Equipment type production scheduling method and system in automobile part industry

Abstract

The invention discloses an automobile part industry equipment type production scheduling method and system, and relates to the technical field of automobile part machining, and the method comprises the steps: 1, carrying out the context construction according to a scheduling request, and generating a production window fragment list; 2, forming an initial chromosome population by using the production window fragment list, performing iterative optimization on chromosomes in the initial chromosome population, and selecting the chromosome with the first fitness value in the chromosome population as a final batch decision scheme; and 3, decoding the chromosome serving as the final batch decision scheme to obtain a final scheduling plan and outputting the final scheduling plan. According to the method, complex scheduling scenes of a large number of orders and equipment can be processed at the same time, various constraint conditions such as process routes, material inventory and equipment maintenance are comprehensively considered, a global optimal scheduling scheme is output, meanwhile, the scheduling scheme can be dynamically adjusted according to emergency situations, production continuity is guaranteed, the resource optimization configuration capacity is improved, manual dependence is reduced, and the scheduling efficiency is improved. The production efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of automotive parts processing technology, and in particular to an equipment-based production scheduling method and system for the automotive parts industry. Background Technology

[0002] The automotive parts industry is currently developing rapidly towards a more diversified and smaller-batch production model. Consumers' increasing demand for personalized vehicles is driving OEMs to continuously adjust model configurations, which in turn requires parts suppliers to have flexible production response capabilities. However, existing production scheduling technologies have significant bottlenecks and are unable to meet the industry's development needs.

[0003] Traditional scheduling methods rely primarily on manual experience or simple Excel spreadsheets, which presents three major problems: First, sluggish response: when unexpected events such as order changes or equipment failures occur, manual scheduling adjustments can take hours or even days, easily leading to production disruptions. Second, low resource utilization: due to the inability to accurately match equipment capacity with order demand, some equipment often operates at overcapacity while others remain idle, resulting in low overall equipment efficiency (OEE). Third, insufficient scheduling accuracy: manual planning struggles to comprehensively consider multiple factors such as material availability, process constraints, and delivery priority, leading to increased order delay rates, increased supply chain costs, and higher customer complaint risks. To address the aforementioned issues, there is an urgent need to provide an equipment-based production scheduling method and system for the automotive parts industry. Summary of the Invention

[0004] The purpose of this invention is to provide an equipment-based production scheduling method and system for the automotive parts industry, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a production scheduling method for equipment in the automotive parts industry, comprising: Step 1: Build the context based on the scheduling request and generate a list of production window fragments; Step 2: Form an initial chromosome population using the production window fragment list, iteratively optimize the chromosomes in the initial chromosome population, and select the chromosome with the highest fitness value in the chromosome population as the final batch decision scheme. Step 3: Decode the chromosomes that will serve as the final batch decision scheme to obtain and output the final scheduling plan.

[0006] Preferably, step 1 includes the following specific steps: Step 1.1: Receive the bill of materials and decompose it into daily demand sequences for each material, and calculate the daily production slots for each material. Step 1.2: Based on material requirements, production line capacity, and mold change constraints, plan continuous production windows for each material on each production line and generate a list of production window segments.

[0007] Preferably, step 1.1 specifically includes: Step 1.11: Receive scheduling requests from external systems. Input data includes, but is not limited to, planning period, order requirements, bill of materials, production line capacity, and economic batch configuration. Step 1.12: Based on the input bill of materials structure, expand the order requirements of the final product step by step, calculate the net requirements of each key material for each day during the planning period, and form a material daily demand curve. Step 1.13: Identify master and slave materials with co-product relationships, proportionally calculate and add the demand of slave materials to the demand of master materials, and retain the independent demand of slave materials for inventory and gap statistics; Step 1.14: Calculate the basic production batch size for each material, and calculate the number of production slots for each production line per day based on the daily available working hours and material production cycle time.

[0008] Preferably, step 1.2 specifically includes: Step 1.21: Based on material requirements, production line capacity, and mold change constraints, plan the production scale of each material on each production line. Step 1.22: The planning results are organized into multiple production line continuous production segments. Each production line continuous production segment defines a suggested time window, batch size, and suggested batch number for producing a single material. Multiple production line continuous production segments generate a list of production window segments for materials.

[0009] Preferably, step 2 specifically includes: Step 2.1: The genetic algorithm execution engine uses a chromosome factory to randomly generate a set of initial chromosomes based on the number of continuous production segments on the production line, thereby forming an initial population. Each chromosome in the initial population corresponds to an integer array, and each position in the array represents the number of production batches installed in a continuous production segment of the production line. Step 2.2, driven by a general genetic algorithm engine, involves multiple iterations based on the configured number of generations and population size. The iteration process includes fitness evaluation, selection, crossover, and mutation operations. The new individuals generated through selection, crossover, and mutation are merged with the elite individuals retained from the previous generation to form a new generation of population. Steps 2.1 to 2.2 are repeated until the preset maximum number of generations is reached or the optimal fitness no longer improves after several consecutive generations, at which point the termination condition is met. Step 2.3: The genetic algorithm execution engine stops iterating and outputs the chromosome with the highest fitness value in the final population as the optimization result.

[0010] Preferably, in step 2.2, the fitness evaluation, selection, crossover, and mutation operations during the iteration process specifically include: Fitness assessment operation: For each chromosome in the population, perform lightweight decoding to simulate production scheduling, and calculate the fitness score based on the simulation results; Selection operation: Based on fitness scores, select dominant individuals from the current population to enter the crossover pool; Crossover operation: Select parent chromosomes from the crossover pool, exchange some continuous gene locus intervals between them, and generate offspring chromosomes; Mutation operation: Randomly select a portion of gene loci in the offspring chromosome, apply random perturbation or reset to their batch number decision value, and ensure that the result value meets the batch number constraint of the window.

[0011] Preferably, step 3 specifically includes: After obtaining the chromosome with the highest fitness value, the genetic algorithm execution engine performs a complete and final decoding on that chromosome, generating a well-formatted scheduling result object, which specifically includes: Detailed layer: Each record describes the production schedule quantity for a specific day, production line, or material; Indicator layer: Includes total demand, total gap, fulfillment rate of each material, inventory curve statistics, mold change frequency, etc., used for scoring and diagnosis.

[0012] On the other hand, the present invention also provides an equipment-based production scheduling system for the automotive parts industry, implementing the equipment-based production scheduling method for the automotive parts industry described in any one of the above claims, wherein the system specifically includes: The context building layer is used to perform input data preprocessing, generate daily demand sequences, calculate batch and capacity, plan continuous production windows, and build a context containing all scheduling input parameters. The genetic algorithm execution engine layer is used to perform chromosome initialization, iterative optimization, and final batch decision selection. The scheduling decoder layer is used to decode the chromosome with the highest fitness value into a complete scheduling plan result.

[0013] Preferably, the preprocessing and planning module includes: Demand decomposer, used to handle the discounting of common product demand; The continuous production planner is used to generate continuous production window segments.

[0014] Preferably, the genetic algorithm execution engine includes: The chromosome factory is used to randomly generate a set of initial chromosomes based on the number of continuous production segments on the production line, forming an initial population of chromosomes. Each chromosome in the initial population corresponds to an integer array, and each position in the array represents the number of production batches installed in a continuous production segment of the production line. The crossover operator is used to select parent chromosomes from the crossover pool and make batch number decisions by exchanging some continuous gene locus intervals to generate offspring chromosomes. The mutation operator is used to randomly select a portion of gene loci in the offspring chromosome and apply random perturbation or reset to the batch number decision value so that the result value satisfies the batch number constraint of the window. A fitness evaluator is used to decode each chromosome in the chromosome population to simulate production scheduling and calculate a fitness score based on the simulation results. The underlying general-purpose genetic algorithm engine framework serves as the execution skeleton of the genetic algorithm engine, used to manage the complete lifecycle of chromosome population evolution.

[0015] The technical effects and advantages of this invention are as follows: This invention can handle complex scheduling scenarios involving a large number of orders and equipment simultaneously. It comprehensively considers various constraints such as process routes, material inventory, and equipment maintenance to output a globally optimal scheduling solution. At the same time, it can dynamically adjust the scheduling solution in response to unforeseen circumstances, ensuring production continuity, improving resource optimization and allocation capabilities, reducing reliance on manual labor, and increasing production efficiency.

[0016] This invention can generate the optimal scheduling scheme for complex equipment processing using a genetic algorithm, thereby meeting processing requirements under given capacity constraints. While meeting processing requirements, it reduces the number of equipment mold changes, smooths capacity and inventory, thereby improving the utilization rate of enterprise equipment, reducing labor costs, and improving the efficiency of enterprise equipment in material processing. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart of the method of the present invention.

[0018] Figure 2 This is a system flowchart of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] This invention provides, for example Figure 1 The illustrated equipment-based production scheduling method for the automotive parts industry includes: Step 1: Based on the scheduling request, construct the context and generate a list of production window fragments; this can transform the original, complex, and diverse business input data into a unified, structured context suitable for algorithm processing. Step 1 includes the following specific steps: Receive scheduling requests from external systems, input data including but not limited to planning period, order requirements, bill of materials, production line capacity and economic batch configuration, and return the final scheduling results to the external system; The system's demand decomposer converts product series requirements and bill of materials (BOM) structures into daily demand curves for materials × dates. If there are co-products (i.e., master-detail materials), the "Apply Co-product Demand" method in the co-product demand tool is called to calculate and add the demand of the sub-materials to the demand of the master material, while retaining the demand of the sub-materials themselves. This ensures the accuracy of the scheduling source data, accurately mapping product-oriented order requirements to specific production materials, avoiding production and demand mismatches caused by demand misalignment (especially master-detail materials), and reducing the risk of shortages from the source. Based on the start and end dates of the planning cycle, a complete date sequence is constructed for subsequent daily-level scheduling simulations. The average daily demand for each material is calculated, and combined with economic batch configuration, the basic production batch size for each material is calculated. Based on the daily available man-hours and material production cycle time of each production line, the number of production slots per day for each production line is calculated, thereby achieving a higher level of precision in the genetic algorithm's search space within the control system. This determines the time range for scheduling, laying the foundation for refined "daily-level" management, ensuring that daily capacity and demand can be accurately calculated. Simultaneously, a reasonable search scale is set for the genetic algorithm; appropriate batch calculations guide the algorithm to find economical production solutions. Accurate daily slot calculations define the upper limit of daily capacity, preventing the generation of unrealistic or overly conservative scheduling plans, significantly improving the efficiency and feasibility of the algorithm's search. The continuous production planner in the system plans the production scale of each material on each production line based on material demand, production line capacity, and mold change constraints, and plans the continuous production window for each material on each production line. Priority is given to allocating longer continuous production windows to materials with high demand, in order to reduce the number of mold changes and frequent production line switching, thus avoiding the problem of reduced production efficiency caused by frequent mold changes and product switching. The above planning results are organized into multiple continuous production segments. Each continuous production segment defines a suggested time window, feasible batches, and suggested batch number for producing a single material. Multiple continuous production segments generate a list of production window segments for materials, and for each window segment, the production line, material, start and end points are determined. Date, batch output, maximum / recommended batch number; thus, by summarizing scheduling inputs, planning period date list, material requirements, basic batch size, production window segment, genetic algorithm parameters, etc., this information serves as a unified context for the subsequent genetic algorithm execution engine and fast fitness evaluator. In this step, material requirements are macroscopically matched with production line capacity and time window, and a dedicated, continuous production time period is allocated for each material. This guides the algorithm to optimize in the general direction of reducing mold changes, avoiding aimless searching by the algorithm, and directly laying the foundation for the final solution's low mold change and high efficiency. At the same time, forming a unified context can provide standardized data services for the subsequent genetic algorithm engine, improve computational efficiency, and ensure data consistency.

[0021] Step 2: An initial chromosome population is formed using a list of production window segments. The chromosomes in the initial chromosome population are iteratively optimized, and the chromosome with the highest fitness value in the chromosome population is selected as the final batch decision scheme. In this step, by simulating the intelligent search mechanism of biological evolution (selection, crossover, mutation), the optimal scheduling implementation scheme can be efficiently found in a possible solution space consisting of multiple sets of continuous production segments. This can save manual allocation, avoid response lag, low equipment resource utilization, and insufficient equipment scheduling accuracy. Step 2 specifically includes: The genetic algorithm execution engine uses a chromosome factory to randomly generate the total number of batches within a certain range, centered on the suggested batch number for each production window segment. This total number is always pruned within the maximum batch number allowed for the corresponding production window segment, thereby generating an initial population of a specified size. Each chromosome in the initial population corresponds to an integer array, and each position in the array represents the number of production batches installed in a continuous production segment of the production line. In this embodiment, initialization is centered on the suggested batch number, which means that the starting quality of the population is relatively high, accelerating the convergence process of the genetic algorithm and finding a feasible solution faster than completely random initialization. Each chromosome is decoded into a lightweight scheduling result, which involves calling the continuous production decoder in the system to traverse by day and production line. Each day, the demand and inventory status are first scanned within the look-ahead window to prioritize the production of materials with near-term shortage risks. Then, based on the batch decision on the chromosome, production batches are arranged within the corresponding continuous production window segment, which tracks the number of batches produced in each window. On the same day, based on the remaining number of production batches and production line capacity, feasible production entries are organized. Finally, the excess capacity is allocated to other materials using the method of filling the remaining production line capacity, thereby generating a list of scheduling entries and scheduling indicators. Driven by a general genetic algorithm engine, the process iterates multiple times based on the configured number of generations and population size. The iteration process includes fitness evaluation, selection, crossover, and mutation operations. New individuals generated through selection, crossover, and mutation are merged with the elite individuals retained from the previous generation to form a new generation. Steps 2.1 to 2.2 are repeated until the preset number of generations is reached or the fitness no longer improves over several consecutive generations, at which point the termination condition is met. Specifically: Fitness Calculation: The fitness of the production line is calculated by calling the "Calculate Fitness" method in the fast fitness evaluator of the system. Specifically, based on the total shortage and the demand fill rate of each material, the demand satisfaction score is calculated. Shortages of key components are penalized more severely, and materials without corresponding production line production capacity are differentiated. In addition, points are deducted based on the number of mold changes and the peak inventory / inventory cost. Penalties for constraints (such as capacity overload) are also added. Finally, a single fitness score is summed up (the higher the score, the better the solution). This can combine multiple conflicting business objectives such as meeting demand, reducing mold changes, and controlling inventory into a single value through weighted penalty items. By optimizing this value, the genetic algorithm can automatically find the best balance point between business objectives. Selection: A competitive selection strategy is typically used to selectively select chromosomes with high fitness values ​​from the current population to enter the crossover pool; this ensures that superior chromosomes have a greater chance of being retained and propagated, driving continuous optimization of chromosome population instructions; Crossover: Through the crossover operator in the system, a portion of the batch decision interval is selected between two parent chromosomes for exchange, forming two new offspring, thereby realizing the total batch number decision recombination of different continuous production window segments; it can combine the excellent decisions of different production segments in two parent schemes to form a new offspring scheme that can combine the advantages of both. Mutation: By randomly selecting several consecutive production window segments through the mutation operator in the system, the corresponding batch decision values ​​are slightly increased, decreased or even reduced to zero, so that the values ​​always remain within the maximum batch allowable range of the corresponding window segment, which can be used to flexibly create new combination possibilities; by making small, random modifications to the existing scheme, a variety of changes are introduced, which can help the genetic algorithm escape local optima, thus enabling it to explore new scheduling combinations. Furthermore, during chromosome iteration, by retaining a certain proportion of elite individuals (referring to the chromosome with the highest fitness value) in each generation, allowing them to directly enter the next generation, we can avoid disruption by crossover or mutation operations. The convergence condition is chosen when the genetic algorithm reaches its maximum iteration count, or when the fitness improvement for multiple consecutive generations falls below a set threshold and exceeds a preset patience count. This causes the genetic algorithm to determine convergence and stop iteration, outputting the chromosome with the highest fitness value in the final population as the optimization result. Through elite retention and convergence judgment, we can prevent crossover and mutation from destroying the currently found optimal solution, thus ensuring continuous optimization of the solution. Simultaneously, the iteration automatically stops when the solution instruction no longer shows significant improvement after iteration, avoiding unnecessary computation and resource consumption. Step 3: Decode the chromosomes that serve as the final batch decision schemes to obtain and output the final scheduling plan, and return it to the scheduling system for use by the upper level; transform the chromosomes corresponding to the final batch decision schemes found by the genetic algorithm into micro-production instructions and performance reports that can be read, reviewed, and executed by managers and downstream systems, thereby facilitating the use and analysis of the scheduling plan by the enterprise; Step 3 specifically includes: After the genetic algorithm execution engine finishes, the chromosome with the highest fitness value is selected from the last generation population as the current optimal scheduling scheme. The system's fast fitness evaluator internally calls the decoding method of the continuous production decoder to decode the fitness value of the first chromosome, generating a complete scheduling result containing information such as inventory trajectory, gap statistics, and mold change details; specifically, it includes: Detailed layer: Each record describes the production schedule quantity for a specific day, production line, or material; Indicator layer: Includes total demand, total gap, fulfillment rate of each material, inventory curve statistics, mold change frequency, etc., used for scoring and diagnosis.

[0022] like Figure 2 As shown, this embodiment also provides an equipment-based production scheduling system for the automotive parts industry, implementing the equipment-based production scheduling method for the automotive parts industry described in the above embodiment. The system specifically includes: The context construction layer performs input data preprocessing, generates daily demand sequences, calculates batch sizes and capacity, plans continuous production windows, and constructs a context containing all scheduling input parameters. It includes a demand decomposer and a continuous production planner, used to handle co-product demand conversion and generate continuous production window segments, respectively. In this system, this layer primarily receives scheduling input from external systems, expands the planning period into a specific date list, and then decomposes it through demand, mapping order demands to daily demand curves for each material based on the bill of materials structure. It can also handle the overlay of demand for master and slave materials (co-products) and calculate the basic production batch size and available scheduling slots for each material, thus enabling the use of the system's genetic algorithm library. The continuous production planner in the inventory service generates "continuous production segment" plans and converts them into a list of continuous production window segments. This forms the context required by the genetic algorithm and provides a unified, self-reading context environment for the subsequent genetic algorithm engine. Finally, by calling the execution method in the genetic algorithm inventory service, the optimal scheduling result is returned to the external system, so that the generated scheduling plan can directly drive the MES system to issue production instructions. Its rich indicators (stockout, load, mold change) provide managers with powerful decision support and analysis tools, which can evaluate the quality of the plan, identify bottlenecks, and perform manual fine-tuning and secondary optimization on this basis, so that the scheduling system is truly integrated into the production management closed loop. The genetic algorithm execution engine layer is used to perform chromosome initialization, iterative optimization, and final batch decision selection; the genetic algorithm execution engine includes: Chromosome Factory: A continuous chromosome generation factory used to randomly generate a set of initial chromosomes based on the number of continuous production segments on the production line, forming an initial population of chromosomes. Each chromosome in the initial population corresponds to an integer array, and each position in the array represents the number of production batches installed in a continuous production segment of the production line. Crossover operator: A continuous production crossover operator used to select parent chromosomes from the crossover pool and make batch number decisions by exchanging some consecutive gene locus intervals to generate offspring chromosomes; Mutation operator: A continuous production mutation operator used to randomly select a portion of gene loci in the offspring chromosome and apply random perturbation or reset to the batch number decision value so that the result value meets the batch number constraint of the window. Fitness evaluator: A fast fitness evaluator is used to decode each chromosome in the chromosome population to simulate production scheduling and calculate fitness scores based on the simulation results; The underlying general-purpose genetic algorithm engine framework serves as the execution skeleton of the genetic algorithm engine, managing the complete lifecycle of chromosome population evolution. It provides a proven and efficient genetic algorithm execution process for the genetic algorithm execution engine. Through parameter configuration, the balance between exploration and utilization of the algorithm can be flexibly adjusted, and the framework design allows for easy replacement of different selection strategies, crossover and mutation operators, and other groups. The genetic algorithm execution engine layer also includes a fitness evaluator, which can call the decoder to obtain the complete scheduling results, and then comprehensively calculate the total shortage quantity and the demand satisfaction rate of each material, the number of production line mold changes and related costs, the peak inventory level and overall inventory cost, as well as the penalties for violations of constraints such as overcapacity, and map them to a single fitness value to drive the purification process of the genetic algorithm. The scheduling decoder layer, which includes a continuous production decoder, is responsible for decoding the genetic algorithm chromosome into specific daily scheduling entries. This includes facilitating and arranging by date and production line, prioritizing production of materials with near-term stockout risks, allocating the total number of batches decided for each continuous production window segment in the chromosome to other corresponding date windows, utilizing remaining capacity to supplement the production of other materials, and finally generating a detailed list of scheduling entries, inventory change trajectories, and various scheduling indicators.

[0023] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A production scheduling method based on equipment in the automotive parts industry, characterized in that, include: Step 1: Build the context based on the scheduling request and generate a list of production window fragments; Step 2: Form an initial chromosome population using the production window fragment list, iteratively optimize the chromosomes in the initial chromosome population, and select the chromosome with the highest fitness value in the chromosome population as the final batch decision scheme. Step 3: Decode the chromosomes that will serve as the final batch decision scheme to obtain and output the final scheduling plan.

2. The equipment-based production scheduling method for the automotive parts industry according to claim 1, characterized in that, The specific steps of step 1 include: Step 1.1: Receive the bill of materials and decompose it into daily demand sequences for each material, and calculate the daily production slots for each material. Step 1.2: Based on material requirements, production line capacity, and mold change constraints, plan continuous production windows for each material on each production line and generate a list of production window segments.

3. The equipment-based production scheduling method for the automotive parts industry according to claim 2, characterized in that, Step 1.1 specifically includes: Step 1.11: Receive scheduling requests from external systems. Input data includes, but is not limited to, planning period, order requirements, bill of materials, production line capacity, and economic batch configuration. Step 1.12: Based on the input bill of materials structure, expand the order requirements of the final product step by step, calculate the net requirements of each key material for each day during the planning period, and form a material daily demand curve. Step 1.13: Identify master and slave materials with co-product relationships, proportionally calculate and add the demand of slave materials to the demand of master materials, and retain the independent demand of slave materials for inventory and gap statistics; Step 1.14: Calculate the basic production batch size for each material, and calculate the number of production slots for each production line per day based on the daily available working hours and material production cycle time.

4. The equipment-based production scheduling method for the automotive parts industry according to claim 2, characterized in that, Step 1.2 specifically includes: Step 1.21: Based on material requirements, production line capacity, and mold change constraints, plan the production scale of each material on each production line. Step 1.22: The planning results are organized into multiple production line continuous production segments. Each production line continuous production segment defines a suggested time window, batch size, and suggested batch number for producing a single material. Multiple production line continuous production segments generate a list of production window segments for materials.

5. The equipment-based production scheduling method for the automotive parts industry according to claim 1, characterized in that, Step 2 specifically includes: Step 2.1: The genetic algorithm execution engine uses a chromosome factory to randomly generate a set of initial chromosomes based on the number of continuous production segments on the production line, thereby forming an initial population. Each chromosome in the initial population corresponds to an integer array, and each position in the array represents the number of production batches installed in a continuous production segment of the production line. Step 2.2, driven by a general genetic algorithm engine, involves multiple iterations based on the configured generation number and population size. The iteration process includes fitness evaluation, selection, crossover, and mutation operations. The new individuals generated through selection, crossover, and mutation are merged with the elite individuals retained from the previous generation to form a new generation of population. Steps 2.1 to 2.2 are repeated until the preset number of evolutionary generations is reached or the fitness no longer improves after several consecutive generations, at which point the termination condition is met. Step 2.3: The genetic algorithm execution engine stops iterating and outputs the chromosome with the highest fitness value in the final population as the optimization result.

6. The equipment-based production scheduling method for the automotive parts industry according to claim 1, characterized in that, In step 2.2, the fitness evaluation, selection, crossover, and mutation operations during the iteration process specifically include: Fitness assessment operation: For each chromosome in the population, perform lightweight decoding to simulate production scheduling, and calculate the fitness score based on the simulation results; Selection operation: Based on fitness scores, select dominant individuals from the current population to enter the crossover pool; Crossover operation: Select parent chromosomes from the crossover pool, exchange some continuous gene locus intervals between them, and generate offspring chromosomes; Mutation operation: Randomly select a portion of gene loci in the offspring chromosome, apply random perturbation or reset to their batch number decision value, and ensure that the result value meets the batch number constraint of the window.

7. The equipment-based production scheduling method for the automotive parts industry according to claim 2, characterized in that, Step 3 specifically includes: After obtaining the chromosome with the highest fitness value, the genetic algorithm execution engine performs a complete and final decoding on that chromosome, generating a well-formatted scheduling result object, which specifically includes: Detailed layer: Each record describes the production schedule quantity for a specific day, production line, or material; Indicator layer: Includes total demand, total gap, fulfillment rate of each material, inventory curve statistics, mold change frequency, etc., used for scoring and diagnosis.

8. An equipment-based production scheduling system for the automotive parts industry, implementing the equipment-based production scheduling method for the automotive parts industry as described in any one of claims 1-7, characterized in that, The system specifically includes: The context building layer is used to perform input data preprocessing, generate daily demand sequences, calculate batch and capacity, plan continuous production windows, and build a context containing all scheduling input parameters. The genetic algorithm execution engine layer is used to perform chromosome initialization, iterative optimization, and final batch decision selection. The scheduling decoder layer is used to decode the chromosome with the highest fitness value into a complete scheduling plan result.

9. The equipment-based production scheduling system for the automotive parts industry according to claim 8, characterized in that, The preprocessing and planning module includes: Demand decomposer, used to handle the discounting of common product demand; The continuous production planner is used to generate continuous production window segments.

10. The equipment-type production scheduling system for the automotive parts industry according to claim 8, characterized in that, The genetic algorithm execution engine includes: The chromosome factory is used to randomly generate a set of initial chromosomes based on the number of continuous production segments on the production line, forming an initial population of chromosomes. Each chromosome in the initial population corresponds to an integer array, and each position in the array represents the number of production batches installed in a continuous production segment of the production line. The crossover operator is used to select parent chromosomes from the crossover pool and make batch number decisions by exchanging some continuous gene locus intervals to generate offspring chromosomes. The mutation operator is used to randomly select a portion of gene loci in the offspring chromosome and apply random perturbation or reset to the batch number decision value so that the result value satisfies the batch number constraint of the window. A fitness evaluator is used to decode each chromosome in the chromosome population to simulate production scheduling and calculate a fitness score based on the simulation results. The underlying general-purpose genetic algorithm engine framework serves as the execution skeleton of the genetic algorithm engine, used to manage the complete lifecycle of chromosome population evolution.

Images