Intelligent scheduling method and device of production line, computer equipment, medium and product

Abstract

The invention relates to an intelligent scheduling method and device for a production line, computer equipment, a medium and a computer program product. The method comprises the following steps: acquiring real-time resource states of each work order, each guide vehicle and each processing device in a production line; determining a scheduling strategy based on the real-time resource state and a preset hybrid scheduling optimization model; and a guide vehicle control instruction and a machining control instruction are generated according to the scheduling strategy, the guide vehicle control instruction is used for scheduling the corresponding guide vehicle, and the machining control instruction is used for controlling the corresponding machining equipment. By adopting the method, synchronous real-time scheduling can be performed on the guide vehicles and the processing equipment based on the real-time resource states of different guide vehicles and processing equipment in the production line, so that the overall production efficiency of the production line is improved.

Description

Technical Field

[0001] This application relates to the field of manufacturing technology, and in particular to an intelligent scheduling method, apparatus, computer equipment, computer-readable storage medium, and computer program product for a production line. Background Technology

[0002] As the manufacturing industry moves towards intelligence and flexibility, Automated Guided Vehicles (AGVs) and processing equipment together constitute the core resources of modern production systems.

[0003] In actual production, the high cost of purchasing and maintaining AGVs limits the number of AGVs that can be configured on a single production line. Meanwhile, the production capacity of processing equipment is relatively fixed and difficult to adjust flexibly according to actual needs. Therefore, how to achieve coordinated scheduling of AGVs and processing equipment under these resource constraints to improve production efficiency has become a pressing problem in this field. Summary of the Invention

[0004] Therefore, it is necessary to provide an intelligent scheduling method, device, computer equipment, computer-readable storage medium, and computer program product for production lines that can coordinate the scheduling of AGVs and processing equipment to improve production efficiency, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides an intelligent scheduling method for a production line, the method comprising:

[0006] Obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line;

[0007] The scheduling strategy is determined based on the real-time resource status and the preset hybrid scheduling optimization model;

[0008] Based on the scheduling strategy, guide vehicle control instructions and processing control instructions are generated. The guide vehicle control instructions are used to schedule the corresponding guide vehicles, and the processing control instructions are used to control the corresponding processing equipment.

[0009] In one embodiment, the method further includes:

[0010] Obtain the attribute information of each of the guide vehicles and each of the processing equipment;

[0011] Obtain work order information, which includes the processing time of each process and the type of product produced by each work order;

[0012] Obtain the transportation time information between each of the guide vehicles and different processing equipment;

[0013] Based on the attribute information, the work order information, the transportation time information, and the preset optimization objectives, a hybrid scheduling optimization model is constructed.

[0014] In one embodiment, the construction of a hybrid scheduling optimization model based on the attribute information, the work order information, the transportation time information, and a preset optimization objective includes:

[0015] Construct a multi-objective optimization function with the objectives of minimizing production completion time, minimizing total completion time, and prioritizing the output of high-priority work orders;

[0016] The constraints of the optimization function are determined based on the attribute information, the work order information, and the transportation time information.

[0017] By integrating the constraints into the optimization function, a hybrid scheduling optimization model is obtained.

[0018] In one embodiment, determining the scheduling strategy based on the real-time resource status and a preset hybrid scheduling optimization model includes:

[0019] The real-time resource status is input into the hybrid scheduling optimization model to obtain the solution space based on the hybrid scheduling optimization model, and an initial population of scheduling strategies is generated.

[0020] The initial population was optimized iteratively using a genetic algorithm;

[0021] During the optimization iteration process of the genetic algorithm, a variable neighborhood search algorithm is used to perform local optimization on individuals in the current population;

[0022] During the optimization iteration process of the genetic algorithm, individuals in the current population are reconstructed through a preset rescheduling mechanism to meet the constraints.

[0023] During the optimization iteration process of the genetic algorithm, an external memory bank is set up to store high-quality individuals in the population for use in the variable neighborhood search algorithm.

[0024] If the optimization iteration process reaches a preset number of iterations, the current population will be used as the final scheduling strategy.

[0025] In one embodiment, the method further includes:

[0026] When the real-time resource status is found to meet a preset trigger event or complete a preset number of tasks, the event scheduling instruction or periodic scheduling instruction corresponding to the trigger event is determined based on a preset mapping relationship.

[0027] The appropriate hybrid scheduling optimization model is invoked according to the event scheduling instruction or periodic scheduling instruction.

[0028] In one embodiment, generating the guide vehicle control command and processing control command according to the scheduling strategy includes:

[0029] The scheduling strategy is decoded into a device processing queue and a handling task sequence that includes work order processing order, planned time information, and identity information.

[0030] Based on the transport task sequence, a guide vehicle control command including the transport path is generated for the guide vehicle corresponding to the identity information;

[0031] Based on the equipment processing queue, a processing control command, including processing start and end instructions, is generated for the processing equipment corresponding to the identity information.

[0032] Secondly, this application also provides an intelligent scheduling device for a production line, comprising:

[0033] The resource status sensing module is used to obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line;

[0034] The optimization solution module is used to determine the scheduling strategy based on the real-time resource status and the preset hybrid scheduling optimization model;

[0035] The execution module is used to generate guide vehicle control instructions and processing control instructions according to the scheduling strategy. The guide vehicle control instructions are used to schedule the corresponding guide vehicle, and the processing control instructions are used to control the corresponding processing equipment.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] Obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line;

[0038] The scheduling strategy is determined based on the real-time resource status and the preset hybrid scheduling optimization model;

[0039] Based on the scheduling strategy, guide vehicle control instructions and processing control instructions are generated. The guide vehicle control instructions are used to schedule the corresponding guide vehicles, and the processing control instructions are used to control the corresponding processing equipment.

[0040] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0041] Obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line;

[0042] The scheduling strategy is determined based on the real-time resource status and the preset hybrid scheduling optimization model;

[0043] Based on the scheduling strategy, guide vehicle control instructions and processing control instructions are generated. The guide vehicle control instructions are used to schedule the corresponding guide vehicles, and the processing control instructions are used to control the corresponding processing equipment.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0045] Obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line;

[0046] The scheduling strategy is determined based on the real-time resource status and the preset hybrid scheduling optimization model;

[0047] Based on the scheduling strategy, guide vehicle control instructions and processing control instructions are generated. The guide vehicle control instructions are used to schedule the corresponding guide vehicles, and the processing control instructions are used to control the corresponding processing equipment.

[0048] The aforementioned intelligent scheduling method, device, computer equipment, computer-readable storage medium, and computer program product for the production line acquire the real-time resource status of each work order, each guide car, and each processing equipment in the production line; determine a scheduling strategy based on the real-time resource status and a preset hybrid scheduling optimization model; and generate guide car control instructions and processing control instructions according to the scheduling strategy. The guide car control instructions are used to schedule the corresponding guide cars, and the processing control instructions are used to control the corresponding processing equipment. This application, after acquiring the real-time resource status of each guide car and processing equipment in the production line, inputs the real-time resource status into a preset hybrid scheduling optimization model to determine the scheduling strategy, and controls each guide car and processing equipment based on this scheduling strategy. It can synchronously schedule guide cars and processing equipment in real time based on the real-time resource status of different guide cars and processing equipment in the production line, thereby improving the overall production efficiency of the production line. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is an application environment diagram of the intelligent scheduling method for a production line in one embodiment;

[0051] Figure 2This is a flowchart illustrating an intelligent scheduling method for a production line in one embodiment;

[0052] Figure 3 This is a flowchart illustrating the intelligent scheduling method for a production line in another embodiment;

[0053] Figure 4 This is a structural block diagram of an intelligent scheduling device for a production line in one embodiment;

[0054] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] The intelligent scheduling method for production lines provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with automated guided vehicles 104 and processing equipment 105 via a network. Terminal 102 acquires the real-time resource status of the automated guided vehicles 104 and processing equipment 105 in the production line, then inputs the real-time resource status into a preset hybrid scheduling optimization model in terminal 102 to determine the scheduling strategy. Based on the scheduling strategy, it generates guide vehicle control commands and sends them to the corresponding automated guided vehicles 104 via the network to schedule the corresponding automated guided vehicles 104. It also generates processing control commands and sends them to the corresponding processing equipment 105 via the network to control the corresponding processing equipment 105. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, or IoT devices. IoT devices can be central control systems, industrial control computers, etc. The automated guided vehicle 104 can be a buffered multi-load guide vehicle, an unbuffered single-load guide vehicle, etc.

[0057] In one exemplary embodiment, such as Figure 2 As shown, an intelligent scheduling method for a production line is provided, which can be applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps 202 to 206. Wherein:

[0058] Step 202: Obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line.

[0059] In this context, a production line refers to a continuous process of production activities, including multiple different types of work orders, various processing equipment, and automated guided vehicles (AGVs) working collaboratively. A work order is a carrier of work tasks and information flow. A AGV is an industrial vehicle that automatically or manually loads goods, automatically travels along a set route, or pulls a cargo trolley to a designated location, and then automatically or manually loads and unloads the goods. Processing equipment refers to equipment used to process materials or products. Real-time resource status refers to the collection of information such as the current working status, position, and load of each AGV and processing equipment in the production line.

[0060] Specifically, real-time resource status includes, but is not limited to: AGV status, equipment status, and work order status. AGV status includes, but is not limited to: the real-time position, remaining power, current load, task execution status, maximum number of buffer positions for AGV-T, the carrying capacity of AGV-B, the buffer capacity of the transfer machine, and its unique capacity attributes (multi-station buffer status of AGV-T, single-load status of AGV-B); equipment status includes, but is not limited to: the busy / idle status of all processing equipment and transfer machines, the currently processed workpiece, and the occupancy status of equipment buffers (especially the limited buffer space occupancy status of AGV-T side equipment and the buffer space occupancy status of transfer machine T side); work order status includes, but is not limited to: the process sequence of each work order and the standard processing time of each process on different selectable equipment, the current progress of all work orders in progress, including completed processes and the current equipment or AGV.

[0061] In this embodiment, the terminal first establishes a communication connection with each guide car and processing equipment on the production line, and receives and parses the status data sent by these devices in real time. This data includes, but is not limited to, the current position and load status of the guide car, as well as the operating status, processing progress, and fault information of the processing equipment. The terminal integrates this data to form real-time resource status information of each guide car and each processing equipment in the production line.

[0062] Step 204: Determine the scheduling strategy based on the real-time resource status and the preset hybrid scheduling optimization model.

[0063] The hybrid scheduling optimization model is a mathematical model used to find the optimal scheduling scheme under given conditions. The scheduling strategy refers to the strategy formulated based on real-time resource status and the hybrid scheduling optimization model to guide how guide vehicles and processing equipment in the production line should work together.

[0064] In this embodiment, the terminal inputs the acquired real-time resource status information into a preset hybrid scheduling optimization model. This model comprehensively considers various constraints of the production line, such as equipment capacity, material requirements, and delivery time, as well as preset optimization objectives, such as minimizing production completion time and minimizing total completion time. The hybrid scheduling optimization model outputs an optimal scheduling strategy for the current production state. This strategy details the task allocation, execution order, and planned time arrangement for each guide car and processing equipment.

[0065] Step 206: Generate guide car control instructions and processing control instructions according to the scheduling strategy. The guide car control instructions are used to schedule the corresponding guide cars, and the processing control instructions are used to control the corresponding processing equipment.

[0066] In this embodiment, the terminal generates guide vehicle control commands for each guide vehicle and processing control commands for each processing equipment according to the established scheduling strategy. The terminal sends these commands to the corresponding guide vehicles and processing equipment through the communication network to ensure that they can perform tasks in accordance with the requirements of the scheduling strategy.

[0067] After obtaining the real-time resource status of each guide car and processing equipment in the production line, this application inputs the real-time resource status into a preset hybrid scheduling optimization model to determine the scheduling strategy, and controls each guide car and processing equipment based on the scheduling strategy. It can synchronously schedule the guide cars and processing equipment in real time based on the real-time resource status of different guide cars and processing equipment in the production line, thereby improving the overall production efficiency of the production line.

[0068] In some embodiments, such as Figure 3 As shown, the intelligent scheduling method for the production line also includes steps 302 to 308. Wherein:

[0069] Step 302: Obtain the attribute information of each guide vehicle and each processing equipment.

[0070] The attribute information includes various characteristic parameters of the guide vehicle itself, covering its model, maximum load capacity, etc. It also includes the inherent characteristic parameters of the processing equipment itself, including the type of processing equipment, buffer zone capacity, and workstation information.

[0071] In this embodiment, the terminal sends attribute information acquisition requests to each guide vehicle and processing equipment on the production line. After receiving the request, the guide vehicle and processing equipment feed back their stored attribute information to the terminal. The terminal receives and stores this feedback information, thereby obtaining the attribute information of each guide vehicle and each processing equipment.

[0072] Step 304: Obtain work order information.

[0073] The work order information includes the processing time for each process and the type of product produced by each work order.

[0074] In this embodiment, the terminal obtains work order information input by the user or by other devices. The work order information includes the processing time of each process in the work order and the product type of the products produced by each work order.

[0075] Step 306: Obtain the transportation time information between each guide vehicle and different processing equipment;

[0076] Among them, the transportation time information guides the time required for the vehicle to move from the material storage point to each processing equipment.

[0077] In this embodiment, the terminal's memory stores the transportation time information between the guide vehicle and different processing equipment in advance, and the terminal directly retrieves the transportation time information from the memory.

[0078] Step 308: Based on attribute information and preset optimization objectives, construct a hybrid scheduling optimization model.

[0079] Among them, the preset optimization target refers to the expected goal set in advance based on production needs, such as minimizing the production cycle, maximizing equipment utilization, reducing energy consumption, and improving product quality.

[0080] In this embodiment, the terminal uses the attribute information of each guide vehicle and processing equipment as input data, combines it with the pre-set optimization goal, and considers various constraints in the production process to construct a hybrid scheduling optimization model that can comprehensively consider multiple factors to achieve the preset optimization goal.

[0081] By acquiring the attribute information of each guide vehicle and processing equipment, and constructing a hybrid scheduling optimization model based on this information and preset optimization objectives, a data foundation is provided for subsequent scheduling strategy formulation. This enables the scheduling strategy to fully consider the actual performance of the equipment and guide vehicles as well as production needs, thereby formulating a more efficient scheduling plan that better suits actual production conditions. This effectively improves the production efficiency, resource utilization, and production benefits of the production line, reduces production costs, and enhances the flexibility and adaptability of the production line.

[0082] In some embodiments, step 308 includes:

[0083] Construct a multi-objective optimization function with the objectives of minimizing production completion time, minimizing total completion time, and prioritizing the output of high-priority work orders.

[0084] The optimization function is a mathematical expression used to quantify the optimization objective. The optimal solution is sought by adjusting the variables in the function to achieve the optimization objective.

[0085] In this embodiment, the terminal sets the production completion time as a combination of variables related to the completion time of each guide vehicle's transportation task and the completion time of each processing equipment's processing task, based on the logical relationship of the production process. Using task start time, processing duration, transportation duration, and work order priority as basic variables, mathematical expressions reflecting the production completion time, total production completion time, and the production completion time corresponding to the priority weight are constructed through mathematical operations. This expression is a comprehensive objective function with the optimization goals of minimizing the production completion time, minimizing the total completion time, and prioritizing the output of high-priority work orders. Its purpose is to minimize the function value through subsequent adjustment of variable values. In practical applications, the optimization objective can be set according to actual production needs; no further limitations are imposed here.

[0086] The constraints of the optimization function are determined based on attribute information, work order information, and transportation time information.

[0087] In this embodiment, the terminal analyzes the attribute information of each guide vehicle and processing equipment, and determines the constraints of the optimization function based on the attribute information. For example, the maximum load capacity of the guide vehicle limits the weight of materials or products it transports each time, and the driving speed range limits its travel time in different road sections or tasks; the processing accuracy of the processing equipment limits the specifications of the products it can process, the processing range limits the types of materials it can handle, and the maximum processing capacity limits its processing volume per unit time, etc. At the same time, considering actual production factors such as the sequence of production processes and the timeliness of material supply, the constraints are further supplemented to ensure that the solution of the optimization function is feasible in actual production.

[0088] By integrating constraints into the optimization function, a hybrid scheduling optimization model is obtained.

[0089] In this embodiment, the terminal incorporates the various constraints determined into the constructed optimization function in the form of mathematical expressions, forming a complete mathematical model that can seek to minimize the production completion time under the premise of satisfying all constraints. This model is the hybrid scheduling optimization model.

[0090] Specifically, constraints may include:

[0091] AGV capacity constraints: The number of tasks that an AGV-T can execute in parallel must not exceed the number of its buffer workstations; an AGV-B can only serve one transport task at a time.

[0092] Equipment processing constraints: Only one workpiece can be processed by the same processing equipment at any given time; the workpiece must be completed before the subsequent process can begin.

[0093] Buffer constraint: A workpiece can only be transported to its target device by an AGV if there is space in the buffer of that device; this constraint is the core of deadlock avoidance on the AGV-T side.

[0094] ATS Collaboration Constraints: When scheduling operations for the transfer machine, AGV tasks need to be assigned to both its T and B sides simultaneously, and the execution times of the two tasks must be synchronized within the transfer machine's processing time window.

[0095] Processing start time coupling constraint: The start time of workpiece processing on the equipment is the maximum value of "the end time of the previous task on the equipment" and "the time when the workpiece is delivered to the equipment by the AGV".

[0096] In the hybrid scheduling optimization model, a two-segment hybrid coding scheme can also be adopted. The first segment is the process sequencing segment, which represents the processing sequence of the work order; the second segment is the equipment allocation and AGV task association segment, which is used to allocate processing machines to processes and bind all material handling tasks to specific AGV-T or AGV-B.

[0097] By constructing a multi-objective optimization function with the objectives of minimizing production completion time, minimizing total completion time, and prioritizing the output of high-priority work orders, the core direction of scheduling optimization was clarified. Constraints were determined based on attribute information, ensuring that the optimization process and results conformed to actual production conditions. Integrating constraints into the optimization function yielded a hybrid scheduling optimization model, enabling the model to comprehensively consider multiple factors. This helps improve production line scheduling efficiency, shorten production cycles, increase resource utilization, reduce production costs, and enhance the flexibility and adaptability of the production line.

[0098] In some embodiments, step 204 described above includes:

[0099] Input the real-time resource status into the hybrid scheduling optimization model to obtain the solution space based on the hybrid scheduling optimization model, and generate the initial population of scheduling strategies.

[0100] In this context, the solution space refers to the set of all possible solutions in a mathematical optimization problem. For a hybrid scheduling optimization model, it is the set of all possible scheduling schemes that satisfy the model's constraints. The initial population, in a genetic algorithm, is a set of randomly generated individuals, each representing a potential scheduling strategy.

[0101] In this embodiment, the terminal inputs the acquired real-time resource status information of the production line into the hybrid scheduling optimization model. After receiving this real-time data, the hybrid scheduling optimization model searches for and determines all possible scheduling schemes while satisfying all constraints. These schemes constitute the solution space of the model. Subsequently, the terminal uses a random generation method to generate a certain number of individuals in the solution space. Each individual represents a potential scheduling strategy, and these individuals together form the initial population of scheduling strategies.

[0102] Specifically, heuristic rules (such as the earliest delivery date priority and the shortest processing time priority) can be combined with random generation methods to create an initial population with high diversity and quality.

[0103] A genetic algorithm is used to optimize and iterate the initial population.

[0104] Genetic algorithms are optimization algorithms that simulate natural selection and genetic mechanisms. Through operations such as selection, crossover, and mutation, the population gradually evolves to find the optimal solution. Optimization iteration refers to the process in genetic algorithms of repeatedly performing selection, crossover, and mutation operations to continuously evolve the population and gradually approach the optimal solution.

[0105] In this embodiment, the terminal follows the genetic algorithm process. First, it evaluates the fitness of individuals in the initial population. Based on a preset fitness function (usually related to the optimization objective, such as production completion time), it calculates the fitness value for each individual, which reflects the quality of the scheduling strategy represented by the individual. Then, based on the fitness values, methods such as roulette wheel selection and tournament selection are used to select a group of individuals with higher fitness from the current population as parents to generate the next generation. Next, crossover is performed on the selected parent individuals, exchanging some genes (i.e., some parameters of the scheduling strategy) to generate new individuals, increasing the diversity of the population. Finally, mutation is performed on the newly generated individuals, randomly changing the values ​​of certain genes with a certain probability to further explore the solution space. After these operations, a new generation of population is obtained, and the above process is repeated for multiple optimization iterations.

[0106] During the optimization and iteration process of the genetic algorithm, individuals in the current population are restructured through a pre-defined rescheduling mechanism to meet the constraints.

[0107] In this embodiment, during the optimization iteration process, individuals in the current population can be restructured through a pre-set rescheduling mechanism to meet the constraints that need to be satisfied after triggering rescheduling.

[0108] During the optimization and iteration process of the genetic algorithm, an external memory bank is set up to store high-quality individuals in the population for use in the variable neighborhood search algorithm.

[0109] Specifically, the optimization operations for the population in the optimization iteration of a genetic algorithm include:

[0110] Selection operation: The tournament selection method is used to select superior individuals from the population to enter the external memory bank and enter the next generation.

[0111] Crossover operation: For the process sequencing segment, a crossover operator similar to POX (Precedence Operation Crossover) is used to preserve the legal process sequence; for the equipment allocation segment, a multi-point crossover operator is used to explore new machine combinations.

[0112] Mutation operations: Mutating individuals with a certain probability, including exchanging the order of processes, changing the machine assignment of processes, etc.

[0113] During the optimization iteration process of the genetic algorithm, a variable neighborhood search algorithm is used to perform local optimization on individuals in the current population.

[0114] Among them, the variable neighborhood search algorithm is a local search algorithm that searches in different neighborhood structures to escape local optima and find better solutions. Local optimization refers to the process of finding better solutions within a local range of the solution space, aiming to improve the quality of the current solution.

[0115] In this embodiment, during each optimization iteration of the genetic algorithm, the terminal performs local optimization for each individual in the current population using a variable neighborhood search algorithm. The variable neighborhood search algorithm defines multiple different neighborhood structures, each representing a specific range in the solution space. The algorithm first searches within a neighborhood of the current individual to see if a better solution exists. If a better solution is found, the current individual is replaced with that solution; otherwise, the search switches to another neighborhood structure. By alternating searches within different neighborhood structures, the variable neighborhood search algorithm can escape the local optima of the current neighborhood and explore a wider solution space, thus performing deeper local optimization on the current individual.

[0116] Specifically, the neighborhood structure can include:

[0117] N1 (Swap Neighborhood): Randomly swap two processing steps on the same device.

[0118] N2 (Insert Neighborhood): Removes a process from its current position and inserts it into another possible position in the same equipment processing sequence.

[0119] N3 (AGV Task Reassignment Neighborhood): Randomly selects a transport task and reassigns it to another compatible, idle AGV.

[0120] N4 (Critical Path Disturbance Neighborhood): Identifies the critical path in the current scheduling scheme and specifically performs machine reselection or sequence adjustment on the processes on the path to directly shorten the total completion time.

[0121] Furthermore, elite individuals from the parent generation can be merged with offspring individuals enhanced by VNS (Variable Neighborhood Search) to form a new generation of population, ensuring that the algorithm does not degenerate.

[0122] If the optimization iteration process reaches the preset number of iterations, the current population will be used as the final scheduling strategy.

[0123] In this embodiment, the terminal records the number of iterations executed in real time during the optimization iteration process of the genetic algorithm. When the number of iterations reaches a preset value, the algorithm stops running. At this point, the individuals in the current population have undergone multiple global searches and local optimizations, exhibiting high fitness and effectively meeting the optimization objective. Furthermore, the terminal comprehensively evaluates all individuals in the current population and selects one or more individuals representing a scheduling strategy as the final scheduling strategy to guide the actual production scheduling of the production line.

[0124] In other implementations, the optimization quality of the current population can be calculated in each iteration based on the optimization objective. If the fluctuation of the optimization quality is less than a certain value in N consecutive iterations, the iteration is stopped, and the current population is used as the final scheduling strategy.

[0125] The above steps help improve production line scheduling efficiency and quality, shorten production cycles, reduce costs, and enhance the adaptability and competitiveness of the production line.

[0126] In some embodiments, the intelligent scheduling method for production lines further includes:

[0127] When a real-time resource status is found to meet a preset trigger event or to complete a preset number of tasks, the event scheduling instruction or periodic scheduling instruction corresponding to the trigger event is determined based on a preset mapping relationship.

[0128] Among them, preset trigger events refer to a series of specific conditions or situations set in advance. When the real-time resource status meets these conditions, the corresponding operation will be triggered. For example, a processing equipment malfunctions, the guide car's battery level drops below a certain threshold, or a material shortage occurs in a certain production stage. Preset mapping relationships refer to the pre-established correspondence between trigger events and event scheduling instructions, clarifying the specific scheduling measures to be taken when each trigger event occurs. For example, when a processing equipment malfunction trigger event occurs, the corresponding event scheduling instruction might be to stop the equipment from operating or to schedule a backup equipment to take over the work. Event scheduling instructions refer to the specific operation commands formulated for trigger events, used to guide the guide car or processing equipment to make corresponding adjustments to cope with abnormal situations or special needs in the production process. Periodic scheduling instructions refer to the specific operation commands formulated for periodic events of a preset number of tasks, used to guide the guide car or processing equipment to periodically execute corresponding operations or actions.

[0129] In this embodiment, the terminal continuously monitors and analyzes the real-time resource status, comparing it with preset trigger event conditions to determine whether an event meeting the trigger conditions has occurred. For example, by monitoring the operating parameters of the processing equipment in real time, when a key parameter is found to exceed the normal range and reach a preset fault trigger threshold, a processing equipment fault trigger event is identified. Once a preset trigger event is identified, the terminal immediately searches for the corresponding event scheduling instruction or periodic scheduling instruction in the stored mapping table according to a preset mapping relationship. For example, the mapping relationship explicitly specifies that the event scheduling instruction corresponding to the processing equipment fault trigger event is "stop the operation of the equipment, send an alarm message to maintenance personnel, and simultaneously schedule a backup device to start and take over the work tasks of the faulty equipment."

[0130] Send the event scheduling command to the corresponding guide vehicle or processing equipment.

[0131] In this embodiment, after determining the event scheduling instruction, the terminal sends the instruction to the corresponding guide vehicle or processing equipment via a wired or wireless communication network (such as industrial Ethernet, Wi-Fi, Bluetooth, etc.) based on the target device information involved in the instruction. For example, if the event scheduling instruction is for a guide vehicle, the terminal will send the instruction to that guide vehicle. After receiving the instruction, the guide vehicle will parse it and execute the corresponding operation, such as changing the driving route or adjusting the transport speed. If the instruction is for a processing equipment, it will be sent to that processing equipment so that it can perform operations such as starting and stopping the equipment or adjusting parameters according to the instruction.

[0132] Furthermore, the triggering events can include events of different priorities, such as high-priority events like AGV or critical equipment failures or urgent order insertions, and low-priority events like task completion times deviating from planned times by more than a preset threshold or continuous deterioration of overall system performance. When the triggering conditions are met, currently executing tasks are immediately frozen, and unstarted tasks and affected tasks in transit are added to a new scheduling set. After adjusting the production line operation based on the triggering events, a new hybrid scheduling optimization model is regenerated using the current attribute information. Then, a scheduling strategy is generated based on this new hybrid scheduling optimization model to adapt to unexpected situations on the production line.

[0133] By pre-setting trigger events and corresponding scheduling instructions, various abnormal situations in the production process can be identified and handled in a timely manner, such as equipment failures and material shortages, to avoid production interruptions and ensure the continuity and stability of production. Furthermore, diverse scheduling strategies can be formulated based on different trigger events, flexibly adjusting the operating status of guide cars and processing equipment to adapt to different production needs and changes, thereby improving the adaptability and flexibility of the production line.

[0134] In some embodiments, step 206 described above includes:

[0135] The scheduling strategy is decoded into equipment processing queues and handling task sequences that include planned time information and identity information.

[0136] The planned time information refers to the start and end times of each production task (including processing and handling tasks), as well as the time intervals between tasks, used to accurately arrange the sequence and pace of the production process. Identification information refers to the guide vehicles involved in the production task, related work order information such as work order number and work order procedure, and the unique identifiers of the processing equipment, such as the guide vehicle number and the model and serial number of the processing equipment, ensuring that tasks are accurately assigned to specific equipment. The equipment processing queue refers to a series of processing tasks arranged in chronological order, with each processing task associated with specific processing equipment identification information, indicating which equipment needs to perform which processing operation at what time. The handling task sequence refers to a series of handling tasks arranged in chronological order, with each handling task associated with the guide vehicle's identification information, indicating when the guide vehicle needs to perform material handling operations from where and where.

[0137] In this embodiment, the terminal parses the scheduling strategy. The scheduling strategy is usually stored in a specific data structure or mathematical form. The terminal uses algorithms and programs corresponding to the specific data structure or mathematical form to transform this information into a device processing queue and a handling task sequence containing time information and identity information.

[0138] For example, the scheduling strategy might exist in the form of a task scheduling table, which records information such as the device number, task type (processing or handling), estimated start and end times for each task. The terminal reads this information, organizes processing tasks into device processing queues according to time sequence, organizes handling tasks into handling task sequences, and associates each task with corresponding device identity information.

[0139] Based on the handling task sequence, guide vehicle control instructions, including the handling path, are generated for the guide vehicle corresponding to the identity information.

[0140] Among them, the guide vehicle control command refers to the control commands specifically formulated for the guide vehicle, which are used to guide the guide vehicle to perform specific handling operations, including parameters such as handling path, speed, and acceleration. The handling path guides the specific route that the guide vehicle needs to travel when performing handling tasks, and consists of a series of coordinate points or path nodes, ensuring that the guide vehicle can accurately and efficiently transport materials from the starting point to the destination.

[0141] In this embodiment, for each handling task in the handling task sequence, the terminal determines the specific guide vehicle based on its associated guide vehicle identity information. Then, considering the production line layout, material storage location, and task target location, the terminal plans the optimal handling path for that guide vehicle.

[0142] When planning the transport path, various factors may be considered, such as path length, obstacle avoidance, and conflicts with other guide vehicles. After planning is completed, the terminal generates guide vehicle control commands that include the transport path and other relevant control parameters (such as speed, acceleration, etc., which can be set according to actual needs).

[0143] For example, for a guide vehicle numbered "GV-001", its task is to transport materials from warehouse A to processing equipment B. The terminal-planned transport path may be a broken line composed of a series of coordinate points. The guide vehicle control command clearly requires the guide vehicle to travel along this path and complete the transport task at a specified speed and acceleration.

[0144] Based on the equipment processing queue, a processing control instruction, including the start and end times of processing, is generated for the processing equipment corresponding to the identity information.

[0145] Among them, processing control instructions refer to control commands specifically formulated for processing equipment, which are used to guide the processing equipment to perform specific processing operations, including processing start time, end time, and processing parameters (such as rotational speed, temperature, pressure, etc.).

[0146] In this embodiment, the terminal determines the specific processing device for each processing task in the processing queue based on its associated processing device identity information. Then, according to the task's time requirements, it generates a processing control instruction containing the processing start and end times. In addition to time information, the processing control instruction may also include processing parameters related to the specific processing task, which are set according to the product's processing technology requirements.

[0147] For example, for a processing machine numbered "MC-001", its processing task is to mill a batch of materials within a specific time period. The processing control instructions generated by the terminal will clearly specify that the machine will start at the [start time] and stop at the [end time], while setting appropriate milling speed and feed rate parameters.

[0148] By decoding the scheduling strategy into specific equipment processing queues and handling task sequences, and generating guide car control instructions and processing control instructions respectively, precise scheduling of guide cars and processing equipment in the production line is achieved, ensuring that each piece of equipment can perform the correct task at the correct time.

[0149] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0150] Based on the same inventive concept, this application also provides an intelligent scheduling device for production lines to implement the intelligent scheduling method for production lines described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations of one or more intelligent scheduling device embodiments for production lines provided below can be found in the limitations of the intelligent scheduling method for production lines described above, and will not be repeated here.

[0151] In one exemplary embodiment, such as Figure 4 As shown, an intelligent scheduling device for a production line is provided, comprising:

[0152] The resource status sensing module 401 is used to obtain the real-time resource status of each work order, each guide car and each processing equipment in the production line.

[0153] The optimization solution module 402 is used to determine the scheduling strategy based on the real-time resource status and the preset hybrid scheduling optimization model;

[0154] The execution module 403 is used to generate guide car control instructions and processing control instructions according to the scheduling strategy. The guide car control instructions are used to schedule the corresponding guide cars, and the processing control instructions are used to control the corresponding processing equipment.

[0155] In one embodiment, the intelligent scheduling device for the production line further includes:

[0156] Modeling module 404 is used to obtain attribute information of each guide vehicle and each processing equipment; obtain work order information, which includes the processing time of each process and the product type produced by each work order; obtain transportation time information between each guide vehicle and different processing equipment; and construct a hybrid scheduling optimization model based on attribute information, work order information, transportation time information and preset optimization objectives.

[0157] In one embodiment, the modeling module 404 is further configured to construct a multi-objective optimization function with the optimization objectives of minimizing production completion time, minimizing total completion time, and prioritizing the output of high-priority work orders; determine the constraints of the optimization function based on attribute information, work order information, and transportation time information; and integrate the constraints into the optimization function to obtain a hybrid scheduling optimization model.

[0158] In one embodiment, the optimization solution module 402 is further configured to input the real-time resource status into the hybrid scheduling optimization model to obtain the solution space based on the hybrid scheduling optimization model, and generate an initial population for the scheduling strategy; use a genetic algorithm to perform optimization iteration on the initial population; during the optimization iteration of the genetic algorithm, use a variable neighborhood search algorithm to perform local optimization on individuals in the current population; during the optimization iteration of the genetic algorithm, reconstruct individuals in the current population through a preset rescheduling mechanism to meet the constraints; during the optimization iteration of the genetic algorithm, set up an external memory bank to store high-quality individuals in the population for the variable neighborhood search algorithm; and when the optimization iteration process reaches a preset number of iterations, use the current population as the final scheduling strategy.

[0159] In one embodiment, the intelligent scheduling device for the production line further includes:

[0160] The event triggering module is used to determine the event scheduling instruction or periodic scheduling instruction corresponding to the triggering event based on a preset mapping relationship when the real-time resource status meets the preset triggering event or a preset number of tasks are completed; and to call the corresponding hybrid scheduling optimization model according to the event scheduling instruction or periodic scheduling instruction.

[0161] In one embodiment, the execution module 403 is further configured to decode the scheduling strategy into a device processing queue and a handling task sequence including work order processing sequence, planned time information and identity information; generate a guide vehicle control instruction including a handling path for the guide vehicle corresponding to the identity information according to the handling task sequence; and generate a processing control instruction including processing start and end for the processing device corresponding to the identity information according to the device processing queue.

[0162] Each module in the intelligent scheduling device of the aforementioned production line can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0163] In one exemplary embodiment, a computer device is provided, the internal structure of which can be as shown in the figure. Figure 5 As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores control data for the computer device. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements an intelligent scheduling method for a production line.

[0164] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0165] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described intelligent scheduling method embodiment for production lines.

[0166] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps in the above-described intelligent scheduling method embodiment for production lines.

[0167] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described intelligent scheduling method embodiment for production lines.

[0168] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0169] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0170] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for intelligent scheduling of a production line, characterized in that, The method includes: Obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line; The scheduling strategy is determined based on the real-time resource status and the preset hybrid scheduling optimization model; Based on the scheduling strategy, guide vehicle control instructions and processing control instructions are generated. The guide vehicle control instructions are used to schedule the corresponding guide vehicles, and the processing control instructions are used to control the corresponding processing equipment.

2. The method according to claim 1, characterized in that, The method further includes: Obtain the attribute information of each of the guide vehicles and each of the processing equipment; Obtain work order information, which includes the processing time of each process and the type of product produced by each work order; Obtain the transportation time information between each of the guide vehicles and different processing equipment; Based on the attribute information, the work order information, the transportation time information, and the preset optimization objectives, a hybrid scheduling optimization model is constructed.

3. The method according to claim 2, characterized in that, The process of constructing a hybrid scheduling optimization model based on the attribute information, the work order information, the transportation time information, and the preset optimization objective includes: Construct a multi-objective optimization function with the objectives of minimizing production completion time, minimizing total completion time, and prioritizing the output of high-priority work orders; The constraints of the optimization function are determined based on the attribute information, the work order information, and the transportation time information. By integrating the constraints into the optimization function, a hybrid scheduling optimization model is obtained.

4. The method according to claim 1, characterized in that, The process of determining the scheduling strategy based on the real-time resource status and a preset hybrid scheduling optimization model includes: The real-time resource status is input into the hybrid scheduling optimization model to obtain the solution space based on the hybrid scheduling optimization model, and an initial population of scheduling strategies is generated. The initial population was optimized iteratively using a genetic algorithm; During the optimization iteration process of the genetic algorithm, a variable neighborhood search algorithm is used to perform local optimization on individuals in the current population; During the optimization iteration process of the genetic algorithm, individuals in the current population are reconstructed through a preset rescheduling mechanism to meet the constraints. During the optimization iteration process of the genetic algorithm, an external memory bank is set up to store high-quality individuals in the population for use in the variable neighborhood search algorithm; If the optimization iteration process reaches a preset number of iterations, the current population will be used as the final scheduling strategy.

5. The method according to claim 1, characterized in that, The method further includes: When the real-time resource status is found to meet a preset trigger event or complete a preset number of tasks, the event scheduling instruction or periodic scheduling instruction corresponding to the trigger event is determined based on a preset mapping relationship. The corresponding hybrid scheduling optimization model is invoked according to the event scheduling instruction or periodic scheduling instruction.

6. The method according to any one of claims 1 to 5, characterized in that, The step of generating guide vehicle control instructions and processing control instructions according to the scheduling strategy includes: The scheduling strategy is decoded into a device processing queue and a handling task sequence that includes work order processing order, planned time information, and identity information. Based on the transport task sequence, a guide vehicle control command including the transport path is generated for the guide vehicle corresponding to the identity information; Based on the equipment processing queue, a processing control command, including processing start and end instructions, is generated for the processing equipment corresponding to the identity information.

7. An intelligent scheduling device for a production line, characterized in that, The device includes: The resource status sensing module is used to obtain the real-time resource status of each work order, each guide car, and each processing equipment in the production line; The optimization solution module is used to determine the scheduling strategy based on the real-time resource status and the preset hybrid scheduling optimization model; The execution module is used to generate guide vehicle control instructions and processing control instructions according to the scheduling strategy. The guide vehicle control instructions are used to schedule the corresponding guide vehicle, and the processing control instructions are used to control the corresponding processing equipment.

8. A computer device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images