Manufacturing system intelligent production scheduling method and system

Abstract

The invention relates to the technical field of intelligent manufacturing, in particular to an intelligent production scheduling method and system for a manufacturing system, and the method comprises the following steps: collecting an equipment state, a material neat rate and an order emergency degree in real time based on dynamic production data, and calculating an equipment availability coefficient, a material guarantee index and an order priority score through feature analysis; and forming a dynamic production feature set. The system constructs a production scheduling optimization model through work order-equipment matching degree calculation and process priority optimization, and performs multi-objective optimization solution by adopting an NSGA-III algorithm to realize the optimal combination of equipment utilization rate, order delivery rate and inventory balance. Meanwhile, an arbitration mechanism is introduced to coordinate process priority conflicts, and the scheme is verified through time, space and dynamic adaptability, so that feasibility and stability of production scheduling execution are ensured. According to the invention, the production scheduling efficiency of the manufacturing system can be improved, the equipment utilization rate can be improved, the order delivery delay rate can be reduced, and the adaptive ability to the change of the production environment can be enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent manufacturing, and particularly relates to an intelligent production scheduling method and system for a manufacturing system. Background Art

[0002] In modern manufacturing systems, intelligent production scheduling is a key link to improve production efficiency, optimize resource allocation, and reduce manufacturing costs. With the development of the manufacturing industry towards intelligence and flexibility, the production environment has become increasingly complex, and manufacturing enterprises need to manage multiple production lines, a large number of production equipment, and orders with different priorities simultaneously. Under this background, the production scheduling system not only needs to meet the process sequence and equipment resource constraints, but also needs to consider multi-dimensional factors such as order urgency, material supply situation, and production load balance to ensure the rationality of the production plan and the stability of execution.

[0003] The production scheduling methods of existing manufacturing systems have technical limitations in many aspects. On the one hand, traditional production scheduling methods lack the ability to analyze dynamic production data in real time, and do not fully consider real-time factors such as equipment status, material supply, and order priority, resulting in the production scheduling plan being unable to adapt to sudden changes in the production process. On the other hand, the current production scheduling optimization models are mostly single-objective optimization or static optimization, and do not comprehensively consider multiple optimization objectives such as equipment utilization rate, order delivery on-time rate, and inventory balance, resulting in the production scheduling plan lacking flexibility and adjustability in the actual execution process. In addition, when dealing with priority conflicts and resource allocation constraints, existing systems usually adopt fixed rules or empirical adjustments, lacking an intelligent decision-making and feedback learning mechanism, and it is difficult to achieve adaptive optimization of production scheduling. Summary of the Invention

[0004] Based on the above purposes, the present invention provides an intelligent production scheduling method and system for a manufacturing system.

[0005] An intelligent production scheduling method for a manufacturing system includes the following steps:

[0006] S1: Real-time obtain the dynamic production data of the manufacturing system, including equipment status data, material availability rate data, and order urgency data;

[0007] S2: Conduct feature analysis on the dynamic production data to generate a dynamic production feature set including equipment availability coefficient, material guarantee index, and order priority score;

[0008] S3: Input the dynamic production feature set into a resource matching model, calculate the matching degree matrix between each work order and equipment, and generate an initial equipment-work order mapping relationship;

[0009] S4: Based on the order priority score in the dynamic production feature set, trigger a cross-process priority adjustment mechanism to generate a dynamic process priority sequence;

[0010] S5: Combine the dynamic process priority sequence with the equipment-work order mapping relationship, and generate a production scheduling plan through a multi-objective optimization model.

[0011] Optionally, the S1 includes:

[0012] S11, Equipment status data collection: Through the OPC UA protocol interface and MQTT Internet of Things gateway deployed on the manufacturing equipment, collect equipment status data in real time, including real-time load rate, fault shutdown signal, and theoretical processing speed;

[0013] S12, Calculation of material availability rate: Call the material availability rate calculation unit, and calculate the material availability rate of each work order based on the work order BOM list and WMS inventory record provided by the manufacturing system;

[0014] S13, Calculation of order urgency: Analyze the production order data stream in the manufacturing system and extract order urgency data;

[0015] S14, Dynamic production database: Establish a dynamic production database, and store the equipment status data, material availability rate data, and order urgency data in the distributed time-series database after aligning them by timestamp;

[0016] S15, Start the data synchronization engine, and push the equipment status data in the dynamic production database to the resource matching model in real time, synchronize the material availability rate data to the work order screening unit, and input the order urgency data into the priority calculation engine.

[0017] Optionally, the S2 includes:

[0018] S21, Calculate the equipment availability coefficient: Based on the collected equipment status data, calculate the equipment availability coefficient;

[0019] S22, Calculate the material guarantee index: Based on the calculated material availability rate data, generate the material guarantee index;

[0020] S23, Calculate the order priority score: Based on the obtained order urgency data, calculate the order priority score;

[0021] S24, Normalization processing: Perform normalization processing on the equipment availability coefficient, material guarantee index, and order priority score;

[0022] S25, Generate and store the dynamic production feature set: Based on the normalized equipment availability coefficient, material guarantee index, and order priority score, generate the dynamic production feature set and store it in the feature warehouse.

[0023] Optionally, the S3 includes:

[0024] S31. Construct a work order - equipment matching degree matrix: Calculate the matching degree between the work order and the equipment based on the equipment availability coefficient, material support index, and order priority score in the dynamic production feature set;

[0025] S32. Apply the equipment constraint rule base: Invoke the equipment process constraint database to screen and adjust the work order - equipment matching degree matrix;

[0026] S33. Execute dynamic weight adjustment: Trigger the matching degree adjustment according to the real - time load status;

[0027] S34. Generate an initial equipment - work order mapping: Use the Hungarian algorithm to solve the optimal allocation scheme of the work order - equipment matching degree matrix.

[0028] Optionally, S3 further includes:

[0029] S35. Conflict depth analysis: Classify the conflicting work orders in the initial mapping, including equipment overload - type conflicts and process - conflict - type conflicts;

[0030] S36. Intelligent re - allocation strategy: According to the conflict type, adopt different optimization strategies for adjustment;

[0031] S37. Generate the final mapping relationship: Based on the optimized work order - equipment matching result, generate a structured production schedule table and register the equipment - work order binding relationship in the distributed task management system.

[0032] Optionally, S4 includes:

[0033] S41. Priority conflict detection and triggering: During the dynamic production process, continuously monitor the priority score of the order, identify the priority conflicts that affect the production rhythm, and trigger the adjustment mechanism when any of the following conditions is met:

[0034] Emergency order insertion trigger: If the priority score of an order suddenly increases by 30% or more compared with the previous moment, it indicates that the urgency of this order has increased significantly, and adjust the process priority;

[0035] Unbalanced priority distribution within the equipment queue: If the difference in the priority scores of the work orders for the same equipment exceeds 50%, it is necessary to re - evaluate the rationality of production scheduling;

[0036] Abnormal priority of the subsequent process: If the priority of the order to which a process belongs is 20% higher than that of its previous process, it may lead to conflicts in the production scheduling order, and adjust the process priority;

[0037] S42. Process - level priority quantitative calculation: In order to accurately evaluate the priority of the process, extract the process attributes from the process knowledge base and calculate its inherent priority;

[0038] S43, Dynamic mapping of work order - level priority: Map the order priority score to specific processes and establish a dynamic adjustment mechanism for process priority;

[0039] S44, Execution of cross - level arbitration algorithm: When there is a conflict between the inherent process priority and the work order priority, execute the hierarchical arbitration mechanism to ensure the rationality of priority adjustment;

[0040] S45, Generation and verification of dynamic sequence: After completing the adjustment of process priority, generate the final dynamic process priority sequence and verify it.

[0041] Optionally, the S5 includes:

[0042] S51, Initialization of scheduling time - space framework: Based on the initial equipment - work order mapping relationship and the generated dynamic process priority sequence, construct the scheduling time - space framework, which includes the division of the time axis and the space axis to ensure the accuracy of production scheduling and the feasibility of execution;

[0043] S52, Construction of multi - objective optimization model: During the scheduling optimization process, establish the objective function of scheduling optimization to achieve the optimal coordination relationship among equipment utilization rate, order delivery timeliness, and inventory balance;

[0044] S53, Loading of composite constraint conditions: During the scheduling optimization process, load multi - dimensional constraint conditions to ensure the executability of the plan and its compliance with the actual production situation. The constraint conditions include equipment constraints, process sequence constraints, and material constraints.

[0045] Optionally, the S5 further includes:

[0046] S54, Execution of hierarchical solution strategy: To ensure the efficiency of the optimization process, use the NSGA - III algorithm for multi - objective optimization solution and gradually optimize the scheduling plan through a hierarchical strategy.

[0047] S55, Time - space verification of scheduling plan: After optimization, conduct a comprehensive verification of the scheduling plan to ensure its executability, rationality, and adaptability.

[0048] S56, Structured output of scheduling plan: After verification, generate a standardized scheduling plan and push the execution instruction to ensure that the scheduling plan can be accurately executed.

[0049] An intelligent scheduling system for a manufacturing system, which is used to implement the above - mentioned intelligent scheduling method for a manufacturing system, includes the following modules:

[0050] Data acquisition module: Used to obtain the dynamic production data of the manufacturing system in real - time, including equipment status data, material availability rate data, and order urgency data;

[0051] Feature Analysis Module: Analyze the features of the collected dynamic production data, calculate the equipment availability coefficient, material support index, and order priority score, and generate a dynamic production feature set;

[0052] Resource Matching Module: Based on the dynamic production feature set, calculate the work order-equipment matching degree matrix, and combine equipment constraints, process requirements, and production load conditions to generate an initial equipment-work order mapping relationship;

[0053] Dynamic Priority Adjustment Module: Dynamically calculate the process priorities, construct a priority sequence by integrating process complexity, equipment bottleneck degree, and order urgency, and use an arbitration mechanism to adjust process priority conflicts;

[0054] Scheduling Optimization Module: Construct a multi-objective optimization model, based on equipment utilization rate, order delivery timeliness, and inventory balance objectives, apply the NSGA-III algorithm to optimize equipment allocation, and use a hierarchical solution strategy to optimize the scheduling plan;

[0055] Scheduling Plan Verification Module: Conduct multi-dimensional verification on the optimized scheduling plan, including time feasibility verification, space rationality verification, and dynamic adaptability verification;

[0056] Scheduling Plan Execution Module: Generate a structured scheduling plan, including an equipment-dimension scheduling table and a work order-dimension progress tracking table, and push equipment instructions, material distribution plans, and quality inspection trigger information to the manufacturing system.

[0057] Advantages of the present invention:

[0058] In the present invention, based on the real-time collected equipment status, material availability rate, and order urgency, the equipment availability coefficient, material support index, and order priority score are calculated to form a dynamic production feature set. Through the calculation of work order-equipment matching degree, the optimization of process priorities, and the multi-objective optimization model, the system can achieve the optimal matching of equipment resources while ensuring the rationality of the process sequence, reduce the idle time of equipment, and improve the overall utilization rate of equipment. At the same time, through the dynamic load balancing strategy, the difference in equipment load rates is controlled within a reasonable range, avoiding the long-term overloading or inefficient operation of some equipment, thereby optimizing production scheduling and improving the overall production capacity.

[0059] In the present invention, by constructing dynamic priority sequences at the process level and work order level, and combining factors such as order urgency, criticality of the process path, and equipment bottleneck coefficient, the priority of production tasks is reasonably adjusted to ensure that high-priority orders are completed first. The system adopts a cross-level arbitration mechanism to coordinate the inherent priority of processes and the priority of work orders, and introduces historical optimization data for decision-making when necessary, making the production scheduling more accurate. In addition, the system integrates functions of material guarantee analysis and inventory balance optimization, and can dynamically adjust the production plan according to the material arrival time, reduce production interruptions caused by material shortages, improve the on-time delivery rate of orders, and ensure the continuity and stability of the production process.

[0060] In the present invention, the production plan is optimized through a hierarchical solution strategy and the NSGA-III algorithm. On the premise of ensuring that process constraints are met, the equipment utilization rate, order delivery rate, and inventory management reach an optimal balance. After optimization, the system verifies through time, space, and dynamic adaptability to ensure the feasibility of the production plan in the actual production environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0062] Figure 1 It is a schematic flow chart of the method according to an embodiment of the present invention;

[0063] Figure 2 It is a schematic flow chart of the system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] The present invention will be described in detail below in conjunction with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; moreover, the drawings are only for more specifically describing the embodiments, and are not intended to specifically limit the present invention.

[0065] It should be pointed out that in the specification, it is mentioned that "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicate that the described embodiments may include specific features, structures, or characteristics, but not necessarily every embodiment includes such specific features, structures, or characteristics. In addition, when combining embodiments to describe specific features, structures, or characteristics, implementing such features, structures, or characteristics in combination with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the relevant art.

[0066] Generally, terms can be understood at least in part from their use in context. For example, depending at least in part on the context, the term "one or more" as used herein can be used to describe any feature, structure, or property in the singular sense, or can be used to describe a combination of features, structures, or properties in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey a set of exclusive factors, but rather can alternatively, depending at least in part on the context, allow for the existence of other factors that are not necessarily explicitly described.

[0067] As Figure 1 shown, a method for intelligent production scheduling of a manufacturing system includes the following steps:

[0068] S1: Obtain the dynamic production data of the manufacturing system in real time, including equipment status data, material availability rate data, and order urgency data;

[0069] S2: Conduct feature analysis on the dynamic production data to generate a dynamic production feature set including equipment availability coefficient, material guarantee index, and order priority score;

[0070] S3: Input the dynamic production feature set into the resource matching model, calculate the matching degree matrix between each work order and the equipment, and generate an initial equipment-work order mapping relationship;

[0071] S4: Trigger a cross-process priority adjustment mechanism based on the order priority score in the dynamic production feature set to generate a dynamic process priority sequence;

[0072] S5: Combine the dynamic process priority sequence with the equipment-work order mapping relationship, and generate a production scheduling plan through a multi-objective optimization model.

[0073] S1 includes:

[0074] S11, Equipment status data acquisition: Real-time acquisition of equipment status data through the OPC UA protocol interface and MQTT Internet of Things gateway deployed on the manufacturing equipment, including real-time load rate, fault shutdown signal, and theoretical processing speed, where:

[0075] The real-time load rate of the equipment is expressed as: where L t is the load rate of the equipment at time t, C t is the current actual processing capacity of the equipment, and C max is the theoretical maximum processing capacity of the equipment;

[0076] The fault shutdown signal is expressed as: where F t is the status flag of the equipment at time t, 1 indicates a fault, and 0 indicates normal;

[0077] The theoretical processing speed is expressed as: where V theo is the theoretical processing speed of the equipment, P rated is the rated power of the equipment, and E rated is the rated energy consumption of the equipment;

[0078] S12, Calculation of material completeness rate: Call the material completeness rate calculation unit, and based on the work order BOM list and WMS inventory records provided by the manufacturing system, calculate the material completeness rate of each work order. The specific calculation process is as follows:

[0079] Traverse the types of materials required for the work order and mark the number of types of materials that have arrived in the warehouse and passed quality inspection;

[0080] Statistically calculate the historical average delay time of materials with delayed arrivals;

[0081] The calculation of the material completeness rate is expressed as: where R m is the material completeness rate, N arr is the number of types of materials that have arrived in the warehouse and passed quality inspection, N total is the total number of types of materials required for this work order, P delay is the proportion of materials with delayed arrivals, and the calculation is: where N delay is the number of types of materials expected to have delayed arrivals

[0082] The historical average delay time of materials with delayed arrivals is expressed as: where T delay is the historical average delay time, and T delay,i is the historical delay time of the i-th type of material;

[0083] S13, Calculation of order urgency: Analyze the production order data stream in the manufacturing system and extract the order urgency data, which specifically includes:

[0084] The urgency of the delivery date is expressed as: where U d is the urgency of the delivery date, T rem is the remaining production time of the order, T std is the standard production cycle of the order, and C cust is the customer level coefficient;

[0085] The dynamic penalty factor is expressed as: where P penalty is the dynamic penalty factor, N late is the number of orders with delivery date defaults for this customer in historical orders, and N total is the total number of cooperative orders of this customer;

[0086] The calculation of the order urgency is expressed as: U o= U d × (1 - P penalty ) + I exp × W exp , where U o is the order urgency, I exp is the urgent order flag, with a value of 0 or 1, and W exp is the preset weight of the urgent order;

[0087] S14, Dynamic Production Database: Establish a dynamic production database, align the equipment status data, material availability rate data, and order urgency data by timestamp and store them in a distributed time series database. The data structure includes:

[0088] Equipment Status Table: The fields include equipment ID, collection timestamp, load rate, and fault code;

[0089] Material Availability Table: The fields include work order number, material code, availability status, and expected arrival time;

[0090] Order Urgency Table: The fields include order number, urgency score, customer level, and delivery deadline:

[0091] S15, Start the data synchronization engine, push the equipment status data in the dynamic production database to the resource matching model in real time, synchronize the material availability rate data to the work order screening unit, and input the order urgency data into the priority calculation engine.

[0092] S2 includes:

[0093] S21, Calculate the equipment availability factor: Based on the collected equipment status data, calculate the equipment availability factor, specifically as follows:

[0094] The failure shutdown rate is expressed as: where R fault is the equipment failure shutdown rate, T fault,total is the total historical failure shutdown duration of the equipment, and T run,total is the cumulative operation duration of the equipment;

[0095] The current load rate is expressed as: where L cur is the current load rate, N WIP is the current in-process quantity, T std is the standard man-hour per piece, and T avail is the equipment available time window.

[0096] The load rate saturation factor is expressed as:

[0097] The equipment availability factor is calculated as: A equip = C theo × (1 - min(Rfault , 0.3)) × (1 - F load ), where A equip is the equipment availability factor, and the theoretical production capacity C of the equipment theo is extracted from the equipment factory parameter library;

[0098] S22, calculate the material support index: Based on the calculated material completeness rate data, generate the material support index, specifically as follows:

[0099] Extract the completeness status and expected arrival time of each work order in the S14 material completeness table;

[0100] The on-time arrival probability of materials within the next T hours is expressed as: where P on-time is the on-time arrival probability, T delay,avg is the historical average delay time, and T buffer is the remaining buffer time;

[0101] The material support index is expressed as: where I mat is the material support index, R m is the current completeness rate, W on-time is the on-time probability weight, N miss is the number of types of uncompleted materials, and P on-time,i is the on-time probability of the i-th type of uncompleted material, and W critical,i is the criticality weight of the i-th type of uncompleted material;

[0102] S23, calculate the order priority score: Based on the obtained order urgency data, calculate the order priority score, specifically as follows:;

[0103] The product profit margin is expressed as: P profit = P sell - P BOM - P proc where P profit is the product profit margin, P sell is the selling price, P BOM is the BOM cost, and P proc is the processing cost;

[0104] The process complexity compensation factor is expressed as: F complex = 1 + N process × 0.05, where N process is the number of process operations;

[0105] The order priority score is expressed as: S order = U o × C cust × P profit × F complex, where S order is the order priority score, U o is the order urgency, and the customer level coefficient C cust is obtained from the CRM system and can be divided into:

[0106]

[0107] S24, normalization processing: Normalize the equipment availability coefficient, material support index, and order priority score as follows:

[0108] The normalized equipment availability coefficient is expressed as: where A equip,norm is the normalized equipment availability coefficient, and A max is the maximum availability coefficient of the production line;

[0109] The piecewise normalization of the material support index is expressed as:

[0110]

[0111] The order priority score is normalized according to the Pareto distribution and expressed as: S order,norm = F pareto (S order ), where F pareto (x) is the Pareto distribution mapping function;

[0112] S25, generate and store the dynamic production feature set: Based on the normalized equipment availability coefficient, material support index, and order priority score, generate the dynamic production feature set and store it in the feature warehouse:

[0113] The data structure of the feature set contains a triple primary key of timestamp, equipment ID, and work order number;

[0114] Each record contains: the normalized equipment availability coefficient, the normalized material support index, and the percentile order priority score;

[0115] Establish a feature version management mechanism to retain historical feature snapshots for feedback correction calls.

[0116] S3 includes:

[0117] S31, construct the work order - equipment matching degree matrix: Based on the equipment availability coefficient, material support index, and order priority score in the dynamic production feature set, calculate the matching degree between the work order and the equipment as follows:

[0118] The processing adaptability is expressed as: M process = A equip,norm × W equip , where M process is the processing adaptability, and Aequip,norm is the normalized equipment availability factor, W equip is the weight of the matching degree of the equipment type required by the work order.

[0119] The material support degree is expressed as: M material = I mat,norm ×W material , where M material is the material support degree, I mat,norm is the normalized material guarantee index, W material is the criticality weight of the work order materials;

[0120] The priority influence factor is expressed as: where F priority is the priority influence factor, S order,norm is the normalized order priority score, S avg is the average priority benchmark value of the production line;

[0121] S32, apply the equipment constraint rule library: call the equipment process constraint database to screen and adjust the work order - equipment matching degree matrix, as follows:

[0122] Hard equipment type constraint: M total = 0 if the equipment is prohibited from being used in the work order process route;

[0123] If a certain equipment type is clearly restricted in the process requirements of the work order, the corresponding matching degree is set to 0 and the combination is removed;

[0124] Soft precision level constraint: W total,adj = M total ×(1 - D precision ×0.1), where M total,adj is the matching degree after precision constraint adjustment, D precision is the grade difference between the equipment processing precision and the work order requirement precision

[0125] Scheduling time period conflict detection: If C conflict = 1, the matching degree of the equipment to the work order is set to 0 and the conflicting work order is marked;

[0126] S33, perform dynamic weight adjustment: Trigger matching degree adjustment according to the real - time load status, as follows:

[0127] Load balancing mode: If the load rates of the equipment clusters vary greatly (more than 20%), increase the processing adaptability weight to prioritize low - load equipment;

[0128] Emergency order mode: If the order priority score is higher than 90%, increase the weight of the priority impact factor to make it more influential;

[0129] S34. Generate the initial equipment-work order mapping: Solve the optimal allocation plan of the work order-equipment matching degree matrix using the Hungarian algorithm, as follows:

[0130] (1) Work order disassembly: Disassemble the work order into the smallest allocable unit (operation-level task);

[0131] (2) Task-equipment matching: For each operation-level task, select the equipment with the highest matching degree, expressed as: where E * is the optimally matched equipment, and M total,adj (W, E) is the final matching degree of work order W on equipment E;

[0132] (3) Record the unallocated work orders: If a work order cannot be matched with any equipment, record it in the pending queue and attach the conflict reason (such as equipment unavailability, process mismatch, etc.).

[0133] S3 also includes:

[0134] S35. Conflict depth analysis: Classify the conflict work orders in the initial mapping, including equipment overload type conflicts and process conflict type conflicts, as follows:

[0135] Equipment overload type conflict: T alloc (E) > T avail (E), where T alloc (E) is the total duration of the tasks already assigned to equipment E, and T avail (E) is the available time window of equipment E within the production scheduling period,

[0136] If this inequality holds, it means that the equipment has been overloaded with tasks;

[0137] The process conflict type conflict is expressed as: T start (W i , S k ) < T end (W i , S j ) + ΔT safe , where W i represents work order i, S k and S j are two operations of the same work order, T start (W i , S k ) is the start time of operation S k on the equipment, and T end (W i , S j) is the completion time of the previous process S j , ΔT safe is the safety interval of the process sequence;

[0138] S36, intelligent reallocation strategy: According to the conflict type, different optimization strategies are adopted for adjustment, as follows:

[0139] (1) Overload resolution engine:

[0140] Arrange the tasks of the overloaded equipment in descending order of matching degree, expressed as:

[0141] M total (W1, E) ≥ M total (W2, E) ≥ …;

[0142] Arrange the tasks in descending order of matching degree.

[0143] The task migration strategy is expressed as: C migrate = (M total (W, E best ) - M total (W, E alt )) × U o (W), where C migrate is the task migration cost, E best is the original matching equipment, E alt is the sub-optimal matching equipment, U o (W) is the order urgency

[0144] When the sub-optimal equipment is unavailable, trigger the process route reconstruction, expressed as:

[0145] Calculate the new process path and select the available equipment with the highest matching degree;

[0146] (2) Process coordination engine:

[0147] Construct a process dependency graph: Let G(W) = (S, E) be a directed graph composed of the process node S and its allocated equipment E;

[0148] Process sequence correction: Use the backpropagation algorithm to adjust the process allocation to ensure:

[0149] T start (W, S k ) ≥ T end (W, S j ) + ΔT safe ; If the constraint is not satisfied, reallocate the process:

[0150] E1 * is the optimal equipment allocation plan after adjustment;

[0151] Optimization of workstations in a continuous process, denoted as: P adj = 1 - D station × 0.05, where P adj is the process continuity adjustment factor, and D station is the distance between workstations between two processes;

[0152] S37, Generate the final mapping relationship: Based on the optimized work order - equipment matching result, generate a structured production schedule, and register the equipment - work order binding relationship in the distributed task management system to ensure the traceability and consistency of production execution. Specifically, it includes

[0153] Structured production schedule: Generate a structured production schedule containing equipment number, work order number, process number, planned start time, and planned end time. This production schedule is used to guide production execution and provide visual data support at the same time;

[0154] Register the equipment - work order binding relationship: Record the final work order - equipment mapping relationship in the distributed task management system to ensure that the production process can be strictly executed according to the optimized production schedule, and avoid production scheduling failures caused by misoperations or system exceptions;

[0155] Send equipment instructions to the manufacturing execution system: Generate and issue equipment preparation instructions to ensure that the equipment completes preparation work such as preheating and calibration before the task starts. At the same time, generate a material distribution requirement list according to the final production schedule to ensure that relevant materials can be delivered to the processing site on time to avoid production stagnation caused by material shortages.

[0156] S4 includes:

[0157] S41, Priority conflict detection and triggering: During the dynamic production process, continuously monitor the priority scores of orders, identify priority conflicts that affect the production rhythm, and trigger the adjustment mechanism when any of the following conditions is met:

[0158] Emergency order insertion trigger: If the priority score of an order suddenly increases by 30% or more compared to the previous moment, it indicates that the urgency of this order has increased significantly, and adjust the process priority;

[0159] Unbalanced priority distribution within the equipment queue: If the difference in the priority scores of work orders for the same equipment exceeds 50%, it is necessary to re - evaluate the rationality of production scheduling;

[0160] Abnormal priority of the subsequent process: If the priority of the order to which a process belongs is 20% higher than that of its previous process, it may lead to conflicts in the production scheduling order, and adjust the process priority;

[0161] S42, Operation - level Priority Quantification Calculation: To accurately evaluate the priority of operations, operation attributes are extracted from the process knowledge base, and their inherent priorities are calculated, mainly considering the following factors:

[0162] Equipment Bottleneck Coefficient: It is used to measure the scarcity of processing resources for an operation, that is, the ratio of the number of the same type of equipment to the demand of this operation in the entire production line. The scarcer the equipment, the higher the priority of the operation.

[0163] Operation Complexity: It is comprehensively calculated based on factors such as the standard processing time of the operation, processing precision requirements, and the number of fixture replacements. The higher the process complexity, the higher the priority of the operation.

[0164] Calculation of Operation Inherent Priority: Considering the equipment bottleneck coefficient and operation complexity comprehensively, calculate the basic priority of the operation according to the preset weight;

[0165] S43, Work - order - level Priority Dynamic Mapping: Map the order priority score to specific operations, and establish a dynamic adjustment mechanism for operation priorities, as follows:

[0166] (1) Operation Mapping of Work - order Priority: The initial priority of an operation inherits from the priority score of its affiliated order to ensure the consistency of overall scheduling.

[0167] (2) Priority Weight Adjustment for Multi - operation Work - orders is as follows:

[0168] The proportion of completed operations affects the weight of the current operation. The more completed, the relatively lower the importance of subsequent operations.

[0169] The proportion of remaining buffer time measures the time margin for order execution. The priority of operations with tight time needs to be appropriately increased.

[0170] (3) Dynamic Operation Priority Calculation: Combine the order priority score, the progress weight of the current operation, and the criticality factor of the process path to calculate the final operation - level priority to ensure the rationality and flexibility of operation scheduling;

[0171] S44, Cross - level Arbitration Algorithm Execution: When there is a conflict between the operation inherent priority and the work - order priority, execute the hierarchical arbitration mechanism to ensure the rationality of priority adjustment, specifically including:

[0172] Primary Arbitration: Judge whether the difference between the operation inherent priority and the work - order priority is within the tolerance range. If the difference is small, the original priority remains unchanged;

[0173] Secondary Arbitration: If the priority difference exceeds the tolerance range, introduce the real - time load status of the equipment to correct the operation priority. The higher the current idle degree of the equipment, the corresponding operation priority can be appropriately increased to make full use of production resources;

[0174] Final arbitration: When consensus still cannot be reached, call the historical decision database to retrieve the optimal scheduling plan for similar scenarios. The weighted voting method is used to comprehensively consider the equipment status, material support situation, and order urgency to determine the final process priority;

[0175] S45, Dynamic sequence generation and verification: After completing the adjustment of process priorities, generate the final dynamic process priority sequence and verify it, specifically including:

[0176] Priority sequence generation: Sort according to the final priority scores. High-priority processes are preferentially scheduled into the scheduling plan. For processes with the same priority, the earliest executable tasks are preferentially selected to reduce equipment idle time.

[0177] Process constraint verification includes:

[0178] Predecessor process check: Ensure that the predecessor processes of the current process have been scheduled in advance to avoid incorrect process sequences.

[0179] Resource conflict detection: Check the availability of equipment, fixtures, and materials during the planned time period to avoid plan execution failures due to resource shortages;

[0180] Output to the production scheduling engine: The final priority sequence is stored in the production scheduling engine in a standardized data format to ensure seamless connection of the production scheduling system to the priority adjustment results;

[0181] Priority feedback learning: To improve the accuracy of subsequent priority calculations, the execution results of arbitration decisions will be stored in the historical decision database and used to optimize the feature weights, specifically as follows:

[0182] (1) Store arbitration decision results: Record the priority plan finally adopted in this arbitration to provide reference for future similar scenarios.

[0183] (2) Dynamically adjust the feature weights as follows:

[0184] If the work order priority is finally adopted, increase the weight of the order urgency in the feature set so that future priority calculations are more inclined to consider the importance of orders.

[0185] If the process priority is finally adopted, increase the weight of the equipment bottleneck coefficient to more accurately reflect the constraints of production line resources.

[0186] (3) Equipment capacity evaluation trigger: If a certain equipment fails in priority adjustment for multiple consecutive arbitrations, it indicates that there is a deviation in the equipment capacity evaluation, and the retraining of the equipment capacity evaluation model will be triggered to optimize the accuracy of subsequent production scheduling calculations.

[0187] S5 includes:

[0188] S51, Initialization of the Scheduling Space-Time Framework: Based on the initial equipment-work order mapping relationship and the generated dynamic process priority sequence, construct the scheduling space-time framework, which includes the division of the time axis and the space axis to ensure the accuracy of production scheduling and the feasibility of execution, as follows:

[0189] Time Axis Division: Divide the entire scheduling period into fixed time windows, with the basic unit of each time window set to 15 minutes to ensure the accuracy of time management and improve the flexibility of scheduling adjustments. For critical processes with higher priorities, use 5-minute ultra-fine-grained time windows to enable more precise control of the refined process flow and improve the adaptability of the scheduling plan;

[0190] Space Axis Construction: Based on the physical layout of the workshop, establish a topological map of equipment positions to ensure that the scheduling plan can comprehensively consider equipment distribution, space utilization, and logistics path optimization. Calculate the time cost matrix of material transfer, and combine the space distance between equipment, transfer methods (such as robotic arms, manual handling, or conveyor belts), and transfer priorities to determine the optimal logistics path for each process, reduce the time cost of material handling, and improve the overall production efficiency;

[0191] S52, Construction of the Multi-Objective Optimization Model: During the scheduling optimization process, establish the objective function of scheduling optimization to achieve the optimal coordination relationship among equipment utilization rate, order delivery timeliness, and inventory balance, as follows:

[0192] Equipment Utilization Optimization: The goal is to minimize the idle time of the equipment during the scheduling period while considering the depreciation cost of the equipment to improve the equipment utilization rate and reduce the unit production cost, expressed as:

[0193] where, T idle,i is the total idle time of equipment i during the scheduling period, C depreciation,i is the depreciation cost coefficient of equipment i;

[0194] Order Delivery Optimization: The goal is to maximize the on-time delivery rate of orders, with priority given to the on-time delivery of high-priority orders. By calculating the priority score of the order and the remaining delivery buffer time, ensure that important orders can be scheduled first and reduce the risk of late delivery, expressed as:

[0195] where, S order,j is the priority score of order j, T buffer,j is the remaining delivery time of the order, and σ(x) is the Sigmoid function used to smooth the influence weight of the delivery time;

[0196] Inventory balance optimization: The goal is to reduce the backlog time of work-in-progress inventory and optimize inventory costs. By analyzing the estimated work-in-progress inventory time of processes and the inventory holding costs, ensure that processing is completed within a reasonable time frame to avoid increased capital occupation and management costs caused by inventory backlogs, expressed as:

[0197] where T WIP,k is the estimated work-in-progress inventory time of process k, and C inventory,k is the corresponding inventory holding cost for this process;

[0198] S53, Composite constraint condition loading: During the production scheduling optimization process, load multi-dimensional constraint conditions to ensure the feasibility of the plan and conform to the actual production situation. The constraint conditions include equipment constraints, process sequence constraints, and material constraints, specifically as follows:

[0199] Equipment hard constraint: The maximum continuous working time of the equipment shall not exceed the threshold allowed by its availability factor (the calculation result of S21 in Claim 3 is cited) to prevent the equipment from overloading.

[0200] Process sequence constraint: In the production scheduling plan, it is necessary to ensure that the completion time of the previous process plus the material transfer time is not later than the earliest startable time of the subsequent process to ensure the rationality and continuity of the process flow.

[0201] Appropriate time windows need to be reserved for the critical path processes to reduce the impact of production bottlenecks on the overall production scheduling progress and improve the stability of the overall process.

[0202] Material soft constraint: The earliest executable time of the process must simultaneously meet the equipment available time and the material availability time, and a certain buffer time is reserved to reduce the risk of production interruption caused by equipment or material unavailability.

[0203] S5 also includes:

[0204] S54, Hierarchical solution strategy execution: To ensure the efficiency of the optimization process, the NSGA-III algorithm is used for multi-objective optimization and solution, and the production scheduling plan is gradually optimized through a hierarchical strategy, specifically as follows:

[0205] First-layer optimization: Fix the dynamic process priority sequence to ensure that the scheduling plan strictly conforms to the logical constraints of the process path. Optimize the equipment allocation plan through the Pareto front solution set to ensure the balance among equipment utilization rate, order delivery rate, and inventory management.

[0206] Second - layer optimization: Select solutions that meet the following conditions from the Pareto solution set. The difference in equipment load rates is less than 15%, ensuring the balance of equipment utilization, avoiding some equipment being overloaded for a long time while other equipment is under - loaded, and ensuring that the top - three priority orders can be delivered 100% on time to guarantee the timeliness of high - priority orders.

[0207] Use the TOPSIS method to score the candidate solutions and finally select the production scheduling plan with the highest comprehensive score.

[0208] S55, Space - time verification of the production scheduling plan: After optimization, conduct a comprehensive verification of the production scheduling plan to ensure its executability, rationality, and adaptability, as follows:

[0209] (1) Time feasibility verification: Check whether the time windows between processes overlap to ensure that the production times of all processes do not conflict with each other.

[0210] Verify the consistency between the material delivery time and the start time of the process to ensure that the materials can arrive in time before the process execution to avoid downtime waiting.

[0211] (2) Space rationality verification: Check whether there are conflicts in the material flow paths between equipment to ensure the stability of the logistics system and reduce the impact of logistics bottlenecks on the production scheduling plan.

[0212] Evaluate the working radius of workshop operators to ensure a reasonable division of the working area and reduce the waste of non - production time caused by operators frequently crossing regions for work.

[0213] (3) Dynamic adaptability verification: Conduct simulation tests to evaluate the emergency adjustment ability of the plan in case of sudden equipment failures, ensuring that the production scheduling plan has sufficient flexibility to cope with uncertain factors.

[0214] Simulate the scenario of emergency order insertion and test the adjustable space of the production scheduling plan to ensure that the scheduling system has the ability to respond quickly without affecting the overall production plan.

[0215] S56, Structured output of the production scheduling plan: After verification, generate a standardized production scheduling plan and push the execution instructions to ensure that the production scheduling plan can be accurately executed. The content of the production scheduling plan is as follows.

[0216] (1) Equipment - dimension production scheduling table: Record the operation plans of each equipment, including equipment number, time window, work order number, and process requirements, to ensure that equipment operators can clearly understand the work arrangements.

[0217] (2) Work - order - dimension progress tracking table: Record the planned start and end times of each process in the work order, mark the key path nodes and buffer periods, so that production managers can monitor the order progress at any time and adjust the production scheduling strategy in a timely manner.

[0218] (3) Push execution instructions to the manufacturing system: Send equipment preparation instructions to ensure that the equipment completes preparation work such as preheating and calibration before the start of the process, generate a material distribution schedule to ensure that materials can be delivered to the production area on time, avoid production interruptions caused by material shortages, set the quality inspection trigger time point, and automatically trigger quality inspection tasks after the process is executed to ensure synchronous product quality control.

[0219] As Figure 2 shown, an intelligent production scheduling system for a manufacturing system is used to implement the above-mentioned intelligent production scheduling method for a manufacturing system, and includes the following modules:

[0220] Data acquisition module: Used to obtain the dynamic production data of the manufacturing system in real time, including equipment status data, material availability rate data, and order urgency data;

[0221] Feature analysis module: Perform feature analysis on the collected dynamic production data, calculate the equipment availability coefficient, material guarantee index, and order priority score, and generate a dynamic production feature set;

[0222] Resource matching module: Based on the dynamic production feature set, calculate the work order-equipment matching degree matrix, and combine equipment constraints, process requirements, and production load conditions to generate an initial equipment-work order mapping relationship;

[0223] Dynamic priority adjustment module: Dynamically calculate the process priority, construct a priority sequence by integrating process complexity, equipment bottleneck degree, and order urgency, and use an arbitration mechanism to adjust process priority conflicts;

[0224] Scheduling optimization module: Construct a multi-objective optimization model, optimize equipment allocation based on equipment utilization rate, order delivery timeliness, and inventory balance objectives, and use a hierarchical solution strategy to optimize the scheduling plan;

[0225] Scheduling plan verification module: Perform multi-dimensional verification on the optimized scheduling plan, including time feasibility verification, space rationality verification, and dynamic adaptability verification;

[0226] Scheduling plan execution module: Generate a structured scheduling plan, including an equipment dimension scheduling table and a work order dimension progress tracking table, and push equipment instructions, material distribution plans, and quality inspection trigger information to the manufacturing system.

[0227] The present invention encompasses any alternatives, modifications, equivalent methods, and solutions within the spirit and scope of the present invention. To enable the public to have a thorough understanding of the present invention, specific details are elaborated in the following preferred embodiments of the present invention. However, those skilled in the art can fully understand the present invention even without the description of these details. Additionally, well-known methods, processes, procedures, components, and circuits are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0228] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent scheduling method for a manufacturing system, characterized in that, It includes the following steps: S1: Obtain the dynamic production data of the manufacturing system in real time, including equipment status data, material availability rate data, and order urgency data; S2: Conduct feature analysis on the dynamic production data to generate a dynamic production feature set including equipment availability coefficient, material guarantee index, and order priority score; S3: Input the dynamic production feature set into the resource matching model, calculate the matching degree matrix between each work order and equipment, and generate an initial equipment-work order mapping relationship; S4: Trigger the cross-process priority adjustment mechanism based on the order priority score in the dynamic production feature set to generate a dynamic process priority sequence; S5: Combine the dynamic process priority sequence with the equipment-work order mapping relationship, and generate a production scheduling plan through a multi-objective optimization model.

2. The intelligent scheduling method for a manufacturing system according to claim 1, characterized in that, The S1 includes: S11, Equipment status data collection: Real-time collect equipment status data, including real-time load rate, fault shutdown signal, and theoretical processing speed, through the OPC UA protocol interface and MQTT Internet of Things gateway deployed on the manufacturing equipment; S12, Material availability rate calculation: Invoke the material availability rate calculation unit to calculate the material availability rate of each work order based on the work order BOM list and WMS inventory record provided by the manufacturing system; S13, Order urgency calculation: Analyze the production order data stream in the manufacturing system and extract the order urgency data; S14, Dynamic production database: Establish a dynamic production database, and store the equipment status data, material availability rate data, and order urgency data in the distributed time series database after aligning them by timestamp; S15, Start the data synchronization engine, and push the equipment status data in the dynamic production database to the resource matching model in real time, synchronize the material availability rate data to the work order screening unit, and input the order urgency data into the priority calculation engine.

3. The intelligent scheduling method for a manufacturing system according to claim 2, wherein The S2 includes: S21, Calculate the equipment availability coefficient: Calculate the equipment availability coefficient based on the collected equipment status data; S22, Calculate the material guarantee index: Generate the material guarantee index based on the calculated material availability rate data; S23, Calculate the order priority score: Calculate the order priority score based on the obtained order urgency data; S24, Normalization processing: Conduct normalization processing on the equipment availability coefficient, material guarantee index, and order priority score; S25, Generate and store the dynamic production feature set: Generate the dynamic production feature set based on the normalized equipment availability coefficient, material guarantee index, and order priority score, and store it in the feature warehouse.

4. The intelligent scheduling method for a manufacturing system according to claim 3, wherein The S3 includes: S31, Construct the work order-equipment matching degree matrix: Calculate the matching degree between the work order and equipment based on the equipment availability coefficient, material guarantee index, and order priority score in the dynamic production feature set; S32, Apply the equipment constraint rule library: Invoke the equipment process constraint database to screen and adjust the work order-equipment matching degree matrix; S33, Execute dynamic weight adjustment: Trigger the matching degree adjustment according to the real-time load status; S34, Generate the initial equipment-work order mapping: Use the Hungarian algorithm to solve the optimal allocation scheme of the work order-equipment matching degree matrix.

5. The intelligent scheduling method for a manufacturing system according to claim 4, wherein The S3 also includes: S35, Conflict Depth Analysis: Classify the conflict work orders in the initial mapping, including equipment overload conflicts and process conflict types; S36, Intelligent Reallocation Strategy: According to the conflict type, adopt different optimization strategies for adjustment; S37, Generate the Final Mapping Relationship: Based on the optimized work order - equipment matching results, generate a structured production schedule table and register the equipment - work order binding relationship in the distributed task management system.

6. The intelligent scheduling method for a manufacturing system according to claim 5, wherein, The said S4 includes: S41, Priority Conflict Detection and Triggering: During the dynamic production process, continuously monitor the priority scores of orders, identify priority conflicts that affect the production rhythm, and trigger the adjustment mechanism when any of the following conditions is met: Emergency Insertion Order Trigger: If the priority score of an order suddenly increases by 30% or more compared to the previous moment, adjust the process priority; Unbalanced Priority Distribution within the Equipment Queue: If the difference in the priority scores of work orders for the same equipment exceeds 50%, it is necessary to re - evaluate the rationality of production scheduling; Abnormal Priority of the Subsequent Process: If the priority of the order to which a process belongs is 20% higher than that of its previous process, adjust the process priority; S42, Process - Level Priority Quantitative Calculation: Extract process attributes from the process knowledge base and calculate their inherent priorities; S43, Work Order - Level Priority Dynamic Mapping: Map the order priority scores to specific processes and establish a dynamic adjustment mechanism for process priorities; S44, Execution of the Cross - Level Arbitration Algorithm: If a conflict occurs between the inherent process priority and the work order priority, execute the hierarchical arbitration mechanism; S45, Dynamic Sequence Generation and Verification: After completing the adjustment of process priorities, generate the final dynamic process priority sequence and verify it.

7. The intelligent scheduling method for a manufacturing system according to claim 6, wherein The said S5 includes: S51, Initialization of the Scheduling Space - Time Framework: Based on the initial equipment - work order mapping relationship and the generated dynamic process priority sequence, construct the scheduling space - time framework; S52, Construction of the Multi - Objective Optimization Model: During the scheduling optimization process, establish the objective function of scheduling optimization to achieve the optimal coordination relationship among equipment utilization rate, order delivery timeliness, and inventory balance; S53, Loading of Composite Constraint Conditions: During the scheduling optimization process, load multi - dimensional constraint conditions to ensure the executability of the plan and conform to the actual production situation. The constraint conditions include equipment constraints, process sequence constraints, and material constraints.

8. The intelligent scheduling method for a manufacturing system according to claim 7, wherein The said S5 also includes: S54, Execution of the Hierarchical Solving Strategy: Use the NSGA - III algorithm for multi - objective optimization solving and gradually optimize the scheduling plan through the hierarchical strategy; S55, Space - Time Verification of the Scheduling Plan: After optimization, verify the scheduling plan; S56, Structured Output of the Scheduling Plan: After verification, generate a standardized scheduling plan and push the execution instruction.

9. An intelligent production scheduling system for a manufacturing system, which is used to implement an intelligent production scheduling method for a manufacturing system as described in any one of claims 1-8, characterized in that, It includes the following modules: Data Acquisition Module: Used to obtain the dynamic production data of the manufacturing system in real - time, including equipment status data, material availability rate data, and order urgency data; Feature Analysis Module: Conduct feature analysis on the collected dynamic production data, calculate the equipment availability coefficient, material guarantee index, and order priority score, and generate a dynamic production feature set; Resource matching module: Based on the dynamic production feature set, calculate the work order - equipment matching degree matrix, and generate the initial equipment - work order mapping relationship in combination with equipment constraints, process requirements, and production load conditions; Dynamic priority adjustment module: Dynamically calculate the operation priorities, construct a priority sequence by comprehensively considering process complexity, equipment bottleneck degree, and order urgency, and adopt an arbitration mechanism to adjust operation priority conflicts; Scheduling optimization module: Construct a multi - objective optimization model, optimize equipment allocation using the NSGA - III algorithm based on equipment utilization rate, order delivery timeliness, and inventory balance objectives, and optimize the scheduling plan using a hierarchical solution strategy; Scheduling plan verification module: Conduct multi - dimensional verification on the optimized scheduling plan, including time feasibility verification, space rationality verification, and dynamic adaptability verification; Scheduling plan execution module: Generate a structured scheduling plan, including the scheduling table from the equipment dimension and the progress tracking table from the work order dimension, and push equipment instructions, material distribution plans, and quality inspection trigger information to the manufacturing system.

Images