Composite process route optimization method for reconfigurable manufacturing system

Abstract

The invention relates to a composite process route optimization method for a reconfigurable manufacturing system, and the method comprises the steps: obtaining a production demand and a workpiece demand through an order, and determining a process sequence of workpieces which are not grouped; according to the process sequence, obtaining a machine tool sequence, calculating a basic process time sequence, extracting a longest common subsequence and a shortest mixed sequence, and calculating a similarity index between two workpieces; calculating the weight of the similarity index by using a dynamic weight distribution method based on fuzzy logic, and calculating a comprehensive similarity coefficient of the two workpieces; clustering the comprehensive similar matrix by using a hierarchical clustering algorithm, and selecting a proper similarity requirement to obtain a finally divided workpiece family; according to the scheme, a final composite process route is obtained by using a composite process route planning method based on genetic optimization. Through the intelligent workpiece family division and process optimization method, the production efficiency and the resource utilization rate are remarkably improved, and the dynamic manufacturing requirements of multi-variety and small-batch production are met.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent industrial control, and in particular to a composite process route optimization method for a reconfigurable manufacturing system. Background Art

[0002] As the manufacturing industry develops towards intelligence and flexibility, the traditional fixed production line model is difficult to meet the needs of multi-variety and small-batch production. Reconfigurable manufacturing systems (RMS) provide flexible solutions for coping with changing production tasks by dynamically adjusting production equipment and resource allocation. However, in the RMS environment, there are many types of workpieces and complex process routes, which makes it difficult to accurately measure the process similarity between workpieces, affecting the rationality of the division of workpiece families; in the process optimization process, traditional methods have limited effect on the feature selection of high-dimensional process data, and it is difficult to effectively improve the model performance; in the process sorting of workpiece families, traditional optimization methods are insufficient in computational efficiency and adaptability.

[0003] Existing technologies are usually based on fixed indicator weight allocation or simple clustering algorithms, which are difficult to dynamically adapt to the complexity of actual production needs. Therefore, there is an urgent need for an intelligent method that can dynamically allocate weights based on multi-dimensional similarity indicators and efficiently complete workpiece family division and process optimization to meet the requirements of a dynamic manufacturing environment. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] The present invention provides a composite process route optimization method for a reconfigurable manufacturing system, aiming to improve resource utilization and production efficiency in a complex manufacturing environment through efficient feature selection, intelligent classification and process optimization.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: Obtain production demand and workpiece demand through orders, and determine the process sequence of ungrouped workpieces; According to the process sequence, the machine tool sequence is obtained, the basic process time sequence is calculated, the longest common subsequence and the shortest mixed sequence are extracted, and the similarity index between the two workpieces is calculated; The weights of similarity indicators are calculated using a dynamic weight allocation method based on fuzzy logic, and the comprehensive similarity coefficient of two workpieces is calculated; The hierarchical clustering algorithm is used to cluster the comprehensive similarity matrix, and the appropriate similarity requirement is selected to obtain the final divided artifact family; According to the different workpiece families divided, the final composite process route is obtained by using the composite process route planning method based on genetic optimization.

[0007] As a preferred solution of the composite process route optimization method for a reconfigurable manufacturing system described in the present invention, wherein: the extracting of the longest common subsequence and the shortest mixed sequence and calculating the similarity index between the two workpieces comprises the following steps: Establish the relationship matrix between artifacts and sort out the longest common subsequence between two artifacts and the shortest mixed sequence ; Calculate the machine idle similarity index between two workpieces , the calculation formula is as follows: , , , In the formula, Indicates that the workpiece is processed using the shortest mixed sequence and artifacts The total number of idle machines generated when Express the dynamic adjustment factor based on processing complexity, Indicates the machine sequence and The length of the shortest mixed sequence, Indicates the machine sequence Length, Indicates the machine sequence Length, Indicates the machine sequence and The longest common subsequence length of ; Calculate the artifact detour similarity index between two artifacts , the calculation formula is as follows: , , In the formula, Indicates that the workpiece is processed using the shortest mixed sequence and artifacts The total number of idle machines that need to be bypassed when Calculate the process time similarity index between two workpieces , the calculation formula is as follows: , , In the formula, Indicates that the workpiece is processed using the shortest mixed sequence The total process time is Indicates that the workpiece is processed using the shortest mixed sequence The total process time is Indicates that the workpiece is processed using the shortest mixed sequence The variance of the time of each process is Indicates that the workpiece is processed using the shortest mixed sequence The variance of the time for each process; Calculate the process requirement similarity index between two workpieces , the calculation formula is as follows: , , In the formula, Representation of workpiece The demand for products Representation of workpiece The demand for products Indicates the minimum required quantity of all workpieces in the order, Indicates the maximum demand for all workpieces in the order, express The proportion of total order demand, express The proportion of total order demand, express The proportion of total order demand, express The proportion of total order demand.

[0008] As a preferred solution of the composite process route optimization method for a reconfigurable manufacturing system described in the present invention, wherein: the weight of the similarity index is calculated by using a dynamic weight allocation method based on fuzzy logic to calculate the comprehensive similarity coefficient of two workpieces, including the following steps: Machine Idle Similarity Index , Workpiece detour similarity index , process time similarity index and artifact requirement similarity index As input variables, Each input variable has three fuzzy output sets: Low, Medium, and High. The fuzzy set of Low output is the low value of the weight range. ; The fuzzy set output by Medium is the low value of the weight range and the middle value of the weight range ; The fuzzy set of High output is the low value of weight range and the high value of weight range , The matching degree between the four input variables and each fuzzy set is calculated based on the membership function. The membership function adopts the form of triangular membership function, and the calculation formula is as follows: , , , According to the needs of production optimization, a fuzzy rule base is constructed for reasoning. The rule base is as follows: Rule 1: When the machine tool is idle similarity index High, other similarity indicators , , When it is low, the idle weight of the machine tool is high. Rule 2: When process time similarity index Similarity index with workpiece demand When both are high, the process time similarity index weight is high, the weight of the workpiece demand similarity index For low, Rule 3: When all similarity indicators , , , When all similarity index weights are medium, , , , Both are medium. Rule 4: When artifacts detour similarity indicators is high, other similarity indicators , , When both are low, the weight of the workpiece detour similarity index is For high, Rule 5: When the machine tool is idle similarity index and process time similarity index When both are high, the machine tool idle similarity index weight and process time similarity index weight All are medium; According to the inference results, the membership function is aggregated to obtain its fuzzy output and matching value. , the calculation formula is as follows: , in, , , The centroid method is used for defuzzification, and the fuzzy set is converted into a specific value to obtain the weight. The calculation formula is as follows: , in, is the corresponding fuzzy membership function value, The weight distribution based on fuzzy logic is normalized and the calculation formula is as follows: .

[0009] According to the four similarity indicators obtained , , , and their weights , , , Calculate the comprehensive similarity coefficient between two artifacts , the calculation formula is as follows: .

[0010] As a preferred solution of the composite process route optimization method for a reconfigurable manufacturing system described in the present invention, wherein: clustering the comprehensive similarity coefficient matrix using a hierarchical clustering algorithm, selecting a suitable similarity requirement, and obtaining the final divided workpiece family includes the following steps: According to the calculated comprehensive similarity coefficient between two workpieces , build a comprehensive similarity matrix between artifacts ; use Instead of Euclidean distance, two artifacts with the largest similarity coefficient values ​​are selected and combined into one category; The calculation and merging are performed through the above two-step calculation method, and the two top-level artifact families of the clustering tree are obtained through iteration.

[0011] The calculation results of each previous step are displayed in the form of a tree diagram to obtain a hierarchical clustering tree. Finally, a suitable similarity is selected to determine the number of artifact families and grouping conditions.

[0012] As a preferred solution of the composite process route optimization method for a reconfigurable manufacturing system described in the present invention, the composite process route planning method based on genetic optimization obtains the final composite process route, comprising the following steps: Model the problem and extract artifact families Medium workpiece The sequence of machine tool usage required for processing ; Corresponding process time series ; and production demand , Constructing the initial composite process route , used for subsequent optimization, the calculation formula is as follows: , Building the evaluation function The calculation formula used to evaluate the detour cost of the composite process route is as follows: , in, It is a machine tool In the composite process route The index in The goal is to find a composite process route , so that the total detour cost is minimized, the optimization problem expression is as follows: , Optimizing composite process routes using genetic algorithms , initialize the population, randomly generate Composite process route , the calculation formula is as follows: , Constructing the fitness function , the calculation formula is as follows: , The probability of fitness value Select excellent individuals from the population to form the parent generation, use The function simulates the partial mapping crossover method in the genetic algorithm. For the selected parent generation, two individuals are randomly selected. , Perform partial crossover to generate offspring , the calculation formula is as follows: , Randomly select some offspring individuals for exchange mutation. The calculation formula is as follows: , Repeat the selection, crossover, and mutation steps and update the population until the number of iterations is reached. Output the lowest fitness value during the iteration As the final composite process route.

[0013] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the composite process route optimization method for a reconfigurable manufacturing system is implemented.

[0014] A computer-readable storage medium stores computer instructions, which, when executed by a processor, implement the composite process route optimization method for a reconfigurable manufacturing system.

[0015] Beneficial effects of the present invention: The present invention significantly improves production efficiency and resource utilization through intelligent workpiece family division and process optimization methods, and adapts to the dynamic manufacturing needs of multi-variety and small-batch production. The innovative use of a dynamic weight allocation method based on fuzzy logic can dynamically adjust the weight allocation according to the actual needs in the production environment, fully consider the relative importance of multi-dimensional indicators such as machine tool idleness, workpiece detours, process time and workpiece demand, and achieve accurate modeling of complex manufacturing scenarios; the workpiece family division strategy based on the hierarchical clustering algorithm not only improves the scientificity and rationality of the division results, but also effectively reduces the switching time and material waste in the production process, and improves the overall efficiency of the manufacturing process; in process optimization, the combination of genetic algorithms and particle swarm optimization algorithms further improves the optimization accuracy and computational efficiency of the composite process route, ensuring that the optimization scheme can quickly respond to production task requirements in a complex dynamic environment. Compared with traditional methods, the intelligent process of the present invention has significant advantages in feature selection and data processing capabilities, and can effectively solve the production planning problems under multiple workpieces and high complexity. It is not only suitable for dynamic and complex intelligent manufacturing environments, but also has important value in improving the decision-making support capabilities and resource scheduling capabilities of reconfigurable manufacturing systems, thereby promoting the digital transformation of the manufacturing and logistics industries. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 A basic flow chart of a composite process route optimization method for a reconfigurable manufacturing system provided by one embodiment of the present invention; Figure 2 A schematic diagram of a specific process flow of a composite process route optimization method for a reconfigurable manufacturing system provided by one embodiment of the present invention; Figure 3 A schematic diagram of a specific flow chart of a dynamic weight allocation method based on fuzzy logic provided by an embodiment of the present invention; Figure 4 A schematic diagram of a specific process flow of a composite process route planning method based on genetic optimization provided by one embodiment of the present invention; Figure 5 A schematic diagram of a result of dividing an artifact family based on hierarchical clustering is provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0017] Example 1 Reference Figure 1-Figure 2, as an embodiment of the present invention, provides a composite process route optimization method for a reconfigurable manufacturing system, such as Figure 1 , as shown in 2, comprising the following steps: S1: Obtain production demand and workpiece demand through orders, and determine the process sequence of ungrouped workpieces; S2: According to the process sequence, the machine tool sequence is obtained, the basic process time sequence is calculated, the longest common subsequence and the shortest mixed sequence are extracted, and the similarity index between the two workpieces is calculated; Furthermore, we build a relationship matrix between artifacts and sort out the longest common subsequences between two artifacts. and the shortest mixed sequence ; Calculate the machine idle similarity index between two workpieces , the calculation formula is as follows: , , , In the formula, Indicates that the workpiece is processed using the shortest mixed sequence and artifacts The total number of idle machines generated when Express the dynamic adjustment factor based on processing complexity, Indicates the machine sequence and The length of the shortest mixed sequence, Indicates the machine sequence Length, Indicates the machine sequence Length, Indicates the machine sequence and The longest common subsequence length of ; Calculate the artifact detour similarity index between two artifacts , the calculation formula is as follows: , , In the formula, Indicates that the workpiece is processed using the shortest mixed sequence and artifacts The total number of idle machines that need to be bypassed when Calculate the process time similarity index between two workpieces , the calculation formula is as follows: , , In the formula, Indicates that the workpiece is processed using the shortest mixed sequence The total process time is Indicates that the workpiece is processed using the shortest mixed sequence The total process time is Indicates that the workpiece is processed using the shortest mixed sequence The variance of the time of each process is Indicates that the workpiece is processed using the shortest mixed sequence The variance of the time for each process; Calculate the process requirement similarity index between two workpieces , the calculation formula is as follows: , , In the formula, Representation of workpiece The demand for products Representation of workpiece The demand for products Indicates the minimum required quantity of all workpieces in the order, Indicates the maximum demand for all workpieces in the order, express The proportion of total order demand, express The proportion of total order demand, express The proportion of total order demand, express The proportion of total order demand.

[0018] S3: The weights of similarity indicators are calculated using a dynamic weight allocation method based on fuzzy logic, and the comprehensive similarity coefficients of the two artifacts are calculated, such as Figure 3 As shown; Furthermore, the machine tool idle similarity index , Workpiece detour similarity index , process time similarity index and artifact requirement similarity index As input variables, Each input variable has three fuzzy output sets: Low, Medium, and High. The fuzzy set of Low output is the low value of the weight range. ; The fuzzy set output by Medium is the low value of the weight range and the middle value of the weight range ; The fuzzy set of High output is the low value of weight range and the high value of weight range , The matching degree between the four input variables and each fuzzy set is calculated based on the membership function. The membership function adopts the form of triangular membership function, and the calculation formula is as follows: , , , According to the needs of production optimization, a fuzzy rule base is constructed for reasoning. The rule base is as follows: Rule 1: When the machine tool is idle similarity index High, other similarity indicators , , When it is low, the idle weight of the machine tool is high. Rule 2: When process time similarity index Similarity index with workpiece demand When both are high, the process time similarity index weight is high, the weight of the workpiece demand similarity index For low, Rule 3: When all similarity indicators , , , When all similarity index weights are medium, , , , Both are medium. Rule 4: When artifacts detour similarity indicators is high, other similarity indicators , , When both are low, the weight of the workpiece detour similarity index is For high, Rule 5: When the machine tool is idle similarity index and process time similarity index When both are high, the machine tool idle similarity index weight and process time similarity index weight Both are medium.

[0019] According to the inference results, the membership function is aggregated to obtain its fuzzy output and matching value. , the calculation formula is as follows: , in, , , The centroid method is used for defuzzification, and the fuzzy set is converted into a specific value to obtain the weight. The calculation formula is as follows: , in, is the corresponding fuzzy membership function value, The weight distribution based on fuzzy logic is normalized and the calculation formula is as follows: .

[0020] According to the four similarity indicators obtained , , , and their weights , , , Calculate the comprehensive similarity coefficient between two artifacts , the calculation formula is as follows: .

[0021] S4: cluster the comprehensive similarity coefficient matrix using a hierarchical clustering algorithm, select an appropriate similarity requirement, and obtain the final divided artifact family; Furthermore, according to the calculated comprehensive similarity coefficient between the two workpieces , build a comprehensive similarity matrix between artifacts ; Furthermore, using Instead of Euclidean distance as the distance metric between artifacts, the artifacts are clustered; Furthermore, the calculation and merging are performed by the calculation method of the above two steps, and the two top-level artifact families of the clustering tree are obtained iteratively; Furthermore, the calculation results of each previous step are displayed in the form of a tree diagram to obtain a hierarchical clustering tree, and finally a suitable similarity is selected to determine the number of artifact families and grouping conditions.

[0022] S5: According to the different workpiece families divided, the final composite process route is obtained by using the composite process route planning method based on genetic optimization, such as Figure 4 shown.

[0023] Going a step further, model the problem and extract artifact families Medium workpiece The sequence of machine tool usage required for processing ; Corresponding process time series ; and production demand , Constructing the initial composite process route , used for subsequent optimization, the calculation formula is as follows: , Building the evaluation function The calculation formula used to evaluate the detour cost of the composite process route is as follows: , in, It is a machine tool In the composite process route The index in The goal is to find a composite process route , so that the total detour cost is minimized, the optimization problem expression is as follows: , Optimizing composite process routes using genetic algorithms , initialize the population, randomly generate Composite process route , the calculation formula is as follows: , Constructing the fitness function , the calculation formula is as follows: , The probability of fitness value Select excellent individuals from the population to form the parent generation, use The function simulates the partial mapping crossover method in the genetic algorithm. For the selected parent generation, two individuals are randomly selected. , Perform partial crossover to generate offspring , the calculation formula is as follows: , Randomly select some offspring individuals for exchange mutation. The calculation formula is as follows: , Repeat the selection, crossover, and mutation steps and update the population until the number of iterations is reached. Output the lowest fitness value during the iteration As the final composite process route.

[0024] Example 2 The present invention provides a composite process route optimization method for a reconfigurable manufacturing system. In order to verify its beneficial effects, a scientific demonstration is carried out through specific implementation methods and implementation effects. Experiments are carried out through PYTHON on a WINDOWS 11 system. The specific implementation methods are as follows: Step 1) Obtain production demand and workpiece demand through orders, determine the process sequence of ungrouped workpieces, and give the demand for each part in accordance with the production method of small and medium batches of 10 common typical parts to simulate the orders expected to be received by a certain enterprise, as shown in Table 1: Table 1 Order generation requirements table Step 2) According to the process sequence, the machine tool sequence is obtained, the basic process time sequence is calculated, and the machine tools are numbered. The machine tool usage sequence is converted into a number series, as shown in Table 2. The longest common subsequence and the shortest mixed sequence are extracted, and the similarity index between the two workpieces is calculated, as shown in Tables 3-1, 3-2, 3-3, and 3-4: Table 2 Workpiece process information table Table 3-1 Machine tool idle similarity index matrix Table 3-2 Workpiece detour similarity index matrix Table 3-3 Process time similarity index matrix Table 3-4 Process requirement similarity index matrix Step 3) The weights of the similarity indexes are calculated using the dynamic weight allocation method based on fuzzy logic, and the comprehensive similarity coefficients of the two artifacts are calculated, as shown in Table 4: Table 4 Comprehensive similarity matrix Step 4) Use the hierarchical clustering algorithm to cluster the comprehensive similarity matrix, such as Figure 5 As shown: The metric value is selected as 0.6 to divide the artifact families, and the final divided artifact families are: {3, 7, 9, 10}, {5, 6, 8}, {4, 1, 2}, That is, workpiece family 1: {output shaft, rack, window spindle box, worm gear reducer housing}, Workpiece family 2: {crosshead, spindle box gear, screw}, workpiece family 3: {eccentric sleeve, gear shaft, piston rod}.

[0025] Step 5) According to the different workpiece families, taking workpiece family 1: {output shaft, rack, window spindle box, worm gear reducer housing} as an example, the composite process route planning method based on genetic optimization is used to obtain the final composite process route {10, 12, 14, 20, 17, 18, 16, 1, 4, 2, 7}, as shown in Table 5: Table 5 Optimal composite process route for workpiece family 1 The present invention provides a composite process route optimization method for a reconfigurable manufacturing system, aiming to solve the problem that traditional methods are difficult to adapt to the needs of multi-variety and small-batch production. The method first obtains production demand and workpiece demand through orders, determines the process sequence of ungrouped workpieces, and extracts multi-dimensional similarity indicators such as machine tool idleness, workpiece detours, process time and workpiece demand; then, a dynamic weight allocation method based on fuzzy logic is used to calculate the comprehensive similarity coefficient, and the workpieces are intelligently grouped and divided into workpiece families through a hierarchical clustering algorithm; finally, the composite process route of the workpiece family is optimized in combination with a particle swarm optimization algorithm to improve resource utilization and production efficiency. The present invention effectively reduces the switching time and resource waste in the production process, enhances the adaptability and computational efficiency of process route optimization, and is suitable for dynamic and complex intelligent manufacturing environments.

[0026] It should be noted that the above embodiments are not intended to limit the protection scope of the present invention, and equivalent changes or substitutions made on the basis of the above technical solutions all fall within the protection scope of the claims of the present invention.

Claims

1. A composite process route optimization method for a reconfigurable manufacturing system, characterized in that: include: Obtain production demand and workpiece demand through orders, and determine the process sequence of ungrouped workpieces; According to the process sequence, the machine tool sequence is obtained, the basic process time sequence is calculated, the longest common subsequence and the shortest mixed sequence are extracted, and the similarity index between the two workpieces is calculated; The weights of similarity indicators are calculated using a dynamic weight allocation method based on fuzzy logic, and the comprehensive similarity coefficient of two workpieces is calculated; The hierarchical clustering algorithm is used to cluster the comprehensive similarity matrix, and the appropriate similarity requirement is selected to obtain the final divided artifact family; According to the different workpiece families divided, the final composite process route is obtained by using the composite process route planning method based on genetic optimization.

2. The composite process route optimization method for a reconfigurable manufacturing system according to claim 1, characterized in that: Calculating the similarity index between two artifacts includes the following steps: Calculate the machine idle similarity index between two workpieces , the calculation formula is as follows: ， ， ， In the formula, Indicates that the workpiece is processed using the shortest mixed sequence and artifacts The total number of idle machines generated when Express the dynamic adjustment factor based on processing complexity, Indicates the machine sequence and The length of the shortest mixed sequence, Indicates the machine sequence Length, Indicates the machine sequence Length, Indicates the machine sequence and The longest common subsequence length of ; Calculate the artifact detour similarity index between two artifacts , the calculation formula is as follows: ， ， In the formula, Indicates that the workpiece is processed using the shortest mixed sequence and artifacts The total number of idle machines that need to be bypassed when Calculate the process time similarity index between two workpieces , the calculation formula is as follows: ， ， In the formula, Indicates that the workpiece is processed using the shortest mixed sequence The total process time is Indicates that the workpiece is processed using the shortest mixed sequence The total process time is Indicates that the workpiece is processed using the shortest mixed sequence The variance of the time of each process is Indicates that the workpiece is processed using the shortest mixed sequence The variance of the time for each process; Calculate the process requirement similarity index between two workpieces , the calculation formula is as follows: ， ， In the formula, Representation of workpiece The demand for products Representation of workpiece The demand for products Indicates the minimum required quantity of all workpieces in the order, Indicates the maximum demand for all workpieces in the order, express The proportion of total order demand, express The proportion of total order demand, express The proportion of total order demand, express The proportion of total order demand.

3. The composite process route optimization method for a reconfigurable manufacturing system according to claim 1, characterized in that: The dynamic weight allocation method based on fuzzy logic includes the following steps: Machine Idle Similarity Index , Workpiece detour similarity index , process time similarity index and artifact requirement similarity index As input variables, Each input variable has three fuzzy output sets: Low, Medium, and High. The fuzzy set of Low output is the low value of the weight range. ; The fuzzy set output by Medium is the low value of the weight range and the middle value of the weight range ; The fuzzy set of High output is the low value of weight range and the high value of weight range , The matching degree between the four input variables and each fuzzy set is calculated based on the membership function. The membership function adopts the form of triangular membership function, and the calculation formula is as follows: ， ， ， According to the needs of production optimization, a fuzzy rule base is constructed for reasoning. The rule base is as follows: Rule 1: When the machine tool is idle similarity index High, other similarity indicators , , When it is low, the idle weight of the machine tool is high. Rule 2: When process time similarity index Similarity index with workpiece demand When both are high, the process time similarity index weight is high, the weight of the workpiece demand similarity index For low, Rule 3: When all similarity indicators , , , When all similarity index weights are medium, , , , Both are medium. Rule 4: When artifacts detour similarity indicators is high, other similarity indicators , , When both are low, the weight of the workpiece detour similarity index is For high, Rule 5: When the machine is idle similarity index and process time similarity index When both are high, the machine tool idle similarity index weight and process time similarity index weight Both are medium. According to the inference results, the membership function is aggregated to obtain its fuzzy output and matching value. , the calculation formula is as follows: , in, , ， The centroid method is used for defuzzification, and the fuzzy set is converted into a specific value to obtain the weight. The calculation formula is as follows: ， in, is the corresponding fuzzy membership function value, The weight distribution based on fuzzy logic is normalized and the calculation formula is as follows: 。 4. The composite process route optimization method for a reconfigurable manufacturing system according to claim 1, characterized in that: The composite process route planning method based on genetic optimization includes the following steps: Model the problem and extract artifact families Medium workpiece The sequence of machine tool usage required for processing ; Corresponding process time series ; and production demand , Constructing the initial composite process route , used for subsequent optimization, the calculation formula is as follows: ， Building the evaluation function The calculation formula used to evaluate the detour cost of the composite process route is as follows: ， in, It is a machine tool In the composite process route The index in The goal is to find a composite process route , so that the total detour cost is minimized, the optimization problem expression is as follows: , Optimizing composite process routes using genetic algorithms , initialize the population, randomly generate Composite process route , the calculation formula is as follows: ， Constructing the fitness function , the calculation formula is as follows: ， The probability of fitness value Select excellent individuals from the population to form the parent generation, use The function simulates the partial mapping crossover method in the genetic algorithm. For the selected parent generation, two individuals are randomly selected. , Perform partial crossover to generate offspring , the calculation formula is as follows: ， Randomly select some offspring individuals for exchange mutation. The calculation formula is as follows: ， Repeat the selection, crossover, and mutation steps and update the population until the number of iterations is reached. Output the lowest fitness value during the iteration As the final composite process route.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the composite process route optimization method for a reconfigurable manufacturing system as described in any one of claims 1 to 4 is implemented.

6. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, a composite process route optimization method for a reconfigurable manufacturing system as described in any one of claims 1 to 4 is implemented.

Images