Multi-AGV flexible job shop active scheduling method based on IWOA algorithm and related device

Abstract

The invention provides a multi-AGV flexible job shop active scheduling method based on an IWOA algorithm and a related device, and belongs to the technical field of shop active scheduling. According to the method, a multi-objective optimization model for active scheduling of a multi-AGV flexible job shop is constructed; setting constraint conditions of the multi-objective optimization model; improving the whale optimization algorithm by adopting a reverse learning mode, a nonlinear convergence factor, a segmented inertia weight and a multi-direction spiral search mechanism to obtain an improved whale optimization algorithm; based on a set constraint condition of the multi-objective optimization model, an improved whale optimization algorithm is adopted to solve decision variables in an objective function of the established multi-objective optimization model for active scheduling of the multi-AGV flexible job shop, and a Pareto frontier is obtained; and selecting a group of solutions from the Pareto frontier to obtain an active scheduling result, thereby carrying out active scheduling on the multi-AGV flexible job shop. According to the invention, the problem of low accuracy of active scheduling of the multi-AGV flexible job shop is solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of active workshop scheduling, and in particular relates to an active scheduling method and related devices for a multi-AGV flexible workshop based on an IWOA (Improved Whale Optimization Algorithm) algorithm. Background Art

[0002] With the rapid development of modern manufacturing, the Flexible Job-shop Scheduling Problem (FJSP) has become a critical issue in production process optimization. Traditional FJSP focuses primarily on optimizing the allocation of machine resources. However, in actual production environments, transportation resources also have a significant impact on production efficiency. The automation upgrade of equipment has exacerbated the fragility of production systems. Machine failures have become a major uncertainty factor in workshop operations, often coupled with the scheduling of multiple AGVs (Automated Guided Vehicles) in workshops, disrupting production rhythms and causing imbalances in material supply. Flexible job-shops need to consider multi-objective optimization, including production efficiency, operating costs, and carbon emissions.

[0003] The Whale Optimization Algorithm (WOA) algorithm was proposed in 2016. Compared with traditional optimization algorithms, the WOA algorithm has excellent global exploration capabilities, efficient convergence performance, and simple parameter design. In recent years, it has performed well in the field of discrete optimization.

[0004] However, when dealing with high-dimensional and complex optimization problems, the standard WOA algorithm sometimes falls into local optimality, resulting in low accuracy of the optimal solution of the objective function and slow convergence. In particular, when dealing with problems with multiple constraints and variables such as PS-FJSP-MA (Proactive Scheduling in Flexible Job Shops with Multiple AGVs), both performance and efficiency need to be improved.

[0005] In summary, the current active scheduling method for multi-AGV flexible workshops based on the WOA algorithm has low accuracy. Summary of the Invention

[0006] The purpose of the present invention is to provide a multi-AGV flexible workshop active scheduling method and related devices based on the IWOA algorithm, which are used to solve the problem of low accuracy of active scheduling of multi-AGV flexible workshops in the prior art.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] In a first aspect, the present invention provides a multi-AGV flexible job shop active scheduling method based on the IWOA algorithm, comprising the following steps:

[0009] Use machine learning algorithms to predict when machine failures will occur, and define decision variables based on the predicted machine failure times.

[0010] Obtain working parameters of multi-AGV flexible workshop;

[0011] Based on the working parameters of a multi-AGV flexible job shop and the predicted time of machine failure, a multi-objective optimization model for active scheduling of a multi-AGV flexible job shop is constructed. The multi-objective optimization model takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load, and minimizing the carbon emissions as the objective functions.

[0012] Defining parameters and setting constraints for the multi-objective optimization model;

[0013] The whale optimization algorithm is improved by adopting reverse learning method, nonlinear convergence factor, segmented inertia weight and multi-directional spiral search mechanism to obtain an improved whale optimization algorithm.

[0014] Based on the constraints of the multi-objective optimization model, an improved whale optimization algorithm is used to solve the decision variables in the objective function of the established multi-objective optimization model for active scheduling of multi-AGV flexible job shops to obtain the Pareto frontier.

[0015] A set of solutions is selected from the Pareto front to obtain active scheduling results, which are used to actively schedule the multi-AGV flexible workshop.

[0016] In a second aspect, the present invention provides a multi-AGV flexible job shop active scheduling system based on the IWOA algorithm, including a decision variable definition module, a work parameter acquisition module, a model construction module, a constraint condition setting module, a whale optimization algorithm improvement module, a decision variable solution module and a scheduling module;

[0017] The decision variable definition module is used to predict the time of occurrence of a machine failure using a machine learning algorithm and define a decision variable based on the predicted time of occurrence of the machine failure;

[0018] The working parameter acquisition module is used to obtain the working parameters of the multi-AGV flexible operation workshop;

[0019] The model building module is used to build a multi-objective optimization model for active scheduling of a multi-AGV flexible job shop based on the working parameters of the multi-AGV flexible job shop and the predicted time of machine failure. The multi-objective optimization model takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load and minimizing the carbon emissions as objective functions;

[0020] The constraint condition setting module is used to set the constraint conditions of the multi-objective optimization model;

[0021] The whale optimization algorithm improvement module is used to improve the whale optimization algorithm by adopting a reverse learning method, a nonlinear convergence factor, a segmented inertia weight and a multi-directional spiral search mechanism to obtain an improved whale optimization algorithm;

[0022] The decision variable solving module is used to solve the decision variables in the objective function of the established multi-objective optimization model for active scheduling of multi-AGV flexible job shops using an improved whale optimization algorithm based on the set constraints of the multi-objective optimization model to obtain the Pareto frontier;

[0023] The scheduling module is used to select a set of solutions from the Pareto front to obtain active scheduling results, thereby actively scheduling the multi-AGV flexible workshop.

[0024] In a third aspect, the present invention provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the above-mentioned method for active scheduling of multi-AGV flexible workshops based on the IWOA algorithm.

[0025] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned method for active scheduling of multi-AGV flexible job shops based on the IWOA algorithm.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] The present invention is an improved invention. Compared with the existing active scheduling method for multi-AGV flexible workshops, on the one hand, the present invention adopts a reverse learning method, a nonlinear convergence factor, a segmented inertia weight, and a multi-directional spiral search mechanism to improve the whale optimization algorithm, thereby obtaining an improved whale optimization algorithm. This can avoid the problem that the original WOA algorithm is prone to falling into local optimality when dealing with high-dimensional complex optimization problems, and can improve the accuracy of solving the optimal solution of the objective function, thereby improving the accuracy of active scheduling of multi-AGV flexible workshops in the later stage. Moreover, when establishing the optimization model, the present invention comprehensively considers the four factors of maximum completion time, total cost, total load, and carbon emissions. The consideration of various factors can also improve the accuracy of active scheduling of multi-AGV flexible workshops in the later stage, thereby solving the problem of low accuracy of active scheduling of multi-AGV flexible workshops in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 This is a flow chart of the active scheduling method for multi-AGV flexible job shop based on the IWOA algorithm of the present invention;

[0029] Figure 2 Schematic diagram of the multi-AGV flexible job shop active scheduling system based on the IWOA algorithm of the present invention;

[0030] Figure 3 This is a flowchart of solving the decision variables in the objective function of the established multi-objective optimization model using the improved whale optimization algorithm in Example 3 of the present invention;

[0031] Figure 4 It is the completion time iteration diagram of the present invention;

[0032] Figure 5 It is the total cost iteration graph of the present invention;

[0033] Figure 6 It is the total load iteration diagram of the present invention;

[0034] Figure 7 Iterative graph of carbon emissions of the present invention;

[0035] Figure 8 This is a box plot of the completion time solution results of the present invention;

[0036] Figure 9 It is a box plot of the total cost solution results of the present invention;

[0037] Figure 10 It is a box plot of the total load solution results of the present invention;

[0038] Figure 11 This is a box plot of the carbon emissions solution results of the present invention;

[0039] Figure 12Gantt chart for trouble-free scheduling of the present invention;

[0040] Figure 13 Actively schedule Gantt chart for the present invention;

[0041] Figure 14 Schematic diagram of the structure of the electronic device of the present invention. DETAILED DESCRIPTION

[0042] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0043] The proposed method for proactive scheduling of a multi-AGV flexible workshop based on the IWOA algorithm uses an improved whale optimization algorithm to solve the decision variables in the objective function of a multi-objective optimization model, based on the constraints of the model, to obtain a Pareto front. A set of solutions from this Pareto front is then selected to generate proactive scheduling results, which are then used to proactively schedule the multi-AGV flexible workshop. Compared to existing technologies, this method effectively addresses the low accuracy of proactive scheduling of multi-AGV flexible workshops.

[0044] Example 1:

[0045] The flowchart of the active scheduling method of multi-AGV flexible workshop based on IWOA algorithm of the present invention is as follows: Figure 1 As shown, the multi-AGV flexible job shop active scheduling method based on the IWOA algorithm of the present invention includes the following steps:

[0046] S1. Use a machine learning algorithm to predict the time when a machine failure will occur, and define decision variables based on the predicted time when the machine failure will occur.

[0047] S2. Obtain the working parameters of the multi-AGV flexible operation workshop and define the decision variables based on the working parameters of the multi-AGV flexible operation workshop;

[0048] S3. Construct a multi-objective optimization model for active scheduling of multi-AGV flexible job shops, wherein the multi-objective optimization model takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load, and minimizing carbon emissions as objective functions;

[0049] S4. Setting the constraints of the multi-objective optimization model;

[0050] S5. The Whale Optimization Algorithm is improved by adopting reverse learning, nonlinear convergence factor, segmented inertia weight and multi-directional spiral search mechanism to obtain an improved Whale Optimization Algorithm.

[0051] S6. Based on the constraints of the multi-objective optimization model, an improved whale optimization algorithm is used to solve the decision variables in the objective function of the established multi-objective optimization model for active scheduling of multi-AGV flexible job shops to obtain the Pareto frontier;

[0052] S7. Select a set of solutions from the Pareto front to obtain active scheduling results, and use them to actively schedule the multi-AGV flexible workshop.

[0053] Example 2:

[0054] The schematic diagram of the multi-AGV flexible workshop active scheduling system based on the IWOA algorithm of the present invention is as follows: Figure 2 As shown, the multi-AGV flexible job shop active scheduling system based on the IWOA algorithm of the present invention includes a decision variable definition module, a work parameter acquisition module, a model construction module, a constraint condition setting module, a whale optimization algorithm improvement module, a decision variable solving module and a scheduling module.

[0055] The decision variable definition module is used to use a machine learning algorithm to predict the time when a machine failure occurs, and to define decision variables based on the predicted time when a machine failure occurs.

[0056] The working parameter acquisition module is used to obtain the working parameters of the multi-AGV flexible operation workshop.

[0057] The model building module is used to construct a multi-objective optimization model for active scheduling of multi-AGV flexible job shops based on the working parameters of the multi-AGV flexible job shops and the predicted time of machine failure. The multi-objective optimization model takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load and minimizing the carbon emissions as objective functions.

[0058] The constraint condition setting module is used to set the constraint conditions of the multi-objective optimization model.

[0059] The whale optimization algorithm improvement module is used to improve the whale optimization algorithm by adopting reverse learning method, nonlinear convergence factor, segmented inertia weight and multi-directional spiral search mechanism to obtain an improved whale optimization algorithm.

[0060] The decision variable solving module is used to solve the decision variables in the objective function of the established multi-objective optimization model for active scheduling of multi-AGV flexible job shops based on the set constraints of the multi-objective optimization model, using the improved whale optimization algorithm to obtain the Pareto frontier.

[0061] The scheduling module is used to select a set of solutions from the Pareto front to obtain active scheduling results, thereby actively scheduling the multi-AGV flexible workshop.

[0062] Example 3:

[0063] The present invention provides a multi-AGV flexible job shop active scheduling method based on the IWOA algorithm, comprising the following steps:

[0064] S1. Use a machine learning algorithm to predict the time when a machine failure will occur, and define decision variables based on the predicted time when the machine failure will occur.

[0065] A machine learning algorithm is used to predict the time when a machine failure will occur. Decision variables are defined based on the predicted time when the machine failure will occur. The defined decision variables are as follows:

[0066]

[0067] Among them, m k 、 and It is the decision variable designed for active scheduling based on the predicted machine failure time. ijk Assign decision variables to the machine, is the decision variable for process sorting, is the AGV allocation decision variable, is the AGV sorting decision variable.

[0068] S2. Obtain the working parameters of the AGV flexible operation workshop and define decision variables based on the working parameters of the AGV flexible operation workshop.

[0069] First, the working parameters of the AGV flexible operation workshop are obtained. The obtained working parameters of the AGV flexible operation workshop are shown in Table 1.

[0070] Table 1 Parameter meaning

[0071]

[0072]

[0073] S3. Based on the working parameters of the multi-AGV flexible job shop and the predicted machine failure time, a multi-objective optimization model for active scheduling of the multi-AGV flexible job shop is constructed.

[0074] Firstly, based on the working parameters of the multi-AGV flexible job workshop and the predicted machine failure time, a multi-objective optimization model for active scheduling of the multi-AGV flexible job workshop is constructed. The multi-objective optimization model for active scheduling of the multi-AGV flexible job workshop takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load and minimizing the carbon emissions as the objective functions.

[0075] The objective function of the multi-objective optimization model is introduced in detail below. The expression of the objective function of the multi-objective optimization model is:

[0076]

[0077] Among them, F is the objective function of the multi-objective optimization model, f1 represents minimizing the maximum completion time, f2 represents minimizing the total cost, f3 represents minimizing the total load, f4 represents minimizing the carbon emissions, and C max is the maximum completion time, PE is the energy consumption cost generated by machine processing, ME is the energy consumption cost generated by the machine when it is idling, RE is the energy consumption cost of AGV loaded, CE is the energy consumption cost of AGV idling, Q max is the total load, EB is the carbon emissions generated by machine processing, EI is the carbon emissions generated by machine no-load, ER is the carbon emissions generated by AGV load, ES is the carbon emissions generated by AGV no-load, and GE is the carbon emissions generated by the consumption of workshop lighting and temperature control systems.

[0078] The calculation formula for the energy consumption cost PE generated by machining is:

[0079]

[0080] The calculation formula for the energy consumption cost ME generated by the machine when it is idling is:

[0081]

[0082] The calculation formula for AGV load energy consumption cost RE is:

[0083]

[0084] The calculation formula for AGV no-load energy consumption cost CE is:

[0085]

[0086] The calculation formula for carbon emissions EB generated by machining is:

[0087]

[0088] The calculation formula for carbon emissions EI generated by the machine when it is idling is:

[0089]

[0090] The calculation formula for carbon emissions ER generated by AGV load is:

[0091]

[0092] The calculation formula for carbon emissions ES generated by AGV no-load is:

[0093]

[0094] The calculation formula for GE carbon emissions generated by workshop lighting and temperature control systems is:

[0095]

[0096] S4. Set constraints for the multi-objective optimization model.

[0097] The constraints of the multi-objective optimization model include the following formulas:

[0098]

[0099]

[0100] C12:i,i′∈{1,2,L n},j,j′∈{1,2,L u i},M∈{1,2,L m},S∈{1,2,L s}

[0101] Among them, C9 and C10 are machine failure period constraints that need to be avoided during active scheduling.

[0102] The constraints are described in detail below:

[0103] Specifically, C1 indicates that processing operations cannot be interrupted, ensuring the priority relationship between operations. C2 indicates that each process can only be assigned to a single machine during processing. C3 indicates that the transfer task of each process can only be performed by one AGV. C4 indicates that conflicts in the order of processes assigned to machines should be avoided. C5 indicates that conflicts in the AGV transport sequence should be avoided. C6 indicates that the start time of any process must be after the end of the load travel and the completion time of the previous process on the same machine. C7 indicates that the start time of the AGV empty transport must be after the completion of the load task of the previous process and the start time of the process of the workpiece to be transported. C8 indicates that the start time of the AGV loaded transport must be after the completion time of the workpiece and the end time of the AGV empty transport. C9 indicates that the process must be processed either before or after the machine failure. C10 indicates that the process planned to be processed on the faulty machine must be completed no later than the time the fault occurs, or its start time must be no earlier than the time the fault is repaired. C11 indicates the value range of the decision variable. C12 indicates the value range of the parameter.

[0104] S5. The whale optimization algorithm is improved by adopting reverse learning method, nonlinear convergence factor, segmented inertia weight and multi-directional spiral search mechanism to obtain an improved whale optimization algorithm.

[0105] The initial population is generated based on reverse learning. The specific process is as follows:

[0106] A. Randomly generate 40% of individuals in the initial population, namely the operation sequence (OS) layer chromosomes, and randomly assign available processing machines and transfer AGVs to each process in turn; among them, 20% of individuals prefer machines with short processing time, 20% of individuals tend to choose machines with low energy consumption, and 20% choose machines with lower costs, generating the initial population P0 = X ij , the length of P0 is M, where i = {1, 2, ..., M}, j = {1, 2, ..., N};

[0107] B. Construct a reverse population based on the generated initial population in n0 is the number of AGVs;

[0108] C. Combine the initial population P0 with the reverse population Merge to obtain the merged population;

[0109] D. Perform non-dominated sorting on the merged population and select the first M individuals as the final initial population.

[0110] The calculation formula of the nonlinear convergence factor is:

[0111]

[0112] Among them, a is the nonlinear convergence factor, t is the current number of iterations, T max is the maximum number of iterations, μ is the control coefficient used to control the convergence of the nonlinear convergence factor, and exp is an exponential function with e as the base.

[0113] The calculation formula of segment inertia weight is:

[0114]

[0115] Among them, w is the inertia weight, exp is the exponential function with e as the base, rand is the generated random number between [0, 1], T is the number of iterations, T max is the maximum number of iterations, and t is the current number of iterations.

[0116] The following is a detailed description of the segmented inertia weight:

[0117] This embodiment uses piecewise inertia weighting. The shrinking, encircling, and spiral position update strategies in the WOA algorithm can be divided into two phases. In the initial phase, the WOA algorithm uses a fixed inertia weight of 1, which facilitates global search and improves the ability to escape local optima. In the later phase, a nonlinearly decreasing dynamic inertia weighting is used to improve the algorithm's convergence accuracy.

[0118] The calculation formula of the multi-directional spiral search mechanism is:

[0119]

[0120] Among them, X (t+1) is the optimal position of the whale in generation t+1, D2 is the encircling step size, b is the spiral equation constant, l is a random number between [-1,1], P3 is a random number between [0,1], x* (t) is the optimal position of the whale in the tth iteration, and w is the distance between the current search individual and the current optimal solution.

[0121] This step also uses the random differential mutation strategy to improve the whale optimization algorithm. The random differential mutation strategy is a mutation operation based on differential evolution. This strategy randomly selects two whale individuals from the population, calculates the difference vector between the two whale individuals, and linearly combines this vector with a specific individual to generate a new individual. The calculation formula of the random differential mutation strategy is:

[0122] X i(t+1) =X p(t) +F·(X q(t) -X r(t) )

[0123] Where F is the scaling factor, X i(t+1) is a newly generated individual, X p(t) 、X q(t) and X r(t) are three randomly selected individuals.

[0124] In the differential mutation operation, individual selection adopts a random mechanism. This random strategy is conducive to reducing the probability of the WOA algorithm falling into a local extreme value. In the shrinking and surrounding stage of the whale optimization algorithm, a differential mutation strategy is introduced to generate new mutant individuals, realizing crossover between whale individuals. Among them, the scaling factor F is usually between 0 and 2 or randomly generated. In this embodiment, the value of F is 0.6, and the value of the differential mutation probability R is 0.8. In the improved shrinking and surrounding individual update formula, the calculation formula for the optimal position of the whale in the t+1 generation is:

[0125]

[0126] Among them, A is the threshold, D1 is the enclosing step size, x (t) is the current individual whale position; x rand(t) To randomly select whale positions, x* (t) is the optimal position of the whale in the tth iteration.

[0127] S6. Based on the constraints of the set multi-objective optimization model, the improved whale optimization algorithm is used to solve the decision variables in the objective function of the established multi-objective optimization model to obtain the Pareto frontier.

[0128] In this step, the improved whale optimization algorithm is used to solve the decision variables in the objective function of the established multi-objective optimization model. Figure 3 The specific process is as follows:

[0129] Step 1: Parameter initialization: population size N, maximum number of iterations Gen max Initialize parameters and AGV quantity;

[0130] Step 2: Chromosome encoding and decoding: Design ROV conversion encoding and decoding methods;

[0131] Step 3: Generate the initial population using a mixed population initialization method based on reverse learning;

[0132] Step 4: Evaluate the fitness of the initial population and perform fast non-dominated sorting, calculate the congestion degree, and save the current optimal individual and corresponding position information;

[0133] Step 5: Search the population individuals in turn and randomly generate a value p between 0 and 1; if p ≥ 0.5, according to Update individual positions, otherwise perform multi-directional spiral search updates according to the calculation formula of the multi-directional spiral search mechanism;

[0134] Step 6: Calculate the nonlinear convergence factor |A| according to the calculation formula of the nonlinear convergence factor. If |A|≥1, update the individual position according to the random search method. Otherwise, update the individual position according to the random search method. Update individual positions by shrinking and surrounding;

[0135] Step 7: Elite retention mechanism: Generate a new generation of population by merging populations and combining non-dominated sorting with elite selection principles;

[0136] Step 8: Determine whether the number of iterations is met. If so, repeat Step 3 to Step 7. Otherwise, output the optimal solution.

[0137] S7. Select a set of solutions from the Pareto front to obtain active scheduling results, and use them to actively schedule the multi-AGV flexible workshop.

[0138] To verify the performance of the proposed method (IWOA algorithm), this example constructs the TMK01-TMK10 benchmark cases based on the MK01-MK10 cases. The transfer times between different machines are randomly generated between [1, 2]. The corresponding machine processing energy consumption and AGV transport energy consumption are designed. The predicted faulty machine and fault onset time are randomly set for each case. The scale of the TMK01-TMK10 cases is shown in Table 2.

[0139] Table 2 Calculation scale of TMK01~TMK10

[0140]

[0141] This example uses the IWOA algorithm, the VNS-INSGA-II (Variable Neighborhood Search-Improved Non-dominated Sorting Genetic Algorithm-II) algorithm, and the NSGA-II (Non-dominated Sorting Genetic Algorithm-II) algorithm to solve benchmark examples TMK01 to TMK10. Each algorithm is executed 10 times, and the average and optimal values ​​are obtained. For example, Table 3 shows the set of non-dominated solutions for solving the TMK05 example, where the optimal makespan is 196.9 minutes, the optimal total cost is 3064.8 yuan, the optimal total load is 714.1 minutes, and the optimal carbon emissions is 3072.1 kg. Table 4 shows the objective function values ​​and runtimes for the three algorithms, with the best performing values ​​highlighted in bold.

[0142] Table 3 Non-dominated solution set (Pareto front) of IWOA algorithm

[0143]

[0144]

[0145] Table 4 Objective function values ​​and running times of different algorithms

[0146]

[0147]

[0148] As shown in Table 4, among the 10 benchmark examples, for the completion time objective, the IWOA algorithm achieved 8 optimal means and 8 optimal values, the VNS-INSGA-II algorithm achieved 4 optimal means and 4 optimal values, and the NSGA-II algorithm achieved 0 optimal values. For the total cost objective, the IWOA algorithm achieved 8 optimal means and 8 optimal values, the VNS-INSGA-II algorithm achieved 2 optimal means and 2 optimal values, and the NSGA-II algorithm achieved 0 optimal values. For the total load objective, the IWOA algorithm achieved 7 optimal means and 7 optimal values, the VNS-INSGA-II algorithm achieved 3 optimal means and 3 optimal values, and the NSGA-II algorithm achieved 0 optimal values. For the carbon emission objective, the IWOA algorithm achieved 7 optimal means and 8 optimal values, the VNS-INSGA-II algorithm achieved 3 optimal means and 2 optimal values, and the NSGA-II algorithm achieved 0 optimal values. Compared with the VNS-INSGA-II and NSGA-II algorithms, the running time of the IWOA algorithm is reduced. In summary, IWOA can obtain a better scheduling solution for PS-FJSP-MA, and the algorithm solution time is short.

[0149] This embodiment uses three algorithms to solve the four objectives of the TMK02 example. Figures 4 to 7 As shown, from Figures 4 to 7 It can be seen that compared with the VNS-INSGA-II algorithm and the NSGA-II algorithm, the IWOA algorithm converges faster and obtains better results when solving the four objectives.

[0150] This example uses three algorithms to solve the TMK02 example. Each algorithm is run independently 10 times. The box plot of the 10 experimental results is as follows: Figures 8 to 11 As shown, from Figures 8 to 11 It can be seen that the three algorithms all have a certain degree of stability in the solution process. Among them, the stability of the NSGA-II algorithm is the worst, the stability of the VNS-INSGA-II and IWOA algorithms is comparable, and the mean and median of the IWOA algorithm are lower. The solution with the shortest completion time is selected, and the scheduling Gantt chart of the TMK02 example is solved by the IWOA algorithm as shown below. Figure 12 As shown, from Figure 12 It can be seen that the TMK02 example can complete the processing and transportation tasks in 49 minutes.

[0151] Table 5 shows the HV (Hypervolume) and IGD (Inverted Generational Distance) indicator results of the three algorithms for solving 10 benchmark examples. The values ​​with the best performance are bolded.

[0152] Table 5 Algorithm evaluation index results

[0153]

[0154] This example uses the TMK01 to TMK10 benchmark examples for verification. The three algorithms are run 10 times, taking the average and optimal values. The objective function values ​​and algorithm runtimes obtained by the three algorithms are shown in Table 6. The objective values ​​with the best performance are highlighted in bold.

[0155] Table 6 Objective function values ​​and running times of different algorithms

[0156]

[0157]

[0158] As can be seen from Table 6, the running time of the IWOA algorithm is significantly reduced compared to the VNS-INSGA-II and NSGA-II algorithms. In summary, the IWOA algorithm can obtain a better scheduling solution for PS-FJSP-MA, and the algorithm solution time is short.

[0159] Select the solution with the shortest completion time and use the IWOA algorithm to solve the active scheduling Gantt chart of the TMK02 example. Figure 13 As shown in the figure, in the TMK02 example, the faulty machine is M4, the fault start time is 35 minutes, and the fault repair time is 10 minutes.

[0160] Example 4:

[0161] See also Figure 14 As shown, the present invention also provides an electronic device 100 for an active scheduling method of a multi-AGV flexible job shop based on the IWOA algorithm; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0162] The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the multi-AGV flexible job shop active scheduling method based on the IWOA algorithm described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the electronic device 100 (such as audio data). In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0163] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 using various interfaces and lines.

[0164] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a multi-AGV flexible job shop active scheduling method based on the IWOA algorithm. The processor 102 can execute the plurality of instructions to implement:

[0165] Use machine learning algorithms to predict when machine failures will occur, and define decision variables based on the predicted machine failure times.

[0166] Obtain working parameters of multi-AGV flexible workshop;

[0167] Based on the working parameters of a multi-AGV flexible job shop and the predicted time of machine failure, a multi-objective optimization model for active scheduling of a multi-AGV flexible job shop is constructed. The multi-objective optimization model takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load, and minimizing the carbon emissions as the objective functions.

[0168] Setting constraints of the multi-objective optimization model;

[0169] The whale optimization algorithm is improved by adopting reverse learning method, nonlinear convergence factor, segmented inertia weight and multi-directional spiral search mechanism to obtain an improved whale optimization algorithm.

[0170] Based on the constraints of the multi-objective optimization model, an improved whale optimization algorithm is used to solve the decision variables in the objective function of the established multi-objective optimization model for active scheduling of multi-AGV flexible job shops to obtain the Pareto frontier.

[0171] A set of solutions is selected from the Pareto front to obtain active scheduling results, which are used to actively schedule the multi-AGV flexible workshop.

[0172] Example 5:

[0173] If the module / unit integrated in the electronic device 100 is implemented in the form of 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 present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0174] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0175] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0178] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A multi-AGV flexible job shop active scheduling method based on the IWOA algorithm, characterized by: The following steps are involved: Use machine learning algorithms to predict when machine failures will occur, and define decision variables based on the predicted machine failure times. Obtain working parameters of multi-AGV flexible workshop; Based on the working parameters of a multi-AGV flexible job shop and the predicted time of machine failure, a multi-objective optimization model for active scheduling of a multi-AGV flexible job shop is constructed. The multi-objective optimization model takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load, and minimizing the carbon emissions as the objective functions. Setting constraints of the multi-objective optimization model; The whale optimization algorithm is improved by adopting reverse learning method, nonlinear convergence factor, segmented inertia weight and multi-directional spiral search mechanism to obtain an improved whale optimization algorithm. Based on the constraints of the multi-objective optimization model, an improved whale optimization algorithm is used to solve the decision variables in the objective function of the established multi-objective optimization model for active scheduling of multi-AGV flexible job shops to obtain the Pareto frontier. A set of solutions is selected from the Pareto front to obtain active scheduling results, which are used to actively schedule the multi-AGV flexible workshop.

2. The multi-AGV flexible job shop active scheduling method based on the IWOA algorithm according to claim 1 is characterized in that: The expression of the objective function of the multi-objective optimization model is: Among them, F is the objective function of the multi-objective optimization model, f1 represents minimizing the maximum completion time, f2 represents minimizing the total cost, f3 represents minimizing the total load, f4 represents minimizing the carbon emissions, and C max is the maximum completion time, PE is the energy consumption cost generated by machine processing, ME is the energy consumption cost generated by the machine when it is idling, RE is the energy consumption cost of AGV loaded, CE is the energy consumption cost of AGV idling, Q max is the total load, EB is the carbon emissions generated by machine processing, EI is the carbon emissions generated by machine no-load, ER is the carbon emissions generated by AGV load, ES is the carbon emissions generated by AGV no-load, and GE is the carbon emissions generated by the consumption of workshop lighting and temperature control systems; The calculation formula for the energy consumption cost PE generated by machining is: The calculation formula for the energy consumption cost ME generated by the machine when it is idling is: The calculation formula for AGV load energy consumption cost RE is: The calculation formula for AGV no-load energy consumption cost CE is: The calculation formula for carbon emissions EB generated by machining is: The calculation formula for carbon emissions EI generated by the machine when it is idling is: The calculation formula for carbon emissions ER generated by AGV load is: The calculation formula for carbon emissions ES generated by AGV no-load is: The calculation formula for GE carbon emissions generated by workshop lighting and temperature control system consumption is: in, For process O ij On machine M k The actual processing time of PC k For machine M k Energy consumption cost per unit time in load state, MC k For machine M k Energy consumption cost per unit time in no-load state, For process O ij On machine M k The processing completion time, For process O ij On machine M k The processing start time, For S h O ij Move to O i,j+1 The end time of the load stroke, For S h O ij Move to O i,j+1 The starting moment of the load stroke, RC h For S h The energy consumption cost per unit time of the load, For S h O i,j+1 Move to O i'j' The end time of the empty load journey, For S h O i,j+1 Move to O i'j' The starting time of the empty load trip, QC h For S h Energy consumption cost per unit time of no-load, ER h is the average processing power of the AGV under load, ES h is the average processing power of AGV in no-load state, GE k is the average processing power under lighting and temperature control conditions, P s is the carbon emission conversion factor; The decision variables of the objective function of the multi-objective optimization model are: Among them, m k 、 and It is the decision variable designed for active scheduling based on the predicted machine failure time. ijk Assign decision variables to the machine, is the decision variable for process sorting, is the AGV allocation decision variable, is the AGV sorting decision variable; The constraints of the multi-objective optimization model include the following formulas: C12:i,i′∈{1,2,L n},j,j′∈{1,2,L u i },M∈{1,2,L m},S∈{1,2,L s} Among them, C9 and C10 are machine failure period constraints that need to be avoided during active scheduling.

3. The multi-AGV flexible job shop active scheduling method based on the IWOA algorithm according to claim 1 is characterized in that: The reverse learning specifically includes: Generate the initial population; Construct a reverse population based on the generated initial population; Merge the generated initial population with the reverse population to obtain a merged population; Perform non-dominated sorting on the merged population to obtain the final initial population.

4. The multi-AGV flexible job shop active scheduling method based on the IWOA algorithm according to claim 1 is characterized in that: The calculation formula of the nonlinear convergence factor is: Among them, a is the nonlinear convergence factor, t is the current number of iterations, T max is the maximum number of iterations, μ is the control coefficient used to control the convergence of the nonlinear convergence factor, and exp is an exponential function with e as the base.

5. The multi-AGV flexible job shop active scheduling method based on the IWOA algorithm according to claim 1 is characterized in that: The calculation formula of segment inertia weight is: Among them, w is the inertia weight, exp is the exponential function with e as the base, rand is the generated random number between [0, 1], T is the number of iterations, T max is the maximum number of iterations, and t is the current number of iterations.

6. The multi-AGV flexible job shop active scheduling method based on the IWOA algorithm according to claim 1 is characterized in that: The calculation formula of the multi-directional spiral search mechanism is: Among them, X (t+1) is the optimal position of the whale in generation t+1, D2 is the encircling step size, b is the spiral equation constant, l is a random number between [-1,1], P3 is a random number between [0,1], x* (t) is the optimal position of the whale in the tth iteration, and w is the distance between the current search individual and the current optimal solution.

7. A multi-AGV flexible workshop active scheduling system based on IWOA algorithm, characterized by: It includes decision variable definition module, working parameter acquisition module, model construction module, constraint condition setting module, whale optimization algorithm improvement module, decision variable solution module and scheduling module; The decision variable definition module is used to predict the time of occurrence of a machine failure using a machine learning algorithm and define a decision variable based on the predicted time of occurrence of the machine failure; The working parameter acquisition module is used to obtain the working parameters of the multi-AGV flexible operation workshop; The model building module is used to build a multi-objective optimization model for active scheduling of a multi-AGV flexible job shop based on the working parameters of the multi-AGV flexible job shop and the predicted time of machine failure. The multi-objective optimization model takes minimizing the maximum completion time, minimizing the total cost, minimizing the total load and minimizing the carbon emissions as objective functions; The constraint condition setting module is used to set the constraint conditions of the multi-objective optimization model; The whale optimization algorithm improvement module is used to improve the whale optimization algorithm by adopting a reverse learning method, a nonlinear convergence factor, a segmented inertia weight and a multi-directional spiral search mechanism to obtain an improved whale optimization algorithm; The decision variable solving module is used to solve the decision variables in the objective function of the established multi-objective optimization model for active scheduling of multi-AGV flexible job shops using an improved whale optimization algorithm based on the set constraints of the multi-objective optimization model to obtain the Pareto frontier; The scheduling module is used to select a set of solutions from the Pareto front to obtain active scheduling results, thereby actively scheduling the multi-AGV flexible workshop.

8. The multi-AGV flexible job shop active scheduling system based on the IWOA algorithm according to claim 7 is characterized in that: The expression of the objective function of the multi-objective optimization model is: Among them, F is the objective function of the multi-objective optimization model, f1 represents minimizing the maximum completion time, f2 represents minimizing the total cost, f3 represents minimizing the total load, f4 represents minimizing the carbon emissions, and C max is the maximum completion time, PE is the energy consumption cost generated by machine processing, ME is the energy consumption cost generated by the machine when it is idling, RE is the energy consumption cost of AGV loaded, CE is the energy consumption cost of AGV idling, Q max is the total load, EB is the carbon emissions generated by machine processing, EI is the carbon emissions generated by machine no-load, ER is the carbon emissions generated by AGV load, ES is the carbon emissions generated by AGV no-load, and GE is the carbon emissions generated by the consumption of workshop lighting and temperature control systems; The calculation formula for the energy consumption cost PE generated by machining is: The calculation formula for the energy consumption cost ME generated by the machine when it is idling is: The calculation formula for AGV load energy consumption cost RE is: The calculation formula for AGV no-load energy consumption cost CE is: The calculation formula for carbon emissions EB generated by machining is: The calculation formula for carbon emissions EI generated by the machine when it is idling is: The calculation formula for carbon emissions ER generated by AGV load is: The calculation formula for carbon emissions ES generated by AGV no-load is: The calculation formula for GE carbon emissions generated by workshop lighting and temperature control system consumption is: in, For process O ij On machine M k The actual processing time of PC k For machine M k Energy consumption cost per unit time in load state, MC k For machine M k Energy consumption cost per unit time in no-load state, For process O ij On machine M k The processing completion time, For process O ij On machine M k The processing start time, For S h O ij Move to O i,j+1 The end time of the load stroke, For S h O ij Move to O i,j+1 The starting moment of the load stroke, RC h For S h The energy consumption cost per unit time of the load, For S h O i,j+1 Move to O i'j' The end time of the empty load journey, For S h O i,j+1 Move to O i'j' The starting time of the empty load trip, QC h For S h Energy consumption cost per unit time of no-load, ER h is the average processing power of the AGV under load, ES h is the average processing power of AGV in no-load state, GE k is the average processing power under lighting and temperature control conditions, P s is the carbon emission conversion factor; The decision variables of the objective function of the multi-objective optimization model are: Among them, m k 、 and It is the decision variable designed for active scheduling based on the predicted machine failure time. ijk Assign decision variables to the machine, is the decision variable for process sorting, is the AGV allocation decision variable, is the AGV sorting decision variable; The constraints of the multi-objective optimization model include the following formulas: C12:i,i′∈{1,2,L n},j,j′∈{1,2,L u i },M∈{1,2,L m},S∈{1,2,L s} Among them, C9 and C10 are machine failure period constraints that need to be avoided during active scheduling.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the multi-AGV flexible job shop active scheduling method based on the IWOA algorithm are implemented as described in any one of claims 1 to 6.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-AGV flexible job shop active scheduling method based on the IWOA algorithm according to any one of claims 1 to 6 are implemented.

Images