Production scheduling method, device and equipment

Abstract

The invention provides a production scheduling method, device and equipment. The method comprises the following steps: acquiring real-time production data through an intelligent manufacturing system; determining constraint conditions of a target optimization model according to the real-time production data; obtaining a plurality of dimension production targets; determining a composite objective function according to the multi-dimensional production objective; determining a target optimization model according to the constraint condition and the composite target function; iteratively solving the target optimization model through at least one optimization model to obtain a target solution set; and controlling a production schedule module to output a target production schedule according to the target solution set. According to the invention, the scheduling quality and efficiency of the production line are improved, and the adaptability to the dynamic production environment is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial production, and also relates to a production scheduling method, device and equipment. Background Art

[0002] In modern manufacturing, production planning and scheduling (referring to the process of optimizing the allocation of production tasks in terms of time, equipment and personnel under the constraint of limited resources, aiming to maximize efficiency, minimize costs and ensure on-time delivery) is a key link affecting production efficiency, resource utilization rate and cost control. Traditional scheduling methods do not consider the factors of production capacity loss caused by the production and transfer of outsourced orders, and cannot provide strong technical support for the formulation of scheduling plans for multi-process collaboration inside and outside the enterprise. Moreover, single constraint algorithms or low heuristic algorithms are used, and these methods generally have problems such as local convergence, high computational complexity, insufficient adaptability, and difficulty in multi-objective optimization, making it difficult to achieve the best results in the actual industrial environment. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a production scheduling method, device and equipment to improve the efficiency of production planning and scheduling.

[0004] To solve the above technical problems, the technical solution of the present invention is as follows:

[0005] In the first aspect of the present invention, a production scheduling method is provided, including:

[0006] Obtaining real-time production data through an intelligent manufacturing system;

[0007] Determining the constraint conditions of the target optimization model according to the real-time production data;

[0008] Obtaining production targets in multiple dimensions;

[0009] Determining a composite objective function according to the production targets in multiple dimensions;

[0010] Determining the target optimization model according to the constraint conditions and the composite objective function;

[0011] Iteratively solving the target optimization model through at least one optimization model to obtain a target solution set;

[0012] Controlling the production scheduling module to output a target production schedule according to the target solution set.

[0013] Optionally, determining the constraint conditions of the target optimization model according to the real-time production data includes:

[0014] Based on the real-time production data, obtain the process processing time data of each device, the available machine time data of the device, the starting time data of each process, the material availability time data, the safety buffer period data, the sequential grading data of the preset key processes and the allowable adjustment range data, the skill level data of the personnel and the skill requirement level data of each process, the historical utilization rate data of each device and the fluctuation range limit data, the historical energy consumption data per unit output value and the energy consumption reduction rate target data;

[0015] Based on the process processing time data of each device and the available machine time data of the device, determine the first constraint condition;

[0016] Based on the starting time data of each process, the material availability time data and the safety buffer period data, determine the second constraint condition;

[0017] Based on the sequential grading data of the preset key processes and the allowable adjustment range data, determine the third constraint condition;

[0018] Based on the skill level data of the personnel and the skill requirement level data of each process, determine the fourth constraint condition;

[0019] Based on the historical utilization rate data of each device and the fluctuation range limit data, determine the fifth constraint condition;

[0020] Based on the historical energy consumption data per unit output value and the energy consumption reduction rate target data, determine the sixth constraint condition;

[0021] Based on the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, the fifth constraint condition, and the sixth constraint condition, determine the constraint conditions of the target optimization model.

[0022] Optionally, based on the multiple-dimensional production targets, determine a composite objective function, including:

[0023] Based on the multiple-dimensional production targets, determine the core objective function;

[0024] Based on the preset auxiliary objective function and the core objective function, determine the composite objective function.

[0025] Optionally, based on the preset auxiliary objective function and the core objective function, determine the composite objective function, including:

[0026] Obtain the preset auxiliary objective function; the preset auxiliary objective function includes maximizing the equipment utilization rate;

[0027] Based on the preset auxiliary objective function and the core objective function, determine the composite objective function; the composite objective function is min(C - λU);

[0028] Among them, C = ∑(P + S + E);

[0029] Among them, min(C - λU) is the composite objective function, C is the total cost in the core objective function, λ is the weight coefficient, U is the maximized equipment utilization rate, P is the penalty cost for delivery deviation, S is the changeover cost, and E is the energy consumption cost.

[0030] Optionally, through at least one optimization model, the target optimization model is iteratively solved to obtain a target solution set, including:

[0031] Determine equipment disturbance events according to the real-time monitoring data of production equipment;

[0032] Determine order-level disturbance events according to the real-time order data;

[0033] Determine resource-level disturbance events according to the real-time personnel data and material supply data;

[0034] Determine a combination of at least one optimization model according to the equipment disturbance events, the order-level disturbance events, the resource-level disturbance events, and multi-dimensional preset performance indicators to obtain an optimized combined model;

[0035] Iteratively solve the target optimization model according to the optimized combined model to obtain a target solution set.

[0036] Optionally, when the optimized combined model includes a first optimization sub-model, a second optimization sub-model, and a third optimization sub-model, iteratively solve the target optimization model according to the optimized combined model to obtain a target solution set, including:

[0037] Obtain a preset random initial solution set;

[0038] Perform a global search according to the first optimization sub-model and the preset random initial solution set to obtain a first optimal solution;

[0039] Perform a local search according to the second optimization sub-model and the first optimal solution to obtain a second optimal solution;

[0040] Perform disturbance processing according to the third optimization sub-model and the second optimal solution to obtain a target solution set.

[0041] Optionally, according to the target solution set, control the production scheduling module to output a target production schedule, including:

[0042] Determine a production task list according to the target solution set; the production task list includes the quantity, priority, and delivery date of production tasks;

[0043] Determine resource allocation according to the production task list; the resource allocation includes equipment resources, human resources, and material resources;

[0044] Determine the target production schedule according to the production task list and the resource allocation;

[0045] Control the production scheduling module to output the target production schedule.

[0046] The second aspect of the present invention provides a production scheduling device, including:

[0047] The first acquisition module is used to acquire real-time production data through the intelligent manufacturing system;

[0048] The first determination module is used to determine the constraint conditions of the target optimization model according to the real-time production data;

[0049] The second acquisition module is used to acquire production targets in multiple dimensions;

[0050] The second determination module is used to determine the composite objective function according to the production targets in multiple dimensions;

[0051] The third determination module is used to determine the target optimization model according to the constraint conditions and the composite objective function;

[0052] The processing module is used to iteratively solve the target optimization model through at least one optimization model to obtain a target solution set;

[0053] The control module is used to control the production scheduling module to output the target production schedule according to the target solution set.

[0054] The third aspect of the present invention provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method described in the first aspect.

[0055] The fourth aspect of the present invention provides a computer-readable storage medium storing instructions. When the instructions are run on a computer, the computer is caused to execute the method described in the first aspect.

[0056] The above solutions of the present invention at least include the following beneficial effects:

[0057] In the above solution of the present invention, real-time production data is obtained through an intelligent manufacturing system, and the constraint conditions of the target optimization model are determined based on this; multiple-dimensional production targets are obtained, and a composite objective function is determined based on this; then, according to the constraint conditions and the composite objective function, a target optimization model is determined, and through at least one optimization model, the target optimization model is iteratively solved to obtain a target solution set. Finally, according to the target solution set, the production scheduling module is controlled to output a target production schedule, which improves the quality and efficiency of the production line scheduling and enhances the adaptability to the dynamic environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 is a schematic flowchart of the production scheduling method in an embodiment of the present invention;

[0059] Figure 2 is a schematic flowchart of solving the target optimization model in an embodiment of the present invention;

[0060] Figure 3 is a schematic structural diagram of the production scheduling device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0061] Hereinafter, exemplary embodiments of the present invention will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present invention can be more thoroughly understood and the scope of the present invention can be completely conveyed to those skilled in the art.

[0062] As Figure 1 shown, an embodiment of the present invention provides a production scheduling method, including the following steps:

[0063] Step 101, obtaining real-time production data through an intelligent manufacturing system;

[0064] Step 102, determining the constraint conditions of the target optimization model according to the real-time production data;

[0065] Step 103, obtaining multiple-dimensional production targets;

[0066] Step 104, determining a composite objective function according to the multiple-dimensional production targets;

[0067] Step 105, determining a target optimization model according to the constraint conditions and the composite objective function;

[0068] Step 106, iteratively solving the target optimization model through at least one optimization model to obtain a target solution set;

[0069] Step 107: Control the production scheduling module to output a target production schedule according to the target solution set.

[0070] The production scheduling method proposed in the embodiment of the present invention obtains real-time production data through an intelligent manufacturing system and determines the constraint conditions of the target optimization model based on this; by obtaining production targets in multiple dimensions and determining a composite objective function based on this; then determining the target optimization model according to the constraint conditions and the composite objective function, and iteratively solving the target optimization model through at least one optimization model to obtain a target solution set, and finally controlling the production scheduling module to output a target production schedule according to the target solution set, improving the quality and efficiency of the production line scheduling and enhancing the adaptability to the dynamic environment.

[0071] In an optional embodiment of the present invention, step 101 includes:

[0072] Obtain real-time first data from the manufacturing execution system; the first data includes work order data, production progress data, and equipment utilization data;

[0073] Obtain real-time second data from the enterprise resource planning system (ERP); the second data includes bill of materials data, inventory data, and production plan data;

[0074] Obtain real-time third data from Internet of Things (IoT) devices through sensors; the third data includes equipment status data and production environment parameter data;

[0075] Preprocess the first data, the second data, and the third data to obtain real-time production data.

[0076] Specifically, the intelligent manufacturing system may include a manufacturing execution system (MES), an enterprise resource planning system (ERP), and Internet of Things (IoT) devices. The manufacturing execution system (MES) can collect production data in real time, and these data include work order data, production progress data, equipment utilization data, etc. Through the equipment data acquisition function, barcode scanning function, and data interface with production equipment of the MES system, the operating status, output, and fault information of the production line can be obtained in real time. The enterprise resource planning system (ERP) stores key information such as the production plan, material requirements, and inventory status of the enterprise. Through integration with the MES system, the ERP system can share these data with the MES system in real time, and at the same time, the MES system also feeds back the real-time data in the production process to the ERP system to achieve two-way data intercommunication. Internet of Things (IoT) devices such as sensors and wireless monitoring devices can monitor various parameters in the production process in real time, such as temperature, pressure, humidity, vibration, etc., and transmit these data to the MES system through wireless or wired networks, providing an important basis for production decision-making. Real-time production data is the basis for subsequent determination of the target optimization model and the target production schedule.

[0077] It should be noted that collection methods such as Ethernet mode, ordinary Ethernet mode, data acquisition card, configuration software acquisition, and manual assistance can cover data in all aspects such as production equipment, personnel, raw materials and materials, production processes and procedures. Therefore, collection methods such as Ethernet mode, ordinary Ethernet mode, data acquisition card, configuration software acquisition, and manual assistance can also be used to obtain real-time production data.

[0078] Here, the preprocessing methods can be integration and cleaning, or data format conversion, outlier processing, and data fusion to ensure the accuracy and consistency of the data.

[0079] In an optional embodiment of the present invention, step 102 includes:

[0080] Step 1021, based on the real-time production data, obtain the process processing time data of each device, the available machine time data of the device, the start time data of each process, the material availability time data, the safety buffer period data, the sequential grading data of the preset key processes and the allowable adjustment range data, the skill level data of the personnel and the skill requirement level data of each process, the historical utilization rate data of each device and the fluctuation range limit data, the historical energy consumption data per unit output value and the energy consumption reduction rate target data;

[0081] Specifically, the above various data are included in the real-time production data or calculated based on the real-time production data, providing a data basis for subsequent determination of various constraint conditions.

[0082] Step 1022, based on the process processing time data of each device and the available machine time data of the device, determine the first constraint condition;

[0083] Specifically, for each device, the sum of the processing times of all its processes should not exceed the available machine time of the device. Therefore, the first constraint condition is the device capacity constraint: ∑ process processing time ≤ available machine time (including reserved maintenance window).

[0084] Step 1023, based on the start time data of each process, the material availability time data, and the safety buffer period data, determine the second constraint condition;

[0085] Specifically, the start time of each process should not be earlier than the material availability time plus the safety buffer period. Therefore, the second constraint condition is the material hard constraint: process start time ≥ material availability time + safety buffer period.

[0086] Step 1024, based on the sequential grading data of the preset key processes and the allowable adjustment range data, determine the third constraint condition;

[0087] Specifically, the third constraint is the process sequence constraint: the strictness of the key process sequence is graded (limited flexibility adjustment is allowed). The order of key processes should follow a strict hierarchy, but flexible adjustment is allowed within a limited range. This usually requires setting a priority matrix for the process sequence and determining it in combination with the actual adjustment range. In a specific embodiment, a production process includes the following five processes: A: raw material preparation, B: preliminary processing, C: key heat treatment, D: fine processing, E: quality inspection. The priorities of these processes are set according to their importance and the impact on the overall production process. At the same time, the strictness of the sequence of key processes is graded, and limited adjustments are allowed on non-key processes. The priority matrix is shown in Table 1.

[0088] Table 1 Priority Matrix

[0089] Process Priority Criticality classification Adjustable range A 2 Low Large B 3 Medium Medium C 5 High None (strict) D 4 Medium Medium E 1 Low Large

[0090] Priority: A higher value indicates a higher priority. In Table 1, quality inspection (E), although the lowest priority, may be the last necessary step in actual production to ensure product quality. Critical heat treatment (C) has the highest priority because it is a key factor affecting product quality and performance.

[0091] Criticality grading: categorized into three levels: high, medium, and low. The sequence of high-criticality processes must be strictly adhered to and no adjustments are permitted. Medium-criticality processes can be adjusted within a limited range to accommodate changes in production. Low-criticality processes have a wider range of adjustments.

[0092] Allowable adjustment range: This is determined by criticality level. High-criticality processes (C) do not allow any adjustments and must be performed in the predetermined order. Medium-criticality processes (B and D) allow for moderate adjustments to accommodate minor changes in production. Low-criticality processes (A and E) have a wider range of adjustments and can be flexibly adjusted to meet production needs.

[0093] Based on the above priority matrix, the following third constraint can be determined:

[0094] Critical heat treatment (C) must be carried out strictly according to the predetermined sequence, and no adjustments are allowed.

[0095] The sequence of preliminary processing (B) and fine processing (D) can be adjusted within a moderate range to accommodate changes in production, but it should be ensured that they do not interfere with the performance of the critical heat treatment (C).

[0096] Raw material preparation (A) and quality inspection (E) have a large adjustment range and can be flexibly arranged according to production needs.

[0097] Step 1025: Determine the fourth constraint condition according to the skill level data of the personnel and the skill requirement level data of each process;

[0098] Specifically, the skill level of the personnel should not be lower than the skill requirement level of the process being performed. Therefore, the fourth constraint condition is the personnel skill matching degree threshold (skill level ≥ process requirement level).

[0099] Step 1026: Determine the fifth constraint condition according to the historical utilization data of each piece of equipment and the fluctuation range limit data;

[0100] Specifically, the utilization fluctuation of a single piece of equipment should be controlled within a certain range, such as not exceeding 15%. Therefore, the fifth constraint condition is the load balance degree limit (single equipment utilization fluctuation ≤ 15%).

[0101] Step 1027: Determine the sixth constraint condition according to the historical energy consumption data per unit output value and the energy consumption reduction rate target data;

[0102] Specifically, the energy consumption reduction rate per unit output value should reach or exceed the given target value, such as 5%. This can be achieved by calculating the actual energy consumption reduction rate and comparing it with the target value. Therefore, the sixth constraint condition is the green production index (energy consumption reduction rate per unit output value ≥ 5%).

[0103] Step 1028: Determine the constraint conditions of the target optimization model according to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, the fifth constraint condition, and the sixth constraint condition.

[0104] Specifically, the constraint conditions of the target optimization model include the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, the fifth constraint condition, and the sixth constraint condition. The constraint conditions of the target optimization model limit the value range of the decision variables (the decision variables include the allocation of production tasks, the arrangement of production time, the selection of equipment, etc.), limit the feasible solution space of the target production scheduling, ensure the feasibility and compliance of the final target production scheduling, and are conducive to improving the effectiveness of the target production scheduling.

[0105] In an optional embodiment of the present invention, step 103 includes:

[0106] Step 1031: Obtain the production target of minimizing the production time dimension;

[0107] Specifically, for the production target of minimizing the production time dimension, it is necessary to optimize the production scheduling, reduce unnecessary waiting time and idle time, and improve production efficiency.

[0108] Step 1032: Obtain the production target of minimizing the cost dimension;

[0109] Specifically, to achieve the production goal of minimizing the cost dimension, it is necessary to optimize the production plan and resource allocation, reduce waste, and lower production costs.

[0110] Step 1033: Obtain the production goal of maximizing resource utilization rate.

[0111] Specifically, to achieve the production goal of maximizing resource utilization rate, it is necessary to reasonably arrange production tasks and equipment usage to improve the utilization rate of equipment and materials.

[0112] Step 1034: Determine the production goals of multiple dimensions according to the production goal of minimizing the production time dimension, the production goal of minimizing the cost dimension, and the production goal of maximizing resource utilization rate.

[0113] Specifically, the production goals of multiple dimensions include the production goal of minimizing the production time dimension, the production goal of minimizing the cost dimension, and the production goal of maximizing resource utilization rate. By obtaining the production goals of these three dimensions, it helps to determine the target optimization model and improve the effectiveness of target production scheduling.

[0114] In an optional embodiment of the present invention, Step 104 includes:

[0115] Step 1041: Determine the core objective function according to the production goals of multiple dimensions.

[0116] Specifically, to achieve the production goal of minimizing the production time dimension, it is necessary to minimize the due date deviation penalty cost P; to achieve the production goal of minimizing the cost dimension, it is necessary to minimize the setup cost S and the energy consumption cost E; to achieve the production goal of maximizing resource utilization rate, it is necessary to minimize the due date deviation penalty cost P, minimize the setup cost S, and the energy consumption cost E. Quantify the due date deviation penalty cost P, and calculate the penalty cost according to the number of days or proportion of late delivery; quantify the setup cost S, including the costs generated by equipment adjustment, production line switching, material replacement, etc.; quantify the energy consumption cost E, measure the energy consumption during the production process, and convert it into cost. After quantifying the due date deviation penalty cost P, the setup cost S, and the energy consumption cost E according to the real-time production data, the core objective function can be determined as min(∑(P + S + E)), where P is the due date deviation penalty cost, S is the setup cost, and E is the energy consumption cost.

[0117] Step 1042: Determine the composite objective function according to the preset auxiliary objective function and the core objective function.

[0118] Specifically, the preset auxiliary objective function can be to maximize equipment utilization rate and / or minimize inventory cost. In a multi-objective optimization problem, there may be conflicts between various objectives. For example, in a production scheduling problem, improving production efficiency may increase energy consumption costs, while reducing changeover costs may extend the delivery period. By introducing the preset auxiliary objective function and combining it with the core objective function to form a composite objective function, the advantages and disadvantages of these objectives can be better weighed, and a solution that meets multiple objectives can be found, making the finally determined target production schedule more in line with the actual production situation and balancing various optimization objectives.

[0119] In an alternative embodiment of the present invention, step 1042 includes:

[0120] Step 10421, obtain a preset auxiliary objective function; the preset auxiliary objective function includes maximizing equipment utilization rate;

[0121] Specifically, the preset auxiliary objective function can be selected according to the actual production situation. The preset auxiliary objective function in this embodiment is to maximize equipment utilization rate. Among them, the equipment utilization rate is a value between 0 and 1, indicating the effective utilization degree of the equipment.

[0122] Step 10422, determine a composite objective function according to the preset auxiliary objective function and the core objective function; the composite objective function is min(C - λU);

[0123] Wherein, C = ∑(P + S + E); min(C - λU) is the composite objective function, C is the total cost, λ is the weight coefficient, U is the maximized equipment utilization rate, where P is the delivery deviation penalty cost, S is the changeover cost, and E is the energy consumption cost.

[0124] Specifically, the total cost of various product productions is C, the delivery deviation penalty is P, the changeover cost is S, and the energy consumption cost is E. Then the core objective function is min(C) = min(∑(P + S + E)). It is also necessary to consider the preset auxiliary objective function, that is, to maximize equipment utilization rate. Then, according to the preset auxiliary objective function and the core objective function, the composite objective function min(C - λU) can be constructed.

[0125] Specifically, λ is a positive weight used to adjust the relative importance between the two objectives (total cost and maximized equipment utilization rate). If λ is larger, then the equipment utilization rate will occupy a more important position in the optimization process; if λ is smaller, then the total cost will occupy a more important position. In practical applications, the optimal value of λ can be found through experiments and adjustments.

[0126] In an alternative embodiment of the present invention, the objective optimization model in step 105 is:

[0127] Objective function: Composite objective function;

[0128] Constraint condition: Target constraint condition.

[0129] In an alternative embodiment of the present invention, step 106 includes:

[0130] Step 1061, determine an equipment disturbance event based on real-time monitoring data of production equipment;

[0131] Specifically, through sensors or monitoring systems deployed on production equipment, real-time monitoring data of production equipment is obtained in real time, such as equipment monitoring data such as fault codes and mean time to repair (MTTR) predictions. If the equipment monitoring data includes fault code identification and / or the MTTR prediction is greater than 1 hour, it is determined as an equipment disturbance event.

[0132] Step 1062, determine an order-level disturbance event based on real-time order data;

[0133] Specifically, through an order management system or a customer relationship management system, the changes in orders are obtained in real time, such as the occurrence of urgent orders (such as the delivery date being less than the preset service period), the impact degree of order insertion, etc. When the real-time order data includes that the delivery date compression rate of an urgent order is greater than or equal to 30%, it is determined as an order-level disturbance event.

[0134] Step 1063, determine a resource-level disturbance event based on real-time personnel data and material supply data;

[0135] Specifically, through a human resource management system, the personnel absenteeism situation is obtained in real time, such as personnel absenteeism rate warnings and other personnel data; through a material management system, the material supply status is obtained in real time, such as material delay probability and other material supply data. Among them, by comparing the production plans before and after order insertion, the additional production time and delayed delivery dates caused by order insertion can be calculated to obtain the production time delay caused by order insertion; by calculating the additional material costs, labor costs, and equipment maintenance costs brought by order insertion to evaluate the impact of cost increase, the additional costs caused by order insertion can be obtained; by comparing the resource utilization rates before and after order insertion, the degree of resource utilization rate decrease caused by order insertion can be obtained; based on the production time delay caused by order insertion, the additional costs caused by order insertion, and the degree of resource utilization rate decrease caused by order insertion, the impact degree of order insertion is determined. When the personnel data includes a personnel absenteeism rate greater than the preset absenteeism rate and / or the material supply data includes incomplete material supply, or the personnel and material availability time delay caused by the personnel absenteeism rate warning and / or the material delay probability is greater than the current work order buffer period, it is determined as a resource-level disturbance event.

[0136] Step 1064, determine a combination of at least one optimization model based on the equipment disturbance event, the order-level disturbance event, the resource-level disturbance event, and multi-dimensional preset performance indicators, and obtain an optimized combined model;

[0137] Specifically, the multi-dimensional preset performance indicators include:

[0138] Convergence speed indicator: By monitoring the improvement rate of fitness in each generation, the convergence speed of the optimization sub-model can be evaluated. A faster convergence speed means that the optimization sub-model can find high-quality solutions in a shorter time.

[0139] Solution quality indicator: Use the hypervolume indicator (HV value) or other similar indicators to evaluate the quality of the solution. The larger the HV value, the wider the coverage of the solution set in the objective space and the higher the quality of the solution.

[0140] Resource consumption indicator: By monitoring the CPU (Central Processing Unit) time and memory occupancy, the resource consumption of the optimization sub-model can be evaluated, which is crucial for optimizing the running efficiency of the optimization sub-model while ensuring the solution quality.

[0141] Dynamically adjust the optimization combination model according to the perturbation event and multi-dimensional preset performance indicators. When the convergence speed indicator drops, add the first optimization sub-model or the second optimization sub-model to the optimization combination model; when the CPU is overloaded, downgrade the optimization combination model to the first optimization sub-model; when the solution quality indicator stagnates, add the third optimization sub-model to the optimization combination model; when it is determined to be a device perturbation event and the maintenance time is greater than 30 minutes, switch the optimization combination model to the first optimization sub-model or the second optimization sub-model; when it is determined to be an order-level perturbation event and the urgency is not greater than 0.9, switch the optimization combination model to the first optimization sub-model; when it is determined to be an order-level perturbation event and the urgency is greater than 0.9, add the second optimization sub-model to the optimization combination model; when it is determined to be a resource-level perturbation event and the gap is greater than 20%, switch the optimization combination model to the third optimization sub-model.

[0142] Step 1065, perform iterative solution on the target optimization model according to the optimization combination model to obtain a target solution set.

[0143] As Figure 2 shown, in an optional embodiment of the present invention, when the optimization combination model in step 1065 includes a first optimization sub-model, a second optimization sub-model, and a third optimization sub-model, step 1065 includes:

[0144] Step 10651, obtain a preset random initial solution set.

[0145] Specifically, by initializing the population, generate a preset random initial solution set including parameters such as device allocation, process sequence, and resource combination, and evaluate the individual fitness based on the multi-objective function. Then enter the iterative optimization loop. In a specific embodiment, 100 preset random initial solution sets can be randomly generated.

[0146] Step 10652: Perform a global search based on the first optimization sub-model and the preset random initial solution set to obtain a first optimal solution;

[0147] Specifically, a preset random initial solution set is input into the first optimization sub-model. In each iteration, the first optimization sub-model first performs a global search, generating a new population through selection, crossover, and mutation operations, focusing on exploring potential high-quality regions in the solution space. The first optimization sub-model converts the problem to be solved into a chromosomal string, such as a binary code. It then selects individuals from the current population for reproduction based on their fitness, mimicking chromosomal crossover in biological genetics to generate new individuals. Genes in these individuals are altered with a preset probability to increase population diversity. The fitness of these individuals is calculated according to the fitness function f(x) = C(x) - λU(x) until a preset first number of iterations or fitness criterion is reached. Here, f(x) is the fitness function, representing the optimization target value for solution x; C(x) is the total cost function, representing the total cost for solution x; U(x) is the equipment utilization function, representing the equipment utilization for solution x; C is the total cost; λ is the weight coefficient; and U is the maximum equipment utilization. By maintaining the diversity of multiple individuals in the population, a global search in the search space is facilitated, leading to the first optimal solution.

[0148] Step 10653: Perform a local search based on the second optimization sub-model and the first optimal solution to obtain a second optimal solution;

[0149] Specifically, when the preset first number of iterations is reached, the second optimization sub-model performs a local fine search based on the first optimal solution, and uses the dual guidance mechanism of individual historical optimal and group optimal solutions to adjust the process time window and resource allocation plan.

[0150] Among them, the second optimization sub-model is calculated by formula v new =w·v+c1·r1·(p Best -x)+c2·r2·(g Best -x) to update the particle's speed, through x new =x+v new Track individual historical optimal p Best and the group optimal solution g Best , where v new is the new velocity vector of the particle, w is the inertia weight, which is used to control the influence of the current velocity of the particle on the subsequent velocity and control the global / local search balance, v is the current velocity vector of the particle, c1 is the individual learning factor, c2 is the social learning factor, r1 and r2 are random numbers between 0 and 1, which are used to increase the randomness of the search, and p Best is the historical optimal position of the particle itself, x is the current position of the particle, where the initial position of the particle is the first optimal solution, gBest is the global optimal position of all particles, x new is the new position of the particle.

[0151] Step 10654, perform perturbation processing according to the third optimization sub-model and the second optimal solution to obtain a target solution set.

[0152] Specifically, when the preset second iteration number is reached, the third optimization sub-model intervenes, applies a controllable perturbation to the second optimal solution, and helps the model jump out of the local optimal trap through the strategy of probabilistically accepting inferior solutions.

[0153] Specifically, the third optimization sub-model first sets an initial temperature T (usually relatively high) and a termination temperature T end (relatively low), as well as a temperature reduction strategy (such as exponential decay); takes the second optimal solution as the initial solution of the third optimization sub-model, makes a small random perturbation to the initial solution to generate a new solution within its neighborhood, which can be achieved by adding random noise in the solution space or applying a certain transformation; calculates the objective function value of the new solution and compares it with the objective function value of the current solution, calculates the objective function value of the solution through f1(x) = C(x) - λU(x), where f1(x) is the objective function value of the solution, C(x) is the total cost function, representing the total cost under the solution x, U(x) is the equipment utilization function, representing the equipment utilization under the solution x, C is the total cost, λ is the weight coefficient, U is to maximize the equipment utilization; if the probability exp(-Δf / T) is less than 0, it means the new solution is better, then unconditionally accept the new solution, if the probability exp(-Δf / T) is greater than 0, it means the new solution is worse, then accept the new solution with a probability of exp(-Δf / T), where Δf is the difference between the objective function value of the new solution and the objective function value of the current solution, T is the current temperature, gradually reduces the temperature using an exponential cooling strategy or other cooling strategies, and if satisfied, stops the calculation and outputs the target solution set (if the temperature T drops to the termination temperature T end below, such as when the temperature is less than 1, stop the calculation), otherwise recalculate the objective function value of the current solution.

[0154] Specifically, during the optimization process of the preset random initial solution set using multiple optimization sub-models, core parameters such as the crossover rate, mutation rate, and inertia weight are dynamically adjusted, and the strategy of retaining the optimal individual and retaining a certain proportion of excellent individuals is adopted to ensure that high-quality solutions are not lost. When the preset iteration number or the solution set convergence threshold is reached, the optimization combination model terminates and outputs the Pareto optimal solution set as the target solution set. The entire process, through the complementary advantages between models, significantly improves the convergence speed while ensuring the diversity of solutions, and effectively copes with the optimization challenges of large-scale complex scheduling problems.

[0155] It should be noted that the optimization combination model can also be the first optimization sub-model, or the second optimization sub-model, or the third optimization sub-model, or the combination of the first optimization sub-model and the second optimization sub-model, or the combination of the first optimization sub-model and the third optimization sub-model, or the combination of the second optimization sub-model and the third optimization sub-model, etc. The solution process will not be elaborated here.

[0156] In an alternative embodiment of the present invention, step 107 includes:

[0157] Step 1071, determine a production task list according to the target solution set; the production task list includes the quantity, priority, and delivery date of production tasks;

[0158] Specifically, the target solution set includes production task allocation: specifying which equipment, production line, or worker should execute each production task; time arrangement: determining the start time and end time of each production task; resource allocation: allocating resources such as required equipment, manpower, tools, and materials; priority management: setting the priority of production tasks according to factors such as order urgency and customer importance; bottleneck management: identifying and optimizing bottleneck processes in the production process to ensure a smooth production process. Therefore, the quantity, priority, and delivery date of production tasks can be extracted from the target solution set to form a production task list.

[0159] According to the target solution set, determine key information such as the quantity, priority, and delivery date of each production task. Then, based on the target solution set, formulate a clear production task list, specifying the specific requirements of each task, such as product type, quantity, quality standards, etc.

[0160] Step 1072, determine resource allocation according to the production task list; the resource allocation includes equipment resources, human resources, and material resources;

[0161] Specifically, according to the production task list and the target solution set, equipment resources, human resources, and material resources can be allocated to determine the resource allocation required for each production task, ensuring that each production task has sufficient resource support while avoiding resource waste.

[0162] Step 1073, determine the target production schedule according to the production task list and the resource allocation;

[0163] Specifically, information such as the specific arrangement of production tasks, resource allocation, and production sequence can be organized into a production plan as the target production schedule, facilitating the subsequent manufacturing execution system to execute production tasks according to this plan.

[0164] Step 1074, control the production scheduling module to output the target production schedule.

[0165] Specifically, the target production schedule can fully consider the actual needs of the enterprise and the real-time changes in the production environment, and control the production scheduling module to output the target production schedule to the MES system (Manufacturing Execution System) for execution. The MES system distributes, schedules, and monitors production tasks according to the target production schedule to ensure the smooth progress of production activities.

[0166] A specific embodiment of the production scheduling method according to the embodiment of the present invention includes:

[0167] First, obtain real-time production data from the Manufacturing Execution System (MES), Enterprise Resource Planning System (ERP), and Internet of Things (IoT) devices.

[0168] Then, construct a target optimization model. The target optimization model realizes the dynamic trade-off of multi-dimensional production goals through a composite objective function and a multi-dimensional constraint system. The multi-objective optimization model takes min(∑(due date deviation penalty + setup cost + energy consumption cost)) as the core objective function, where:

[0169] Due date deviation penalty: designed with a piecewise function (differentiated penalty coefficients for early / late); Setup cost: includes the cost converted from equipment setup time and material switching loss; Energy consumption cost is based on a dynamic electricity cost model of process parameters and equipment load rate;

[0170] The construction of the multi-dimensional constraint system adopts a three-level hierarchical architecture:

[0171] 1. Hard constraint layer:

[0172] Equipment capacity constraint: ∑ process processing time ≤ available machine time (including reserved maintenance window);

[0173] Material hard constraint: process start time point ≥ material availability time + safety buffer period;

[0174] 2. Soft constraint layer:

[0175] Process sequence constraint: strictness grading of key process sequences (allowing limited flexible adjustment) (as shown in Table 1);

[0176] Threshold for personnel skill matching degree (skill level ≥ process requirement level);

[0177] 3. Optimization orientation layer:

[0178] Load balance degree limit (fluctuation of single equipment utilization rate ≤ 15%);

[0179] Green production index (decrease rate of energy consumption per unit output value ≥ 5%);

[0180] Then, through at least one optimization model, the target optimization model is iteratively solved. The solution of the target optimization model dynamically adjusts the target weights through an adaptive weight allocator, combines the Pareto front screening mechanism to output a non-dominated solution set, and supports decision-makers to select the optimal balance solution based on the actual scenario.

[0181] Here, by constructing a three-layer intelligent decision-making system, the dynamic optimization of the combination of the first optimization sub-model, the second optimization sub-model, and the third optimization sub-model is realized:

[0182] 1. Environment perception layer, by deploying a distributed sensor network, three types of production disturbance events are captured in real time:

[0183] Equipment-level disturbances (fault code identification, MTTR prediction);

[0184] Order-level disturbances (urgent order feature extraction, impact degree calculation of inserted orders);

[0185] Resource-level disturbances (personnel absenteeism rate warning, material delay probability);

[0186] 2. Algorithm decision-making layer, by constructing an algorithm performance monitoring matrix through three indicators:

[0187] Convergence speed index (fitness improvement rate per generation);

[0188] Solution quality index (hypervolume index);

[0189] Resource consumption index (CPU time / memory occupancy);

[0190] It is also possible to automatically combine and use the three first optimization sub-models, the second optimization sub-model, and the third optimization sub-model through pre-stored historical data, such as historical scenario feature matching (triggering the reuse of similar cases when the Euclidean distance ≤ 0.2); or model combination recommendation (such as automatically switching to the second optimization sub-model + the third optimization sub-model fast convergence combination in the equipment failure scenario).

[0191] 3. Execution regulation layer

[0192] When the optimization combination model is a combination of the first optimization sub-model, the second optimization sub-model, and the third optimization sub-model, the hybrid algorithm relay mechanism:

[0193] Initial stage (iteration 1 - 100): The first optimization sub-model dominates the global exploration (crossover rate linearly decays from 0.8 to 0.6); Middle stage (iteration 101 - 300): The second optimization sub-model (inertia weight dynamically adjusts from 0.9 to 0.4); Later stage (iteration 301 - 500): The third optimization sub-model jumps out of the local optimum (cooling coefficient 0.95).

[0194] Adaptive adjustment of the parameters in the three optimized sub - models: Automatically adjust the mutation rate (0.01 → 0.1) according to the population diversity index (gene entropy value); or dynamically adjust the particle velocity limit value of the second optimized sub - model based on the neighborhood search effect.

[0195] As Figure 2 shown, the specific process for solving the multi - objective optimization model includes: achieving the dynamic balance between global exploration and local optimization through the cross - iteration of the first, second, and third optimized sub - models. First, initialize the population to generate an initial solution set (random scheduling plan) containing parameters such as equipment allocation, process sequence, and resource combination, and evaluate the individual fitness based on the multi - objective function. Subsequently, enter the iterative optimization loop: In each iteration, the first optimized sub - model first performs global search, generating a new population through selection, crossover, and mutation operations, focusing on exploring potential high - quality regions in the solution space; the second optimized sub - model conducts local fine - grained search based on the current optimal solution, using the dual - guidance mechanism of individual historical optimal and population optimal solutions to adjust the process time window and resource allocation plan; the third optimized sub - model intervenes at the end of each iteration, applying a controllable perturbation to the current optimal solution, and using the strategy of probabilistically accepting inferior solutions to help the model jump out of the local optimal trap. During the three - stage optimization process, core parameters such as the crossover rate, mutation rate, and inertia weight are dynamically adjusted, and the elite retention strategy is adopted to ensure that high - quality solutions are not lost. When the preset number of iterations or the solution set convergence threshold is reached, the optimized combined model terminates and outputs the Pareto optimal solution set as the target solution set. Through the complementary advantages among sub - models, the entire process significantly improves the convergence speed while ensuring solution diversity, effectively coping with the optimization challenges of large - scale complex scheduling problems.

[0196] Among them, it is also necessary to optimize the combination of the three optimized sub - models or the parameters of the model when a perturbation event occurs. Among them, a double - loop control architecture is adopted to achieve rapid response and continuous optimization of abnormal events (perturbation events):

[0197] Outer loop (event response loop):

[0198] 1. Intelligent discrimination of perturbation events for triggering conditions:

[0199] Equipment failure: MTTR (Mean Time To Repair) > 1 hour;

[0200] Emergency order: Delivery time compression rate ≥ 30%;

[0201] Material exception: Kit - up time delay > current work order buffer period;

[0202] 2. Hierarchical response strategy for perturbation events:

[0203] Local adjustment: Process - level rearrangement of affected work orders (response time < 2 minutes);

[0204] Use tabu search to quickly generate alternative process sequences and retain the original scheduling of unaffected processes;

[0205] Global adjustment: Full optimization of the rolling time window (response time < 8 minutes);

[0206] Freeze the status of started processes;

[0207] Inner loop (continuous optimization loop):

[0208] 1. Time window rolling mechanism:

[0209] Perform incremental optimization every 15 minutes (only adjust the schedule for the next 2 hours);

[0210] Perform full optimization every 4 hours (reconstruct the schedule for the next 8 hours);

[0211] 2. Digital twin simulation verification:

[0212] Preview the adjustment plan in a virtual environment;

[0213] Output key indicators such as the predicted fluctuation of production capacity utilization rate and the probability of overdue risk;

[0214] Automatically select and implement the plan with the highest comprehensive score of key performance indicators.

[0215] The production scheduling method according to the embodiment of the present invention obtains real-time production data from a manufacturing execution system (MES), an enterprise resource planning system (ERP), and Internet of Things (IoT) devices, such as work order information, equipment status, inventory situation, etc. Then comes modeling and goal setting, by constructing a multi-objective optimization mathematical model and setting optimization goals (such as minimizing production time, reducing costs, improving resource utilization rate, etc.). Then comes the hyper-heuristic control strategy, which dynamically adjusts the optimization algorithm according to the search progress and selects the optimal optimization method at different stages. Next comes the hybrid optimization solution, which combines models such as the first optimization sub-model, the second optimization sub-model, and the third optimization sub-model, and improves the search efficiency and solution quality in a cross-iterative manner. Then comes dynamic adjustment and real-time optimization, which uses an adaptive adjustment mechanism to cope with sudden changes in the production environment and make the scheduling plan more flexible. Finally comes the output of the optimization plan, and the finally generated target production schedule is automatically pushed to the manufacturing execution system (MES) for execution. The entire process combines multiple optimization strategies to ensure high-quality production scheduling plans in different production scenarios.

[0216] As Figure 3 shown, an embodiment of the present invention proposes a production scheduling device 200, including:

[0217] A first acquisition module 201, configured to acquire real-time production data through an intelligent manufacturing system;

[0218] The first determination module 202 is configured to determine the constraint conditions of the target optimization model according to the real-time production data;

[0219] The second acquisition module 203 is configured to acquire production targets in multiple dimensions;

[0220] The second determination module 204 is configured to determine a composite objective function according to the production targets in multiple dimensions;

[0221] The third determination module 205 is configured to determine the target optimization model according to the constraint conditions and the composite objective function;

[0222] The processing module 206 is configured to iteratively solve the target optimization model through at least one optimization model to obtain a target solution set;

[0223] The control module 207 is configured to control the production scheduling module to output a target production schedule according to the target solution set.

[0224] Optionally, the first determination module 202 is specifically configured to:

[0225] According to the real-time production data, obtain the process processing time data of each device, the available machine hours data of the device, the start time data of each process, the material availability time data, the safety buffer period data, the sequential classification data of the preset key processes and the allowable adjustment range data, the skill level data of the personnel and the skill requirement level data of each process, the utilization history data of each device and the fluctuation range limit data, the energy consumption history data per unit output value and the energy consumption reduction rate target data;

[0226] Determine the first constraint condition according to the process processing time data of each device and the available machine hours data of the device;

[0227] Determine the second constraint condition according to the start time data of each process, the material availability time data and the safety buffer period data;

[0228] Determine the third constraint condition according to the sequential classification data of the preset key processes and the allowable adjustment range data;

[0229] Determine the fourth constraint condition according to the skill level data of the personnel and the skill requirement level data of each process;

[0230] Determine the fifth constraint condition according to the utilization history data of each device and the fluctuation range limit data;

[0231] Determine the sixth constraint condition according to the energy consumption history data per unit output value and the energy consumption reduction rate target data;

[0232] Determine the constraint conditions of the target optimization model according to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, the fifth constraint condition, and the sixth constraint condition.

[0233] Optionally, the second determination module 204 is specifically configured to:

[0234] Determine the core objective function according to the production targets of the multiple dimensions;

[0235] Determine the composite objective function according to the preset auxiliary objective function and the core objective function.

[0236] Optionally, determining the composite objective function according to the preset auxiliary objective function and the core objective function includes:

[0237] Obtain the preset auxiliary objective function; the preset auxiliary objective function includes maximizing equipment utilization rate;

[0238] Determine the composite objective function according to the preset auxiliary objective function and the core objective function; the composite objective function is min(C - λU);

[0239] Wherein, C = ∑(P + S + E); min(C - λU) is the composite objective function, C is the total cost in the core objective function, λ is the weight coefficient, U is the maximized equipment utilization rate, P is the penalty cost for delivery deviation, S is the changeover cost, and E is the energy consumption cost.

[0240] Optionally, the processing module 206 is specifically configured to:

[0241] Determine the equipment disturbance event according to the real-time monitoring data of the production equipment;

[0242] Determine the order-level disturbance event according to the real-time order data;

[0243] Determine the resource-level disturbance event according to the real-time personnel data and material supply data;

[0244] Determine at least one combination of optimization models according to the equipment disturbance event, the order-level disturbance event, the resource-level disturbance event, and the multi-dimensional preset performance indicators, and obtain the optimized combined model;

[0245] Iteratively solve the target optimization model according to the optimized combined model to obtain the target solution set.

[0246] Optionally, the processing module 206 is specifically configured to:

[0247] Obtain the preset random initial solution set;

[0248] Perform a global search based on the first optimization sub-model in the optimization combination model and the preset random initial solution set to obtain the first optimal solution;

[0249] Perform a local search based on the second optimization sub-model in the optimization combination model and the first optimal solution to obtain the second optimal solution;

[0250] Perform a perturbation process based on the third optimization sub-model in the optimization combination model and the second optimal solution to obtain the target solution set.

[0251] Optionally, the control module 207 is specifically configured to:

[0252] Determine a production task list according to the target solution set; the production task list includes the quantity, priority, and delivery date of production tasks;

[0253] Determine resource allocation according to the production task list; the resource allocation includes equipment resources, human resources, and material resources;

[0254] Determine a target production schedule according to the production task list and the resource allocation;

[0255] Control the production scheduling module to output the target production schedule.

[0256] The production scheduling device proposed in the embodiment of the present invention obtains real-time production data through an intelligent manufacturing system and determines the constraint conditions of the target optimization model based on this; by obtaining production targets in multiple dimensions and determining a composite objective function based on this; then, according to the constraint conditions and the composite objective function, determine the target optimization model, and through at least one optimization model, iteratively solve the target optimization model to obtain the target solution set, and finally, according to the target solution set, control the production scheduling module to output the target production schedule, improving the quality and efficiency of the production line scheduling and enhancing the adaptability to the dynamic environment.

[0257] It should be noted that this device is the device corresponding to the above method, and all implementation manners in the above method embodiments are applicable to the embodiments of this device and can also achieve the same technical effects. Details are not described herein again.

[0258] The embodiment of the present invention also provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method described in any one of the above embodiments. All implementation manners in the above method embodiments are applicable to the embodiments of this device and can also achieve the same technical effects. Details are not described herein again.

[0259] An embodiment of the present invention further provides a computer-readable storage medium, on which instructions are stored. When the instructions run on a computer, the computer is caused to execute the method described in any one of the above embodiments. All implementation manners in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effects. Details are not described again in this embodiment.

[0260] It should be noted that in the device and method of the present invention, obviously, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations shall be regarded as equivalent solutions of the present invention. Moreover, the steps of performing the above series of processes can naturally be executed in chronological order according to the described order, but it is not necessary to execute them in chronological order. Some steps can be executed in parallel, crosswise, or independently of each other.

[0261] It should be noted that in the above embodiments, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising that element. In addition, it should be pointed out that the scope of the method and device in the above embodiments of the implementation manner is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described method may be executed in a different order from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0262] The above is the preferred embodiment 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 modifications can be made, and these improvements and modifications should also be regarded as the protection scope of the present invention.

Claims

1. A production scheduling method, characterized in that Including: Obtaining real-time production data through an intelligent manufacturing system; Determining the constraint conditions of the target optimization model according to the real-time production data; Obtaining production targets in multiple dimensions; Determining a composite objective function according to the production targets in multiple dimensions; Determining the target optimization model according to the constraint conditions and the composite objective function; Iteratively solving the target optimization model through at least one optimization model to obtain a target solution set; Controlling the production scheduling module to output a target production schedule according to the target solution set; 2. The production scheduling method according to claim 1, wherein Determining the constraint conditions of the target optimization model according to the real-time production data, including: Obtaining the process processing time data of each device, the available machine time data of the device, the starting time data of each process, the material availability time data, the safety buffer period data, the sequential grading data of the preset key processes and the allowable adjustment range data, the skill level data of the personnel and the skill requirement level data of each process, the historical utilization rate data of each device and the fluctuation range limit data, the historical energy consumption data per unit output value and the energy consumption reduction rate target data according to the real-time production data; Determining the first constraint condition according to the process processing time data of each device and the available machine time data of the device; Determining the second constraint condition according to the starting time data of each process, the material availability time data and the safety buffer period data; Determining the third constraint condition according to the sequential grading data of the preset key processes and the allowable adjustment range data; Determining the fourth constraint condition according to the skill level data of the personnel and the skill requirement level data of each process; Determining the fifth constraint condition according to the historical utilization rate data of each device and the fluctuation range limit data; Determining the sixth constraint condition according to the historical energy consumption data per unit output value and the energy consumption reduction rate target data; Determining the constraint conditions of the target optimization model according to the first constraint condition, the second constraint condition, the third constraint condition, the fourth constraint condition, the fifth constraint condition and the sixth constraint condition; 3. The production scheduling method according to claim 1, wherein Determining a composite objective function according to the production targets in multiple dimensions, including: Determining a core objective function according to the production targets in multiple dimensions; Determining a composite objective function according to a preset auxiliary objective function and the core objective function; 4. The production scheduling method according to claim 3, wherein Determining a composite objective function according to a preset auxiliary objective function and the core objective function, including: Obtaining a preset auxiliary objective function; the preset auxiliary objective function includes maximizing the equipment utilization rate; Determining a composite objective function according to a preset auxiliary objective function and the core objective function; the composite objective function is min(C - λU); Wherein, C = ∑(P + S + E); Wherein, min(C - λU) is the composite objective function, C is the total cost in the core objective function, λ is the weight coefficient, U is the maximized equipment utilization rate, P is the penalty cost for delivery deviation, S is the changeover cost, and E is the energy consumption cost; 5. The production scheduling method according to claim 1, wherein Iteratively solving the target optimization model through at least one optimization model to obtain a target solution set, including: Determining device disturbance events according to the real-time monitoring data of production equipment; Determine order-level disturbance events based on real-time order data; Determine resource-level disturbance events based on real-time personnel data and material supply data; Determine a combination of at least one optimization model according to the equipment disturbance events, the order-level disturbance events, the resource-level disturbance events, and multi-dimensional preset performance indicators, and obtain an optimized combined model; Iteratively solve the target optimization model according to the optimized combined model to obtain a target solution set.

6. The production scheduling method according to claim 5, wherein When the optimized combined model includes a first optimization sub-model, a second optimization sub-model, and a third optimization sub-model, iteratively solving the target optimization model according to the optimized combined model to obtain a target solution set includes: Obtain a preset random initial solution set; Perform a global search according to the first optimization sub-model and the preset random initial solution set to obtain a first optimal solution; Perform a local search according to the second optimization sub-model and the first optimal solution to obtain a second optimal solution; Perform a perturbation process according to the third optimization sub-model and the second optimal solution to obtain a target solution set.

7. The production scheduling method according to claim 1, wherein Control the production scheduling module to output a target production schedule according to the target solution set, including: Determine a production task list according to the target solution set; the production task list includes the quantity, priority, and delivery date of production tasks; Determine resource allocation according to the production task list; the resource allocation includes equipment resources, human resources, and material resources; Determine a target production schedule according to the production task list and the resource allocation; Control the production scheduling module to output a target production schedule.

8. A production scheduling device, characterized in that, Include: A first acquisition module for acquiring real-time production data through an intelligent manufacturing system; A first determination module for determining the constraint conditions of the target optimization model according to the real-time production data; A second acquisition module for acquiring production targets in multiple dimensions; A second determination module for determining a composite objective function according to the production targets in multiple dimensions; A third determination module for determining a target optimization model according to the constraint conditions and the composite objective function; A processing module for iteratively solving the target optimization model through at least one optimization model to obtain a target solution set; A control module for controlling the production scheduling module to output a target production schedule according to the target solution set.

9. A computing device, characterized in that, Include: A processor and a memory storing a computer program, and when the computer program is run by the processor, it executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Instructions are stored, and when the instructions are run on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images