Dispatching optimization method for discrete manufacturing unmanned intelligent workshop AGV under machine fault and related device

Abstract

The invention relates to the technical field of discrete manufacturing workshops, in particular to a discrete manufacturing unmanned intelligent workshop AGV scheduling optimization method under a machine fault and a related device. The method comprises the following steps: constructing a workshop scheduling model for the discrete manufacturing unmanned intelligent workshop according to a preset multi-constraint condition and a preset objective function, and determining optimal operation parameters for the workshop scheduling model based on a grey wolf-tabu search algorithm, the optimal operation parameter is used for representing an optimal scheduling strategy for the AGV and an optimal operation index of the discrete manufacturing unmanned intelligent workshop. According to the invention, machine fault disturbance can be handled in real time, and rapid recovery of production logistics and minimization of productivity loss are realized through dynamic scheduling.

Description

Technical Field

[0001] This application relates to the field of discrete manufacturing workshop technology, and in particular to an AGV scheduling optimization method and related device for an unmanned intelligent workshop in discrete manufacturing under machine failure. Background Technology

[0002] Discrete manufacturing unmanned intelligent workshops have long process chains and strict cycle times, and their production logistics are highly dependent on AGV systems. Production machines are prone to sudden failures under long-term high loads, leading to material flow interruptions, buffer backlogs, and material shortages for subsequent processes, resulting in significant capacity losses.

[0003] Currently, AGV scheduling in the industry largely relies on fixed rules or manual experience. While this works under steady-state conditions, it reveals shortcomings in dynamic fault scenarios, such as delayed response, rigid resource allocation, and insufficient global optimization, failing to minimize the production capacity impact of faults. Existing AGV scheduling algorithms in research are mostly designed for simplified, static environmental models, failing to fully couple with actual production characteristics such as multi-process chain collaboration in the workshop, cache constraints, and material timeliness. Furthermore, their robustness and real-time performance under machine failure disturbances are insufficient. Summary of the Invention

[0004] To address the aforementioned issues, this application provides an AGV scheduling optimization method and related apparatus for discrete manufacturing unmanned intelligent workshops under machine failure conditions. This method can respond to machine failure disturbances in real time and achieve rapid recovery of production logistics and minimize capacity loss through dynamic scheduling.

[0005] According to one aspect of the embodiments of this application, a method for optimizing AGV scheduling in a discrete manufacturing unmanned intelligent workshop under machine tool failure is proposed, the method comprising: A workshop scheduling model for unmanned intelligent workshops in discrete manufacturing is constructed based on preset multiple constraints and preset objective functions. The optimal operating parameters for the workshop scheduling model are determined based on the gray wolf-taboo search algorithm. These optimal operating parameters are used to characterize the optimal scheduling strategy for AGVs and the optimal operating indicators of the discrete manufacturing unmanned intelligent workshop.

[0006] In the above scheme, the preset objective function is used to characterize minimizing the production capacity loss caused by the failure of machines in the discrete manufacturing unmanned intelligent workshop.

[0007] In the above scheme, the preset multiple constraints include material processing uniqueness constraint, AGV transportation time calculation constraint, material removal constraint from the discharge port, process sequence constraint, task exclusivity constraint, buffer capacity constraint, and material buffer time constraint.

[0008] In the above scheme, determining the optimal operating parameters for the workshop scheduling model based on the gray wolf-tabu search algorithm includes: Define the operating parameters for the gray wolf-tabu search algorithm; Based on the aforementioned operating parameters, a tabu search is performed, and key parameters used to control the balance between global and local searches are iteratively updated. Based on the key parameters, neighborhood search, population evaluation, and leader wolf pack update are performed to obtain the optimal operating parameters for the workshop scheduling model.

[0009] In the above scheme, the method further includes: The optimal operating parameters are configured into the discrete manufacturing unmanned intelligent workshop to obtain the first scheduling result; The preset baseline operating parameters are configured into the discrete manufacturing unmanned intelligent workshop to obtain the second scheduling result; The first scheduling result is compared and verified with the second scheduling result to obtain a verification result, and the AGV scheduling optimization is performed for the discrete manufacturing unmanned intelligent workshop based on the verification result.

[0010] According to one aspect of the embodiments of this application, an AGV scheduling optimization device for discrete manufacturing unmanned intelligent workshops under machine tool failure is proposed, the device comprising: The building unit is used to construct a workshop scheduling model for discrete manufacturing unmanned intelligent workshops based on preset multiple constraints and preset objective functions. The determining unit is used to determine the optimal operating parameters for the workshop scheduling model based on the gray wolf-tabu search algorithm. The optimal operating parameters are used to characterize the optimal scheduling strategy for AGVs and the optimal operating indicators of the discrete manufacturing unmanned intelligent workshop.

[0011] According to one aspect of the embodiments of this application, an electronic device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions as described above.

[0012] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including a computer program, the computer program being read and executed by a processor of an electronic device, causing the electronic device to execute the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure as described above.

[0013] The beneficial effects of this application are as follows: First, this application constructs a workshop scheduling model for a discrete manufacturing unmanned intelligent workshop through preset multiple constraints and preset objective functions. Then, it determines the optimal operating parameters for the workshop scheduling model through the gray wolf-taboo search algorithm, so that in the event of machine failure, the determined optimal operating parameters can be used to achieve rapid recovery of production logistics and minimize capacity loss. Attached Figure Description

[0014] Figure 1 This is a system architecture diagram of the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure provided in the embodiments of this application; Figure 2 A flowchart illustrating the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine tool failure conditions provided in this application embodiment; Figure 3 A schematic diagram of the layout of a discrete manufacturing unmanned intelligent workshop provided in an embodiment of this application; Figure 4 This is a fitness comparison and iteration diagram of three different algorithms provided in the embodiments of this application. Figure 5 These are simulation result diagrams provided in the embodiments of this application; Figure 6 This is a Gantt chart of the optimization algorithm for scheduling faulty processes provided in the embodiments of this application; Figure 7 This is a basic scheduling fault procedure Gantt chart provided in the embodiments of this application; Figure 8 A block diagram of an AGV scheduling optimization device for discrete manufacturing unmanned intelligent workshops under machine tool failure conditions provided in an embodiment of this application; Figure 9 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application; Figure 10 This is a schematic diagram of the structure of a server provided in an embodiment of this application. Detailed Implementation

[0015] To enable those skilled in the art to better understand the solutions of this application, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0016] It should be noted that while some processes described in the specification, claims, and accompanying drawings include multiple steps appearing in a specific order, it should be clearly understood that these steps may not be performed in the order they appear herein, or may be performed in parallel. The step numbers are merely used to distinguish different steps and do not themselves represent any execution order. Furthermore, descriptions such as "first," "second," or "objective" in this document are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. "Multiple" in this document refers to at least two.

[0017] It is worth noting that in the specific embodiments of this application, data such as operating parameters and objective functions are involved. When the above embodiments of this application are applied to specific products or technologies, permission or consent from the target object is required, and the collection, use, and processing of related data must comply with relevant laws, regulations, and standards. For example, when an embodiment of this application needs to obtain data such as operating parameters and objective functions, separate permission or consent from the target object can be obtained through pop-up windows or redirection to a confirmation page. After obtaining the separate permission or consent from the target object, the operating parameters, objective functions, and other related data used to enable the embodiment of this application to operate normally can then be obtained.

[0018] Please see Figure 1 , Figure 1 This is a system architecture diagram of the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions provided in this application embodiment. It includes a terminal 140, an Internet connection 130, a gateway 120, a server 110, etc.

[0019] Terminal 140 can take various forms, including desktop computers, laptops, PDAs (personal digital assistants), mobile phones, vehicle terminals, and dedicated terminals. Furthermore, it can be a single device or a collection of multiple devices. For example, multiple desktop computers can be interconnected via a local area network, sharing a single monitor to work collaboratively, forming a single terminal 140. Terminal 140 can communicate with the Internet 130 via wired or wireless means to exchange data.

[0020] Server 110 refers to a computer system capable of providing certain services to terminal 140. Compared to ordinary terminal 140, server 110 has higher requirements in terms of stability, security, and performance. Server 110 can be a single high-performance computer in a network platform, a cluster of multiple high-performance computers, a portion of a single high-performance computer (e.g., a virtual machine), or a combination of portions of multiple high-performance computers (e.g., virtual machines). Server 110 can also communicate with the Internet 130 via wired or wireless means to exchange data.

[0021] Gateway 120, also known as an internetwork connector or protocol converter, is a computer system or device that acts as a translator, enabling network interconnection at the transport layer. It bridges the gap between two systems using different communication protocols, data formats, languages, or even completely different architectures. Gateways can also provide filtering and security functions. Messages sent from terminal 140 to server 110 are forwarded to the corresponding server 110 via gateway 120. Messages sent from server 110 to terminal 140 are also forwarded to the corresponding terminal 140 via gateway 120.

[0022] The following provides a detailed description of the specific implementation methods of the embodiments of this application: Please see Figure 2 , Figure 2 This is a flowchart illustrating the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions provided in this application embodiment. The AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions can be implemented by server 110 and / or terminal 140. Figure 2 The AGV scheduling optimization method shown for discrete manufacturing unmanned intelligent workshops under machine failure includes: Step 210: Construct a workshop scheduling model for unmanned intelligent workshops in discrete manufacturing based on preset multi-constraint conditions and preset objective functions; Step 220: Determine the optimal operating parameters for the workshop scheduling model based on the gray wolf-taboo search algorithm. The optimal operating parameters are used to characterize the optimal scheduling strategy for AGVs and the optimal operating indicators of the discrete manufacturing unmanned intelligent workshop.

[0023] The complete embodiments of this application are explained in detail below: First, the overall approach of this application can be summarized into the following five parts: S1 (Part 1): Create a two-dimensional grid map that conforms to the actual layout of the workshop machines, such as... Figure 3 As shown, this includes the AGV loading and unloading points, the AGV's initial position, etc.

[0024] S2 (Part Two): Next, the complex shop floor scheduling problem is abstracted into a mixed-integer linear programming model with the core objective of minimizing capacity loss due to machine failures. This model systematically integrates multiple real-world constraints such as material balance, machine capacity, AGV paths, buffer capacity, and process sequence.

[0025] S3 (Part Three): Based on the mathematical model constructed in S2, a hybrid gray wolf-tabu search algorithm is designed. By embedding a tabu search strategy into the gray wolf optimization algorithm, this manifests as a tabu search local optimization performed every 5 generations during the algorithm's iteration process, i.e., on the current optimal solution (Alpha wolf). TS avoids circular searches by maintaining a "tabu table" that records recently visited solutions and performs neighborhood searches near the current optimal solution to find a better "amnesty solution".

[0026] S4 (Part Four): The AGV scheduling strategy is dynamically adjusted by optimizing the workshop scheduling parameters. The Grey Wolf Optimization Algorithm and the Particle Swarm Optimization Algorithm are set as comparison benchmarks, and all comparison algorithms are run in the same simulation environment and under the same initial conditions.

[0027] S5 (Part 5): Build a workshop environment using Flexsim simulation software, set the hybrid gray wolf-tacit search strategy obtained in S4 into the workshop environment, and compare it with the basic workshop scheduling rules.

[0028] Furthermore, S1 is specifically as follows: S11: Rasterized Modeling of Workshop Environment Based on the actual physical dimensions of the workshop, a two-dimensional grid map is created, clearly defining the obstacle machine area and the AGV's walkable area. The loading and unloading positions of all machines and the initial position coordinates of the AGV are accurately marked on the map.

[0029] S12: Path Network and Distance Matrix Calculation Based on the grid map and key point coordinates, a topological network for AGV path planning is constructed. A graph search algorithm is used to calculate the shortest path distance between any pair of key points in the network, generating a distance matrix.

[0030] Further, step S2 includes the following steps: S21: The model established in S2 makes the following assumptions: The faulty machine is in a faulty state at the start of the simulation; Ignoring the number of AGVs and the occurrence of malfunctions Ignoring the charging status of the AGV S22: The workshop scheduling model is as follows: The objective function is to minimize the production capacity loss caused by faulty machines. ; In equation (1.1), For specific processes, it is a set of processes. One of the elements; This refers to the collection of all processes in the workshop. For specific faulty machines; This is a normal machine. This refers to the set of machines used in the u-th production process. The time step is the discretized time step, which is a certain moment within the scheduling period; This represents the total number of time steps in the scheduling cycle. For time The number of AGVs arriving at the faulty machine; for From the faulty machine within the time limit Distribute materials to the machine The number of AGVs; This represents the average transport time of materials within the workshop. The time required to process a batch of materials for the uth process; This represents the production capacity per minute of the faulty machine. The formula consists of two additions: the penalty cost incurred due to unsuccessful material allocation and the direct production capacity loss corresponding to the time spent transporting materials. The aim is to minimize the production capacity loss caused by machine failure.

[0031] Material processing uniqueness constraint: ;

[0032] In equation (1.2): For specific AGV carts; A collection of AGV carts; For all machines; The constraint indicates that a value of 1 represents material being delivered to the i-th machine in the u-th process, and 0 otherwise; the constraint indicates that for any material arriving at a faulty machine, it must and can only be assigned to one process. One of the normal machines Processing is then carried out. This constraint prevents materials from being repeatedly dispatched or left unused, ensuring the certainty of production tasks.

[0033] AGV transport time calculation constraints: ;

[0034] In equation (1.3): the constraint represents the total time required for the AGV to perform a single transport task. It consists of three parts: from the current position of the AGV to the faulty machine. Idle running time, from the faulty machine To the target machine Full-load driving time and fixed docking and operation time This constraint translates spatial distance and AGV performance parameters into time costs.

[0035] Material removal constraints at the discharge port: ; In equation (1.4): For AGVr to reach the process from its current position machine The distance; This constraint defines the AGV's no-load speed; it aims to prevent blockages at the AGV's discharge port due to material delays, which could force upstream processes to shut down. The constraint requires that the time it takes for the AGV to remove material from the AGV's discharge port must not exceed the standard processing cycle time for that process. This ensures that the logistics cycle time matches the production cycle time.

[0036] Process sequence constraints: ; In equation (1.5): This indicates that AGVr will move materials from the process. machine Transport to process machine The value is 1 if the condition is met, and 0 otherwise; this constraint mandates that the material flow path within the workshop must be strictly ordered. It indicates that the materials transported by the AGV are destined for a specific process. It must be the source process. The next step is the next process. This eliminates unnecessary material transport that skips steps, flows back, or violates the process flow.

[0037] Task exclusivity constraint: ; In equation (1.6): This indicates that AGVr is at any time The value is 1 if a material transport task is performed, and 0 otherwise; this constraint guarantees that at any given time... The same specific handling task (from the process) machine to process machine This task can only be performed by one AGV. This avoids conflicts and resource waste caused by assigning the same task to multiple AGVs.

[0038] Cache capacity constraints: ; Equation (1.7): For any time Arrival Process machine The number of AGV carts; For process The buffer capacity of the feed port on the machine; constraints require that at any given time... any process any machine The amount of material accumulated in the buffer area The capacity of the cache must not exceed the maximum capacity designed for the cache area. This prevents buffer overflows caused by improper scheduling, which could lead to material damage or production interruptions in actual production.

[0039] Material buffer time constraints: ; In equation (1.8): For AGVr leaving the process machine Time; For AGVr to enter the process machine Time; For process The maximum storage time for materials; this constraint reflects the control over material quality and production timeliness. The residence time (departure time) of any material in the buffer area. With arrival time The difference (total storage time) must not exceed its maximum allowable storage time. This is mainly used to prevent time-sensitive materials from degrading or becoming unusable due to long waiting times, thus integrating quality control requirements into scheduling optimization.

[0040] Further, step S3 includes the following steps: S31: Algorithm Initialization and Parameter Setting First, the algorithm's operating parameters are defined to prepare for solving the mathematical model established in step S2. Key parameters include: setting the maximum number of iterations, Max_iter, to 150 to control the algorithm's total search time; setting the number of wolves, SearchAgents_no, to 4 to balance the algorithm's global exploration capability with computational complexity; and determining the solution vector's dimension, dim, to 4, with a lower bound of lb and an upper bound of ub, based on the boundaries of the mathematical model's decision variables. Finally, the initial positions of the wolves in the solution space, Positions, are randomly initialized, and Alpha, Beta, and Delta wolves are initialized to record the optimal, second-best, and third-best solutions and their fitness values.

[0041] S32: Taboo Search Module Initialization To embed the tabu search strategy, its key components need to be initialized. This includes setting the maximum capacity of the tabu table, `tabu_list_size`, to 5 to store recently visited solutions; setting the tabu tenure, `tabu_tenure`, to 3 to control the time each solution stays in the tabu table; and defining the neighborhood size, `neighborhood_size`, to 5 to control the scope of the local search. Simultaneously, the tabu table `tabu_list` and its corresponding tabu tenure counter, `tabu_time`, are created and initialized.

[0042] S33: Main Iteration Loop and Standard Gray Wolf Position Update The algorithm enters the main iteration loop. In each iteration t, the key parameter 'a' controlling the balance between global and local search is first calculated and updated, decreasing linearly with the number of iterations. Then, following the standard gray wolf optimization algorithm, based on the current positions of Alpha, Beta, and Delta wolves, the position of each ordinary wolf in the population is updated by simulating the social hierarchy and hunting behavior of the wolf pack. The update formula is a weighted average combining the influence of Alpha, Beta, and Delta wolf positions, and random perturbation factors A and C are introduced to maintain the exploratory nature of the algorithm. The updated positions must ensure that they satisfy the boundary constraints of the solution variables.

[0043] S34: Tabu List Constraints and Neighborhood Search Based on the updated wolf positions, a tabu search avoidance strategy is implemented. For each updated wolf position, the algorithm calculates its "solution distance" to all records in the tabu list (tabu_list). If the distance is less than a preset threshold, the new position is considered a tabu solution. When a tabu solution is detected, the algorithm does not directly accept the position but generates several candidate new solutions within a small "neighborhood". These neighborhood solutions are evaluated by calling the fitness evaluation function (evaluateSolution), and the solution that is not in the tabu list and has the best fitness is selected as the wolf's final new position.

[0044] S35: Periodic Tabu Search with Local Enhancement To achieve deep mining within the global search framework, the algorithm employs a periodic local enhancement strategy. Specifically, every 5 iterations, the algorithm performs a concentrated tabu search for local optimization on the current global optimum (Alpha Wolf). This operation is implemented by the independent function `tabuLocalSearch`, which performs a fine-grained search within a defined neighborhood centered on the Alpha Wolf's current position. This local search also maintains a short-term tabu list to avoid repeated searches within extremely small ranges and allows for "amnesty solutions" that are better than the current historical optimum. If the local search finds a solution superior to the current Alpha Wolf, the Alpha Wolf's position and fitness value are immediately updated. This step is the core innovation of the hybrid algorithm, effectively combining the global guidance capability of GWO with the local mining capability of TS.

[0045] S36: Population Assessment and Leadership Renewal of the Wolf Pack After updating the positions of all wolves, the `evaluateSolution` function is called to evaluate the fitness value of the entire new population. This fitness value is the objective function value of the mathematical model. Based on the evaluation results, the positions and fitness values ​​of the Alpha, Beta, and Delta wolves, representing the optimal, second-best, and third-best solutions, are updated. Simultaneously, the optimal fitness value of this iteration is recorded for plotting the convergence curve (`Convergence_curve`).

[0046] S37: Algorithm Termination and Output of Optimal Solution The algorithm terminates after reaching the maximum number of iterations, Max_iter. The final output, Alpha_pos, is the optimal scheduling parameter vector found by the algorithm that minimizes production capacity loss. This parameter vector can be decoded into specific shop floor scheduling instructions, with scheduling parameters including the fault buffer material inspection frequency, AGV allocation strategy weight, target machine selection strategy weight, and the maximum number of AGVs to be deployed in a single operation. The complete convergence process and optimization history are also output.

[0047] Further, step S4 includes the following steps: S41: Decode the optimized solution vector into specific scheduling parameters The optimal solution vector output from step S3 The scheduling decision information is extracted and decoded into scheduling parameters that can be directly applied to the FlexSim simulation model. The specific decoding method is as follows: Parameter X1 is decoded as the material inspection frequency: ; in, This represents the frequency of material checks in the buffer area, and is a random number ranging from 1 to 20. Parameters X2 and X3 are decoded into allocation strategies: X2 and X3 serve as weights to dynamically adjust the allocation strategy between the AGV and the target machine. The AGV allocation strategy is a weighted mixture of "nearest assignment" and "random assignment" based on the value of X2, while the target machine selection strategy is a trade-off between "buffer space priority" and "nearest distance priority" based on the value of X3.

[0048] Parameter X4 is decoded to the maximum single distribution amount: ; in, This represents the maximum number of AGVs that can be dispatched in each check of the buffer area, and is a random number ranging from 1 to 10. This parameter limits the upper limit of the number of AGVs that can be dispatched to a faulty machine in a single scheduling. It is directly related to the task exclusivity constraint (Formula 1.7) and the buffer area capacity constraint (Formula 1.8), and aims to avoid path congestion or target buffer area overflow caused by dispatching too many AGVs in a short period of time.

[0049] S42: Set the benchmark algorithm First benchmark for comparison: Implementation of the standard gray wolf optimization algorithm. This algorithm serves as the foundational framework of the core algorithm of this invention. Its social hierarchy (Alpha, Beta, Delta) and encirclement mechanism are consistent with the main gray wolf optimization framework of this invention, but it lacks the tabu search local optimization module embedded in this invention. The process includes population initialization, hierarchy-based position updates, simulation of cooperative hunting behavior of the wolf pack using formulas, and iterative updates of the leader wolf pack.

[0050] ; in, Indicates the first Sekiro in the 1990s A new position in the solution space; The positional components calculated for attraction to Alpha wolves; Positional components calculated for attraction to Beta wolves; The positional component calculated for attraction to Delta wolves.

[0051] The second benchmark is the implementation of the particle swarm optimization algorithm, which guides the search by using the historical best of individual particles and the global best experience of the swarm.

[0052] The speed update formula is: ; in, Indicates the first The current velocity vector of each particle; Inertial weights control the degree to which the particle's historical velocity affects its current velocity; For individual learning factors; As a social learning factor; , These are random numbers uniformly distributed in [0,1]. For the first The individual best position in the history found by each particle; The globally optimal position is found for the entire particle swarm; all algorithms call the same `evaluateSolution` function to calculate fitness, which directly corresponds to the minimization of productivity loss objective defined in the mathematical model of this invention (Equation 1.1). The same maximum number of iterations (150 iterations), population size (4), and solution space dimension (4) are set.

[0053] Further, step S5 includes the following steps: S51: Constructing a high-fidelity FlexSim discrete event simulation model In FlexSim software, an accurate digital twin model is constructed based on the physical layout, process flow, and equipment parameters of the smart workshop. This model includes: Static entity modeling: Creating 3D models of physical entities such as AGVs, processing machines for each process, buffer areas, material sources, and product absorbers, and defining their coordinates and travel paths based on the 2D grid map and topology network established by S1. Dynamic logic modeling: Assigning the model behavioral logic consistent with actual production, including: processing cycles and fault triggering logic for machines, AGV handling task execution flow, buffer area capacity management, and material flow transfer rules between processes.

[0054] S52: Configure GWO-TS optimized scheduling strategy The optimal parameter vector [X1, X2, X3, X4] obtained in step S4 through the hybrid gray wolf-tabu search algorithm is transformed into specific dynamic scheduling rules that can be recognized and executed by the FlexSim model through the decoding logic defined in step S41. These rules dynamically determine the key behaviors of the AGV, such as inspection frequency, allocation preference, and target selection, and are configured into the same constructed FlexSim model.

[0055] like Figure 4 , Figure 5 , Figure 6 , Figure 7As shown in the simulation results, in 10 independent simulations, the proposed Hybrid Grey Wolf-Taboo Search (GWO-TS) optimization strategy (i.e., optimal operating parameters) significantly outperforms the basic workshop scheduling rules (i.e., the preset baseline operating parameters). Under the same fault scenarios, the GWO-TS strategy reduces capacity loss by approximately 40%-70%, and the operating results are stable. From the machine state Gantt chart, under the GWO-TS strategy, the processing status of each machine is continuous with minimal congestion, and the system operates smoothly; while under the basic rules, large-scale and prolonged congestion occurs, leading to frequent production interruptions. The simulation results fully demonstrate that this method can effectively reduce capacity loss under machine faults and effectively prevent congestion through intelligent dynamic scheduling, ensuring continuous material flow and efficient equipment operation, thereby significantly improving workshop production resilience and overall efficiency. The beneficial effects of this application are as follows: By deeply integrating digital twin simulation with the self-designed hybrid Grey Wolf-Taboo Search (GWO-TS) intelligent optimization algorithm, a dynamic scheduling system for AGVs is constructed, achieving a comprehensive improvement in scheduling response, optimization quality, and system stability under machine failure conditions in discrete manufacturing unmanned intelligent workshops. The system's scheduling instructions, aimed at minimizing production capacity loss, have been verified by FlexSim simulation. Under the same failure scenario, its scheduling scheme can reduce production capacity loss by 40%-70% compared to existing basic rules in the workshop, and effectively avoid material flow blockage and buffer overflow caused by improper scheduling, significantly enhancing the production system's anti-disturbance capability and operational smoothness. Simultaneously, the constructed "modeling-optimization-simulation-verification" technical framework possesses good versatility and scalability, providing a reliable and efficient solution for dynamic scheduling optimization in intelligent manufacturing workshops.

[0056] Please see Figure 8 , Figure 8 This is a schematic diagram of the AGV scheduling optimization device for discrete manufacturing unmanned intelligent workshops under machine failure conditions provided in this application embodiment. This device is applied to computer equipment and may include: Construction unit 401 is used to construct a workshop scheduling model for discrete manufacturing unmanned intelligent workshops based on preset multiple constraints and preset objective functions; The determining unit 402 is used to determine the optimal operating parameters for the workshop scheduling model based on the gray wolf-tabu search algorithm. The optimal operating parameters are used to characterize the optimal scheduling strategy for AGVs and the optimal operating indicators of the discrete manufacturing unmanned intelligent workshop.

[0057] Reference Figure 9 , Figure 9To implement the structural block diagram of a portion of the terminal 140 in this application embodiment, the terminal 140 includes: a radio frequency (RF) circuit 710, a memory 715, an input unit 730, a display unit 740, a sensor 750, an audio circuit 760, a wireless fidelity (WiFi) module 770, a processor 780, and a power supply 790, among other components. Those skilled in the art will understand that... Figure 9 The terminal 140 structure shown does not constitute a limitation on a mobile phone or computer, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0058] The RF circuit 710 can be used to receive and transmit signals during information transmission or calls. In particular, it receives downlink information from the base station and processes it with the processor 780; in addition, it transmits uplink data to the base station.

[0059] The memory 715 can be used to store software programs and modules. The processor 780 executes various terminal functions and AGV scheduling optimization processing in discrete manufacturing unmanned intelligent workshops by running the software programs and modules stored in the memory 715.

[0060] The input unit 730 can be used to receive input numeric or character information, and to generate key signal inputs related to the terminal's settings and function control. Specifically, the input unit 730 may include a touch panel 731 and other input devices 732.

[0061] The display unit 740 can be used to display input or provided information, as well as various menus of the terminal. The display unit 740 may include a display panel 741.

[0062] Audio circuitry 760, speaker 761, and microphone 762 provide an audio interface.

[0063] In this embodiment, the processor 780 included in the terminal 140 can execute the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions as described in the previous embodiment.

[0064] The terminal 140 in this application embodiment includes, but is not limited to, mobile phones, computers, intelligent voice interaction devices, smart home appliances, vehicle terminals, and aircraft. This application embodiment can be applied to various scenarios, including but not limited to cloud technology, artificial intelligence, smart transportation, and assisted driving.

[0065] Figure 10This is a partial structural block diagram of a server 110 implementing an embodiment of this application. The server 110 can vary significantly due to different configurations or performance characteristics, and may include one or more central processing units (CPUs) 822 (e.g., one or more processors) and memory 832, and one or more storage media 830 (e.g., one or more mass storage devices) for storing application programs 842 or data 844. The memory 832 and storage media 830 can be temporary or persistent storage. The program stored in the storage media 830 may include one or more modules (not shown in the diagram), each module including a series of instruction operations on the server 110. Furthermore, the CPU 822 may be configured to communicate with the storage media 830 and execute the series of instruction operations in the storage media 830 on the server 110.

[0066] Server 110 may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input / output interfaces 858, and / or one or more operating systems 841, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0067] The central processing unit 822 in server 110 can be used to execute the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure according to the embodiments of this application.

[0068] This application also provides a computer-readable storage medium for storing program code, which is used to execute the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions in the foregoing embodiments.

[0069] This application also provides a computer program product, which includes a computer program. The processor of a computer device reads and executes the computer program, causing the computer device to implement the above-described AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions.

[0070] Furthermore, the terms “comprising” and “including”, and any variations thereof, are intended to cover non-exclusive inclusion, such that a process, method, system, product, or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or apparatus.

[0071] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0072] It should be understood that in the description of the embodiments of this application, "multiple" means two or more, "greater than", "less than", "exceeding" etc. are understood to exclude the number itself, and "above", "below", "within" etc. are understood to include the number itself.

[0073] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between apparatuses or units, and may be electrical, mechanical, or other forms.

[0074] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0075] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0076] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0077] It should also be understood that the various implementation methods provided in this application can be combined arbitrarily to achieve different technical effects.

[0078] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0079] The above is a detailed description of the embodiments of this application. However, this application is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for optimizing AGV scheduling in a discrete manufacturing unmanned intelligent workshop under machine failure, characterized in that: The method includes: A workshop scheduling model for unmanned intelligent workshops in discrete manufacturing is constructed based on preset multiple constraints and preset objective functions. The optimal operating parameters for the workshop scheduling model are determined based on the gray wolf-taboo search algorithm. These optimal operating parameters are used to characterize the optimal scheduling strategy for AGVs and the optimal operating indicators of the discrete manufacturing unmanned intelligent workshop.

2. The AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions as described in claim 1, characterized in that, The preset objective function is used to characterize minimizing the production capacity loss caused by the failure of machines in the discrete manufacturing unmanned intelligent workshop.

3. The AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions as described in claim 1, characterized in that, The preset multiple constraints include material processing uniqueness constraint, AGV transportation time calculation constraint, material removal constraint from the discharge port, process sequence constraint, task exclusivity constraint, buffer capacity constraint, and material buffer time constraint.

4. The AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions as described in claim 1, characterized in that, The determination of optimal operating parameters for the workshop scheduling model based on the gray wolf-tabu search algorithm includes: Define the operating parameters for the gray wolf-tabu search algorithm; Based on the aforementioned operating parameters, a tabu search is performed, and key parameters used to control the balance between global and local searches are iteratively updated. Based on the key parameters, neighborhood search, population evaluation, and leader wolf pack update are performed to obtain the optimal operating parameters for the workshop scheduling model.

5. The AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure conditions as described in claim 1, characterized in that, The method further includes: The optimal operating parameters are configured into the discrete manufacturing unmanned intelligent workshop to obtain the first scheduling result; The preset baseline operating parameters are configured into the discrete manufacturing unmanned intelligent workshop to obtain the second scheduling result; The first scheduling result is compared and verified with the second scheduling result to obtain a verification result, and the AGV scheduling optimization is performed for the discrete manufacturing unmanned intelligent workshop based on the verification result.

6. A scheduling and optimization device for AGVs in a discrete manufacturing unmanned intelligent workshop under machine failure, characterized in that, The device includes: The building unit is used to construct a workshop scheduling model for discrete manufacturing unmanned intelligent workshops based on preset multiple constraints and preset objective functions. The determining unit is used to determine the optimal operating parameters for the workshop scheduling model based on the gray wolf-tabu search algorithm. The optimal operating parameters are used to characterize the optimal scheduling strategy for AGVs and the optimal operating indicators of the discrete manufacturing unmanned intelligent workshop.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure as described in any one of claims 1 to 5.

8. A computer program product, the computer program product comprising a computer program, characterized in that, The computer program is read and executed by the processor of the electronic device, causing the electronic device to perform the AGV scheduling optimization method for discrete manufacturing unmanned intelligent workshops under machine failure as described in any one of claims 1 to 5.

Images