Intelligent factory advanced scheduling optimization method based on big data

Abstract

The invention relates to the technical field of intelligent manufacturing, in particular to an intelligent factory advanced scheduling optimization method based on big data, and the method comprises the following steps: obtaining the production task, equipment availability and production bottleneck data of a factory in real time through a plurality of data collection systems, carrying out the cleaning and standardization processing of the collected data, and carrying out the optimization of the production task, equipment availability and production bottleneck data; the method comprises the steps of processing data, ensuring the accuracy and consistency of the data, constructing a dynamic scheduling optimization model based on the processed data, analyzing the priority, the resource state and the production bottleneck of tasks in the production process, further providing optimal decision support for production scheduling, dynamically adjusting the production scheduling according to a model result through an optimization algorithm, and improving the production scheduling efficiency. Various production tasks are ensured to be smoothly completed in proper time and resources; according to the method, the production bottleneck can be effectively reduced, the resource utilization rate can be improved, dynamic changes in the production process can be flexibly coped, it is ensured that production tasks are completed on time, and high production scheduling efficiency and strain capacity are achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an advanced scheduling optimization method for intelligent factories based on big data. Background Art

[0002] With the rapid development of intelligent manufacturing, the application of smart factories in the manufacturing industry is becoming more and more extensive. Relying on technologies such as big data, the Internet of Things, cloud computing and artificial intelligence, smart factories have realized the automation, digitization and intelligence of the production process.

[0003] At present, although there have been many studies and application solutions on production scheduling optimization, most traditional scheduling methods usually rely on static, rule-based algorithms. These methods have certain limitations when dealing with complex dynamic changes in production tasks, resource status and production processes. For example, the scheduling algorithms in the prior art are difficult to flexibly adjust the allocation of tasks and resources according to changes in real-time data, which often leads to inefficient use of equipment resources or delayed completion of tasks. In addition, existing scheduling systems usually lack sufficient data preprocessing and optimization, there may be noise in the data collection process, and there is a lack of effective fusion between different data sources, resulting in inaccurate decision support. Summary of the invention

[0004] The present invention provides an advanced scheduling optimization method for smart factories based on big data.

[0005] The advanced scheduling optimization method of smart factory based on big data includes the following steps: S1, data collection: Through multiple data collection systems installed in the smart factory, multi-source data is collected in real time. The multi-source data includes production task data, resource status data and production process data.

[0006] S2, data preprocessing: cleaning and standardizing the collected multi-source data; S3, construction of scheduling optimization model: based on pre-processed multi-source data, a dynamic scheduling model is constructed to provide optimal decision support for production scheduling; S4, optimization algorithm design: based on the constructed dynamic scheduling model, the objective function of the dynamic scheduling model is solved by the optimization algorithm; S5, production scheduling generation: Based on the calculation results of the optimization algorithm, a global optimal scheduling plan is generated, and the scheduling plan is sent to the production line and related departments in real time to guide the smooth progress of production activities and ensure that production tasks are completed on time.

[0007] Optionally, the S1 includes: S21, production task data collection: The production task data is collected in real time through the data collection system within the factory. The production task data includes task type, task quantity and task priority.

[0008] S22, resource status data collection: through the resource management system and equipment monitoring system, resource status data is collected in real time. The resource status data includes equipment availability, equipment maintenance status and raw material inventory.

[0009] S23, production process data collection: through the production process monitoring system and sensor network, real-time production process data is collected. Production process data includes equipment operation status, production progress and production line bottlenecks; S24, data storage and management: The collected multi-source data is stored through the factory's data management system and archived by timestamp and task ID for subsequent retrieval and analysis.

[0010] Optionally, S2 includes: S31, data cleaning: Clean the collected multi-source data to ensure the accuracy and completeness of the data. Data cleaning includes noise removal, missing data filling and error detection.

[0011] S32, standardization processing: standardize the cleaned multi-source data to facilitate subsequent analysis and optimization.

[0012] S33, data integration and storage: Integrate cleaned and standardized multi-source data into a unified data warehouse to ensure that the data used in subsequent model training and scheduling optimization processes are clean and unified.

[0013] Optionally, the S3 includes: S41, model construction: construct a dynamic scheduling model based on multi-objective optimization, and the input data of the dynamic scheduling model is pre-processed multi-source data.

[0014] S42, model output: Based on the input multi-source data, an optimal production scheduling solution is output through the scheduling optimization model.

[0015] Optionally, the multi-objective optimization dynamic scheduling model includes: Objective function: The multi-objective optimization dynamic scheduling model aims to optimize the production cycle, resource utilization and production bottleneck at the same time. The objective function is expressed as: ; in, is the total production cycle, which means the total time required from the start to the completion of the task. is the equipment utilization rate, which indicates the ratio of the equipment’s working time in production to its available time. The production bottleneck indicates the maximum delay or stagnation time of the bottleneck link in the production process; Constraints: The constraints considered in the dynamic scheduling model include equipment availability constraints, raw material constraints, and task priority constraints.

[0016] Optionally, the S4 includes: S41, optimization algorithm objective: based on the constructed dynamic scheduling optimization model, the objective function is solved by the optimization algorithm; S42, algorithm selection: Genetic algorithm is used as the optimization algorithm to solve the objective function.

[0017] S43, optimization result output: after solving the objective function through the genetic algorithm, the optimal scheduling plan is output.

[0018] Optionally, the S5 includes: S51, real-time dispatch of scheduling plans: the generated scheduling plan is dispatched to the production line and related departments in real time through the automation system; S52, production scheduling monitoring: during the production process, real-time monitoring of the execution of the scheduling plan; S53, dynamic adjustment mechanism: dynamically adjust the production scheduling plan according to the results of real-time monitoring.

[0019] Optionally, S5 further includes: S54, scheduling plan visualization: presenting the generated scheduling plan through a visualization tool.

[0020] Beneficial effects of the present invention: The present invention, through the intelligent factory scheduling optimization method based on big data, can collect multi-source data in real time and perform intelligent processing, so as to accurately capture the dynamic changes in production tasks, resource status and production process. By constructing a dynamic scheduling optimization model, it is possible to optimize the task sequence and resource allocation according to factors such as production task priority, resource availability and production bottleneck, and maximize equipment utilization and production resource utilization efficiency. At the same time, by optimizing production scheduling, idle resources and over-consumption are avoided, thereby improving overall production efficiency.

[0021] The optimization algorithm of the present invention can detect bottlenecks in the production process in real time, and avoid bottlenecks affecting the production process in advance by dynamically adjusting production scheduling and resource allocation. For example, by adjusting the scheduling of equipment or reallocating production tasks, it is possible to effectively prevent production stagnation or reduced efficiency due to delays in a certain link. In addition, real-time monitoring can help the production scheduling system flexibly adjust production arrangements according to real-time conditions, ensure that production tasks are completed on time, and enhance the factory's adaptability and ability to respond to emergencies. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 The figure is a schematic diagram of a method flow of an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0025] It should be noted that the references to "one embodiment", "embodiment", "exemplary embodiments", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0026] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0027] like Figure 1 As shown in the figure, the advanced scheduling optimization method of smart factory based on big data includes the following steps: S1, data collection: Through multiple data collection systems installed in the smart factory, multi-source data is collected in real time. The multi-source data includes production task data, resource status data and production process data.

[0028] S2, data preprocessing: cleaning and standardizing the collected multi-source data; S3, construction of scheduling optimization model: based on pre-processed multi-source data, a dynamic scheduling model is constructed to provide optimal decision support for production scheduling; S4, optimization algorithm design: based on the constructed dynamic scheduling model, the objective function of the dynamic scheduling model is solved by the optimization algorithm; S5, production scheduling generation: Based on the calculation results of the optimization algorithm, a global optimal scheduling plan is generated, and the scheduling plan is sent to the production line and related departments in real time to guide the smooth progress of production activities and ensure that production tasks are completed on time.

[0029] S1 includes: S21, production task data collection: through the data collection system inside the factory, the production task data is collected in real time. The production task data includes task type, task quantity and task priority, among which; Task type: Indicates the type of production task, such as production batch, equipment maintenance, quality inspection, etc. Each task type will affect subsequent scheduling and resource allocation.

[0030] Task quantity: Indicates the number of production tasks that need to be executed. It is usually automatically generated by the production planning system based on order requirements and reflects the production demand of the factory.

[0031] Task priority: Set the priority of tasks based on factors such as the urgency and importance of the tasks. Tasks with higher priorities will be arranged first to ensure the timeliness and efficiency of production.

[0032] S22, resource status data collection: through the resource management system and equipment monitoring system, real-time collection of resource status data, resource status data including equipment availability, equipment maintenance status and raw material inventory, among which; Equipment availability: Real-time monitoring of the equipment's operating status to determine whether the equipment is in standby, running, or faulty state. Equipment availability data is collected through sensors and equipment management systems and fed back to the data acquisition system in real time.

[0033] Equipment maintenance status: Monitor and record the maintenance status of equipment, including ongoing maintenance, scheduled maintenance, and equipment information that has been repaired. This data helps assess the availability of equipment and its impact on production scheduling.

[0034] Raw material inventory: The inventory management system collects inventory data of various raw materials in real time to ensure sufficient and timely supply of materials during the production process. When the inventory level falls below the predetermined threshold, the system will automatically send an alarm to prompt the need to replenish inventory.

[0035] S23, production process data collection: through the production process monitoring system and sensor network, real-time production process data is collected. Production process data includes equipment operation status, production progress and production line bottlenecks, among which; Equipment operating status: Monitor the operating status of the equipment, including equipment working hours, load conditions, temperature, humidity and other parameters. Sensors are used to collect various performance data of the equipment in real time to ensure that the equipment can operate in the optimal state.

[0036] Production progress: Through the production management system, the progress of each production task can be tracked in real time, and information such as the start time, end time, and phased progress of production can be recorded. Production progress data helps to adjust the production scheduling plan and optimize the order of task execution.

[0037] Production line bottleneck: By analyzing various data in the production process, identify and record the bottleneck links in the production line. Bottlenecks may be caused by factors such as equipment failure, shortage of raw materials, and insufficient staff. By collecting bottleneck data, it helps to optimize the scheduling plan later; S24, data storage and management: The collected multi-source data is stored through the factory's data management system and archived by timestamp and task ID for subsequent retrieval and analysis.

[0038] S2 includes: S31, Data cleaning: Clean the collected multi-source data to ensure the accuracy and completeness of the data. Data cleaning includes noise removal, missing data filling and error detection, including: Remove noise data: By setting threshold filters, the collected multi-source data is subjected to noise removal. Specifically, outliers that are significantly deviated from the expected range, such as incorrect or sudden fluctuations in device sensor readings, are removed to ensure data reliability.

[0039] Filling missing data: For missing values ​​that may exist during the collection process, linear interpolation is used to fill the missing data; Error detection and correction: Detect errors in data through rule-based detection methods, automatically identify and correct erroneous data. For example, check whether the equipment status data matches the production task progress, and mark it as erroneous data if it does not match.

[0040] S32, standardization processing: standardize the cleaned multi-source data to facilitate subsequent analysis and optimization. Standardization processing includes the following: Numerical standardization: Standardize numerical data (such as equipment operating status, production progress, etc.) and convert data of different dimensions into dimensionless data. The specific method is to use Z-score standardization or Min-Max standardization to ensure that the mean of the data is zero and the standard deviation is one, or the data is scaled to a predetermined range (such as [0, 1]).

[0041] Categorical data encoding: Encode categorical data (such as task type, equipment maintenance status, etc.) and convert non-numeric data into numeric data. One-hot encoding or label encoding can be used to facilitate subsequent algorithm processing.

[0042] Missing value processing: For the standardized data, if there are still missing values, interpolation method is used to process them to ensure that the data set is not affected by missing data in subsequent analysis.

[0043] S33, data integration and storage: Integrate cleaned and standardized multi-source data into a unified data warehouse to ensure that the data used in subsequent model training and scheduling optimization processes are clean and unified.

[0044] S3 includes: S41, model construction: construct a dynamic scheduling model based on multi-objective optimization. The input data of the dynamic scheduling model is pre-processed multi-source data. The specific input is as follows: Production task data: including task type, task quantity and task priority. Task type describes the specific content of the production task, task quantity affects resource scheduling, and task priority determines the execution order of tasks.

[0045] Resource status data: including equipment availability, equipment maintenance status and raw material inventory. These data affect whether production tasks can be started on time and whether the required resources are sufficient.

[0046] Production process data: including equipment operating status, production progress and production line bottlenecks. These data help adjust production scheduling in real time and affect the execution process of production tasks.

[0047] S42, model output: Based on the input multi-source data, an optimal production scheduling solution is output through the scheduling optimization model.

[0048] The dynamic scheduling model for multi-objective optimization includes: Objective function: The dynamic scheduling model of multi-objective optimization aims to optimize the production cycle, resource utilization and production bottleneck at the same time. The objective function is expressed as: ; in, is the total production cycle, which means the total time required from the start to the completion of the task. is the equipment utilization rate, which indicates the ratio of the equipment’s working time in production to its available time. The production bottleneck indicates the maximum delay or stagnation time of the bottleneck link in the production process; The optimization of this objective function aims to minimize the production cycle, maximize resource utilization and reduce production bottlenecks. Minimization of the objective function can effectively improve production efficiency; Constraints: The constraints considered in the dynamic scheduling model include equipment availability constraints, raw material constraints, and task priority constraints, including: Equipment availability constraint: Each production task can only be scheduled when the equipment is available. If the equipment status is faulty or under maintenance, the production task cannot be scheduled; Raw material constraints: Each production task must ensure that the required raw materials are sufficient. If the raw material inventory is insufficient, the corresponding task needs to be postponed or adjusted; Task priority constraint: Tasks with higher priority should be executed first. If there is a time conflict between a high-priority task and a low-priority task, the high-priority task should be scheduled first.

[0049] S4 includes: S41, optimization algorithm goal: Based on the constructed dynamic scheduling optimization model, the objective function is solved by the optimization algorithm. The main goals of the optimization algorithm are: Minimize the total production cycle to ensure that production tasks are completed as quickly as possible; Maximize resource utilization, improve equipment efficiency, and reduce idle time; Reduce production bottlenecks by optimizing resource allocation and task scheduling to avoid bottlenecks in the production process; S42, algorithm selection: using genetic algorithm as the optimization algorithm to solve the objective function; The design steps of genetic algorithm include: Coding method: The solution to the production scheduling problem is represented as a chromosome. The genes in the chromosome represent the execution order of the tasks. The value of each gene is the task number. The gene arrangement of the entire chromosome represents a complete production scheduling plan.

[0050] Fitness function: A fitness function is designed for each chromosome. The fitness function is used to evaluate the quality of the production scheduling scheme. The form of the fitness function is: ; in, is the total production cycle, is the equipment utilization rate, As a production bottleneck, To avoid division by zero errors, and is the weight coefficient of the objective function; Selection operator: Use the roulette wheel selection method to select individuals with higher fitness for crossover and mutation operations. The roulette wheel selection method selects the reproduction probability of an individual based on its fitness value. The higher the fitness value, the greater the probability of selection.

[0051] Crossover operator: select some excellent individuals for crossover to generate new solutions. Use the single-point crossover method to randomly select a crossover point at a certain position on the chromosome, and then exchange the gene fragments after the crossover point to generate a new production scheduling plan.

[0052] Mutation operator: To prevent the algorithm from falling into a local optimal solution, a gene mutation operation is introduced. The mutation operation generates new solutions by randomly exchanging certain gene positions in the chromosome to increase the search space and maintain the diversity of solutions.

[0053] Selection operation: Generate a new generation of chromosomes through crossover and mutation operations and compare them with the chromosomes of the current generation. Use the elite strategy to retain the individuals with the best fitness in the current generation and add them to the next generation to ensure that the optimization process of the algorithm will not degenerate.

[0054] Termination condition: The genetic algorithm iterates until the termination condition is met, such as reaching the maximum number of iterations or the fitness value converges to the preset threshold. After termination, the chromosome with the highest fitness is output, which is the optimal production scheduling solution.

[0055] S43, optimization result output: After solving the objective function through the genetic algorithm, the optimal scheduling plan is output. The scheduling plan includes: Optimal task execution sequence: The execution order of each production task on the timeline ensures that the tasks are completed in the optimal order.

[0056] Optimal resource allocation: Optimal allocation of equipment and raw materials to ensure maximum resource utilization.

[0057] Optimized production cycle and bottlenecks: Shortest production cycle calculated through optimization, and minimization of production bottlenecks.

[0058] S5 includes: S51, real-time dispatch of scheduling plan: The generated scheduling plan is dispatched to the production line and related departments in real time through the automation system. The dispatch process includes: Production line reception: By connecting with the production line control system, the scheduling plan is automatically sent to each production unit to ensure that each production link is executed as planned.

[0059] Equipment management department receives: the scheduling plan and equipment use arrangement are sent to the equipment management department to ensure the reasonable scheduling and regular maintenance of the equipment.

[0060] Received by the raw material supply department: The scheduling plan and raw material demand are sent to the material supply department to ensure sufficient supply of raw materials during the production process and avoid production delays caused by material shortages; S52, production scheduling monitoring: during the production process, real-time monitoring of the execution of the scheduling plan; S53, dynamic adjustment mechanism: according to the results of real-time monitoring, the production scheduling plan is dynamically adjusted. The adjustment contents include: Task priority adjustment: When a production task is delayed, the priority of the task is dynamically adjusted based on real-time data to ensure that key tasks are completed on time.

[0061] Resource reallocation: When resources are in short supply or surplus, timely adjust the resource allocation plan to ensure optimal use of resources.

[0062] Equipment scheduling optimization: When a piece of equipment fails or is under maintenance, production tasks are rescheduled to avoid production stagnation or bottlenecks.

[0063] The S5 also includes: S54, scheduling plan visualization: The generated scheduling plan is presented through visualization tools, so that production line staff and relevant departments can intuitively understand the production task arrangement. The visualization content includes: Gantt chart: displays the timing, execution sequence and resource allocation of each production task.

[0064] Equipment operation status diagram: Displays the usage status, workload, and downtime of each device to help optimize equipment maintenance and adjust production rhythm.

[0065] Bottleneck area identification: Identify the production bottleneck area on the Gantt chart and equipment operation status chart so that relevant departments can take measures to resolve it.

[0066] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0067] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An advanced scheduling optimization method for smart factories based on big data, characterized in that: The following steps are involved: S1, data collection: multiple data collection systems installed in the smart factory collect multi-source data in real time, including production task data, resource status data and production process data; S2, data preprocessing: cleaning and standardizing the collected multi-source data; S3, construction of scheduling optimization model: based on pre-processed multi-source data, a dynamic scheduling model is constructed to provide optimal decision support for production scheduling; S4, optimization algorithm design: based on the constructed dynamic scheduling model, the objective function of the dynamic scheduling model is solved by the optimization algorithm; S5, production scheduling generation: Based on the calculation results of the optimization algorithm, a global optimal scheduling plan is generated, and the scheduling plan is sent to the production line and related departments in real time to guide the smooth progress of production activities.

2. The intelligent factory advanced scheduling optimization method based on big data according to claim 1 is characterized in that: The S1 includes: S21, production task data collection: through the factory's internal data collection system, real-time collection of production task data, production task data including task type, task quantity and task priority; S22, resource status data collection: through the resource management system and equipment monitoring system, real-time collection of resource status data, resource status data including equipment availability, equipment maintenance status and raw material inventory; S23, production process data collection: through the production process monitoring system and sensor network, the production process data is collected in real time. The production process data includes equipment operation status, production progress and production line bottlenecks; S24, data storage and management: The collected multi-source data is stored through the factory's data management system and archived according to timestamps and task IDs.

3. The intelligent factory advanced scheduling optimization method based on big data according to claim 2 is characterized in that: The S2 includes: S31, data cleaning: cleaning the collected multi-source data, including noise removal, missing data filling and error detection; S32, standardization processing: standardization processing is performed on the cleaned multi-source data; S33, Data integration and storage: Integrate cleaned and standardized multi-source data into a unified data warehouse.

4. The intelligent factory advanced scheduling optimization method based on big data according to claim 3 is characterized in that: The S3 includes: S41, model construction: construct a dynamic scheduling model based on multi-objective optimization, the input data of the dynamic scheduling model is pre-processed multi-source data; S42, model output: Based on the input multi-source data, an optimal production scheduling solution is output through the scheduling optimization model.

5. The intelligent factory advanced scheduling optimization method based on big data according to claim 4 is characterized in that: The multi-objective optimization dynamic scheduling model includes: Objective function: The multi-objective optimization dynamic scheduling model aims to optimize the production cycle, resource utilization and production bottleneck at the same time. The objective function is expressed as: ； in, is the total production cycle, which means the total time required from the start to the completion of the task. is the equipment utilization rate, which indicates the ratio of the equipment’s working time in production to its available time. The production bottleneck indicates the maximum delay or stagnation time of the bottleneck link in the production process; Constraints: The constraints considered in the dynamic scheduling model include equipment availability constraints, raw material constraints, and task priority constraints.

6. The intelligent factory advanced scheduling optimization method based on big data according to claim 5 is characterized in that: The S4 includes: S41, optimization algorithm objective: based on the constructed dynamic scheduling optimization model, the objective function is solved by the optimization algorithm; S42, algorithm selection: using genetic algorithm as the optimization algorithm to solve the objective function; S43, optimization result output: after solving the objective function through the genetic algorithm, the optimal scheduling plan is output.

7. The intelligent factory advanced scheduling optimization method based on big data according to claim 6 is characterized in that: The S5 includes: S51, real-time dispatch of scheduling plans: the generated scheduling plan is dispatched to the production line and related departments in real time through the automation system; S52, production scheduling monitoring: during the production process, real-time monitoring of the execution of the scheduling plan; S53, dynamic adjustment mechanism: dynamically adjust the production scheduling plan according to the results of real-time monitoring.

8. The intelligent factory advanced scheduling optimization method based on big data according to claim 7 is characterized in that: The S5 further includes: S54, scheduling plan visualization: presenting the generated scheduling plan through a visualization tool.

Images