, plasticity, and toughness, and the energy consumption indicator is the power consumption of the hydraulic pump of the hydraulic system.

4. The method for optimizing energy consumption in aluminum profile extrusion process based on digital twin according to claim 1, characterized in that: The multi-objective optimization algorithm is a multi-objective particle swarm optimization algorithm improved by multiple strategies based on non-dominated sorting, crowding distance calculation strategy and survival of the fittest selection strategy, and includes one or a combination of the following steps: Initialize a particle group, each particle represents a set of aluminum profile extrusion process parameter combinations Pi = [Ti, Vi, Phi, Pei, Gi, Mi], where Ti represents the extrusion temperature in the parameter combination represented by the i-th particle, Vi represents the extrusion speed used in the i-th particle, Phi represents the working pressure of the hydraulic system in the i-th particle, Pei represents the power of the electrical system in the i-th particle, Gi represents the die geometry parameters in the i-th particle, and Mi represents the raw material characteristic parameters used in the i-th particle; The initial position Xi and velocity Vi of each particle are randomly generated and meet the upper and lower limit constraints of the process parameters; In each iteration, the energy consumption E(Pi) and quality index Q(Pi) of each particle Pi are simulated and calculated using the digital twin model. The fitness of each particle is determined by its objective function value. The particle's position and velocity are updated using the following formula: In the formula, is the velocity of particle i at the tth iteration, is the position of particle i at the tth iteration, ω: Inertia weight, in the range of [0.4, 0.9], used to control the balance between large-scale search and local optimization, c1=c2=2.0: learning factor, c1 controls the degree to which the individual follows its own historical best position, and c2 controls the degree to which the individual follows the group's best position. r1, r2: random numbers, ranging from [0, 1], P besr : The historical optimal position of particle i, G besr : The optimal position among all particles; For each particle group, non-dominated sorting is performed based on the dual objectives of energy consumption and quality, and the particle dominance relationship satisfies the condition: if particle Pi is not worse than Pj in all objectives and is better than Pj in at least one objective, then Pi dominates Pj, that is: P i Dominate And Q(P i )≥Q min ) or (E(P i )<E(P j ) and Q(P i )>Q(P j )) For each particle Pi, calculate the number ni of particles it is dominated by: Among them, Ⅱ is the indicator function, when Pj dominates Pi, Ⅱ = 1, otherwise Ⅱ = 0; The particles with a dominance number of 0 form the first layer of non-dominated solutions. These solutions are removed from the particle set, and the dominance numbers of the remaining particles are calculated to form the second layer of non-dominated solutions. This process is repeated until all particles are classified; Calculate the crowding distance of each particle in the non-dominated layer to ensure diversity; Particles are selected to enter the next generation based on non-dominated sorting and crowding distance, with priority given to solutions with low energy consumption and satisfying quality constraints; For each non-dominated layer, the solution with a large crowding distance is selected first to increase the diversity of solutions. If the number of solutions in the solution set exceeds the requirement, the solution with lower energy consumption is selected by comparing the energy consumption values. Based on the convergence conditions, it is determined whether the optimization process is completed and the optimal aluminum profile extrusion process parameters are output.

5. The method for optimizing energy consumption in aluminum profile extrusion process based on digital twin according to claim 4, characterized in that: The convergence and termination conditions include: The improvement rate of energy consumption during the optimization process is lower than the preset threshold ∈; Reach the maximum number of iterations Tmax; The Pareto front is stable and has no significant changes.

6. The method for optimizing energy consumption in aluminum profile extrusion process based on digital twin according to claim 4, characterized in that: The multi-objective optimization algorithm introduces global search and local search mechanisms, combines fuzzy logic control and neural networks to assist decision-making in the optimization process, and dynamically adjusts ω, c1, and c2 according to the convergence state of the particle swarm.

7. The method for optimizing energy consumption in aluminum profile extrusion process based on digital twin according to claim 4, characterized in that: The multi-objective optimization algorithm takes the minimum energy consumption of the aluminum profile extrusion process as the main goal.

8. A system for executing the energy consumption optimization method of aluminum profile extrusion process based on digital twinning according to claims 1-7, characterized in that: include Process parameter setting module, used to set the range of aluminum profile extrusion process parameters; The digital twin model module imports the set aluminum profile extrusion process parameters, simulates the extrusion process, and generates simulation results, including energy consumption indicators and product quality indicators; Optimization module, which uses multi-objective optimization algorithm to optimize the aluminum profile extrusion process parameters; The feedback module is used to import the optimized process parameters into the digital twin model for re-simulation, generate new energy consumption and quality indicators, and compare them with the results before optimization; The control module is used to judge whether the product quality is qualified and whether the energy consumption reaches the optimization target according to the results of the feedback module. If the conditions are met, the optimized process parameters are output and applied to actual production. Otherwise, the process parameters are continuously optimized until the predetermined energy consumption and quality requirements are met.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed, the energy consumption optimization method for aluminum profile extrusion process based on digital twin as described in any one of claims 1 to 7 is implemented.

10. A computer 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 program, it implements the energy consumption optimization method of aluminum profile extrusion process based on digital twin as described in any one of claims 1-7.

Images