APS intelligent plan scheduling system and optimization method thereof

Through the multi-algorithm combination and artificial intelligence technology of the APS intelligent planning scheduling system, the problems of low scheduling efficiency and insufficient resource utilization in complex production environments are solved, and more efficient and intelligent production planning optimization and Resource management.

CN119005600APending Publication Date: 2024-11-22NINGBO SUYOU DIGITAL INTELLIGENCE TECHNOLOGY CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411051940.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

When facing a complex and changing production environment, the existing production planning and scheduling system has low scheduling efficiency, insufficient resource utilization, lack of intelligence and flexibility, and cannot meet the high requirements of manufacturing companies.

Method used

Provides an APS intelligent planning scheduling system, using intelligent algorithms that use multi-algorithm combination, multi-rule combination, algorithm rule fusion combination and dynamic optimization mechanism, combining artificial intelligence and machine learning technology, and adjust resource allocation in real time through parallel computing and distributed processing. Optimize production planning and resource utilization.

Benefits of technology

It significantly improves scheduling efficiency and resource utilization, enhances the intelligence and flexibility of the system, can quickly adapt to changes in the production environment, and ensures the continuity and stability of production.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005600A_ABST
    Figure CN119005600A_ABST
Patent Text Reader

Abstract

The invention discloses an APS intelligent plan scheduling system and an optimization method thereof, and belongs to the technical field of intelligent production, and the system comprises a data input module which is used for receiving a production order and resource data; the production plan generation module is used for generating a target production plan by using a preset intelligent algorithm based on the production order and the resource data; the dynamic resource allocation module is used for generating a resource allocation plan according to the target production plan and the resource data, adjusting the resource allocation plan and feeding back and adjusting the target production plan; the intelligent optimization module is used for adjusting the target production plan and the resource allocation plan based on the artificial intelligence model and optimizing the artificial intelligence model; the user-defined optimization module is used for optimizing a target production plan and a resource allocation plan according to a weight ratio in a user-defined scene; and the data output module is used for outputting the target production plan and the resource allocation plan. According to the invention, the intelligence and flexibility of the APS system can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of intelligent production technology, and in particular to an APS intelligent planning and scheduling system and an optimization method thereof. Background Art

[0002] Advanced Planning and Scheduling (APS) is an advanced planning and scheduling software specifically designed for production and manufacturing industries. The APS system is not only powerful but also user-friendly, allowing users to easily input the data required to generate production plans, view production plans, and adjust production plans. The APS system is crucial to improving the competitiveness of manufacturing companies. It can help manufacturing companies quickly respond to market changes, improve customer satisfaction, and reduce production costs.

[0003] However, with the rapid development of the manufacturing industry, manufacturing companies have higher and higher requirements for production planning and scheduling. Although the existing APS system has played an important role in improving production efficiency and resource utilization, its limitations are increasingly evident in the face of complex and changing production environments, and it cannot meet the needs of manufacturing companies. Compared with the needs of manufacturing companies, the existing APS system has low scheduling efficiency, insufficient resource utilization, and lacks intelligence and flexibility. Summary of the invention

[0004] The embodiments of the present application provide an APS intelligent planning and scheduling system and an optimization method thereof, which can significantly improve the scheduling efficiency and resource utilization of the APS system, and enhance the intelligence and flexibility of the APS system.

[0005] According to one aspect of an embodiment of the present application, an APS intelligent planning and scheduling system is provided, the system comprising:

[0006] A data input module, for receiving a production order and resource data, wherein the production order includes order parameters for indicating order requirements, and the resource data includes resource parameters for generating constraint conditions;

[0007] A production plan generation module, used to generate a target production plan based on the production order and the resource data using a preset intelligent algorithm, wherein the target production plan meets the order requirements and the constraints; the preset intelligent algorithm is an intelligent algorithm that supports multi-algorithm combination, multi-rule combination, algorithm rule fusion combination and dynamic optimization mechanism;

[0008] A dynamic resource allocation module, configured to generate a resource allocation plan according to the target production plan and the resource data, adjust the resource allocation plan according to the real-time resource status during the production process, and adjust the target production plan based on feedback from the resource allocation plan;

[0009] An intelligent optimization module, used to adjust the target production plan and the resource allocation plan based on the artificial intelligence model, and optimize the artificial intelligence model based on the adjustment of the resource allocation plan and the feedback adjustment of the target production plan;

[0010] A custom optimization module, used to optimize the target production plan and the resource allocation plan according to the weight ratio in the scenario customized by the user, wherein the weight ratio indicates the proportion of production factors and the proportion of various resources in the production scenario;

[0011] A data output module is used to output the target production plan and the resource allocation plan.

[0012] In one embodiment, the production plan generation module is used to perform the following operations:

[0013] Based on the target production requirements and the constraints, a mode parameter is determined, the mode parameter indicates whether to use a multi-algorithm combination, whether to use a multi-rule combination, whether to use an algorithm-rule fusion combination, and whether to use a dynamic optimization mechanism. The multi-algorithm combination includes combining at least two algorithms from among a genetic algorithm, a particle swarm algorithm, and an ant colony algorithm. The multi-rule combination includes combining at least two rules of a shortest construction period scheduling rule, a scheduling rule according to the order of delivery dates, a scheduling rule considering the distance between construction period and delivery date, a CR value scheduling rule, and a shortest process scheduling rule. The algorithm-rule fusion combination includes combining at least one of the above algorithms and at least one of the above rules. The multi-algorithm combination, the multi-rule combination, and the algorithm-rule fusion combination are in a one-to-one selection relationship.

[0014] In the case where the mode parameter indicates the use of a combination of multiple algorithms, an algorithm selection interface is displayed, and at least two target algorithms are determined according to the result of the user triggering the algorithm selection interface; based on the at least two target algorithms, the target production plan is generated;

[0015] In the case where the mode parameter indicates the use of a combination of multiple rules, a rule selection interface is displayed, and at least two target rules are determined according to the result of the user triggering the rule selection interface; based on the at least two target rules, the target production plan is generated;

[0016] When the mode parameters indicate the use of an algorithm-rule fusion combination, an algorithm-rule selection interface is displayed, and at least one target algorithm and at least one target rule are determined based on the result of the user triggering the algorithm-rule selection interface; based on the at least one target algorithm and the at least one target rule, the target production plan is generated.

[0017] In one embodiment, the process of generating the target production plan uses parallel computing and distributed processing, and the target production plan includes an optimal production plan and a suboptimal production plan.

[0018] In one embodiment, the dynamic resource allocation module is used to perform the following operations:

[0019] When any production node in the production plan is not completed on time, obtaining usage of various resources corresponding to the production node;

[0020] Determine, according to the usage of the various resources, a target resource type corresponding to a bottleneck resource, wherein the bottleneck resource is a resource that causes the production node to not be completed on time;

[0021] Acquire all associated production plans, wherein the resource allocation plans corresponding to the associated production plans have the target resource type and are allowed to be adjusted;

[0022] Determine at least one reference production plan among all the associated production plans, wherein the reference production plan does not have any production nodes that are not completed on time, and the target resource type in the reference production plan is in a normal state or an idle state;

[0023] Without affecting the implementation of each of the reference production plans, the allocation value of the target resource type corresponding to the reference production plan is reduced, and the allocation value of the target resource type corresponding to the target generation plan is increased accordingly to complete bottleneck resource scheduling and achieve bottleneck resource load balancing.

[0024] In one embodiment, the dynamic resource allocation module is used to perform the following operations:

[0025] When each production node of each production plan is completed on time, the resources used by the production node and the corresponding planned resources are counted, where the planned resources are the resources allocated to the production node by the resource allocation plan corresponding to the production plan;

[0026] Based on the difference between the used resources and the planned resources, the state of each type of resources is determined, and the state includes a normal state, a bottleneck state and an idle state.

[0027] In one embodiment, the intelligent optimization module is used to perform the following operations:

[0028] Training the artificial intelligence model, wherein the training samples of the artificial intelligence model include an initial production plan and an initial resource allocation plan having a corresponding relationship, and an optimized production plan corresponding to the initial production plan and an optimized resource allocation plan corresponding to the initial resource allocation plan;

[0029] The target production plan and the corresponding resource allocation plan are input into the artificial intelligence model to obtain an optimized target production plan and a corresponding optimized resource allocation plan.

[0030] According to another aspect of an embodiment of the present application, a scheduling optimization method based on an APS intelligent planning and scheduling system is provided, the method being applied to any of the aforementioned APS intelligent planning and scheduling systems, the method comprising:

[0031] receiving a production order and resource data, wherein the production order includes order parameters for indicating order requirements, and the resource data includes resource parameters for generating constraint conditions;

[0032] Based on the production order and the resource data, a target production plan is generated, wherein the target production plan meets the order requirements and the constraint conditions;

[0033] Generate a resource allocation plan according to the target production plan and the resource data;

[0034] Adjust the target production plan and the resource allocation plan based on the artificial intelligence model;

[0035] Optimizing the target production plan and the resource allocation plan according to the weight ratio in the user-defined scenario;

[0036] The target production plan and the resource allocation plan are output.

[0037] In one embodiment, generating a target production plan based on the production order and the resource data includes:

[0038] Based on the production order and the resource data, a target production plan is generated using a preset intelligent algorithm, where the preset intelligent algorithm is an intelligent algorithm that supports multi-algorithm combination, multi-rule combination, algorithm-rule fusion combination, and dynamic optimization mechanism.

[0039] In one embodiment, the method further comprises:

[0040] The artificial intelligence model is optimized based on adjustments to the resource allocation plan and feedback adjustments to the target production plan.

[0041] According to another aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the aforementioned scheduling optimization method based on the APS intelligent planning and scheduling system.

[0042] The technical solution provided in the embodiments of the present application can bring the following beneficial effects:

[0043] The present application embodiment proposes an APS intelligent planning and scheduling system and an optimization method thereof, which has the following significant advantages:

[0044] (1) Combination optimization using multiple algorithms and multiple rules: In order to improve scheduling efficiency, the APS intelligent planning and scheduling system introduces a combination of multiple optimization algorithm rules, such as genetic algorithm, particle swarm algorithm and ant colony algorithm, such as the shortest construction period scheduling rule, the scheduling rule according to the order of delivery date, the scheduling rule considering the distance between the construction period and the delivery date, the CR value scheduling rule, the shortest process scheduling rule, etc. These algorithms and rules can quickly process large-scale data and adapt to the dynamically changing production environment through parallel computing and distributed processing. By combining the advantages of different algorithms and rules, the system can find the optimal or suboptimal scheduling plan in a shorter time, significantly improving scheduling efficiency and accuracy.

[0045] (2) Dynamically adjust resource allocation strategies: In order to improve resource utilization, the system can adjust resource allocation in real time according to production demand and resource status to ensure that resources are maximized. By automatically identifying bottleneck resources and optimizing and adjusting them, the system can avoid idle or overloaded resources, thereby improving resource utilization and production efficiency. For example, during peak production periods, the system can automatically adjust the utilization of key equipment to ensure the balance and smooth operation of the production line.

[0046] (3) Introducing artificial intelligence and machine learning technologies: In order to enhance the intelligence and flexibility of the system, the APS intelligent planning and scheduling system combines artificial intelligence and machine learning technologies. Through data analysis and model training, the system can continuously optimize and adjust scheduling strategies to adapt to different production needs and environmental changes. The system can autonomously learn and adapt to changes in the production environment, improving the intelligence level and response speed of scheduling. For example, when the number of orders suddenly increases or a production line fails, the system can quickly adjust the scheduling strategy to ensure the continuity and stability of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is a schematic diagram of the architecture of the APS intelligent planning and scheduling system provided by one embodiment of the present application;

[0049] Figure 2It is a block diagram of the relevant functional modules of the APS intelligent planning and scheduling system provided by one embodiment of the present application;

[0050] Figure 3 It is a schematic diagram of a process for generating a target production plan provided by an embodiment of the present application;

[0051] Figure 4 This is a schematic diagram of a dynamic resource allocation process provided by an embodiment of the present application;

[0052] Figure 5 It is a scheduling optimization method provided by an embodiment of the present application;

[0053] Figure 6 It is a complete implementation process diagram provided by an embodiment of the present application;

[0054] Figure 7 It is a system-level framework diagram of an embodiment of the present application that supports the APS intelligent planning and scheduling system and its optimization method. DETAILED DESCRIPTION

[0055] Before describing the embodiments of the present application in detail, the relevant technical background related to the embodiments of the present application is introduced to facilitate understanding by those skilled in the art in the field of the present application.

[0056] Advanced Planning and Scheduling (APS) is an advanced planning and scheduling software specifically for the production and manufacturing industries. The APS system is designed to optimize the production process, improve efficiency, reduce waste, and ensure on-time delivery of products. The APS system not only supports accurate resource allocation based on production needs and available resources, such as machines, labor, and raw materials, but also supports detailed planning of the start and end time of each process to ensure a smooth production process. The APS system can generate production plans based on various production constraints, such as equipment capacity, labor skills, delivery deadlines, etc., to improve the scientificity and rationality of the production process. Not only that, the APS system can also integrate real-time data, such as order changes, inventory levels, equipment status, etc., to facilitate dynamic adjustment of production plans, and allow users to simulate different production scenarios and evaluate the impact of different production plans on the production process.

[0057] The APS system is not only powerful but also user-friendly. It provides an intuitive graphical user interface that allows users to easily input the data required to generate production plans, view production plans, and adjust production plans.

[0058] In short, the APS system is crucial to improving the competitiveness of manufacturing companies. It can help manufacturing companies respond quickly to market changes, improve customer satisfaction, and reduce production costs.

[0059] However, with the rapid development of the manufacturing industry, manufacturing companies have higher and higher requirements for production planning and scheduling. Although the existing APS system has played an important role in improving production efficiency and resource utilization, its limitations are increasingly evident in the face of complex and changing production environments, and it cannot meet the needs of manufacturing companies. Compared with the needs of manufacturing companies, the existing APS system has the following shortcomings:

[0060] (1) Low scheduling efficiency: Existing APS systems usually rely on a single rule for scheduling, such as the first-come, first-served rule (FCFS) or the shortest processing time first rule (SPT). These simple rule-based scheduling methods may be effective in simple production environments, but they are inefficient in complex and changing production environments and cannot fully adapt to dynamically changing production needs. Due to the lack of multi-algorithm combination, multi-rule combination, algorithm-rule fusion combination and dynamic optimization mechanism, existing APS systems are difficult to generate high-quality production plans when there are large order volumes, complex order situations, frequently changing production plans and multiple resource constraints, resulting in low scheduling efficiency.

[0061] (2) Insufficient resource utilization: Existing APS systems usually adopt fixed strategies for resource allocation and lack the ability to flexibly adjust. This leads to low resource utilization, often idle or overloaded resources, increased production costs and resource waste. For example, during peak production periods, some key equipment may be overloaded, while other equipment is idle and not fully utilized.

[0062] (3) Lack of intelligence and flexibility: Most existing APS systems rely on preset rules and parameters and lack the ability to learn and adapt autonomously. When faced with changes in the production environment and emergencies, existing APS systems often require manual intervention for adjustment. They lack intelligence and flexibility, which affects the continuity and stability of production. For example, when the number of orders suddenly increases or a production line fails, the existing APS system cannot quickly adjust the scheduling strategy, resulting in a decrease in production efficiency.

[0063] In view of this, the present application embodiment provides an APS intelligent planning and scheduling system and an optimization method thereof. The APS intelligent planning and scheduling system has high decoupling capability, a complete logical architecture and powerful functions. Please refer to Figure 1 , which shows a schematic diagram of the architecture of the APS intelligent planning and scheduling system of the embodiment of the present application. The architecture includes the following components:

[0064] User interface: responsible for interaction with users, including interaction based on the work interface and display of specific data;

[0065] Core functions: responsible for providing users with production plan management, material management, optimization algorithm management, linear programming management and heuristic algorithm management. Production plan management and material management are the main service contents of the APS system, which assists users in generating, adjusting and optimizing production plans and resource allocation plans. Different from the APS system in the prior art, the APS system in the embodiment of the present application allows access to various algorithms for realizing automated production plan generation and resource allocation plan generation in an extensible manner, including linear programming algorithms and heuristic algorithms, and these algorithms can be optimized. Specifically, time management functions and task scheduling functions are also provided in the production plan management function.

[0066] Data layer: responsible for providing underlying data support, including databases, data input components and data output components. Specifically, the APS system of the embodiment of the present application supports relational databases and data warehouses.

[0067] Functions such as security modules, permission management and data encryption are used to provide security support and permission protection to enhance the security of the APS system.

[0068] Please refer to Figure 2 , which shows a block diagram of the relevant functional modules of the APS intelligent planning and scheduling system provided in the embodiment of the present application. The APS intelligent planning and scheduling system includes:

[0069] The data input module 201 is used to receive a production order and resource data, wherein the production order includes order parameters for indicating order requirements, and the resource data includes resource parameters for generating constraint conditions.

[0070] The embodiments of the present application do not limit order parameters, order requirements, resource parameters and constraints, which are basic concepts of the production process and do not constitute implementation obstacles.

[0071] The production plan generation module 202 is used to generate a target production plan based on the production order and the resource data using a preset intelligent algorithm, and the target production plan meets the order requirements and the constraints; the preset intelligent algorithm is an intelligent algorithm that supports multiple algorithm combinations, multiple rule combinations, algorithm rule fusion combinations and dynamic optimization mechanisms.

[0072] The embodiments of the present application can support the separate implementation of any algorithm and any rule to obtain the target production plan. The technical solution for generating the target production plan based on a single algorithm and a single rule is the technical solution adopted by the prior art. Therefore, the embodiments of the present application can be compatible with the prior art. Specifically, the single algorithms supported by the embodiments of the present application include genetic algorithm, particle swarm algorithm and ant colony algorithm, and the single rules supported include: shortest construction period scheduling rule, scheduling rule according to delivery date, scheduling rule considering the distance between construction period and delivery date, CR value scheduling rule, shortest process scheduling rule, wherein the CR value calculation method in the CR value scheduling rule is (delivery date - current date) / construction period, and the smaller the value, the higher the urgency and the higher the scheduling priority.

[0073] In one embodiment, the embodiment of the present application also supports generating a target production plan based on any single algorithm or single rule, and adjusting the target production plan using a dynamic optimization mechanism on this basis. Compared with the prior art, this embodiment improves the quality of the target production plan by adding a dynamic optimization mechanism. The dynamic optimization mechanism can be a mechanism for real-time monitoring, evaluation and adjustment of the production plan to adapt to changes during the execution of the production plan. The embodiment of the present application does not elaborate on the details of the dynamic optimization mechanism, which does not constitute an implementation obstacle. For example, the dynamic optimization mechanism may include the following:

[0074] Data-driven decision making: Use the collected data for analysis and make more accurate decisions based on the data.

[0075] Demand forecast update: Regularly update market demand forecasts to adjust production plans in a timely manner.

[0076] Resource allocation optimization: Dynamically adjust resource allocation based on real-time production data and resource utilization.

[0077] Bottleneck identification and relief: Identify bottlenecks in the production process and take measures to alleviate them, such as increasing resources, optimizing processes, etc.

[0078] Priority Adjustment: Dynamically adjust production plans based on order urgency, customer requirements or production efficiency.

[0079] Flexible schedule adjustment: When unexpected events or changes occur, the production schedule can be adjusted quickly to minimize the impact on the production plan.

[0080] Inventory management optimization: Dynamically adjust inventory to reduce inventory costs and ensure timely supply of materials.

[0081] Quality control feedback: timely adjust production plans and process parameters through feedback during the quality control process.

[0082] Risk Assessment and Management: Assess potential risks and develop response strategies to reduce the impact of uncertainty on production plans.

[0083] Simulation and scenario analysis: Use simulation technology to predict different production scenarios and develop corresponding countermeasures.

[0084] Supply chain collaboration: Work together with supply chain partners to share information and optimize the entire supply chain.

[0085] In one embodiment, the present application also supports generating a target production plan based on a combination of multiple algorithms, a combination of multiple rules, and a combination of algorithm rules, and optionally uses a dynamic optimization mechanism to adjust the target production plan. In this embodiment, please refer to Figure 3 , which shows a schematic diagram of the process of generating a target production plan. The production plan generating module 202 is used to perform the following operations:

[0086] Step S310. Based on the target production requirements and the constraints, determine the mode parameters, the mode parameters indicating whether to use a multi-algorithm combination, whether to use a multi-rule combination, whether to use an algorithm-rule fusion combination, and whether to use a dynamic optimization mechanism. The multi-algorithm combination includes combining at least two algorithms from among genetic algorithm, particle swarm algorithm, and ant colony algorithm. The multi-rule combination includes combining at least two rules of the shortest construction period scheduling rule, scheduling rule according to delivery date, scheduling rule considering the distance between construction period and delivery date, CR value scheduling rule, and shortest process scheduling rule. The algorithm-rule fusion combination includes combining at least one of the above algorithms and at least one of the above rules. The multi-algorithm combination, the multi-rule combination, and the algorithm-rule fusion combination are in a one-to-one selection relationship.

[0087] The mode parameters may be determined automatically or input by a user, and are not limited in the embodiments of the present application.

[0088] Step S320. When the mode parameters indicate the use of a combination of multiple algorithms, an algorithm selection interface is displayed, and at least two target algorithms are determined according to the result of the user triggering the algorithm selection interface; based on the at least two target algorithms, the target production plan is generated; when the mode parameters indicate the use of a combination of multiple rules, a rule selection interface is displayed, and at least two target rules are determined according to the result of the user triggering the rule selection interface; based on the at least two target rules, the target production plan is generated; when the mode parameters indicate the use of an algorithm and rule fusion combination, an algorithm and rule selection interface is displayed, and at least one target algorithm and at least one target rule are determined according to the result of the user triggering the algorithm and rule selection interface; based on the at least one target algorithm and the at least one target rule, the target production plan is generated.

[0089] Since each selected target rule or target algorithm can independently obtain the corresponding production plan, each production plan includes multiple production nodes, the resources that each production node needs to occupy, and the cycle of the entire production plan, so in this embodiment, multiple production plans can be obtained, and these production plans are screened and comprehensively analyzed. Specifically, it includes selecting reasonable production nodes, reasonable cycles and reasonable resources to obtain a target production plan. The target production plan can be a production plan among the multiple production plans, or it can be a new production plan generated by analyzing the strengths of multiple production plans. The embodiments of this application do not elaborate on the execution details and do not constitute an implementation obstacle.

[0090] In one embodiment, the process of generating the target production plan uses parallel computing and distributed processing, and the target production plan includes an optimal production plan and a suboptimal production plan.

[0091] The dynamic resource allocation module 203 is used to generate a resource allocation plan according to the target production plan and the resource data, adjust the resource allocation plan according to the real-time resource status during the production process, and adjust the target production plan based on the feedback of the resource allocation plan.

[0092] Please refer to Figure 4 , which shows a schematic diagram of the process of dynamic resource allocation. The dynamic resource allocation module 203 is used to perform the following operations:

[0093] Step S410: When any production node in the production plan is not completed on time, obtain the usage of various resources corresponding to the production node.

[0094] Step S420: Determine the target resource type corresponding to the bottleneck resource according to the usage of the various resources, where the bottleneck resource is the resource that causes the production node to not be completed on time.

[0095] Step S430: Obtain all associated production plans, wherein the resource allocation plans corresponding to the associated production plans have the target resource type and are allowed to be adjusted.

[0096] Step S440. Determine at least one reference production plan among all the associated production plans, wherein the reference production plan does not have any production nodes that are not completed on time, and the target resource type in the reference production plan is in a normal state or an idle state.

[0097] In one embodiment, the dynamic resource allocation module 203 is used to perform the following operations: when each production node of each production plan is completed on time, the resources used by the production node and the corresponding planned resources are counted, and the planned resources are the resources allocated to the production node by the resource allocation plan corresponding to the production plan; based on the difference between the used resources and the planned resources, the state of each type of resource is determined, and the state includes a normal state, a bottleneck state, and an idle state. Through this operation, the dynamic resource allocation module 203 can grasp the state of each type of resources in the production process corresponding to each production plan.

[0098] Step S450. Under the premise of not affecting the implementation of each of the reference production plans, reduce the allocation value of the target resource type corresponding to the reference production plan, and increase the allocation value of the target resource type corresponding to the target generation plan accordingly, so as to complete the bottleneck resource scheduling and achieve bottleneck resource load balancing.

[0099] The intelligent optimization module 204 is used to adjust the target production plan and the resource allocation plan based on the artificial intelligence model, and optimize the artificial intelligence model based on the adjustment of the resource allocation plan and the feedback adjustment of the target production plan.

[0100] Specifically, the intelligent optimization module 204 is used to perform the following operations: training the artificial intelligence model, wherein the training samples of the artificial intelligence model include an initial production plan and an initial resource allocation plan having a corresponding relationship, and an optimized production plan corresponding to the initial production plan and an optimized resource allocation plan corresponding to the initial resource allocation plan. The training process of the artificial intelligence model can use machine learning technology, which does not constitute an implementation obstacle and is not elaborated. The target production plan and the corresponding resource allocation plan are input into the artificial intelligence model to obtain an optimized target production plan and a corresponding optimized resource allocation plan.

[0101] The custom optimization module 205 is used to optimize the target production plan and the resource allocation plan according to the weight ratio in the user-defined scenario, and the weight ratio indicates the proportion of production factors and the proportion of various resources in the production scenario.

[0102] The data output module 206 is used to output the target production plan and the resource allocation plan.

[0103] Please refer to Figure 5 , which shows a scheduling optimization method in an embodiment of the present application, the method is applied to the aforementioned APS intelligent planning and scheduling system, the method comprising:

[0104] Step S510: Receive a production order and resource data, wherein the production order includes order parameters for indicating order requirements, and the resource data includes resource parameters for generating constraint conditions.

[0105] Step S520. Based on the production order and the resource data, a target production plan is generated, where the target production plan meets the order requirements and the constraints.

[0106] In the foregoing, the embodiments of the present application propose three feasible modes for generating a target production plan. In the first mode, the separate implementation of any algorithm and any rule is supported to obtain a target production plan. In the second mode, the target production plan is generated based on any single algorithm or single rule, and the target production plan is adjusted using a dynamic optimization mechanism on this basis. In the third mode, the target production plan is generated based on a combination of multiple algorithms, a combination of multiple rules, and a fusion combination of algorithms and rules, and the target production plan is optionally adjusted using a dynamic optimization mechanism on this basis.

[0107] In the case of high requirements for the target production plan, it is preferred to use an intelligent algorithm, that is, based on the production order and the resource data, a preset intelligent algorithm is used to generate a target production plan, and the preset intelligent algorithm is an intelligent algorithm that supports multiple algorithm combinations, multiple rule combinations, algorithm rule fusion combinations, and dynamic optimization mechanisms.

[0108] Step S530: Generate a resource allocation plan based on the target production plan and the resource data.

[0109] Step S540. Adjust the target production plan and the resource allocation plan based on the artificial intelligence model.

[0110] In the embodiment of the present application, the artificial intelligence model can also be optimized based on the adjustment of the resource allocation plan and the feedback adjustment of the target production plan. The artificial intelligence model is continuously iterated and updated to continuously provide better plan adjustment capabilities.

[0111] Step S550: Optimize the target production plan and the resource allocation plan according to the weight ratio in the user-defined scenario.

[0112] The embodiment of the present application does not limit step S550. The user can set the weight ratio according to his or her own needs in any customized scenario. The APS system can automatically optimize the target production plan and the resource allocation plan based on the weight ratio, and the user can also actively adjust the optimization results.

[0113] Step S560: Output the target production plan and the resource allocation plan.

[0114] Please refer to Figure 6 , which shows a complete schematic diagram of the implementation process of the embodiment of the present application. This implementation process corresponds to the second mode. In the data input and optimization link, production orders and resource data can be received, and data useful for automatically generating a target production plan can be extracted. The data processing link determines the order requirements and constraints, so as to generate a target production plan that meets the order requirements and constraints in the multi-algorithm optimization process. When a certain algorithm is selected, for example, a particle swarm optimization algorithm, the particle swarm algorithm can be used to obtain the target production plan, and then the dynamic optimization mechanism is started to adjust the target production plan and the corresponding resource allocation plan, that is, to perform dynamic resource allocation optimization. It is also possible to receive user-defined optimization dynamically, and this step corresponds to step S550.

[0115] The present application embodiment proposes an APS intelligent planning and scheduling system and an optimization method thereof, which has the following significant advantages:

[0116] (1) Combination optimization using multiple algorithms and multiple rules: In order to improve scheduling efficiency, the APS intelligent planning and scheduling system introduces a combination of multiple optimization algorithm rules, such as genetic algorithm, particle swarm algorithm and ant colony algorithm, such as the shortest construction period scheduling rule, the scheduling rule according to the order of delivery date, the scheduling rule considering the distance between the construction period and the delivery date, the CR value scheduling rule, the shortest process scheduling rule, etc. These algorithms and rules can quickly process large-scale data and adapt to the dynamically changing production environment through parallel computing and distributed processing. By combining the advantages of different algorithms and rules, the system can find the optimal or suboptimal scheduling plan in a shorter time, significantly improving scheduling efficiency and accuracy.

[0117] (2) Dynamically adjust resource allocation strategies: In order to improve resource utilization, the system can adjust resource allocation in real time according to production demand and resource status to ensure that resources are maximized. By automatically identifying bottleneck resources and optimizing and adjusting them, the system can avoid idle or overloaded resources, thereby improving resource utilization and production efficiency. For example, during peak production periods, the system can automatically adjust the utilization of key equipment to ensure the balance and smooth operation of the production line.

[0118] (3) Introducing artificial intelligence and machine learning technologies: In order to enhance the intelligence and flexibility of the system, the APS intelligent planning and scheduling system combines artificial intelligence and machine learning technologies. Through data analysis and model training, the system can continuously optimize and adjust scheduling strategies to adapt to different production needs and environmental changes. The system can autonomously learn and adapt to changes in the production environment, improving the intelligence level and response speed of scheduling. For example, when the number of orders suddenly increases or a production line fails, the system can quickly adjust the scheduling strategy to ensure the continuity and stability of production.

[0119] Figure 7It is a schematic diagram of a system-level framework supporting the APS intelligent planning and scheduling system and its optimization method provided by an embodiment of the present application. The system-level framework includes a public network and an enterprise local network, and the two networks can communicate. The cloud computing server cluster communicates with the enterprise local network through the public network and the gateway node, and the cloud computing server cluster supports the algorithm logic and algorithm deployment of the embodiment of the present application, thereby running the computing tasks related to the embodiment of the present application. The enterprise locally deploys the APS intelligent planning and scheduling system, and the APS intelligent planning and scheduling system is connected to the ERP system. The ERP system refers to the software or service for managing enterprise resource planning (Enterpr i se Resource Planning, ERP), thereby helping the enterprise to manage and coordinate all aspects of the enterprise. And the APS intelligent planning and scheduling system obtains the support of the GPU hardware acceleration component. GPU (Graphics Processing Unit, graphics processor) is a hardware device specially designed for processing graphics and image computing tasks. The GPU hardware acceleration component configured in the embodiment of the present application can process a large amount of data at the same time, thereby realizing parallel computing services, supporting the local deployment of the algorithm and the algorithm logic. The APS intelligent planning and scheduling system can interact with users through artificial intelligence (AI) text and voice. The underlying layer of the APS intelligent planning and scheduling system is supported by the local database and IOT data acquisition customized edge algorithm acceleration equipment, and the IOT data acquisition customized edge algorithm acceleration equipment is supported by the local production equipment cluster.

[0120] The APS intelligent planning and scheduling system can generate various production-related plans, which can be output in sequence to the user's mobile device.

[0121] The above-mentioned memory also includes a computer program, which is stored in the memory and configured to be executed by one or more processors to implement the above-mentioned scheduling optimization method based on the APS intelligent planning and scheduling system.

[0122] Optionally, the computer readable storage medium may include: ROM (Read On ly Memory), RAM (Random Access Memory), SSD (Solid State Drives) or optical disk, etc. Among them, the random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0123] In an exemplary embodiment, a computer program product or a computer program is also provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above-mentioned scheduling optimization method based on the APS intelligent planning and scheduling system.

[0124] It should be understood that the "multiple" mentioned in this article refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. In addition, the step numbers described in this article only illustrate a possible execution sequence between the steps. In some other embodiments, the above steps may not be executed in the order of the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in the opposite order to the diagram. The embodiments of the present application are not limited to this.

[0125] In addition, in the specific implementation of this application, related data such as user information is involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0126] The above are merely exemplary embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. An APS intelligent planning and scheduling system, characterized in that: The system comprises: A data input module, for receiving a production order and resource data, wherein the production order includes order parameters for indicating order requirements, and the resource data includes resource parameters for generating constraint conditions; A production plan generation module, used to generate a target production plan based on the production order and the resource data using a preset intelligent algorithm, wherein the target production plan meets the order requirements and the constraints; the preset intelligent algorithm is an intelligent algorithm that supports multi-algorithm combination, multi-rule combination, algorithm rule fusion combination and dynamic optimization mechanism; A dynamic resource allocation module, configured to generate a resource allocation plan according to the target production plan and the resource data, adjust the resource allocation plan according to the real-time resource status during the production process, and adjust the target production plan based on feedback from the resource allocation plan; An intelligent optimization module, used to adjust the target production plan and the resource allocation plan based on the artificial intelligence model, and optimize the artificial intelligence model based on the adjustment of the resource allocation plan and the feedback adjustment of the target production plan; A custom optimization module, used to optimize the target production plan and the resource allocation plan according to the weight ratio in the scenario customized by the user, wherein the weight ratio indicates the proportion of production factors and the proportion of various resources in the production scenario; A data output module is used to output the target production plan and the resource allocation plan.

2. The system according to claim 1, characterized in that The production plan generation module is used to perform the following operations: Based on the target production requirements and the constraints, a mode parameter is determined, the mode parameter indicates whether to use a multi-algorithm combination, whether to use a multi-rule combination, whether to use an algorithm-rule fusion combination, and whether to use a dynamic optimization mechanism. The multi-algorithm combination includes combining at least two algorithms from among a genetic algorithm, a particle swarm algorithm, and an ant colony algorithm. The multi-rule combination includes combining at least two rules of a shortest construction period scheduling rule, a scheduling rule according to the order of delivery dates, a scheduling rule considering the distance between construction period and delivery date, a CR value scheduling rule, and a shortest process scheduling rule. The algorithm-rule fusion combination includes combining at least one of the above algorithms and at least one of the above rules. The multi-algorithm combination, the multi-rule combination, and the algorithm-rule fusion combination are in a one-to-one selection relationship. In the case where the mode parameter indicates the use of a combination of multiple algorithms, an algorithm selection interface is displayed, and at least two target algorithms are determined according to a trigger result of the algorithm selection interface by the user; generating the target production plan based on the at least two target algorithms; In the case where the mode parameter indicates the use of a combination of multiple rules, a rule selection interface is displayed, and at least two target rules are determined according to the result of the user triggering the rule selection interface; based on the at least two target rules, the target production plan is generated; When the mode parameters indicate the use of an algorithm-rule fusion combination, an algorithm-rule selection interface is displayed, and at least one target algorithm and at least one target rule are determined based on the result of the user triggering the algorithm-rule selection interface; based on the at least one target algorithm and the at least one target rule, the target production plan is generated.

3. The system according to claim 2, characterized in that The generation process of the target production plan uses parallel computing and distributed processing, and the target production plan includes an optimal production plan and a suboptimal production plan.

4. The system according to any one of claims 1 to 3, characterized in that: The dynamic resource allocation module is used to perform the following operations: When any production node in the production plan is not completed on time, obtaining usage of various resources corresponding to the production node; Determine, according to the usage of the various resources, a target resource type corresponding to a bottleneck resource, wherein the bottleneck resource is a resource that causes the production node to not be completed on time; Acquire all associated production plans, wherein the resource allocation plans corresponding to the associated production plans have the target resource type and are allowed to be adjusted; Determine at least one reference production plan among all the associated production plans, wherein the reference production plan does not have any production nodes that are not completed on time, and the target resource type in the reference production plan is in a normal state or an idle state; Without affecting the implementation of each of the reference production plans, the allocation value of the target resource type corresponding to the reference production plan is reduced, and the allocation value of the target resource type corresponding to the target generation plan is increased accordingly to complete bottleneck resource scheduling and achieve bottleneck resource load balancing.

5. The system according to claim 4, characterized in that The dynamic resource allocation module is used to perform the following operations: When each production node of each production plan is completed on time, count the resources used by the production node and the corresponding planned resources, where the planned resources are the resources allocated to the production node by the resource allocation plan corresponding to the production plan; Based on the difference between the used resources and the planned resources, the state of each type of resources is determined, and the state includes a normal state, a bottleneck state and an idle state.

6. The system according to claim 1, characterized in that The intelligent optimization module is used to perform the following operations: Training the artificial intelligence model, wherein the training samples of the artificial intelligence model include an initial production plan and an initial resource allocation plan having a corresponding relationship, and an optimized production plan corresponding to the initial production plan and an optimized resource allocation plan corresponding to the initial resource allocation plan; The target production plan and the corresponding resource allocation plan are input into the artificial intelligence model to obtain an optimized target production plan and a corresponding optimized resource allocation plan.

7. A scheduling optimization method based on APS intelligent planning and scheduling system, characterized in that: The method is applied to the APS intelligent planning and scheduling system according to any one of claims 1 to 6, and the method comprises: receiving a production order and resource data, wherein the production order includes order parameters for indicating order requirements, and the resource data includes resource parameters for generating constraint conditions; Based on the production order and the resource data, a target production plan is generated, wherein the target production plan meets the order requirements and the constraint conditions; Generate a resource allocation plan according to the target production plan and the resource data; Adjust the target production plan and the resource allocation plan based on the artificial intelligence model; Optimizing the target production plan and the resource allocation plan according to the weight ratio in the user-defined scenario; The target production plan and the resource allocation plan are output.

8. The method according to claim 7, characterized in that The generating a target production plan based on the production order and the resource data includes: Based on the production order and the resource data, a target production plan is generated using a preset intelligent algorithm, where the preset intelligent algorithm is an intelligent algorithm that supports multi-algorithm combination, multi-rule combination, algorithm-rule fusion combination, and dynamic optimization mechanism.

9. The method according to claim 7, characterized in that: The method further comprises: The artificial intelligence model is optimized based on adjustments to the resource allocation plan and feedback adjustments to the target production plan.

10. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by the processor to implement the scheduling optimization method based on the APS intelligent planning and scheduling system as described in any one of claims 7 to 9.

Citation Information

Patent Citations

  • Dynamic optimization method and device for production planning and resource allocation

    CN104484751A

  • Order planning optimization method suitable for manufacturing plants

    CN107578158A

  • Advanced plan scheduling system

    CN112633769A

  • Dynamic production plan scheduling system and method based on information feedback

    CN114897379A

  • Intelligent management method, system and equipment for digital factory and storage medium

    CN116976614A