Intelligent flexible scheduling method and system for tire vulcanization plant facing dynamic disturbance

Abstract

The application belongs to the field of workshop dynamic scheduling, and provides a kind of intelligent flexible scheduling method and system for dynamic disturbance of tire vulcanization workshop, which comprises establishing production scheduling model with minimizing maximum completion time as optimization target;Obtain the initial processing sequence of each workpiece process and the optional machine set, and solve the production scheduling model as the objective function to obtain the optimal initial scheduling scheme;When dynamic event occurs in the production process, detect the type of dynamic event and the time of event occurrence, extract the completed process, the process being processed and the process not started;Based on the influence of dynamic event on the process being processed and the process not started, determine the process to be scheduled, retain the process processing sequence of the optimal initial scheduling scheme, update the optimal processing machine of the process to be scheduled, and generate a rescheduling scheme.The application only replaces the machine of the unprocessed process, embeds the cooling time buffer between the processes of the same workpiece, solves the problem of insufficient rubber cooling, and guarantees the quality and process stability.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of workshop dynamic scheduling, and particularly relates to a tire vulcanization workshop intelligent flexible scheduling method and system for dynamic disturbance. BACKGROUND

[0002] The statements in this section merely provide background information related to the application and do not necessarily constitute prior art.

[0003] With the increase of per capita car ownership, the demand for tires continues to grow, and tire manufacturing is facing the dual pressures of capacity expansion and efficiency improvement. Tire production has the characteristics of large scale, multi-category and high customization, especially in the mixing workshop, the processing quality directly determines the performance of the finished product. Mixing scheduling not only needs to consider basic elements such as workpiece quantity, process sequence, equipment processing time, etc., but also needs to deal with process characteristics such as equipment switching rules, cooling time constraints, resource conflicts, etc. The scheduling complexity is high. At the same time, dynamic disturbances such as order insertion, cancellation and equipment failure frequently occur in the production process. If the scheduling strategy does not respond in time and adjust flexibly, it will lead to production delay, resource idling and overall efficiency decline. Therefore, in the mixing scheduling, it is necessary to achieve a better scheduling result, improve equipment utilization, enhance the flexibility of equipment selection, shorten the workpiece completion time, and have a fast and stable adjustment capability in the event of an emergency, so as to improve the overall production efficiency and system flexibility of the workshop.

[0004] The current scheduling problem of the mixing workshop is usually modeled as a flexible job shop scheduling problem (FJSP, Flexible job-shop scheduling problem), which is a typical NP-hard problem, and it is difficult to obtain the optimal solution by traditional algorithms. Although some research based on genetic algorithm, ant colony algorithm, particle swarm optimization and deep learning has made some progress, most of the methods still take the static environment as the premise, lack of adaptability to dynamic disturbance, and it is difficult to achieve efficient application in actual production. In addition, many researches ignore the special process requirements in tire mixing production, resulting in poor feasibility and weak continuity of the scheduling scheme in actual scene. In the current processing of dynamic events for workshop scheduling, the following methods are mainly used in the prior art:

[0005] (1) Dynamic adjustment scheme based on heuristic algorithm, which realizes a more robust rescheduling strategy under the condition of sudden events by introducing a hybrid event-driven strategy and three types of stability indicators. However, due to the large number of parameters in workshop scheduling, it is difficult to optimize and the scheduling result is unstable.

[0006] (2) Dynamic adjustment scheme based on deep reinforcement learning, focusing on the impact of operation processing time uncertainty on job shop scheduling to deal with the scheduling instability problem caused by such single dynamic event, and improving the training efficiency and generalization ability of the scheduling strategy in uncertain environment through the mixed priority experience replay mechanism. The strategy of this method is complex, has strong training dependence, has different effects for different scenes, and has limited generalization ability.

[0007] Therefore, based on the field of job shop dynamic scheduling, a large amount of work is concentrated on the excellence of the solution and various algorithms, and the complexity of this problem is mainly aimed at the processing sequence and machine selection of the workpiece process. In the existing method, compared with the heuristic algorithm, the scheduling strategy of reinforcement learning is better, but the training difficulty is large, the generalization ability is weak, and the influence of dynamic events on the processing sequence and machine selection of the workpiece process in the final optimal scheduling scheme is ignored, which makes the solving efficiency low and the scheduling scheme inaccurate. SUMMARY

[0008] In order to overcome the shortcomings of the existing scheduling strategy in dealing with dynamic disturbance and resource allocation, the present application proposes a dynamic disturbance-oriented intelligent flexible scheduling method and system for a tire vulcanization workshop, which comprehensively considers the maximum machine processing capacity and the minimum machine load imbalance, and dynamically allocates the optimal machine for each process. This method can effectively improve the machine utilization efficiency and avoid resource waste such as equipment overload or idling; at the same time, through the real-time machine selection mechanism, when dynamic events such as order insertion, cancellation or equipment failure occur, the processing equipment can be flexibly adjusted on the basis of maintaining the original process sequence, ensuring that the scheduling scheme has stronger stability and faster response ability.

[0009] According to some embodiments, the first aspect of the application provides a dynamic disturbance-oriented intelligent flexible scheduling method for a tire vulcanization workshop, which adopts the following technical scheme:

[0010] The dynamic disturbance-oriented intelligent flexible scheduling method for a tire vulcanization workshop comprises:

[0011] Establish a production scheduling model with the optimization goal of minimizing the maximum completion time and considering the continuous processing buffer of workpieces;

[0012] Obtain the initial processing sequence and the set of selectable machines for each workpiece process, and solve the production scheduling model as the objective function to obtain the optimal initial scheduling scheme;

[0013] Based on the optimal initial scheduling scheme, schedule the production scheduling, and when a dynamic event occurs during production, detect the type and occurrence time of the dynamic event, and extract the completed process, the processing process and the unstarted process;

[0014] The to-be-scheduled process is determined based on the influence of the dynamic event on the process being processed and the process not being processed, the process processing order of the optimal initial scheduling scheme is reserved, the optimal processing machine of the to-be-scheduled process is updated, and a rescheduling scheme is generated.

[0015] Further, the constraint condition of the production scheduling model with the target of minimizing the maximum completion time comprises:

[0016] Machine unique occupation constraint, that is, each process can be processed only once by a processing machine;

[0017] Machine capacity constraint, that is, each machine can process only one process at the same time;

[0018] Workpiece processing order constraint, that is, the next process starts processing only after the previous process is completed;

[0019] Process time buffer constraint, that is, the processes of the same workpiece cannot be continuously processed, and there is a cooling buffer time between each process;

[0020] All processes need to be processed once.

[0021] Further, the initial processing order of each workpiece process and the optional machine set are obtained, and the production scheduling model is taken as a target function to be solved, so as to obtain an optimal initial scheduling scheme, which comprises:

[0022] The initial processing order of each workpiece process is obtained, and an ascending position mapping coding strategy is used for coding to obtain the optimal processing order of each workpiece process;

[0023] Based on the optimal processing order of each workpiece process and the optional machine set, the production scheduling model is taken as a target function to be solved, so as to obtain an optimal initial scheduling scheme.

[0024] Further, the to-be-scheduled process is determined based on the influence of the dynamic event on the process being processed and the process not being processed, which comprises:

[0025] If the dynamic event is a machine failure type, the subsequent processing of the process being processed is stopped, and the process being processed and the process not being processed are taken as the to-be-scheduled process;

[0026] If the dynamic event is a workpiece cancellation type, the process being processed is stopped, and the process not being processed is taken as the to-be-scheduled process;

[0027] If the dynamic event is an order insertion type, the workpiece process of the inserted order is optimized, and the workpiece process of the inserted order, the process being processed and the process not being processed are taken as the to-be-scheduled process.

[0028] Further, the optimal processing machine of the to-be-scheduled process is updated, and a rescheduling scheme is generated, which comprises:

[0029] Based on the current status, processing capacity, and load of all machines, a set of available machines is obtained;

[0030] With the production scheduling model as the objective, the optimal processing machine for the scheduled process is determined from the set of available machines. Based on the optimal processing machine for the scheduled process, the start and end times of each scheduled process and the optimal processing machine number are determined, and a rescheduling scheme is generated.

[0031] Furthermore, based on the current state, processing capacity, and load of all machines, the set of available machines is obtained, including:

[0032] Based on the current status of all machines, idle machines are selected with the goal of balancing machine load.

[0033] When multiple machines are available, choose the one with the highest processing capacity.

[0034] When there are multiple machines with strong processing capabilities to choose from, select the machine with the larger machine number as the usable machine.

[0035] Obtain the set of available machines.

[0036] According to some embodiments, a second aspect of the present invention provides an intelligent flexible scheduling system for tire vulcanizing workshops oriented towards dynamic disturbances, employing the following technical solution:

[0037] An intelligent and flexible scheduling system for tire vulcanizing workshops accommodating dynamic disturbances includes:

[0038] The production scheduling model building module is configured to build a production scheduling model with the optimization objective of minimizing the maximum completion time and taking into account the buffer of continuous processing of workpieces;

[0039] The initial scheduling module is configured to obtain the initial processing sequence and the set of available machines for each workpiece, and solve the optimal initial scheduling scheme by using the production scheduling model as the objective function.

[0040] The dynamic event detection module is configured to schedule production based on the optimal initial scheduling scheme. When a dynamic event occurs during the production process, it detects the type of dynamic event and the time of the event, and extracts the completed processes, the processes being processed, and the processes that have not yet started.

[0041] The rescheduling module is configured to determine the processes to be scheduled based on the impact of dynamic events on the processes currently being processed and the processes that have not yet started. It retains the process processing order of the optimal initial scheduling scheme, updates the optimal processing machine for the processes to be scheduled, and generates a rescheduling scheme.

[0042] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium.

[0043] A computer readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the steps of the intelligent flexible scheduling method for dynamic disturbance-oriented tire vulcanization plant according to the first aspect.

[0044] According to some embodiments, a fourth aspect of the present application provides a computer device.

[0045] A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the intelligent flexible scheduling method for dynamic disturbance-oriented tire vulcanization plant according to the first aspect when executing the program.

[0046] According to some embodiments, a fifth aspect of the present application provides a computer program product or a computer program.

[0047] A computer program product or a computer program, comprising computer instructions stored in a computer readable storage medium, wherein a processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to cause the computer device to perform the steps of the intelligent flexible scheduling method for dynamic disturbance-oriented tire vulcanization plant according to the first aspect.

[0048] Compared with the prior art, the present application has the following beneficial effects:

[0049] The intelligent scheduling method of the present application takes into account the characteristics of the mixing process and the dynamic response capability, can maintain the stability of the overall scheduling in an uncertain environment, realize local rapid optimization and efficient operation of the system, and thus meet the urgent needs of modern tire production for flexible and intelligent scheduling.

[0050] The present application provides a scheduling scheme based on minimizing the completion time and comprehensively considering the maximum processing capacity of the machine and the minimum machine load imbalance, which meets the full utilization of each machine, avoids machine overload and excessive machine idle, and through the scheduling selection mode based on the machine processing capacity and the current state of the machine, a more efficient, more stable and more suitable for factory processing demand scheduling scheme is obtained.

[0051] The present application provides a new rescheduling scheme, which retains the workpiece process processing sequence of the original scheduling scheme, maximally utilizes each processing machine, and ensures that after the occurrence of a dynamic event, the system can quickly and efficiently respond to the disturbance event, flexibly schedules the machine, and adjusts the processing machine selection in real time based on the original plan.

[0052] The application provides a strategy of alternately processing procedures, different workpiece procedures can be continuously processed, and there is a certain time buffer between different workpiece procedures, so that the quality problem of finished rubber caused by insufficient cooling during continuous processing is effectively avoided. The procedure and individual code are constructed by using ascending position mapping mode, and the cooperative optimization of workpiece procedure sequence and machine selection is completed by improving the algorithm.

[0053] The application provides a rescheduling strategy suitable for various dynamic events, which can be applied to disturbance events such as machine failure, workpiece insertion and workpiece cancellation encountered in actual production process. BRIEF DESCRIPTION OF DRAWINGS

[0054] The drawings accompanying the specification of the application form part of the application and serve to further understand the application. The illustrative embodiments of the application and their description serve to explain the application without constituting an improper limitation of the application.

[0055] Figure 1 The flow chart of the intelligent flexible scheduling method for dynamic disturbance in the embodiment of the application;

[0056] Figure 2 The mapping relationship between the processing sequence of workpiece procedures and individual elements in the embodiment of the application;

[0057] Figure 3 The selection diagram of the dynamic machine selection rule in the embodiment of the application;

[0058] Figure 4 The original production scheduling Gantt chart of the first workshop instance, 15 workpieces and 6 machines in the embodiment of the application;

[0059] Figure 5 The rescheduling Gantt chart after machine failure of the first workshop instance, 15 workpieces and 6 machines in the embodiment of the application;

[0060] Figure 6 The original production scheduling Gantt chart of the second workshop instance, 10 workpieces and 6 machines in the embodiment of the application;

[0061] Figure 7 The rescheduling Gantt chart after insertion of 5 new workpieces of the second workshop instance, 10 workpieces and 6 machines in the embodiment of the application;

[0062] Figure 8 The original production scheduling Gantt chart of the third workshop instance, 15 workpieces and 6 machines in the embodiment of the application;

[0063] Figure 9 The rescheduling Gantt chart after cancellation of workpiece 9 of the third workshop instance, 15 workpieces and 6 machines in the embodiment of the application. DETAILED DESCRIPTION

[0064] The application will be further described below in connection with the drawings and examples.

[0065] It should be noted that the following detailed description is illustrative only and is intended to provide further description of the application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0066] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0067] The embodiments in the application and the features in the embodiments can be combined with each other without conflict.

[0068] Embodiment one

[0069] The embodiment provides a tire vulcanization plant intelligent flexible scheduling method for dynamic disturbance. The embodiment takes the method applied to a server as an example. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server and is realized through interaction of the terminal and the server. The server can be a stand-alone physical server, a server cluster composed of multiple physical servers or a distributed system, and can also be a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, security services CDN, and basic cloud computing services such as big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch and the like, but is not limited thereto. The terminal and the server can be directly or indirectly connected through wired or wireless communication, which is not limited in the application. In the embodiment, the method comprises the following steps:

[0070] A production scheduling and dispatching model is established, which takes minimizing the maximum completion time as an optimization objective and considers workpiece continuous processing buffer;

[0071] An initial processing sequence of each workpiece process and a set of selectable machines are obtained, and the production scheduling and dispatching model is taken as a target function to obtain an optimal initial scheduling scheme;

[0072] The scheduling is based on the optimal initial scheduling scheme. When a dynamic event occurs in the production process, the type of the dynamic event and the time of the event are detected, and the completed process, the processing process and the unstarted process are extracted;

[0073] Based on the influence of the dynamic event on the processing process and the unstarted process, the to-be-scheduled process is determined, the process processing order of the optimal initial scheduling scheme is reserved, the optimal processing machine of the to-be-scheduled process is updated, and the rescheduling scheme is generated.

[0074] As Figure 1 shown, the specific process of the method described in the embodiment is as follows:

[0075] Step S1: Establish a production scheduling model;

[0076] A production scheduling model is established, which takes minimizing the maximum completion time as the optimization goal and considers the workpiece continuous processing buffer. The parameter variables in the production scheduling model are set as shown in Table 1.

[0077] Table 1 Variable Description

[0078]

[0079] The production scheduling model for minimizing the maximum completion time is as follows:

[0080] (1);

[0081] Among them, minimizing the maximum completion time, is the completion time of the workpiece .

[0082] Step S102: The constraint condition of the production scheduling model with workpiece continuous processing buffer is:

[0083] Constraint condition 1: machine unique occupation constraint, each process can only be processed by a processing machine once.

[0084] (2);

[0085] Constraint condition 2: machine capacity constraint, each machine can only process one process at the same time.

[0086] (3);

[0087] Constraint condition 3: workpiece processing order constraint, the workpiece process satisfies the sequential processing, that is, after the previous process is completed, the next process can be processed; process time buffer constraint, the same workpiece process cannot be continuously processed, and a cooling buffer time is required between each process .

[0088] If there is a 4-hour cooling buffer time between each process, the specific value can be dynamically adjusted according to the process requirements. The workpiece processing method with the cooling time buffer avoids the quality problem of the rubber material caused by the continuous processing of the workpiece, and ensures that different workpiece processes can be alternately processed. On the basis of ensuring the buffer cooling time between processes, the production efficiency is improved.

[0089] (4);

[0090] wherein, is the process of the workpiece the start processing time on the machine ;

[0091] Constraint condition 4: all processes need to be processed once.

[0092] (5).

[0093] Step S2: solving the optimal initial scheduling scheme - obtaining the initial processing order of each workpiece process and the optional machine set, solving the scheduling model as the objective function to obtain the optimal initial scheduling scheme, including:

[0094] The initial processing order of each workpiece process is obtained, and an ascending position mapping coding strategy is used for coding to obtain the optimal processing order of each workpiece process;

[0095] Based on the optimal processing order of each workpiece process and the optional machine set, the scheduling model is solved as the objective function to obtain the optimal initial scheduling scheme.

[0096] The optimal initial scheduling scheme includes the start and end time and the processing machine of each process of each workpiece.

[0097] It should be noted that when the objective function is solved, the initial processing order of each workpiece process and the optional machine set are used as the data basis, therefore, the embodiment adopts ascending position sorting of individuals to realize the mapping relationship between discrete solutions and continuous solutions, so as to realize the mapping of the position of the individual to the processing order of the workpiece process. Based on the initial processing order of each workpiece process, the individual position vector is converted into the optimal processing order of the workpiece process by using the ascending position mapping coding strategy. The embodiment converts the individual position vector into the optimal processing order of the workpiece process by using the ascending position mapping coding strategy. The coding mode can realize the conversion between continuous and discrete solutions, ensure the one-to-one correspondence relationship between the process and the machine allocation, and facilitate scheduling modeling and objective function solving.

[0098] In a preferred embodiment of the application, the mapping relationship between the processing order of the workpiece process and the individual element is as follows: Figure 2As shown, the decoding process of converting individual position vector into the optimized processing sequence of workpiece processes using ascending position mapping encoding strategy includes the following steps:

[0099] Obtain the initial processing sequence of each workpiece process:

[0100] This embodiment takes scheduling three workpieces (1, 2, 3) as an example. Workpiece 1 has two processes, workpiece 2 has two processes, and workpiece 3 has one process. The total number of processes is 5, and the initial processing sequence set is: {1-1, 1-2, 2-1, 2-2, 3}, that is Figure 2 gray 1, blue 1, gray 2, green 2, orange 3. Among them, 1-1 represents the first process of workpiece 1, and the others are similar.

[0101] Based on the initial processing sequence set, generate or receive a continuous value individual position vector:

[0102] Generate a continuous value vector using an optimization algorithm (such as genetic algorithm) as an individual's chromosome. The dimension of the vector is the same as the total number of processes, and an individual position vector containing 5 random continuous values is generated: X = [-2.3, 2.1, 1.2, 1.0, 0.5];

[0103] Sort the vector values in ascending order and get the index, including:

[0104] Sort all elements in the individual position vector X in ascending order according to their numerical values. After sorting, record the position index (starting from 1) of each element in the original vector, so as to obtain an index sequence, as shown in Table 2.

[0105] Table 2 Ascending sorting mapping table

[0106]

[0107] The above table shows the sorting process. Finally, what is needed is not the sorted value, but the original index sequence corresponding to the sorted value;

[0108] According to the sorting result, the index sequence I = [1, 5, 4, 3, 2] is obtained. The meaning of this sequence is that the position of the smallest value (-2.3) in the original vector is 1, the position of the second smallest value (0.5) is 5, and so on. The position of the largest value (2.1) is 2.

[0109] Map the index sequence to the workpiece process processing sequence:

[0110] Replace each index in the index sequence I with the workpiece process it represents.

[0111] First, the correspondence between the index number and the process needs to be established. In this embodiment, the following convention is adopted: the index position in the vector is assigned in the order of the workpiece. That is:

[0112] Index 1 corresponds to process 1-1; index 2 corresponds to process 1-2; index 3 corresponds to process 2-1; index 4 corresponds to process 2-2; and index 5 corresponds to process 3.

[0113] Each number in the index sequence I = [1, 5, 4, 3, 2] is replaced by a specific process according to the correspondence described above:

[0114] 1 corresponds to process 1-1; 5 corresponds to process 3; 4 corresponds to process 2-2; 3 corresponds to process 2-1; and 2 corresponds to process 1-2;

[0115] Thus, the optimized processing order S of the workpiece is obtained:

[0116] S = [1-1, 3, 2-2, J2-1, 2-1, 1-2], that is, Figure 2 gray 1, orange 3, green 2, gray 2, and blue 1.

[0117] In the verification phase, this embodiment uses a genetic algorithm (Genetic Algorithm, GA) to solve the instance of the scheduling model to verify the adaptability and optimization effect of the proposed scheduling strategy under typical working conditions. That is, this embodiment is based on the basic framework of the genetic algorithm for scheduling optimization, but the core point is still in the subsequent rescheduling optimization process, rather than relying on the specific optimization algorithm itself.

[0118] Step S3: Based on the optimal initial scheduling scheme, schedule the production, and detect the production situation in real time, that is, detect whether a dynamic event occurs in real time.

[0119] In this embodiment, a dynamic event refers to an unexpected disturbance or unplanned change that occurs during the production execution process in the tire mixing or vulcanization workshop, which may interfere with the current scheduling scheme and trigger a dynamic response and rescheduling mechanism. In order to improve the stability and flexibility of the scheduling system, this embodiment focuses on the following three types of dynamic events:

[0120] 1. Workpiece cancellation type: including cases where part of the workpiece is suspended, reworked, or canceled due to raw material shortage, quality problem, or process abnormality;

[0121] 2. Machine failure type: including equipment failure, insufficient maintenance, personnel change, energy consumption limitation, and other factors that cause equipment to stop running or availability to decrease;

[0122] 3. Order insertion class: refers to temporarily receiving emergency orders or high-priority tasks in the production process, which need to be dynamically inserted and adjusted on the basis of the current schedule.

[0123] The scheduling method and system proposed in this embodiment can quickly identify and respond to the above dynamic events. Through local rescheduling and real-time machine selection mechanism, process-level adjustment and optimal allocation of resources are realized, ensuring the continuous and stable operation of the workshop under disturbance conditions.

[0124] Dynamic event state simulation, simulate the actual production, under the condition of sufficient productivity, new order receiving, capacity quality problem, non-ideal workpiece stop production, machine maintenance deficiency, machine failure. The arrival time of the above dynamic events changes with the machine load;

[0125] To simulate the actual production process, the dynamic events are set as follows:

[0126] The occurrence time of all types of dynamic events is set as:

[0127] (6);

[0128] wherein, and are constant coefficients between 0 and 1, and the values are , , is the maximum completion time.

[0129] Wherein, the machine failure setting: there is only one machine failure, the failure probability increases with the increase of machine load, the maintenance time is related to the order completion time.

[0130] The machine failure probability when the machine failure event occurs is set as:

[0131] (7);

[0132] wherein, is the running failure probability of machine , is the load time of machine , is the total machine load time.

[0133] The maintenance time range after machine failure is set as:

[0134] (8);

[0135] wherein, is and is a constant coefficient between 0 and 1, and is , , is the maximum completion time.

[0136] Step S4: if a dynamic event occurs, go to step S5; if no dynamic event occurs, go to S8;

[0137] Among the dynamic events of the order insertion class, the machining priority of the workpiece process is the highest, and among the dynamic events of the workpiece cancellation class, the remaining machining processes of the cancelled workpiece are all cancelled.

[0138] Step S5: detect the dynamic event type and event occurrence time, extract the completed process, the processing process and the unstarted process;

[0139] Step S6: determine the to-be-scheduled process based on the influence of the dynamic event on the processing process and the unstarted process, retain the process machining order of the optimal initial scheduling scheme, update the optimal machining machine of the to-be-scheduled process, and generate a rescheduling scheme, specifically:

[0140] Step S601: determine the to-be-scheduled process based on the influence of the dynamic event on the processing process and the unstarted process, including:

[0141] If the dynamic event is the machine failure class, stop the subsequent processing of the processing process, and take the processing process and the unstarted process as the to-be-scheduled process;

[0142] If the dynamic event is the workpiece cancellation class, stop the processing process, and take the unstarted process as the to-be-scheduled process;

[0143] If the dynamic event is the order insertion class, optimize the scheduling of the workpiece process of the inserted order, and take the workpiece process of the inserted order, the processing process and the unstarted process as the to-be-scheduled process.

[0144] In the scheduling process, not only machine failure will cause the process machining to be affected, but also workpiece cancellation, insertion and other dynamic events will affect the scheduling scheme, therefore, the dynamic event influence here more accurately reflects the influence of various real-time changes in the scheduling process on the process machining.

[0145] The workshop event log can be obtained in real time, which is used to judge whether the rescheduling mechanism is triggered, and the scheduling priority is adjusted in dynamic rescheduling, wherein the priority of the inserted order is higher than that of the original order, and the remaining machining processes of the cancelled workpiece are deleted.

[0146] The triggering conditions of the rescheduling mechanism include: machine failure or maintenance, workpiece cancellation or rework, emergency order insertion, and scheduling blockage due to resource conflict, etc. When the original optimal initial scheduling scheme cannot be normally executed or affects the overall progress, the system will start the rescheduling mechanism to ensure the scheduling continuity and rapid response at the process level.

[0147] If a dynamic event such as machine failure occurs during the processing of a workpiece, the current processing machine cannot continue to complete the process, and the process is considered to be affected by the disturbance. At this time, the process cannot be successfully completed on the original processing machine, and the rescheduling mechanism needs to be triggered to reevaluate the available processing resources and select a new processing machine from the candidate machine set to complete the process, ensuring the continuity and executability of the overall production plan.

[0148] Step S602: Real-time detection of processing machine state, reservation of process processing order of optimal initial scheduling scheme, priority balance of load and minimization of completion time, update of optimal processing machine selection of workpiece to be scheduled, generation of rescheduling scheme, specific measures as follows:

[0149] Based on the current state, processing capacity and load of all machines, the available machine set is obtained, including:

[0150] Based on the current state of all machines, the idle machines are selected as the target of balancing machine load;

[0151] When there are multiple idle machines, the machine with strong processing capacity is selected;

[0152] When there are multiple machines with strong processing capacity, the machine with large machine number is selected as the available machine;

[0153] The available machine set is obtained.

[0154] From the available machine set, the optimal processing machine of the workpiece to be scheduled is determined based on the scheduling model, and the rescheduling scheme is generated, including:

[0155] As shown in Figure 3 , based on the dynamic machine selection rule of the workpiece sequence to be scheduled, when the workpiece to be scheduled is scheduled, the machine that minimizes the global completion time is selected from the available machine set , the optimal processing machine of the workpiece to be scheduled is determined , that is :

[0156] (9);

[0157] (10);

[0158] Wherein, is the machine machining theoretical completion time of the workpiece, the maximum value of the machine numbers of the available machines, , , the machine set with the minimum predicted completion time among the machines that can process the workpiece process in the available machines, the machine set with the minimum predicted processing time among the machines that can process the workpiece process in the available machines.

[0159] As Figure 3 illustrated, the selection process of the dynamic machine selection rule is as follows with specific examples:

[0160] Step 1: First, determine the next workpiece process that needs to be assigned the optimal machine, i.e. Figure 3 is the process 3 of the workpiece 1;

[0161] Step 2: The machine set that can process this process is:

[0162] Machine 1, processing time of this process is 2;

[0163] Machine 2, processing time of this process is 1;

[0164] Machine 3, processing time of this process is 1;

[0165] Step 3: The predicted completion time of Machine 1 processing this process is 7;

[0166] The predicted completion time of Machine 2 processing this process is 7;

[0167] The predicted completion time of Machine 3 processing this process is 7;

[0168] Need to select the machine with the minimum predicted completion time, then the machine set of is still:

[0169] {Machine 1, Machine 2, Machine 3};

[0170] Need to select the machine with the minimum predicted processing time, then the machine set of is:

[0171] {Machine 2, Machine 3};

[0172] Step 4: Finally, select the machine with the maximum machine number in , then the final optimal processing machine is Machine 3.

[0173] ​Based on the optimal processing machine of the to-be-scheduled process, the processing start and end time and the optimal processing machine number of each to-be-scheduled process are determined, a rescheduling scheme is generated, and a visual result in the form of a Gantt chart is output.

[0174] The processing machine selection for the to-be-scheduled process follows the dynamic machine selection rule, idle state equipment is preferentially selected in the processable machine, the processing capacity is then considered, and finally, the allocation is realized through number sorting to realize the optimal processing efficiency and load balancing. The rescheduling optimization strategy provided in the embodiment avoids algorithm re-optimization and responds more quickly. If an event occurs, the rescheduling strategy is selectively executed, the process processing order of the original optimal initial scheduling scheme is retained, and the machine is flexibly changed.

[0175] Step S7: According to the rescheduling scheme, the production processing is re-sequenced;

[0176] Step S8: All production tasks are sequenced, and the scheduling is completed. The scheduling result generated based on the rescheduling scheme includes the processing start and end time of each process, the processing machine number, and whether it is a rescheduled process, and a visual result in the form of a Gantt chart is output.

[0177] The embodiment is based on the genetic algorithm architecture and fuses cooling buffer processing, ascending coding strategy, dynamic machine selection rule and disturbance event response mechanism, and can realize stable solution of a high-quality scheduling scheme in a dynamic flexible scheduling scenario. It should be noted that although the optimization framework is based on GA, the core innovation point of the embodiment is the construction of the scheduling strategy and the optimization design of the process-machine allocation logic, rather than relying on the specific optimization algorithm itself.

[0178] The embodiment provides an intelligent flexible scheduling optimization method for a tire vulcanization workshop, aiming to improve production efficiency, reduce resource waste, and enhance the response capability to dynamic disturbances (such as insertion, cancellation, equipment failure, etc.). The method dynamically selects the optimal processing equipment based on the processing order of the workpiece process and the machine state, takes into account the maximum processing capacity and the minimum load imbalance of the machine, effectively improves the equipment utilization rate and shortens the completion time. In view of the process requirements such as cooling time and continuous processing constraints in actual production, the invention introduces a time buffer mechanism to ensure the quality of the rubber material and the continuity of the process. When a dynamic event occurs, a local rescheduling strategy is adopted to flexibly adjust the machine based on the original process order, thereby improving the scheduling stability and system flexibility. The method can output a visual production scheduling result in the form of a Gantt chart, has the advantages of fast response, high adaptability and strong feasibility, and is suitable for dynamic production environment in modern tire manufacturing.

[0179] Simulation experiment

[0180] An implementation case of simulating a specific factory is shown in the following table, in which the faulty machine in the example is machine 2, the fault duration is 29h to 47h, and the rework process is process 1 of workpiece 7; the workpiece insertion order is workpiece 11 to workpiece 15 inserted as an emergency order; and the workpiece cancellation is workpiece 9 cancelled for subsequent process processing.

[0181] As shown in Figure 4 and Figure 5 , a scheduling Gantt chart of a machine fault case extracted from actual production data of the factory, Figure 4 is a Gantt chart of the original production planning scheme, Figure 5 is a scheduling Gantt chart after the machine fault occurs. As shown in Figure 6 and Figure 7 , a scheduling Gantt chart of a workpiece insertion order case extracted from actual production data of the factory, Figure 6 is a Gantt chart of the original production planning scheme, Figure 7 is a scheduling Gantt chart after the workpiece insertion order occurs. As shown in Figure 8 and Figure 9 , a scheduling Gantt chart of a workpiece cancellation case extracted from actual production data of the factory, Figure 8 is a Gantt chart of the original production planning scheme, Figure 9 is a scheduling Gantt chart after the workpiece cancellation occurs.

[0182] In view of the dynamic production environment of a tire vulcanization workshop, a scheduling response mechanism is constructed to cope with disturbances such as insertion orders, cancellations, and machine faults, process-level rapid rescheduling is realized, and the stability and flexibility of scheduling are improved. In this embodiment, a dynamic machine selection rule is used in combination with processing capacity and current load to preferentially select idle high-capacity equipment and introduce a number discrimination to enhance feasibility and balance. A local rescheduling method that preserves the original process order is used to replace only the unprocessed process machine to reduce fluctuations. A cooling time buffer is embedded between processes of the same workpiece to solve the problem of insufficient rubber cooling and ensure quality and process stability. A composite production scheduling model is used to minimize the maximum completion time, maximize machine capacity utilization, and minimize load imbalance, etc. to improve the global quality of the solution. A visual Gantt chart output is provided to support real-time rescheduling feedback triggered by dynamic events, and to assist human-machine collaboration and real-time intervention.

[0183] Embodiment Two

[0184] The embodiment provides a dynamic disturbance-oriented intelligent flexible scheduling system for a tire vulcanization workshop, which comprises:

[0185] A production scheduling model establishment module is configured to establish a production scheduling model with the optimization objective of minimizing the maximum completion time and considering workpiece continuous processing buffer;

[0186] An initial scheduling module is configured to obtain an initial processing order of each workpiece process and a set of selectable machines, and to obtain an optimal initial scheduling scheme by solving a production scheduling model as a target function.

[0187] The dynamic event detection module is configured to schedule the production based on the optimal initial scheduling scheme, detect the type of dynamic event and the time of event occurrence when a dynamic event occurs in the production process, and extract the completed process, the process being processed, and the process not started;

[0188] The rescheduling module is configured to determine the process to be scheduled based on the influence of the dynamic event on the process being processed and the process not started, reserve the process processing sequence of the optimal initial scheduling scheme, update the optimal processing machine of the process to be scheduled, and generate a rescheduling scheme.

[0189] The above modules and the examples and application scenarios realized by the corresponding steps are the same, but are not limited to the content disclosed in the above embodiment one. It should be noted that the above modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0190] The description of each of the above embodiments has its own emphasis, and the parts not described in detail in a certain embodiment can refer to the related description of other embodiments.

[0191] The proposed system can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the above modules is only a logical function division, and in actual implementation, there can be another division method, for example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0192] Embodiment three

[0193] The embodiment provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the steps in the intelligent flexible scheduling method for dynamic disturbance-oriented tire vulcanization plant as described in the above embodiment one.

[0194] Embodiment four

[0195] The embodiment provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the program to realize the steps in the intelligent flexible scheduling method for dynamic disturbance-oriented tire vulcanization plant as described in the above embodiment one.

[0196] Embodiment five

[0197] The embodiment provides a computer program product or a computer program, including computer instructions stored in a computer readable storage medium, the computer instructions being read by a processor of a computer device from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes steps in the dynamic disturbance-oriented tire vulcanization plant intelligent flexible scheduling method described in the embodiment one.

[0198] Those skilled in the art should understand that the embodiments of the present application can provide a method, a system or a computer program product. Therefore, the present application can take the form of a hardware embodiment, a software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer usable storage media (including, but not limited to, disk storage and optical storage, etc.) containing computer usable program code.

[0199] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system) and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flow(s) or block(s).

[0200] These computer program instructions can also be stored in a computer readable storage medium capable of guiding the computer or other programmable data processing devices to work in a specific way, so that the instructions stored in the computer readable storage medium produce a product including instruction means, which realizes the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flow(s) or block(s).

[0201] These computer program instructions can also be loaded into a computer or other programmable data processing device, so that a series of operation steps are performed on the computer or other programmable device to produce a computer implemented process, so that the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in the flowcharts and / or block diagrams. Figure 1 one or more flows and / or blocks Figure 1 means for performing the functions specified in the flow(s) or block(s).

[0202] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing relevant hardware, and the program can be stored in a computer readable storage medium. When the program is executed, the program can include the processes of the above-mentioned embodiment methods. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like.

[0203] Although the specific embodiments of the present application are described above with reference to the drawings, the description is not a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications or changes made on the basis of the technical solutions of the present application without creative labor are still within the scope of protection of the present application.

Claims

1. A dynamic disturbance-oriented intelligent flexible scheduling method for tire curing plant, characterized in that, The application relates to a production scheduling method and device. The production scheduling model with the optimization target of minimizing the maximum completion time considers continuous processing buffers of workpieces; The constraint conditions of the production scheduling model with the optimization target of minimizing the maximum completion time include: Workpiece processing sequence constraints, that is, after a previous process is completed, a next process starts processing; Process time buffer constraints, that is, workpiece processes cannot be continuously processed, and there is a cooling buffer time between processes; ； wherein, is the workpiece is the process is the start processing time on the machine ; is the workpiece is the process is the processing time on the machine , is the workpiece is the process is the start processing time on the machine , is the number of processes of the workpiece ; is the order workpiece quantity; 4 is a cooling buffer time of 4 hours between each process; An initial processing sequence of each workpiece process and a selectable machine set are obtained, and the production scheduling model is used as a target function to solve the optimal initial scheduling scheme, which includes: An initial processing sequence of each workpiece process is obtained, and an ascending position mapping coding strategy is used for coding to obtain an optimal processing sequence of each workpiece process, which includes: An initial processing sequence of each workpiece process is obtained; Based on the initial processing sequence set, a continuous value individual position vector is generated or received; The individual position vector value is sorted in ascending order, and an index sequence is obtained; The index sequence is mapped into a workpiece process processing sequence as the optimal processing sequence of each workpiece process; Based on the optimal processing sequence of each workpiece process and the selectable machine set, the production scheduling model is used as a target function to solve the optimal initial scheduling scheme; Based on the optimal initial scheduling scheme, production scheduling is performed, when a dynamic event occurs in the production process, the type and occurrence time of the dynamic event are detected, and a completed process, a processing process and an unstarted process are extracted; Based on the influence of the dynamic event on the processing process and the unstarted process, a to-be-scheduled process is determined, the process processing sequence of the optimal initial scheduling scheme is retained, the optimal processing machine of the to-be-scheduled process is updated, and a rescheduling scheme is generated, which includes: Based on the current state, processing capacity and load of all machines, an available machine set is obtained; The optimal processing machine of the to-be-scheduled process is determined from the available machine set based on the production scheduling model as the target, which includes: The selection process is based on the dynamic machine selection rules of the sequence of processes to be scheduled. When the process to be scheduled... When scheduled, from the set of available machines Select the machine that minimizes the global completion time to determine the optimal processing machine for the scheduled operation. ,Right now: ； ； wherein is the machine processing the theoretical completion time, is the maximum value of the machine number among the available machines, , , is the set of machines selected from among the machines that can process the workpiece process, among the available machines, in which the estimated completion time is the smallest, is the set of machines selected from among the machines that can process the workpiece process, among the available machines, in which the estimated processing time is the shortest; Based on the optimal processing machine of the to-be-scheduled process, the processing start and end time and the optimal processing machine number of each to-be-scheduled process are determined, and a rescheduling scheme is generated.

2. The dynamic disturbance oriented tire curing plant intelligent flexible scheduling method of claim 1, wherein, The constraint conditions of the production scheduling model with the optimization target of minimizing the maximum completion time also include: Machine unique occupation constraints, that is, each process can be processed only once by a processing machine; Machine capacity constraints, that is, each machine can process only one process at the same time; All processes need to be processed once.

3. The dynamic disturbance oriented tire curing plant intelligent flexible scheduling method of claim 1, wherein, The determination of the to-be-scheduled process based on the influence of the dynamic event on the processing process and the unstarted process includes: If the dynamic event is a machine failure type, the subsequent processing of the processing process is stopped, and the processing process and the unstarted process are used as the to-be-scheduled process; If the dynamic event is a workpiece cancellation type, the processing process is stopped, and the unstarted process is used as the to-be-scheduled process; If the dynamic event is an order insertion type, the workpiece processes of the inserted order are optimized and scheduled, and the workpiece processes of the inserted order, the processing process and the unstarted process are used as the to-be-scheduled process.

4. The dynamic disturbance oriented tire curing plant intelligent flexible scheduling method of claim 1, wherein, Based on the current state, processing capacity and load of all machines, an available machine set is obtained, which includes: Based on the current state of all machines, idle machines are selected as the target of balancing machine load; When there are multiple idle machines, machines with strong processing capacity are selected. When there are multiple machines with strong processing capacity and multiple selectable machines, a machine with a large number is selected as a usable machine; Get the set of available machines.

5. A dynamically perturbation-oriented intelligent flexible scheduling system for a tire vulcanization plant, characterized in that, It comprises: The production scheduling model establishment module is configured to establish a production scheduling model with the optimization objective of minimizing the maximum completion time and considering the continuous processing buffer of workpieces; The constraint conditions of the production scheduling model with the objective of minimizing the maximum completion time include: Workpiece processing sequence constraint, i.e. the next process starts processing after the previous process is completed; Process time buffer constraint, i.e. the same workpiece process cannot be continuously processed, and there is a cooling buffer time between each process; ； wherein is the process of the workpiece is the start processing time on the machine is the process of the workpiece is the processing time on the machine is the start processing time of the workpiece is the process on the machine is the number of processes of the workpiece is the order workpiece number;4 is a cooling buffer time of 4 hours between each process; The initial scheduling module is configured to obtain the initial processing sequence of each workpiece process and the set of selectable machines, and solve the production scheduling model as the objective function to obtain the optimal initial scheduling scheme, including: Obtain the initial processing sequence of each workpiece process, and encode the initial processing sequence of each workpiece process using the ascending order position mapping coding strategy to obtain the optimal processing sequence of each workpiece process, including: Obtain the initial processing sequence of each workpiece process; Based on the initial processing sequence, generate or receive a continuous value individual position vector; Sort the individual position vector values in ascending order and obtain an index sequence; Map the index sequence to the workpiece process processing sequence as the optimal processing sequence of each workpiece process; Based on the optimal processing sequence of each workpiece process and the set of selectable machines, solve the production scheduling model as the objective function to obtain the optimal initial scheduling scheme; The dynamic event detection module is configured to schedule production based on the optimal initial scheduling scheme, detect the type and occurrence time of the dynamic event when a dynamic event occurs in the production process, and extract the completed process, the processing process and the unstarted process; The rescheduling module is configured to determine the to-be-scheduled process based on the influence of the dynamic event on the processing process and the unstarted process, retain the process processing sequence of the optimal initial scheduling scheme, update the optimal processing machine of the to-be-scheduled process, and generate a rescheduling scheme, including: Based on the current state, processing capacity and load of all machines, obtain the set of available machines; From the set of available machines, determine the optimal processing machine of the to-be-scheduled process based on the production scheduling model, including: The selection process is based on the dynamic machine selection rules of the sequence of processes to be scheduled. When the process to be scheduled... When scheduled, from the set of available machines Select the machine that minimizes the global completion time to determine the optimal processing machine for the scheduled operation. ,Right now: ； ； wherein is the machine processing the theoretical completion time of the workpiece process, is the maximum value of the machine number among the available machines, , , is the set of machines among the available machines, selected from the machines that can process the workpiece process, in which the estimated completion time is the smallest, is the set of machines among the available machines, selected from the machines that can process the workpiece process, in which the estimated processing time is the shortest. Based on the optimal processing machine of the to-be-scheduled process, determine the processing start and end time and the optimal processing machine number of each to-be-scheduled process, and generate a rescheduling scheme.

6. A computer-readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps in the dynamic disturbance-oriented intelligent flexible scheduling method for tire vulcanization plant in any one of claims 1-4.

7. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to implement the steps in the dynamic disturbance-oriented intelligent flexible scheduling method for tire vulcanization plant in any one of claims 1-4.

8. A computer program product, characterised in that, The computer program product comprises a computer program, which is executed by the processor to implement the steps in the dynamic disturbance-oriented intelligent flexible scheduling method for tire vulcanization plant in any one of claims 1-4.

Images