A workshop scheduling method and system based on intelligent optimization algorithms

Abstract

This invention discloses a workshop production scheduling method and system based on intelligent optimization algorithms, relating to the fields of intelligent manufacturing and production scheduling technology. The key technical points include the following steps: first, acquiring preprocessed multi-source production data; then, constructing a production scheduling strategy model and a multi-objective optimization function to jointly optimize objectives such as delivery delay, mold switching cost, equipment load balancing, and energy consumption, obtaining the production scheduling result; performing simulation and risk assessment before the production scheduling result is released; and collecting actual execution data after the production scheduling result is issued and executed, iteratively optimizing the production scheduling strategy model, and triggering rolling rescheduling when the plan deviates from a preset threshold or when a new order is received. This invention solves the problems of fragmented multi-stage production scheduling, difficulty in quantifying mold switching cost, and the inability to close the loop between delivery control and execution feedback in existing technologies.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing and production scheduling technology, and more specifically, to a workshop production scheduling method and system based on intelligent optimization algorithms. Background Technology

[0002] In the context of motor manufacturing, orders typically require multiple stages and workshops to be completed before delivery, including stamping (high-speed stamping), stator, rotor, and assembly testing. Existing production scheduling methods often rely on manual experience or simple rules for a single stage, easily overlooking the downtime and economic costs caused by mold switching. They also struggle to incorporate the completion time of upstream stages as a release constraint for downstream stages into unified calculations, resulting in production plans that are difficult to implement, large fluctuations in delivery dates, and a lack of traceability in the execution process.

[0003] Especially in the motor industry, there are many product models, small batches, frequent model changes, and disturbances such as order insertions and abnormal shutdowns are common. Traditional production scheduling is difficult to reschedule online in a timely manner and form a closed loop of planning-execution-feedback.

[0004] In view of this, the present invention proposes a workshop production scheduling method and system based on intelligent optimization algorithms. Summary of the Invention

[0005] The purpose of this invention is to provide a workshop production scheduling method and system based on intelligent optimization algorithms to solve the above-mentioned problems.

[0006] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0007] The first aspect of this invention provides a workshop production scheduling method based on an intelligent optimization algorithm, comprising the following steps:

[0008] S100. Obtain preprocessed multi-source production data;

[0009] S200. Construct a production scheduling strategy model and a multi-objective optimization function, perform optimization and solution, and construct an optimized production scheduling strategy model based on the optimal solution;

[0010] S300. Input the preprocessed multi-source production data into the optimized production scheduling strategy model and output the production scheduling results;

[0011] S400. Perform simulation and risk assessment on the production scheduling results. If the simulation fails, return to S200 to adjust the weights of the multi-objective optimization function and / or re-optimize the solution. If the simulation succeeds, obtain the production scheduling results that pass the assessment.

[0012] S500. The production scheduling results based on the assessment will be sent to offline production, and the actual execution data will be collected.

[0013] S600. Iteratively optimize the optimized production scheduling strategy model using actual execution data.

[0014] In conjunction with the first aspect, the present invention is further configured such that: in step S100, the acquisition of preprocessed multi-source production data includes the following steps: acquiring multi-source production data, preprocessing heterogeneous data, and obtaining preprocessed multi-source production data;

[0015] The multi-source production data includes order data, MES work orders, on-site energy consumption and quality inspection data.

[0016] MES stands for Manufacturing Execution System.

[0017] In conjunction with the first aspect, the present invention is further configured such that, in step S100, the preprocessing includes one or more of the following: time-series alignment, abnormal data classification processing, order decomposition, data filtering, and normalization processing.

[0018] In conjunction with the first aspect, the present invention is further configured such that, in step S200, the production scheduling strategy model includes one or more of constraint programming, particle swarm optimization, and reinforcement learning strategy models.

[0019] In conjunction with the first aspect, the present invention is further configured such that, in step S200, the multi-objective optimization function includes two or more of the following: delivery delay term based on delivery priority, mold switching cost term, equipment load balancing term, and energy consumption term.

[0020] In conjunction with the first aspect, the present invention is further configured such that, in step S400, the simulation and risk assessment includes one or more of the following: logic verification, time overlap detection, resource conflict detection, and key performance indicator calculation.

[0021] In conjunction with the first aspect, the present invention is further configured such that: in step S600, when the deviation between the plan and the actual situation exceeds a threshold or when a new order is inserted, an online rolling reorder is triggered.

[0022] A second aspect of the present invention also provides an apparatus / device / system for a workshop production scheduling method and system based on an intelligent optimization algorithm, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above method.

[0023] A third aspect of the present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0024] A fourth aspect of the present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0025] In summary, the present invention has the following beneficial effects:

[0026] 1) By unifying access to multi-source production data and forming a single source of fact, unified modeling is achieved from orders to equipment, molds, energy consumption and quality information, thereby improving the consistency and traceability of production scheduling data.

[0027] 2) By using the production scheduling strategy model as a higher-level concept to carry multiple types of solution algorithms and combining it with multi-objective optimization functions for joint solution, it is possible to take into account delivery time, switching losses, equipment balance and energy consumption while ensuring feasibility.

[0028] 3) By performing simulations and risk assessments before the plan is released, time conflicts, resource constraint conflicts, and delay risks can be identified in advance, improving the feasibility of the production scheduling results.

[0029] 4) By continuously collecting actual execution data during the execution phase and retraining or adjusting the model parameters, a closed loop of planning, execution, and feedback can be formed, thereby improving the system's online learning and continuous optimization capabilities.

[0030] 5) By performing rolling reordering in scenarios triggered by deviation thresholds or order insertion, and locking started jobs while only adjusting unstarted jobs, the ability to respond to on-site disturbances can be improved while maintaining stable production order. Attached Figure Description

[0031] Figure 1 This is a flowchart of a workshop production scheduling method based on intelligent optimization algorithm in Embodiment 1 of the present invention;

[0032] Figure 2 This is a closed-loop architecture diagram of the workshop production scheduling system based on intelligent optimization algorithm in Embodiment 1 of the present invention. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] In the embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. The system embodiments described below are merely illustrative. For example, the division of units and modules is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or modules can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, and can be electrical, mechanical, or other forms.

[0035] In addition, each functional unit in the various embodiments of this application can be integrated into a single processor, or each unit can be a separate device, or two or more units can be integrated into a single device; each functional unit in the various embodiments of this application can be implemented in hardware or in the form of hardware plus software functional units.

[0036] Those skilled in the art will understand that all or part of the steps of the following method embodiments can be implemented by program instructions and related hardware. The aforementioned program instructions can be stored in a computer-readable storage medium. When the program instructions are executed, they perform the steps of the following method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0037] It should be understood that the use of terms such as "system," "device," "unit," and / or "module" in this application is merely one method of distinguishing different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0038] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "a plurality of" or "several" means two or more, unless otherwise explicitly specified.

[0039] If a flowchart is used in this application, it is used to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0040] It should also be noted that, in this document, terms such as “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase “comprising one…” does not exclude the presence of other identical elements in the article or device that includes the aforementioned element.

[0041] Example 1:

[0042] A workshop scheduling method based on intelligent optimization algorithms, such as Figure 1 As shown, it includes the following steps:

[0043] S100. Obtain preprocessed multi-source production data;

[0044] S200. Construct a production scheduling strategy model and a multi-objective optimization function, perform optimization and solution, and construct an optimized production scheduling strategy model based on the optimal solution;

[0045] S300. Input the preprocessed multi-source production data into the optimized production scheduling strategy model and output the production scheduling results;

[0046] S400. Perform simulation and risk assessment on the production scheduling results. If the simulation fails, return to S200 to adjust the weights of the multi-objective optimization function and / or re-optimize the solution. If the simulation succeeds, obtain the production scheduling results that pass the assessment.

[0047] S500. The production scheduling results based on the assessment will be sent to offline production, and the actual execution data will be collected.

[0048] S600. Iteratively optimize the optimized production scheduling strategy model using actual execution data.

[0049] A closed-loop architecture diagram of a workshop production scheduling system based on intelligent optimization algorithms, as shown below. Figure 2 As shown.

[0050] In step S100, acquiring the preprocessed multi-source production data includes the following steps:

[0051] Acquire multi-source production data, preprocess the heterogeneous data to obtain preprocessed multi-source production data; the multi-source production data includes order data, MES work orders, on-site energy consumption and quality inspection. The preprocessing includes time-series alignment, hierarchical processing of abnormal data, order breakdown, data filtering and normalization.

[0052] Specifically, the process involves: acquiring multi-source production data: A pre-built standardized interface adaptation layer aggregates heterogeneous data from ERP systems (such as SAP and Yonyou U8), MES work orders, on-site energy consumption, and quality inspection into the database. This adaptation layer provides standard API interfaces based on a RESTful architecture, enabling automatic capture and cleaning of multi-source heterogeneous data through configuration mapping, and using a unified data model to achieve time-series alignment, forming a single source of fact. This step includes built-in rules for handling tiered exception data: For missing data, the system implements tiered processing based on exception type, impact level, and recoverability: data that can be automatically completed is re-collected or imputed; data that cannot be automatically repaired triggers alarms and records correction logs to ensure the integrity and traceability of subsequent production scheduling inputs.

[0053] Order decomposition and virtual batch construction: The system decomposes orders into atomic operation objects such as stamping, stator, and rotor, and performs cluster analysis based on key attributes such as mold model, formula, material specifications, and delivery date. Operations with the same attributes and similar delivery dates are pre-packaged into virtual production batches to reduce the space complexity of subsequent solutions and reduce mold changeover losses.

[0054] Data filtering and normalization: Filter incomplete parts and standardize mold / recipe / parameter value formats; perform consistency checks and alignment on order / work order, resource status, and time information to construct a searchable production scheduling status space. This step establishes an alarm closed-loop mechanism: when data consistency checks fail and cannot be automatically corrected, the system immediately pushes the anomaly to the production scheduling position and automatically initiates a degraded production scheduling mode, that is, temporarily using the scheduling parameters of similar historical orders to replace the current abnormal parameters for calculation, ensuring that the production scheduling process is not interrupted.

[0055] Build the operation: calculate the processing time for the stamping stage based on quantity / efficiency; accumulate the processing time for the stator / rotor stage based on the process template sequence, and determine the type of work mold and workshop information.

[0056] In step S200, the scheduling strategy model includes one or more of constraint programming, particle swarm optimization, or reinforcement learning strategies. Alternatively, a hybrid solution framework of "constraint programming + particle swarm optimization" can be used: constraint programming is used to express process sequence constraints, equipment capacity constraints, mold mutual exclusion constraints, and release time constraints; particle swarm optimization is used to search for better machine allocation and job sequencing schemes within the feasible region.

[0057] The multi-objective optimization function takes delivery priority, minimizing delivery delay, minimizing mold switching costs, balancing equipment load, and minimizing energy consumption as its optimization objectives.

[0058] The multi-objective optimization function can be expressed as:

[0059]

[0060] in, This indicates the completion time of order i. Indicates order i Delivery date, This represents the delivery priority coefficient of order i. Indicates the cost of mold switching. Indicates equipment load rate, Indicates the average load factor. Indicates energy consumption per unit time period. to This indicates configurable weight parameters. By jointly optimizing the above objectives, a balance can be achieved between delivery time, switching losses, equipment balancing, and energy consumption.

[0061] When the production scheduling strategy model adopts a reinforcement learning strategy model, the current workshop state is represented by features such as order urgency, equipment occupancy status, mold status, and work-in-process position. The strategy network outputs the action to be scheduled for the process or equipment selection, and constructs a reward signal based on the multi-objective optimization function. Iterative training is then performed continuously using actual execution data.

[0062] Step S400 also includes simulation and multi-dimensional risk assessment: logical verification (such as time overlap and constraint conflict) and KPI calculation of the production scheduling plan. This invention utilizes discrete event simulation technology to simulate the execution process of the production scheduling plan in a virtual environment, predicting potential logistics bottlenecks and delivery delay risks. If the delay risk shown by the simulation exceeds a preset safety value, the system will automatically trigger local optimization or rollback to S200 to adjust weights and re-solve / train, ensuring that the issued plan has high confidence and executability.

[0063] In step S400, the system performs simulation and risk assessment on candidate production scheduling schemes, including logic verification, time overlap detection, resource conflict detection, and key performance indicator calculation. If the simulation shows that the delay risk exceeds the preset safety value, or there are equipment conflicts or constraint conflicts, the system adjusts the weight parameters, updates the constraints, or calls the production scheduling solution module again to ensure that the issued plan has high executability.

[0064] Step S500 also includes visualization and publishing: the system generates production scheduling plans, Gantt chart data, costs, and delay summary data, and publishes the plans to offline production through an interface. During execution, the system continuously collects equipment status, completion information, abnormal events, and energy consumption feedback to form actual execution data.

[0065] Step S600 also includes rolling rescheduling: when the planned deviation from the actual situation exceeds a threshold or a new order is inserted, online rolling rescheduling is triggered. This step clarifies the dynamic configuration rules for the deviation threshold: the system sets deviation thresholds based on order type (e.g., urgent / regular orders) and equipment type (e.g., critical equipment / general equipment). A dual-mode triggering mechanism is supported: real-time triggering rescheduling is used for urgent orders; timed rescheduling is used for regular schedule deviations. During rolling rescheduling, the system forcibly locks the resources and time of already started tasks, adjusting only unstarted tasks to maintain production stability.

[0066] Example 2:

[0067] The present invention also provides an apparatus / device / system for a workshop production scheduling method and system based on intelligent optimization algorithms, comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of the above method.

[0068] The present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the above-described method.

[0069] The present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the above-described method.

[0070] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0071] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0072] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0073] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0074] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A workshop production scheduling method based on intelligent optimization algorithms, characterized by: Includes the following steps: S100. Obtain preprocessed multi-source production data; S200. Construct a production scheduling strategy model and a multi-objective optimization function, perform optimization and solution, and construct an optimized production scheduling strategy model based on the optimal solution; S300. Input the preprocessed multi-source production data into the optimized production scheduling strategy model and output the production scheduling results; S400. Perform simulation and risk assessment on the production scheduling results. If the simulation fails, return to S200 to adjust the weights of the multi-objective optimization function and / or re-optimize and solve the problem. If approved, the production schedule will be determined based on the successful evaluation. S500. The production scheduling results based on the assessment will be sent to offline production, and the actual execution data will be collected. S600. Iteratively optimize the optimized production scheduling strategy model using actual execution data.

2. The workshop production scheduling method according to claim 1, characterized in that: In step S100, obtaining the preprocessed multi-source production data includes the following steps: obtaining multi-source production data, preprocessing the heterogeneous data, and obtaining the preprocessed multi-source production data; The multi-source production data includes order data, MES work orders, on-site energy consumption and quality inspection data.

3. The workshop production scheduling method according to claim 2, characterized in that: In step S100, the preprocessing includes one or more of the following: time alignment, abnormal data classification processing, order breakdown, data filtering, and normalization processing.

4. The workshop production scheduling method according to claim 1, characterized in that: In step S200, the production scheduling strategy model includes one or more of the following: constraint programming, particle swarm optimization, and reinforcement learning strategy models.

5. The workshop production scheduling method according to claim 1, characterized in that: in In step S200, the multi-objective optimization function includes two or more of the following: delivery delay term based on delivery priority, mold switching cost term, equipment load balancing term, and energy consumption term.

6. The workshop production scheduling method according to claim 1, characterized in that: in In step S400, the simulation and risk assessment includes one or more of the following: logic verification, time overlap detection, resource conflict detection, and key performance indicator calculation.

7. The workshop production scheduling method according to claim 1, characterized in that: In step S600, when the deviation between the plan and the actual situation exceeds a threshold or when a new order is inserted, an online rolling reorder is triggered.

8. A device / equipment / system for workshop production scheduling based on intelligent optimization algorithms, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

Images