Optimization Scheduling Method, Medium and Equipment for Welding Unit Based on Improved Simulated Annealing Particle Swarm Algorithm

Abstract

The present invention proposes a welding cell optimization scheduling method, medium and device based on an improved simulated annealing particle swarm algorithm, aiming to solve problems such as low efficiency and resource waste existing in traditional welding cell scheduling. First, by modeling the welding tasks and resources, the priorities of the tasks and the constraint conditions of the resources are determined. Then, individuals are encoded with two-dimensional matrix real numbers, and the population is initialized chaotically to improve the diversity and coverage of the initial population. The optimization objective function is defined, and a penalty function is added to update the objective function. The fitness of each particle is evaluated, and the individual optimal solution and the global optimal solution are updated. According to the global optimal fitness, the initial temperature of the simulated annealing algorithm is calculated, and optimization calculation is performed based on the simulated annealing particle swarm algorithm to obtain an optimized decision-making scheme. The method proposed by the present invention can effectively improve the production efficiency of the welding cell, reduce energy consumption, and reduce production costs, and has good application prospects and economic benefits.

Description

Technical Field

[0001] The present invention belongs to the technical field of manufacturing scheduling, and particularly relates to a welding cell optimization scheduling method, medium and device based on an improved simulated annealing particle swarm algorithm. Background Technique

[0002] In modern manufacturing, the welding process is an indispensable key link in fields such as automobiles, aviation, and shipbuilding. A welding cell usually includes multiple welding robots and related equipment, and these robots need to work together to complete complex welding tasks. In order to improve production efficiency and reduce production costs, the optimization scheduling problem of welding cells has become an important issue that needs to be solved urgently.

[0003] The scheduling problem of welding cells is a typical combinatorial optimization problem, and its goal is to maximize production efficiency and resource utilization under the premise of meeting various constraint conditions. This problem usually involves the allocation and scheduling of multiple tasks and resources, and multiple factors such as task priorities, welding times, energy consumption, and human resources need to be considered. Due to its complexity and multi-constraint nature, traditional optimization methods (such as linear programming, dynamic programming, etc.) are often inefficient in solving this problem and it is difficult to obtain an ideal scheduling scheme. Combining the simulated annealing algorithm with the particle swarm algorithm can utilize the global search ability of the simulated annealing algorithm to make up for the deficiency that the particle swarm algorithm is prone to falling into local optima, resulting in the search efficiency and effect being affected, thereby improving the global search ability and convergence speed of the algorithm. Therefore, aiming at the limitations of traditional optimization methods, a welding cell optimization scheduling method based on an improved simulated annealing particle swarm algorithm is proposed. By combining the advantages of the two algorithms, the solution effect and efficiency of the welding cell scheduling problem are improved, which has important theoretical significance and practical application value. Summary of the Invention

[0004] Aiming at the defects that the applicability of traditional welding cell optimization scheduling is limited and it cannot effectively solve the computational requirements of non-linear problems and high-dimensional problems, the present invention provides a welding cell optimization scheduling method, medium and device based on an improved simulated annealing particle swarm algorithm.

[0005] To achieve the above object, the present invention adopts the following technical solutions:

[0006] A welding cell optimization scheduling method based on an improved simulated annealing particle swarm algorithm, characterized by including the following steps:

[0007] Construct a problem model for welding cell optimization scheduling;

[0008] Analyze the welding tasks and available resources during the welding process, determine task priorities, and set constraint conditions for resources;

[0009] Define the optimization objective function of the problem model;

[0010] Design an optimized scheduling plan for the welding unit according to the task priority, resource constraints, and optimization objective function, and perform optimization calculations based on the simulated annealing particle swarm algorithm to obtain the optimized decision-making plan.

[0011] Specific measures taken to optimize the above technical solutions also include:

[0012] Furthermore, the welding tasks include the type, size, shape, and welding time of the workpieces to be welded, and the resources include welding robots and welding equipment.

[0013] Furthermore, the specific form of the optimization objective function is as follows:

[0014] h(X i，j ) = ω 1 ·p 1 + ω 2 ·p 2 ;

[0015] In the formula, h(X i，j ) represents the optimization objective function, X i，j represents the assignment of the i-th task to the j-th resource; p 1 is the production efficiency, expressed as where r is the number of tasks completed, m is the number of resources participating in the work, V i is the output value brought by completing task i, T i is the completion time of task i; p 2 is the resource utilization rate, expressed as t i，j is the working time of the i-th task assigned to the j-th resource; ω 1 , ω 2 are the weight coefficients.

[0016] Furthermore, the resource constraints include the working time limit and energy consumption limit of the welding robot.

[0017] Furthermore, the design of the optimized scheduling plan for the welding unit according to the task priority, resource constraints, and optimization objective function is as follows:

[0018] 1) Design particle encoding. Each particle represents a possible task assignment plan. The decision of assigning tasks to resources is represented by a real number encoding. Among them, the particle position X i，j represents the task assignment plan, which is represented by an r×m matrix. In this matrix, each row represents a task, each column represents a resource, and the matrix element represents the assignment of the i-th task to the j-th resource;

[0019] 2) Initialize the population using chaotic mapping and perform chaotic search using the Circle mapping:

[0020]

[0021] where x n is the value of the particle position X i，j at the n-th iteration, x n ∈ [0, 1]; mod(a, b) represents the remainder operation of a divided by b;

[0022] 3) Perform initialization operations on the population introduced with the Circle mapping:

[0023]

[0024] After generating the chaotic sequence, optimize the characteristics of each chaotic variable and then transform it into the feasible space of the original optimization variable C. Here, C n is the original optimization variable C and the corresponding value of the chaotic variable x n ; and C are the upper and lower bounds of the feasible space of the original optimization variable C respectively, and x n is the value of the chaotic sequence generated by the Circle mapping on the corresponding particle dimension;

[0025] 4) Add a penalty function to the optimization objective function for updating, and evaluate the position X i，j of each particle according to the updated function, and calculate its fitness H(X i，j );

[0026] 5) Update the individual optimal fitness and the global optimal fitness according to the calculated individual fitness of each particle.

[0027] Furthermore, the adding of the penalty function to the optimization objective function for updating, the updated function is:

[0028]

[0029] where ΔC e is the degree of violation of the constraint e, expressed as k is the number of iterations, e is the number of the energy consumption constraint violation, and C k，e is the value of the decision variable corresponding to the constraint e at the k-th iteration; C k，e is the upper and lower bounds of C k，e ; g is the number of violated constraints; E e is the penalty coefficient for the violation of the constraint e.

[0030] Further, the update of the individual optimal fitness and the global optimal fitness is specifically as follows:

[0031] When updating the individual optimal fitness, compare the fitness of each particle with the individual historical optimal fitness. If the fitness of the particle is greater than the individual historical optimal fitness, then select the fitness of the particle as the individual historical optimal fitness; otherwise, the individual historical optimal fitness remains unchanged.

[0032] When updating the global optimal fitness, consider the individual optimal fitness of all particles. Compare the maximum value of the individual optimal fitness among the particles with the global optimal fitness. If the individual optimal fitness is greater than the global optimal fitness, then select the individual optimal fitness to replace the global optimal fitness; otherwise, the global optimal fitness remains unchanged.

[0033] Further, the optimization calculation based on the simulated annealing particle swarm algorithm is specifically as follows:

[0034] 1) Calculate the initial temperature T of the simulated annealing algorithm according to the global optimal fitness, and the calculation formula is: 0 , and the calculation formula is:

[0035]

[0036] where GB is the global optimal position, and f(GB) is the global optimal fitness of the simulated annealing algorithm.

[0037] 2) Calculate the fitness of the simulated annealing algorithm at the current temperature T for each individual optimal position, and the formula is:

[0038]

[0039] where represents the historical optimal position of particle i at the k-th iteration, is the corresponding fitness of the historical optimal position of particle i at the k-th iteration, and r represents the number of tasks.

[0040] 3) Adopt the idea of the roulette wheel selection algorithm, calculate the cumulative probability according to the fitness of the simulated annealing algorithm. If the condition is satisfied, then select one from the individual historical optimal positions to replace the global optimal position GB, and denote it as where rand() is a random number from 0 to 1.

[0041] 4) Replace the original global optimal position GB with Update the positions and velocities of each particle, and update the optimal positions of the individual and the population. The formulas are as follows:

[0042]

[0043]

[0044] wherein, is the velocity of particle i at the (k + 1)-th iteration; ω is the inertia factor at the k-th iteration; c 1 is the local learning factor; c 2 is the global learning factor; r 1 and r 2 are two independent random numbers with values in the range [0, 1]; is the position of particle i at the (k + 1)-th iteration; represents the historical optimal position when task i is assigned to a resource at the k-th iteration;

[0045] 5) Perform an annealing operation, and the formula is as follows:

[0046] T′ = δT:

[0047] In the formula, δ is the annealing speed; T is the current temperature; T′ is the temperature after annealing;

[0048] 6) Determine whether the stopping criterion is met. If the stopping criterion is met, go to step 7); otherwise, go to step 2);

[0049] 7) Stop the search and output the optimal task allocation scheme for the welding unit. The two-dimensional matrix of the global optimal individual is the optimal task allocation scheme for the welding unit.

[0050] Correspondingly, the present invention proposes a computer-readable storage medium storing a computer program, characterized in that the computer program causes a computer to execute the welding unit optimization scheduling method based on the improved simulated annealing particle swarm algorithm as described above.

[0051] Correspondingly, the present invention proposes an electronic device, characterized in that it includes: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the welding unit optimization scheduling method based on the improved simulated annealing particle swarm algorithm as described above.

[0052] The beneficial effects of the present invention are:

[0053] (1) By combining the fast convergence characteristic of the particle swarm algorithm and the global search ability of the simulated annealing algorithm, the present invention effectively avoids falling into local optimal solutions, improves the search probability of global optimal solutions, increases the robustness and reliability of the algorithm while maintaining a high optimization efficiency, and enhances the overall optimization performance. This optimization scheduling can not only improve efficiency but also improve welding quality. By reasonably arranging the welding sequence and time, welding deformation and residual stress can be reduced, and the quality of the final product can be improved.

[0054] (2) The present invention adapts to the actual situation in the welding unit scheduling. By introducing a penalty function, it can effectively handle complex non-linear and multi-constraint optimization problems, ensure the feasibility of solutions and the optimization effect, and can meet the task requirements of multi-constraints, multi-objectives and dynamic changes, solving the problem that traditional welding unit scheduling methods are difficult to handle complex task scheduling problems. Description of the Drawings

[0055] Figure 1 is the flowchart of the optimized scheduling method for welding units based on the improved simulated annealing particle swarm optimization algorithm in the present invention.

[0056] Figure 2 is the flowchart of designing the welding unit scheduling scheme and calculating the optimized decision-making scheme based on the improved simulated annealing particle swarm optimization algorithm in the present invention. Detailed Embodiments

[0057] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application.

[0058] In one embodiment, as Figure 1 shown, the present invention proposes an optimized scheduling method for welding units based on the improved simulated annealing particle swarm optimization algorithm, which specifically includes the following steps.

[0059] S1: Construct a problem model of the optimized scheduling method for welding units based on the improved simulated annealing particle swarm optimization algorithm. The welding tasks include information such as the type, size, shape, and welding time of the welded workpieces, and the resources include welding robots, welding equipment, workers, etc. participating in the work.

[0060] S2: Analyze the welding tasks and available resources during the welding process and determine the priority of the tasks.

[0061] S3: To effectively improve the production efficiency of the welding unit, reduce energy consumption, and reduce production costs, in this embodiment, the constraint conditions of the resources are set as the working time limit t and the energy consumption limit e of the welding robot; it should be noted that in some other embodiments, the required resource constraint conditions can be selected according to specific situations, and the welding tasks and resources can also be set according to actual situations.

[0062] S4: In this embodiment, with the goal of improving production efficiency and resource utilization rate, an optimization objective function is defined as follows:

[0063] h(X i，j ) = ω 1 ·p 1 + ω 2 ·p 2 ;

[0064] Among them, X i，j indicates that the i-th task is assigned to the j-th welding robot; p 1 is the production efficiency, expressed as r is the number of tasks completed, m is the number of resources participating in the work, V i is the output value brought by completing task i, T i is the completion time of task i; p 2 is the resource utilization rate, expressed as t i，j is the working time when the i-th task is assigned to the j-th resource; the optimization objective function h(X i，j ) is to maximize the weighted combination of the production efficiency p 1 and the resource utilization rate p 2 ; ω 1 , ω 2 are the weight coefficients.

[0065] S5: Design a welding cell scheduling scheme according to the task priority, resource constraints, and optimization objective function, and calculate the optimized decision-making scheme based on the improved simulated annealing particle swarm algorithm.

[0066] As Figure 2 shown, the improved simulated annealing particle swarm algorithm specifically includes the following steps:

[0067] S5.1: Design particle encoding. Each particle represents a welding task assignment scheme, and the decision of assigning tasks to resources is represented by a real number encoding. Among them, the particle position X i，j represents the task assignment scheme, which is represented by an r×m matrix. In this matrix, each row represents a task, each column represents a resource, and the matrix element represents that the i-th task is assigned to the j-th resource; in this embodiment, the matrix element represents that the i-th task is assigned to the j-th welding robot.

[0068] S5.2: Chaotically initialize the population before obtaining the optimized scheduling decision of the welding cell. In this embodiment, chaotic mapping is used to initialize the population to improve the diversity and coverage of the initial population, and the Circle mapping is used for chaotic search:

[0069]

[0070] Among them, x n is the value of the particle position X i，j at the n-th iteration, representing the n-th chaotic sequence number, x n ∈[0, 1]; mod(a, b) represents the modulo operation of a with respect to b.

[0071] S5.3: The population initialization operation introducing the Circle mapping includes the initialization of the position:

[0072]

[0073] After the chaotic sequence is generated, the characteristics of each chaotic variable should be optimized and then transformed into the feasible space of the original optimization variable C, where C n is the corresponding value of the original optimization variable C and the chaotic variable x n ; and C are the upper and lower bounds of the feasible space of the original optimization variable C respectively; x n is the value of the chaotic sequence generated by the Circle mapping in the dimension corresponding to the welding unit scheduling task.

[0074] S5.4: Evaluate the fitness, that is, the production efficiency and resource utilization function brought when the welding task scheduling scheme is assigned to a specific position, add a penalty function to update the objective function, and evaluate the position X i，j of each welding unit scheduling scheme, and calculate its fitness value H(X i，j ), that is, the value of the objective function:

[0075]

[0076] where, ΔC e is the degree of violation of the constraint e, expressed as k is the number of iterations, e is the number of the energy consumption constraint violation; C k，e is the value of the decision variable corresponding to the constraint e at the k-th iteration; C k，e is the upper and lower bounds of C k，e ; g is the number of constraint violations; E e is the penalty coefficient for the violation of the constraint e.

[0077] S5.5: Update the individual optimal solution and the global optimal solution of the welding unit scheduling scheme.

[0078] When updating the position of the welding unit scheduling scheme, each scheme needs to calculate its individual fitness, compare the fitness of each scheme with its own historical optimal fitness. If the fitness of this scheme is greater than its own historical optimal fitness, then select the fitness of this scheme as the historical optimal fitness. Otherwise, the historical optimal fitness of this scheme remains unchanged; when updating the global optimal solution of the welding unit scheduling scheme, the optimal solution among all schemes needs to be considered. Compare the fitness value of the scheme with the largest fitness value in the individual optimal schemes with the fitness of the global optimal scheme. If the fitness value of the individual optimal scheme is larger than the fitness value of the global optimal scheme, then select the optimal fitness of this individual scheme to replace the optimal fitness of the global scheme. Otherwise, the optimal fitness of the global scheme remains unchanged.

[0079] S5.6: Calculate the initial temperature T of the simulated annealing algorithm according to the global optimal fitness of the welding unit scheduling scheme 0 , and the calculation formula is:

[0080]

[0081] where GB is the global optimal position of the welding unit scheduling scheme, and f(GB) is the global optimal fitness of this scheme.

[0082] S5.7: Calculate the fitness of the simulated annealing algorithm for the individual optimal positions of each welding unit scheduling scheme at the current temperature T. The formula is:

[0083]

[0084] where represents the historical optimal position of particle i at the k-th iteration, is the corresponding fitness of the historical optimal position of particle i at the k-th iteration.

[0085] S5.8: Adopt the roulette wheel selection algorithm idea. According to the fitness of the simulated annealing algorithm calculate the cumulative probability. If the condition of is satisfied, then select one from the individual historical optimal positions to replace the global optimal position GB, and denote it as where rand() is a random number from 0 to 1.

[0086] S5.9: Replace the original global optimal position GB with Update the positions and velocities of each particle, and update the individual and population optimal positions. The formulas are as follows:

[0087]

[0088]

[0089] where is the velocity of particle i at the (k + 1)-th iteration; ω is the inertia factor at the k-th iteration; c 1 is the local learning factor; c 2 is the global learning factor; r 1 and r 2 are two independent random numbers with values in the range [0, 1]; is the position of particle i at the (k + 1)-th iteration; represents the historical optimal position when task i is assigned to a resource at the k-th iteration.

[0090] S5.10: Perform the annealing operation. The formula is as follows:

[0091] T′ = δT:

[0092] Wherein, δ is the annealing speed; T is the current temperature; T′ is the temperature after annealing.

[0093] S5.11: Determine whether the stopping criterion is satisfied. If the stopping criterion is satisfied, go to S5.12; otherwise, go to S5.7. The stopping criterion is that continuous iteration reaches the maximum number of evolutionary generations.

[0094] S5.12: Stop the search and output the optimal task allocation scheme sequence of the welding unit. The two-dimensional matrix of the global optimal individual is the optimal task allocation scheme sequence of the welding unit.

[0095] The welding unit optimization scheduling method based on the improved simulated annealing particle swarm algorithm proposed in this embodiment combines the global search ability of the simulated annealing algorithm, effectively avoids falling into local optimal solutions, and improves the search probability of global optimal solutions. By combining the simulated annealing mechanism and the particle swarm algorithm, the robustness of the algorithm is improved, and it can handle complex non-linear and multi-constraint optimization problems, adapting to the actual situation in welding unit scheduling. By introducing a penalty function, various constraint conditions are effectively processed to ensure the feasibility of the solution and the optimization effect.

[0096] In another embodiment, the present invention proposes a computer-readable storage medium storing a computer program, and the computer program causes a computer to execute the welding unit optimization scheduling method based on the improved simulated annealing particle swarm algorithm as described in Embodiment 1.

[0097] In another embodiment, the present invention proposes an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the welding unit optimization scheduling method based on the improved simulated annealing particle swarm algorithm as described in Embodiment 1.

[0098] In the embodiments disclosed in the present application, the computer storage medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of the computer storage medium would include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0099] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this application can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0100] The above are only the preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions falling within the idea of the present invention belong to the protection scope of the present invention. It should be pointed out that for those of ordinary skill in the art in this technical field, several improvements and refinements made without departing from the principle of the present invention should be regarded as within the protection scope of the present invention.

Claims

1. A welding unit optimization scheduling method based on improved simulated annealing particle swarm algorithm is characterized by: The steps include: Construct a problem model for optimal scheduling of welding cells; Analyze welding tasks and available resources during the welding process, determine task priorities, and set resource constraints; Define the optimization objective function of the problem model; Design the optimal scheduling scheme of welding unit according to the task priority, resource constraints and optimization objective function, and perform optimization calculation based on simulated annealing particle swarm algorithm to obtain the optimal decision-making scheme; The optimization objective function is as follows: h(X i,j )=ω1·p1+ω2·p2; In the formula, h(X i,j ) represents the optimization objective function, X i,j indicates that the i-th task is assigned to the j-th resource; p1 is the production efficiency, expressed as r is the number of completed tasks, V i The output value brought by completing task i, T i is the completion time of task i; p2 is the resource utilization, expressed as t i,j is the working time assigned to the jth resource for the i-th task; ω1 and ω2 are weight coefficients, and m is the number of resources involved in the work; The resource constraints include working time limit and energy consumption limit of the welding robot; The welding unit optimization scheduling scheme is designed according to the task priority, resource constraints and optimization objective function, as follows: 1) Design particle encoding, where each particle represents a possible task allocation scheme, and the decision of task allocation to resources is represented as a real number code, where the particle position X i,j Represents the task allocation scheme, represented by an r×m matrix, in which each row represents a task, each column represents a resource, and the matrix element represents the assignment of the i-th task to the j-th resource; 2) Use chaotic mapping to initialize the population and use Circle mapping for chaotic search: Among them, x n is the particle position X i,j The value at the nth iteration, x n ∈[0,1]; mod(a,b) means the modulus operation of a on b; 3) Initialize the population introduced into the Circle map: After the chaotic sequence is generated, the characteristics of each chaotic variable are optimized and converted into the feasible space of the original optimization variable C, where C n is the original optimization variable C and the chaotic variable x n The corresponding value of and C are the upper and lower bounds of the feasible space of the original optimization variable C, x n It is the chaotic sequence value generated by the Circle mapping on the corresponding particle dimension; 4) Add the penalty function to the optimization objective function for update, and adjust the position X of each particle according to the updated function. i,j Evaluate and calculate its fitness H(X i,j ); 5) According to the calculated individual fitness of each particle, update the individual optimal fitness and the global optimal fitness; The penalty function is added to the optimization objective function for updating, and the updated function is: Where, ΔC e is the degree of destruction of constraint e, expressed as k is the number of iterations, e is the energy consumption constraint violation number, C k,e is the decision variable value corresponding to constraint e at the kth iteration; C k,e C k,e The upper and lower bounds of g are as follows; g is the number of constraint violations; E e is the damage penalty coefficient of constraint e; The optimization calculation based on simulated annealing particle swarm algorithm is specifically as follows: 1) The initial temperature T0 of the simulated annealing algorithm is calculated according to the global optimal fitness, and the calculation formula is: Among them, GB is the global optimal position, f(GB) is the global optimal fitness of the simulated annealing algorithm; 2) Calculate the fitness of the simulated annealing algorithm for the optimal position of each individual at the current temperature T. The formula is: in, represents the historical optimal position of particle i at the kth iteration, is the fitness corresponding to the historical optimal position of particle i at the kth iteration, and r represents the number of tasks; 3) Using the roulette wheel selection algorithm, according to the fitness of the simulated annealing algorithm Calculate the cumulative probability, if , then from the individual historical optimal position Select one from the above to replace the global optimal position GB and record it as Among them, rand() is a random number between 0 and 1; 4) Replace the original global optimal position GB with Update the position and velocity of each particle, and update the optimal position of individuals and populations. The formula is as follows: in, is the velocity of particle i at the k+1th iteration; ω is the inertia factor at the kth iteration; c1 is the local learning factor; c2 is the global learning factor; r1 and r2 are two independent random numbers in the range [0,1]; is the position of particle i at the kth iteration; It is represented as the historical optimal position of task i assigned to resource j at the kth iteration; 5) Perform annealing operation, the formula is as follows: T′=δT; Where, δ is the annealing rate; T is the current temperature; T′ is the temperature after annealing; 6) Determine whether the stopping criteria are met. If the stopping criteria are met, go to step 7); otherwise, go to step 2); 7) Stop searching and output the optimal task allocation scheme for the welding unit. The two-dimensional matrix of the global optimal individuals is the optimal task allocation scheme for the welding unit.

2. The welding unit optimization scheduling method based on improved simulated annealing particle swarm algorithm according to claim 1, characterized in that: The welding task includes the type, size, shape and welding time of the welding workpiece, and the resources include welding robots and welding equipment.

3. The welding unit optimization scheduling method based on improved simulated annealing particle swarm algorithm according to claim 1, characterized in that: The updating of individual optimal fitness and global optimal fitness is specifically as follows: When updating the individual optimal fitness, compare the fitness of each particle with the individual historical optimal fitness. If the particle fitness is greater than the individual historical optimal fitness, the particle fitness is selected as the individual historical optimal fitness. Otherwise, the individual historical optimal fitness remains unchanged. When updating the global optimal fitness, the individual optimal fitness of all particles is considered, and the maximum value of the individual optimal fitness of each particle is compared with the global optimal fitness. If the individual optimal fitness is greater than the global optimal fitness, the individual optimal fitness is selected to replace the global optimal fitness. Otherwise, the global optimal fitness remains unchanged.

4. A computer-readable storage medium storing a computer program, characterized in that: The computer program enables the computer to execute the welding unit optimization scheduling method based on the improved simulated annealing particle swarm algorithm as described in any one of claims 1 to 3.

5. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the welding unit optimization scheduling method based on the improved simulated annealing particle swarm algorithm as described in any one of claims 1 to 3 is implemented.

Images