Enterprise order collaborative manufacturing scheduling optimization method and system based on improved SPSA

Abstract

The invention discloses an enterprise order collaborative manufacturing scheduling optimization method and system based on improved SPSA. The enterprise order collaborative manufacturing scheduling optimization method based on the improved SPSA comprises the following steps: constructing a network collaborative scheduling model; determining constraint conditions of the network collaborative scheduling model; solving the network collaborative scheduling model by adopting an improved SPSA scheduling algorithm; and generating a scheduling scheme of an optimal solution. According to the method, an order is divided into a plurality of sub-tasks, then a network collaborative scheduling model is constructed, the model is solved through an improved SPSA-based scheduling algorithm, a scheduling scheme of an optimal solution is generated, the order is allocated to a proper enterprise, and an order production task is completed collaboratively. According to the method, resources between enterprises can be dispatched in a coordinated manner, the overall production efficiency and the product quality are improved, waste and repeated configuration of the resources can be avoided, and the research blank of application of small and medium-sized enterprises in the textile industry at home and abroad can be filled up.

Description

Technical Field

[0001] The present invention relates to the technical field of task allocation, and in particular to an enterprise order collaborative manufacturing scheduling optimization method and system based on improved SPSA. Background Art

[0002] In a multi-agent collaborative production environment, the task scheduling problem has attracted much attention from scholars at home and abroad, and a variety of effective methods have been proposed. However, current research mainly focuses on workshop scheduling, project scheduling, and assembly line scheduling, and rarely involves task scheduling problems between manufacturing companies in a network collaborative manufacturing environment. Although certain results have been achieved in the field of network collaborative manufacturing at home and abroad, there is still relatively little application research in small and medium-sized enterprises in the textile industry. As an important part of the manufacturing industry, the textile industry has huge potential for the development and optimization of small and medium-sized enterprises.

[0003] In long-term production practice, in order to shorten the supply chain and reduce transaction costs, small and medium-sized textile enterprises in the upstream and downstream of the textile industry chain have divided the work and complemented each other, gradually forming industrial clusters and industrial ecosystems with regional advantages. However, due to their small scale and limited resources, these small and medium-sized enterprises often face problems such as insufficient production capacity, small and few orders, and low scheduling efficiency. Therefore, how to optimize the task scheduling of small and medium-sized enterprises in the textile industry in a network collaborative manufacturing environment has become an important issue that needs to be solved urgently. Summary of the invention

[0004] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description and other drawings of the description.

[0005] The purpose of the present invention is to overcome the above-mentioned shortcomings and provide an enterprise order collaborative manufacturing scheduling optimization method and system based on improved SPSA.

[0006] The technical solution adopted by the present invention to solve the technical problem is: an enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA, comprising the following steps: Build a network collaborative scheduling model, collect and analyze order information, and use multi-objective optimization methods to build a network collaborative scheduling model; Determine the constraints of the network collaborative scheduling model, and determine the constraints according to the network collaborative scheduling model; The network collaborative scheduling model is solved by using an improved SPSA scheduling algorithm. The SPSA algorithm is improved by using a Pareto optimization method to obtain an improved SPSA scheduling algorithm. The improved SPSA scheduling algorithm is used to process the gradient information of multiple objectives to obtain the Pareto optimal solution set. Generate the optimal solution scheduling plan, decode the Pareto optimal solution set into the corresponding scheduling plan through the improved SPSA scheduling algorithm decoding method, and then select the optimal solution scheduling plan according to actual needs.

[0007] The present invention takes textile orders as the core of scheduling, divides an order into different manufacturing tasks and assigns them to small and medium-sized textile enterprises in the region for network collaborative resource scheduling among enterprises. A network collaborative scheduling model is constructed based on the characteristics of small and medium-sized textile enterprises and the characteristics of network collaborative manufacturing; then the model is solved by a scheduling algorithm based on the improved SPSA to generate an optimal scheduling solution, assign the order to the appropriate enterprise, and collaboratively complete the order production task. The present invention can not only coordinate the scheduling of resources among enterprises, improve overall production efficiency and product quality, but also avoid waste and repeated configuration of resources, and also help fill the research gap in the application of small and medium-sized enterprises in the textile industry at home and abroad.

[0008] In some embodiments, the steps for constructing a network collaborative scheduling model are as follows: obtain information on order tasks that can be completed, collect and analyze order information to obtain information on order tasks that can be completed by each enterprise; establish a network collaborative scheduling model, and use a multi-objective optimization method to construct an enterprise network collaborative scheduling model.

[0009] In some embodiments, the information that can complete the order task includes production cost, production time, production quality, customer satisfaction, resource utilization, transportation cost and transportation time.

[0010] In some embodiments, a multi-objective optimization method is used to construct an enterprise network collaborative scheduling model, including the following steps: Construct an objective function that minimizes total production cost f 1. Construct an objective function to minimize the total production cost based on the total production cost of the order f 1, whose expression is: , Among them, the total production cost of an order includes the production cost and transportation cost required for the enterprise to complete the production task. C represents the total production cost, n Indicates the number of subtasks, m Indicates the number of enterprises, and the subtask number is i , q ∈( 1 , n), the enterprise number is j , k ∈( 1 , m ), m i Indicates that the subtask can be completed i of enterprises, m i ={ M 1, M 2,..., M j}, C ij Indicates the enterprise j Complete subtasks i production costs, dC jk Indicates the enterprise M j To the enterprise M k The transportation cost between t i Represents a subtask i The start time of t i Moment subtask i By Enterprise j Completed, then x ij ( t i )=1, otherwise 0; if the subtask i It is a subtask q , then O iq =1, otherwise 0; Construct an objective function that minimizes total completion time f 2. Construct an objective function to minimize the total completion time based on the total completion time of the order f 2, its expression is: , The total completion time of an order includes the production time and transportation time to complete the production task. T represents the total completion time, T ij Indicates the enterprise j Complete subtasks i production time, dT jk Indicates the enterprise M j To the enterprise M k The transportation time between d i Represents a subtaski Completion time; Constructing the objective function to maximize production quality f 3. Construct an objective function to maximize production quality based on the production quality of the order f 3, whose expression is: , Among them, the production quality of the order is the average of the completion quality of each manufacturing subtask, Q Indicates the production quality of the order, Q ij Represents a subtask i By Enterprise j The quality of the finished product; Constructing the objective function to maximize customer satisfaction f 4. Construct an objective function to maximize customer satisfaction based on the customer satisfaction of the order f 4, whose expression is: , Among them, the customer satisfaction of the order is the mean of the customer satisfaction of each manufacturing subtask, S Indicates customer satisfaction with the order, S ij Indicates the enterprise j Complete subtasks i Customer satisfaction; Constructing the objective function to maximize resource utilization f 5. Construct an objective function to maximize resource utilization based on the resource utilization of the order f 5, whose expression is: , Among them, the resource utilization rate of an order is the average of the resource utilization rates of each manufacturing subtask. R Indicates the resource utilization of the order, R ij Indicates the enterprise j Complete subtasks i resource utilization.

[0011] In some embodiments, the constraints include selection constraints, timing constraints, time constraints, production quality constraints, customer satisfaction constraints, and resource utilization constraints; wherein the selection constraints are that each subtask must be m i Select one enterprise to produce, and each subtask can only select one enterprise to produce. The expression is: , The timing constraint condition is that there are two subtasks with a timing sequence, and the end time of the previous subtask is not greater than the start time of the next subtask. The expression is: , The time constraint is that the completion time of the last subtask is no longer than the delivery time D of the entire order, expressed as: , The production quality constraint condition is that the production quality of the order task is not lower than the minimum production quality requirement, and the expression is: , The customer satisfaction constraint is that the customer satisfaction with the order task is not less than the minimum customer satisfaction, and the expression is: , The resource utilization constraint condition is that the resource utilization of the order task is not less than the minimum resource utilization, and the expression is: .

[0012] In some embodiments, the network collaborative scheduling model is solved by using an improved SPSA scheduling algorithm, including: Set parameters and set the initial parameter vector θ 1. Set the step sequence k =1, positive sequence of control step length a k , a positive sequence that controls the size of the disturbance c k And the Pareto front solution set is empty; Encode constraints, processes, and enterprises, and set the initial population size N , the number of subtasks is n The number of enterprises is m , m i ={ M 1 ,M 2 ,...,M j}, randomly generated N 1* n One-dimensional array of X =[ x 1, x 2,..., x n ],in x i Represents a subtask i Will be provided by the enterprise M j Complete manufacturing, M j is throughx i The value of m i The enterprises obtained by indexing in x i The value corresponds to m i The x i Enterprises; Generate a perturbation vector, at each iteration k When , the perturbation vector is randomly generated by Bernoulli distribution Δ k ; Evaluate the objective function and calculate the objective function value for each positive and negative perturbation of the objective function. and disturbance Δ k , substitute the parameter vector after the disturbance of the system state iteration algorithm , And two loss function evaluation values and ; Estimate the gradient and calculate the gradient of each objective function: , in, It is for i The gradient estimate of the objective function; Update the parameters and set the weight of each objective function according to the multi-objective strategy. , integrating the gradient estimates of all objective functions , update the parameter vector ; Non-dominated sorting and Pareto front maintenance, in each iteration, take the current solution Compare the non-dominated solution with the existing Pareto frontier solution; if If it is not dominated by any existing Pareto frontier solution, it will be added to the Pareto frontier set and the dominated solution will be removed; Termination conditions, k = k +1, repeatedly generate perturbation vectors to non-dominated sorting and Pareto front maintenance steps, and output the solution in the Pareto front set after the preset termination condition is met for the maximum number of iterations.

[0013] In some embodiments, the solution set is decoded into corresponding scheduling schemes through an improved SPSA algorithm decoding method, and then the most appropriate scheduling scheme can be selected from the optimized scheduling scheme set according to actual needs.

[0014] The present invention also provides an enterprise order collaborative manufacturing scheduling optimization system based on improved SPSA, comprising: A construction module, which is used to collect and analyze order information and build a network collaborative scheduling model using a multi-objective optimization method; A determination module, which is used to determine constraint conditions according to a network collaborative scheduling model; A solution module, which is used to improve the SPSA algorithm by using a Pareto optimization-based method to obtain an improved SPSA scheduling algorithm, and use the improved SPSA scheduling algorithm to process gradient information of multiple objectives to obtain a Pareto optimal solution set; The generation module is used to decode the Pareto optimal solution set into the corresponding scheduling scheme through the decoding method of the improved SPSA scheduling algorithm, and then select the scheduling scheme with the optimal solution according to actual needs.

[0015] In some embodiments, the building blocks include: The acquisition module is used to collect and analyze order information to obtain information about the order tasks that can be completed by each enterprise; A module is established for constructing an enterprise network collaborative scheduling model using a multi-objective optimization method.

[0016] In some embodiments, the establishment module includes a multi-objective optimization unit, and the multi-objective optimization unit includes: A total production cost optimization subunit, which is used to optimize the total production cost by constructing an objective function that minimizes the total production cost; A total completion time optimization subunit is used to optimize the total completion time by constructing an objective function that minimizes the total completion time; A production quality optimization subunit, which is used to optimize production quality by constructing an objective function that maximizes production quality; A customer satisfaction optimization subunit, which is used to optimize customer satisfaction by constructing an objective function that maximizes customer satisfaction; The resource utilization optimization subunit is used to construct an objective function that maximizes resource utilization to optimize resource utilization.

[0017] By adopting the above technical solution, the beneficial effects of the present invention are: The present invention takes textile orders as the core of scheduling, divides an order into multiple subtasks and assigns them to small and medium-sized textile enterprises in the region for network collaborative resource scheduling among enterprises. The present invention constructs a network collaborative scheduling model according to the characteristics of small and medium-sized textile enterprises and the characteristics of network collaborative manufacturing, and then solves the model through a scheduling algorithm based on an improved SPSA to generate an optimal scheduling solution, assigns orders to suitable enterprises, and collaboratively completes order production tasks; the present invention can not only collaboratively schedule resources among enterprises and improve overall production efficiency and product quality, but also avoid waste and repeated configuration of resources, and also help to fill the research gap in the application of small and medium-sized enterprises in the textile industry at home and abroad.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0019] Undoubtedly, these and other objects of the present invention will become more apparent after the following detailed description of the preferred embodiment described with reference to various figures and drawings.

[0020] In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, one or several preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation of the present invention.

[0022] In the drawings, the same reference numerals are used for the same components and the drawings are schematic and not necessarily drawn to scale.

[0023] 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 one or several embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on such drawings without paying creative work.

[0024] Figure 1 It is an overall flow chart of an enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA of the present invention; Figure 2 is a flow chart of an improved SPSA scheduling algorithm in some embodiments of the present invention; Figure 3 A diagram showing the relationship between timing constraints of subtasks in some embodiments of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but are not used to limit the present invention.

[0026] In the present invention, unless otherwise clearly specified and limited, the first feature "on" or "under" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in an appropriate manner in any one or more embodiments or examples.

[0027] Reference Figure 1 , Figure 1 It is an overall flow chart of an enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA of the present invention.

[0028] According to some embodiments of the present invention, the present invention provides an enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA, comprising the following steps: Build a network collaborative scheduling model, collect and analyze order information, and use multi-objective optimization methods to build a network collaborative scheduling model; Determine the constraints of the network collaborative scheduling model, and determine the constraints according to the network collaborative scheduling model; The network collaborative scheduling model is solved by using an improved SPSA scheduling algorithm. The SPSA algorithm is improved by using a Pareto optimization method to obtain an improved SPSA scheduling algorithm. The improved SPSA scheduling algorithm is used to process the gradient information of multiple objectives to obtain the Pareto optimal solution set. Generate the optimal solution scheduling plan, decode the Pareto optimal solution set into the corresponding scheduling plan through the improved SPSA scheduling algorithm decoding method, and then select the optimal solution scheduling plan according to actual needs.

[0029] The present invention takes textile orders as the core of scheduling, divides an order into different manufacturing tasks and assigns them to small and medium-sized textile enterprises in the region for network collaborative resource scheduling among enterprises. A network collaborative scheduling model is constructed based on the characteristics of small and medium-sized textile enterprises and the characteristics of network collaborative manufacturing; then the model is solved by a scheduling algorithm based on the improved SPSA to generate an optimal scheduling solution, assign the order to the appropriate enterprise, and collaboratively complete the order production task. The present invention can not only coordinate the scheduling of resources among enterprises, improve overall production efficiency and product quality, but also avoid waste and repeated configuration of resources, and also help fill the research gap in the application of small and medium-sized enterprises in the textile industry at home and abroad.

[0030] According to some embodiments of the present invention, optionally, the steps for constructing a network collaborative scheduling model are as follows: obtaining information on order tasks that can be completed, collecting and analyzing order information to obtain information on order tasks that can be completed by each enterprise; establishing a network collaborative scheduling model, and using a multi-objective optimization method to construct an enterprise network collaborative scheduling model.

[0031] According to some embodiments of the present invention, optionally, the information on the order task that can be completed includes production cost, production time, production quality, customer satisfaction, resource utilization, transportation cost and transportation time.

[0032] According to some embodiments of the present invention, optionally, a multi-objective optimization method is used to construct an enterprise network collaborative scheduling model, including the following steps: Construct an objective function that minimizes total production cost f 1. Construct an objective function to minimize the total production cost based on the total production cost of the order f 1, whose expression is: , Among them, the total production cost of an order includes the production cost and transportation cost required for the enterprise to complete the production task. C represents the total production cost, n Indicates the number of subtasks, m Indicates the number of enterprises, and the subtask number is i , q ∈( 1 , n ), the enterprise number is j , k ∈( 1 , m ), m i Indicates that the subtask can be completed i of enterprises, m i ={ M 1, M 2,..., Mj}, C ij Indicates the enterprise j Complete subtasks i production costs, dC jk Indicates the enterprise M j To the enterprise M k The transportation cost between t i Represents a subtask i The start time of t i Moment subtask i By Enterprise j Completed, then x ij ( t i )=1, otherwise 0; if the subtask i It is a subtask q , then O iq =1, otherwise 0; Construct an objective function that minimizes total completion time f 2. Construct an objective function to minimize the total completion time based on the total completion time of the order f 2, its expression is: , The total completion time of an order includes the production time and transportation time to complete the production task. T represents the total completion time, T ij Indicates the enterprise j Complete subtasks i production time, dT jk Indicates the enterprise M j To the enterprise M k The transportation time between d i Represents a subtask i Completion time; Constructing the objective function to maximize production quality f 3. Construct an objective function to maximize production quality based on the production quality of the order f 3, whose expression is: , Among them, the production quality of the order is the average of the completion quality of each manufacturing subtask, Q Indicates the production quality of the order, Qij Represents a subtask i By Enterprise j The quality of the finished product; Constructing the objective function to maximize customer satisfaction f 4. Construct an objective function to maximize customer satisfaction based on the customer satisfaction of the order f 4, whose expression is: , Among them, the customer satisfaction of the order is the mean of the customer satisfaction of each manufacturing subtask, S Indicates customer satisfaction with the order, S ij Indicates the enterprise j Complete subtasks i Customer satisfaction; Constructing the objective function to maximize resource utilization f 5. Construct an objective function to maximize resource utilization based on the resource utilization of the order f 5, whose expression is: , Among them, the resource utilization rate of an order is the average of the resource utilization rates of each manufacturing subtask. R Indicates the resource utilization of the order, R ij Indicates the enterprise j Complete subtasks i resource utilization.

[0033] According to some embodiments of the present invention, optionally, the solution set is decoded into corresponding scheduling schemes through an improved SPSA algorithm decoding method, and then the most suitable scheduling scheme can be selected from the optimized scheduling scheme set according to actual needs.

[0034] The present invention also provides an enterprise order collaborative manufacturing scheduling optimization system based on improved SPSA, comprising: A construction module, which is used to collect and analyze order information and build a network collaborative scheduling model using a multi-objective optimization method; A determination module, which is used to determine constraint conditions according to a network collaborative scheduling model; A solution module, which is used to improve the SPSA algorithm by using a Pareto optimization-based method to obtain an improved SPSA scheduling algorithm, and use the improved SPSA scheduling algorithm to process gradient information of multiple objectives to obtain a Pareto optimal solution set; The generation module is used to decode the Pareto optimal solution set into the corresponding scheduling scheme through the decoding method of the improved SPSA scheduling algorithm, and then select the scheduling scheme with the optimal solution according to actual needs.

[0035] According to some embodiments of the present invention, optionally, the building block includes: The acquisition module is used to collect and analyze order information to obtain information about the order tasks that can be completed by each enterprise; A module is established for constructing an enterprise network collaborative scheduling model using a multi-objective optimization method.

[0036] According to some embodiments of the present invention, optionally, the establishment module includes a multi-objective optimization unit, and the multi-objective optimization unit includes: A total production cost optimization subunit, which is used to optimize the total production cost by constructing an objective function that minimizes the total production cost; A total completion time optimization subunit is used to optimize the total completion time by constructing an objective function that minimizes the total completion time; A production quality optimization subunit, which is used to optimize production quality by constructing an objective function that maximizes production quality; A customer satisfaction optimization subunit, which is used to optimize customer satisfaction by constructing an objective function that maximizes customer satisfaction; The resource utilization optimization subunit is used to construct an objective function that maximizes resource utilization to optimize resource utilization.

[0037] Reference Figure 2 , Figure 2 This is a flow chart of an improved SPSA scheduling algorithm in some embodiments of the present invention.

[0038] According to some embodiments of the present invention, optionally, the network collaborative scheduling model is solved by using an improved SPSA scheduling algorithm, including: Set parameters and set the initial parameter vector θ 1. Set the step sequence k =1, positive sequence of control step length a k , a positive sequence that controls the size of the disturbance c k And the Pareto front solution set is empty; Encode constraints, processes, and enterprises, and set the initial population size N , the number of subtasks is n The number of enterprises is m , m i ={ M 1 ,M 2 ,...,M j}, randomly generated N 1* n One-dimensional array of X =[ x 1, x2,..., x n ],in x i Represents a subtask i Will be provided by the enterprise M j Complete manufacturing, M j is through x i The value of m i The enterprises obtained by indexing in x i The value corresponds to m i The x i Enterprises; Generate a perturbation vector, at each iteration k When , the perturbation vector is randomly generated by Bernoulli distribution Δ k ; Evaluate the objective function and calculate the objective function value for each positive and negative perturbation of the objective function. and disturbance Δ k , substitute the parameter vector after the disturbance of the system state iteration algorithm , And two loss function evaluation values and ; Estimate the gradient and calculate the gradient of each objective function: , in, It is for i The gradient estimate of the objective function; Update the parameters and set the weight of each objective function according to the multi-objective strategy. , integrating the gradient estimates of all objective functions , update the parameter vector ; Non-dominated sorting and Pareto front maintenance, in each iteration, take the current solution Compare the non-dominated solution with the existing Pareto frontier solution; if If it is not dominated by any existing Pareto frontier solution, it will be added to the Pareto frontier set and the dominated solution will be removed; Termination conditions, k = k+1, repeatedly generate perturbation vectors to non-dominated sorting and Pareto front maintenance steps, and output the solution in the Pareto front set after the preset termination condition is met for the maximum number of iterations.

[0039] Reference Figure 3 , Figure 3 A diagram showing the relationship between timing constraints of subtasks in some embodiments of the present invention.

[0040] According to some embodiments of the present invention, optionally, the constraint conditions include selection constraint conditions, timing constraint conditions, time constraint conditions, production quality constraint conditions, customer satisfaction constraint conditions, and resource utilization constraint conditions; wherein, Select the constraints that each subtask must have from m i Select one enterprise to produce, and each subtask can only select one enterprise to produce. The expression is: , The timing constraint condition is that there are two subtasks with a timing sequence, and the end time of the previous subtask is not greater than the start time of the next subtask. The expression is: , The time constraint is that the completion time of the last subtask is no longer than the delivery time D of the entire order, expressed as: , The production quality constraint condition is that the production quality of the order task is not lower than the minimum production quality requirement, and the expression is: , The customer satisfaction constraint is that the customer satisfaction with the order task is not less than the minimum customer satisfaction, and the expression is: , The resource utilization constraint condition is that the resource utilization of the order task is not less than the minimum resource utilization, and the expression is: .

[0041] Example 1 Reference Figure 1-Figure 3 This embodiment provides an enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA, including the following steps: Construct a network collaborative scheduling model, collect and analyze order information, and use a multi-objective optimization method to construct a network collaborative scheduling model. Specifically, the steps for constructing a network collaborative scheduling model are as follows: obtain information about order tasks that can be completed, collect and analyze order information to obtain information about order tasks that can be completed by each enterprise and establish a network collaborative scheduling model. Use a multi-objective optimization method to construct an enterprise network collaborative scheduling model, where: Information that can complete order tasks includes production cost, production time, production quality, customer satisfaction, resource utilization, transportation cost and transportation time; The enterprise network collaborative scheduling model is constructed using a multi-objective optimization method, which includes the following steps: Construct an objective function that minimizes total production cost f 1. Construct an objective function to minimize the total production cost based on the total production cost of the order f 1, whose expression is: , Among them, the total production cost of an order includes the production cost and transportation cost required for the enterprise to complete the production task. C represents the total production cost, n Indicates the number of subtasks, m Indicates the number of enterprises, and the subtask number is i , q ∈( 1 , n ), the enterprise number is j , k ∈( 1 , m ), m i Indicates that the subtask can be completed i of enterprises, m i ={ M 1, M 2,..., M j}, C ij Indicates the enterprise j Complete subtasks i production costs, dC jk Indicates the enterprise M j To the enterprise M k The transportation cost between t i Represents a subtask i The start time of t i Moment subtask i By Enterprisej Completed, then x ij ( t i )=1, otherwise 0; if the subtask i It is a subtask q , then O iq =1, otherwise 0; Construct an objective function that minimizes total completion time f 2. Construct an objective function to minimize the total completion time based on the total completion time of the order f 2, its expression is: , The total completion time of an order includes the production time and transportation time to complete the production task. T represents the total completion time, T ij Indicates the enterprise j Complete subtasks i production time, dT jk Indicates the enterprise M j To the enterprise M k The transportation time between d i Represents a subtask i Completion time; Constructing the objective function to maximize production quality f 3. Construct an objective function to maximize production quality based on the production quality of the order f 3, whose expression is: , Among them, the production quality of the order is the average of the completion quality of each manufacturing subtask, Q Indicates the production quality of the order, Q ij Represents a subtask i By Enterprise j The quality of the finished product; Constructing the objective function to maximize customer satisfaction f 4. Construct an objective function to maximize customer satisfaction based on the customer satisfaction of the order f 4, whose expression is: , Among them, the customer satisfaction of the order is the mean of the customer satisfaction of each manufacturing subtask, S Indicates customer satisfaction with the order, S ij Indicates the enterprisej Complete subtasks i Customer satisfaction; Constructing the objective function to maximize resource utilization f 5. Construct an objective function to maximize resource utilization based on the resource utilization of the order f 5, whose expression is: , Among them, the resource utilization rate of an order is the average of the resource utilization rates of each manufacturing subtask. R Indicates the resource utilization of the order, R ij Indicates the enterprise j Complete subtasks i resource utilization.

[0042] Determine the constraints of the network collaborative scheduling model. Determine the constraints according to the network collaborative scheduling model. Specifically, the constraints include selection constraints, timing constraints, time constraints, production quality constraints, customer satisfaction constraints, and resource utilization constraints. Select the constraints that each subtask must have from m i Select one enterprise to produce, and each subtask can only select one enterprise to produce. The expression is: , The timing constraint condition is that there are two subtasks with a timing sequence, and the end time of the previous subtask is not greater than the start time of the next subtask. The expression is: , The time constraint is that the completion time of the last subtask is no longer than the delivery time D of the entire order, expressed as: , The production quality constraint condition is that the production quality of the order task is not lower than the minimum production quality requirement, and the expression is: , The customer satisfaction constraint is that the customer satisfaction with the order task is not less than the minimum customer satisfaction, and the expression is: , The resource utilization constraint condition is that the resource utilization of the order task is not less than the minimum resource utilization, and the expression is: ; The network collaborative scheduling model is solved by using an improved SPSA scheduling algorithm. The SPSA algorithm is improved by using a Pareto optimization method to obtain an improved SPSA scheduling algorithm. The improved SPSA scheduling algorithm is used to process the gradient information of multiple objectives to obtain the Pareto optimal solution set. Furthermore, the network collaborative scheduling model is solved based on the improved SPSA scheduling algorithm, including: Set parameters and set the initial parameter vector θ 1. Set the step sequence k =1, positive sequence of control step length a k , a positive sequence that controls the size of the disturbance c k And the Pareto front solution set is empty; Encode constraints, processes, and enterprises, and set the initial population size N , the number of subtasks is n The number of enterprises is m , m i ={ M 1 ,M 2 ,...,M j}, randomly generated N 1* n One-dimensional array of X =[ x 1, x 2,..., x n ],in x i Represents a subtask i Will be provided by the enterprise M j Complete manufacturing, M j is through x i The value of m i The enterprises obtained by indexing in x i The value corresponds to m i The x i Enterprises; Generate a perturbation vector, at each iteration k When , the perturbation vector is randomly generated by Bernoulli distribution Δ k ; Evaluate the objective function and calculate the objective function value for each positive and negative perturbation of the objective function. and disturbance Δ k , substitute the parameter vector after the disturbance of the system state iteration algorithm , And two loss function evaluation values and ; Estimate the gradient and calculate the gradient of each objective function: , in, It is for i The gradient estimate of the objective function; Update the parameters and set the weight of each objective function according to the multi-objective strategy. , integrating the gradient estimates of all objective functions , update the parameter vector ; Non-dominated sorting and Pareto front maintenance, in each iteration, take the current solution Compare the non-dominated solution with the existing Pareto frontier solution; if If it is not dominated by any existing Pareto frontier solution, it will be added to the Pareto frontier set and the dominated solution will be removed; Termination conditions, k = k +1, repeatedly generate perturbation vectors to non-dominated sorting and Pareto front maintenance steps, and output the solution in the Pareto front set after the preset termination condition is met for the maximum number of iterations.

[0043] Generate the optimal solution scheduling plan, decode the Pareto optimal solution set into the corresponding scheduling plan through the improved SPSA scheduling algorithm decoding method, and then select the optimal solution scheduling plan according to actual needs; Furthermore, the optimal scheduling solution is generated, including: Through the improved SPSA algorithm decoding method, the solution set is decoded into the corresponding scheduling scheme, and then the most appropriate scheduling scheme can be selected from the optimized scheduling scheme set according to actual needs.

[0044] Example 2 Reference Figure 1-Figure 3 This embodiment provides an enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA, including the following steps: Construct a network collaborative scheduling model, collect and analyze order information, and use a multi-objective optimization method to construct a network collaborative scheduling model. Specifically, the steps for constructing a network collaborative scheduling model are as follows: obtain information about order tasks that can be completed, collect and analyze order information to obtain information about order tasks that can be completed by each enterprise and establish a network collaborative scheduling model. Use a multi-objective optimization method to construct an enterprise network collaborative scheduling model, where: Information that can complete order tasks includes production cost, production time, production quality, customer satisfaction, resource utilization, transportation cost and transportation time; The enterprise network collaborative scheduling model is constructed using a multi-objective optimization method, which includes the following steps: Construct an objective function that minimizes total production cost f 1. Construct an objective function to minimize the total production cost based on the total production cost of the order f 1, whose expression is: , Among them, the total production cost of an order includes the production cost and transportation cost required for the enterprise to complete the production task. C represents the total production cost, n Indicates the number of subtasks, m Indicates the number of enterprises, and the subtask number is i , q ∈( 1 , n ), the enterprise number is j , k ∈( 1 , m ), m i Indicates that the subtask can be completed i of enterprises, m i ={ M 1, M 2,..., M j}, C ij Indicates the enterprise j Complete subtasks i production costs, dC jk Indicates the enterprise M j To the enterprise M k The transportation cost between t i Represents a subtask i The start time of t i Moment subtask i By Enterprisej Completed, then x ij ( t i )=1, otherwise 0; if the subtask i It is a subtask q , then O iq =1, otherwise 0; Construct an objective function that minimizes total completion time f 2. Construct an objective function to minimize the total completion time based on the total completion time of the order f 2, its expression is: , The total completion time of an order includes the production time and transportation time to complete the production task. T represents the total completion time, T ij Indicates the enterprise j Complete subtasks i production time, dT jk Indicates the enterprise M j To the enterprise M k The transportation time between d i Represents a subtask i Completion time; Constructing the objective function to maximize production quality f 3. Construct an objective function to maximize production quality based on the production quality of the order f 3, whose expression is: , Among them, the production quality of the order is the average of the completion quality of each manufacturing subtask, Q Indicates the production quality of the order, Q ij Represents a subtask i By Enterprise j The quality of the finished product; Constructing the objective function to maximize customer satisfaction f 4. Construct an objective function to maximize customer satisfaction based on the customer satisfaction of the order f 4, whose expression is: , Among them, the customer satisfaction of the order is the mean of the customer satisfaction of each manufacturing subtask, S Indicates customer satisfaction with the order, S ij Indicates the enterprisej Complete subtasks i Customer satisfaction; Constructing the objective function to maximize resource utilization f 5. Construct an objective function to maximize resource utilization based on the resource utilization of the order f 5, whose expression is: , Among them, the resource utilization rate of an order is the average of the resource utilization rates of each manufacturing subtask. R Indicates the resource utilization of the order, R ij Indicates the enterprise j Complete subtasks i resource utilization.

[0045] Determine the constraints of the network collaborative scheduling model. Determine the constraints according to the network collaborative scheduling model. Specifically, the constraints include selection constraints, timing constraints, time constraints, production quality constraints, customer satisfaction constraints, and resource utilization constraints. Select the constraints that each subtask must have from m i Select one enterprise to produce, and each subtask can only select one enterprise to produce. The expression is: , The timing constraint condition is that there are two subtasks with a timing sequence, and the end time of the previous subtask is not greater than the start time of the next subtask. The expression is: , The time constraint is that the completion time of the last subtask is no longer than the delivery time D of the entire order, expressed as: , The production quality constraint condition is that the production quality of the order task is not lower than the minimum production quality requirement, and the expression is: , The customer satisfaction constraint is that the customer satisfaction with the order task is not less than the minimum customer satisfaction, and the expression is: , The resource utilization constraint condition is that the resource utilization of the order task is not less than the minimum resource utilization, and the expression is: ; Assume that the number of subtasks for a textile order is n =7, enterprises participating in collaborative manufacturing system m=10, numbered as: 1, 2, 3, ..., 10; subtasks can be completed i Manufacturing companies m i The collection is: m 1={1,2,4,6,8}, m 2={2,3,6,9}, m 3={3,4,9,10}, m 4={1,4,8,9,10}, m 5={2,4,8}, m 6={4,5,8,9}, m 7={3,5,6,7,9}, the subtask timing constraints are: O 12 =1, O 13 =1, O 24 =1, O 25 =1, O 46 =1, O 36 =1, O 56 =1, O 67 =1, the latest delivery time required by the customer D = 80 days; obtain the production cost (10,000 yuan), production time (days), production quality (value range 0-10), customer satisfaction (value range 0-10) and resource utilization (value range 0-1) of each subtask completed by the collaborative manufacturing enterprise, as shown in Table 1; transportation cost between manufacturing enterprises dC jk and shipping time dT jk ; Set the production quality of the order Q min =6, customer satisfaction S min =6, resource utilization R min =0.6.

[0046] Table 1 Information table of tasks completed by enterprises

[0047]

[0048] The network collaborative scheduling model is solved by using an improved SPSA scheduling algorithm. The SPSA algorithm is improved by using a Pareto optimization method to obtain an improved SPSA scheduling algorithm. The improved SPSA scheduling algorithm is used to process the gradient information of multiple objectives to obtain the Pareto optimal solution set. Furthermore, the network collaborative scheduling model is solved based on the improved SPSA scheduling algorithm, including: Set parameters and set the initial parameter vector θ 1. Set the step sequence k =1, positive sequence of control step length a k , a positive sequence that controls the size of the disturbance c k And the Pareto front solution set is empty; Encode constraints, processes, and enterprises, and set the initial population size N , the number of subtasks is n The number of enterprises is m , m i ={ M 1 ,M 2 ,...,M j}, randomly generated N 1* n One-dimensional array of X =[ x 1, x 2,..., x n ],in x i Represents a subtask i Will be provided by the enterprise M j Complete manufacturing, M j is through x i The value of m i The enterprises obtained by indexing in x i The value corresponds to m i The x i Enterprises; Generate a perturbation vector, at each iteration k When , the perturbation vector is randomly generated by Bernoulli distribution Δ k ; Evaluate the objective function and calculate the objective function value for each positive and negative perturbation of the objective function. and disturbance Δ k , substitute the parameter vector after the disturbance of the system state iteration algorithm , And two loss function evaluation values and ; Estimate the gradient and calculate the gradient of each objective function: , in, It is for i The gradient estimate of the objective function; Update the parameters and set the weight of each objective function according to the multi-objective strategy. , integrating the gradient estimates of all objective functions , update the parameter vector ; Non-dominated sorting and Pareto front maintenance, in each iteration, take the current solution Compare the non-dominated solution with the existing Pareto frontier solution; if If it is not dominated by any existing Pareto frontier solution, it will be added to the Pareto frontier set and the dominated solution will be removed; Termination conditions, k = k +1, repeatedly generate perturbation vectors to non-dominated sorting and Pareto front maintenance steps, and output the solution in the Pareto front set after the preset termination condition is met for the maximum number of iterations.

[0049] In this embodiment, the population size is initialized N =1000, number of iterations 1000 times.

[0050] Generate the optimal solution scheduling plan, decode the Pareto optimal solution set into the corresponding scheduling plan through the improved SPSA scheduling algorithm decoding method, and then select the optimal solution scheduling plan according to actual needs; Furthermore, the optimal scheduling solution is generated, including: Through the improved SPSA algorithm decoding method, the solution set is decoded into the corresponding scheduling scheme, and then the most appropriate scheduling scheme can be selected from the optimized scheduling scheme set according to actual needs.

[0051] In this embodiment, the generated scheduling scheme is shown in Table 2. The chromosomes of the scheduling scheme are decoded to obtain the values ​​of each optimization target of each scheme, as shown in Table 3. It can be found from the table that the specific attributes of each scheduling scheme are different under the scheduling requirements. For example, Scheme 1 has the lowest production cost, the highest production quality and resource utilization, but the longest completion time; Scheme 2 has relatively average data; Scheme 3 has the highest production cost, the worst production quality, but the fastest completion time and the best customer evaluation. Finally, the most suitable scheduling scheme can be selected according to the actual situation.

[0052] Table 2 Scheduling scheme

[0053] Table 3 Decoded scheduling scheme

[0054] Example 3 Reference Figure 1-Figure 3 This embodiment provides an enterprise order collaborative manufacturing scheduling optimization system based on improved SPSA. The difference between this embodiment and embodiment 1 is that: An enterprise order collaborative manufacturing scheduling optimization system based on improved SPSA is characterized by: A construction module, which is used to collect and analyze order information and build a network collaborative scheduling model using a multi-objective optimization method; A determination module, which is used to determine constraint conditions according to a network collaborative scheduling model; A solution module, which is used to improve the SPSA algorithm by using a Pareto optimization-based method to obtain an improved SPSA scheduling algorithm, and use the improved SPSA scheduling algorithm to process gradient information of multiple objectives to obtain a Pareto optimal solution set; The generation module is used to decode the Pareto optimal solution set into the corresponding scheduling scheme through the decoding method of the improved SPSA scheduling algorithm, and then select the scheduling scheme with the optimal solution according to actual needs.

[0055] Furthermore, the building blocks include: The acquisition module is used to collect and analyze order information to obtain information about the order tasks that can be completed by each enterprise; A module is established for constructing an enterprise network collaborative scheduling model using a multi-objective optimization method.

[0056] Further, the establishment module includes a multi-objective optimization unit, and the multi-objective optimization unit includes: A total production cost optimization subunit, which is used to optimize the total production cost by constructing an objective function that minimizes the total production cost; A total completion time optimization subunit is used to optimize the total completion time by constructing an objective function that minimizes the total completion time; A production quality optimization subunit, which is used to optimize production quality by constructing an objective function that maximizes production quality; A customer satisfaction optimization subunit, which is used to optimize customer satisfaction by constructing an objective function that maximizes customer satisfaction; The resource utilization optimization subunit is used to construct an objective function that maximizes resource utilization to optimize resource utilization.

[0057] It should be understood that the embodiments disclosed in the present invention are not limited to the specific processing steps or materials disclosed herein, but should be extended to equivalent substitutions of such features understood by ordinary technicians in the relevant field. It should also be understood that the terms used herein are only used for the purpose of describing specific embodiments and are not meant to be limiting.

[0058] The "embodiment" mentioned in the specification means that the specific features or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present invention. Therefore, the phrases or "embodiment" appearing in various places throughout the specification do not necessarily refer to the same embodiment.

[0059] In addition, the described features or characteristics may be combined in one or more embodiments in any other suitable manner. In the above description, some specific details, such as thickness, quantity, etc., are provided to provide a comprehensive understanding of the embodiments of the present invention. However, those skilled in the relevant art will understand that the present invention can be implemented without one or more of the above specific details or can also be implemented using other methods, components, materials, etc.

Claims

1. An enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA, characterized by: The following steps are involved: Build a network collaborative scheduling model, collect and analyze order information, and use multi-objective optimization methods to build a network collaborative scheduling model; Determine the constraints of the network collaborative scheduling model, and determine the constraints according to the network collaborative scheduling model; The network collaborative scheduling model is solved by using an improved SPSA scheduling algorithm. The SPSA algorithm is improved by using a Pareto optimization method to obtain an improved SPSA scheduling algorithm. The improved SPSA scheduling algorithm is used to process the gradient information of multiple objectives to obtain the Pareto optimal solution set. Generate the optimal solution scheduling plan, decode the Pareto optimal solution set into the corresponding scheduling plan through the improved SPSA scheduling algorithm decoding method, and then select the optimal solution scheduling plan according to actual needs.

2. The enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA according to claim 1 is characterized in that: The steps to build the network collaborative scheduling model are as follows: Obtain information about tasks that can complete orders, collect and analyze order information to obtain information about tasks that can complete orders for each enterprise; A network collaborative scheduling model is established, and a multi-objective optimization method is used to construct an enterprise network collaborative scheduling model.

3. The enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA according to claim 2 is characterized in that: Information that can be used to complete order tasks includes production cost, production time, production quality, customer satisfaction, resource utilization, transportation cost and transportation time.

4. The enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA according to claim 2 is characterized in that: The enterprise network collaborative scheduling model is constructed using a multi-objective optimization method, which includes the following steps: Construct an objective function that minimizes total production cost f 1. Construct an objective function to minimize the total production cost based on the total production cost of the order f 1, whose expression is: ， Among them, the total production cost of an order includes the production cost and transportation cost required for the enterprise to complete the production task. C represents the total production cost, n Indicates the number of subtasks, m Indicates the number of enterprises, and the subtask number is i , q ∈( 1 , n ), the enterprise number is j , k ∈( 1 , m ), m i Indicates that the subtask can be completed i of enterprises, m i ={ M 1, M 2,..., M j }, C ij Indicates the enterprise j Complete subtasks i production costs, dC jk Indicates the enterprise M j To the enterprise M k The transportation cost between t i Represents a subtask i The start time of t i Moment subtask i By Enterprise j Completed, then x ij ( t i )=1, otherwise 0; if the subtask i It is a subtask q , then O iq =1, otherwise 0; Construct an objective function that minimizes total completion time f 2. Construct an objective function to minimize the total completion time based on the total completion time of the order f 2, its expression is: ， The total completion time of an order includes the production time and transportation time to complete the production task. T represents the total completion time, T ij Indicates the enterprise j Complete subtasks i production time, dT jk Indicates the enterprise M j To the enterprise M k The transportation time between d i Represents a subtask i Completion time; Constructing the objective function to maximize production quality f 3. Construct an objective function to maximize production quality based on the production quality of the order f 3, whose expression is: ， Among them, the production quality of the order is the average of the completion quality of each manufacturing subtask, Q Indicates the production quality of the order, Q ij Represents a subtask i By Enterprise j The quality of the finished product; Constructing the objective function to maximize customer satisfaction f 4. Construct an objective function to maximize customer satisfaction based on the customer satisfaction of the order f 4, whose expression is: ， Among them, the customer satisfaction of the order is the mean of the customer satisfaction of each manufacturing subtask, S Indicates customer satisfaction with the order, S ij Indicates the enterprise j Complete subtasks i Customer satisfaction; Constructing the objective function to maximize resource utilization f 5. Construct an objective function to maximize resource utilization based on the resource utilization of the order f 5, whose expression is: ， Among them, the resource utilization rate of an order is the average of the resource utilization rates of each manufacturing subtask. R Indicates the resource utilization of the order, R ij Indicates the enterprise j Complete subtasks i resource utilization.

5. The enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA according to claim 1 is characterized in that: Constraints include selection constraints, timing constraints, time constraints, production quality constraints, customer satisfaction constraints, and resource utilization constraints; among them, Select the constraints that each subtask must have from m i Select one enterprise to produce, and each subtask can only select one enterprise to produce. The expression is: ， The timing constraint condition is that there are two subtasks with a timing sequence, and the end time of the previous subtask is not greater than the start time of the next subtask. The expression is: ， The time constraint is that the completion time of the last subtask is no longer than the delivery time D of the entire order, expressed as: ， The production quality constraint condition is that the production quality of the order task is not lower than the minimum production quality requirement, and the expression is: ， The customer satisfaction constraint is that the customer satisfaction with the order task is not less than the minimum customer satisfaction, and the expression is: ， The resource utilization constraint condition is that the resource utilization of the order task is not less than the minimum resource utilization, and the expression is: 。 6. The enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA according to claim 1 is characterized in that: The network collaborative scheduling model is solved based on the improved SPSA scheduling algorithm, including: Set parameters and set the initial parameter vector θ 1. Set the step sequence k =1, positive sequence of control step length a k , a positive sequence that controls the size of the disturbance c k And the Pareto front solution set is empty; Encode constraints, processes, and enterprises, and set the initial population size N , the number of subtasks is n The number of enterprises is m , m i ={ M 1 , M 2 ,...,M j }, randomly generated N 1* n One-dimensional array of X =[ x 1, x 2,..., x n ],in x i Represents a subtask i Will be provided by the enterprise M j Complete manufacturing, M j is through x i The value of m i The enterprises obtained by indexing in x i The value corresponds to m i The x i Enterprises; Generate a perturbation vector, at each iteration k When , the perturbation vector is randomly generated by Bernoulli distribution Δ k ; Evaluate the objective function and calculate the objective function value for each positive and negative perturbation of the objective function. and disturbance Δ k , substitute the parameter vector after the disturbance of the system state iteration algorithm , And two loss function evaluation values and ; Estimate the gradient and calculate the gradient of each objective function: ， in, It is for i The gradient estimate of the objective function; Update the parameters and set the weight of each objective function according to the multi-objective strategy. , integrating the gradient estimates of all objective functions , update the parameter vector ; Non-dominated sorting and Pareto front maintenance, in each iteration, take the current solution Compare the non-dominated solution with the existing Pareto frontier solution; if If it is not dominated by any existing Pareto frontier solution, it will be added to the Pareto frontier set and the dominated solution will be removed; Termination conditions, k = k +1, repeatedly generate perturbation vectors to non-dominated sorting and Pareto front maintenance steps, and output the solution in the Pareto front set after the preset termination condition is met for the maximum number of iterations.

7. The enterprise order collaborative manufacturing scheduling optimization method based on improved SPSA according to claim 1 is characterized in that: Generate the optimal solution scheduling plan, including: Through the improved SPSA algorithm decoding method, the solution set is decoded into the corresponding scheduling scheme, and then the most appropriate scheduling scheme can be selected from the optimized scheduling scheme set according to actual needs.

8. An enterprise order collaborative manufacturing scheduling optimization system based on improved SPSA, characterized by: include: A construction module, which is used to collect and analyze order information and build a network collaborative scheduling model using a multi-objective optimization method; A determination module, which is used to determine constraint conditions according to a network collaborative scheduling model; A solution module, which is used to improve the SPSA algorithm by using a Pareto optimization-based method to obtain an improved SPSA scheduling algorithm, and use the improved SPSA scheduling algorithm to process gradient information of multiple objectives to obtain a Pareto optimal solution set; The generation module is used to decode the Pareto optimal solution set into the corresponding scheduling scheme through the decoding method of the improved SPSA scheduling algorithm, and then select the scheduling scheme with the optimal solution according to actual needs.

9. The enterprise order collaborative manufacturing scheduling optimization system based on improved SPSA according to claim 8 is characterized in that: The building blocks include: The acquisition module is used to collect and analyze order information to obtain information about the order tasks that can be completed by each enterprise; A module is established for constructing an enterprise network collaborative scheduling model using a multi-objective optimization method.

10. The enterprise order collaborative manufacturing scheduling optimization system based on improved SPSA according to claim 9 is characterized in that: The building module includes a multi-objective optimization unit, and the multi-objective optimization unit includes: A total production cost optimization subunit, which is used to optimize the total production cost by constructing an objective function that minimizes the total production cost; A total completion time optimization subunit is used to optimize the total completion time by constructing an objective function that minimizes the total completion time; A production quality optimization subunit, which is used to optimize production quality by constructing an objective function that maximizes production quality; A customer satisfaction optimization subunit, which is used to optimize customer satisfaction by constructing an objective function that maximizes customer satisfaction; The resource utilization optimization subunit is used to construct an objective function that maximizes resource utilization to optimize resource utilization.

Images