Production battle situation center scheduling method and device based on machine learning
Through the production situation center scheduling method based on machine learning, a scheduling model is built for real-time monitoring and early warning, solving the problem that the existing technology cannot predict product demand and production environment changes, realizing intelligent production scheduling and resource scheduling, and improving production efficiency and security.
Patent Information
- Application Number
- CN202411091548.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-12-06
AI Technical Summary
The existing technology cannot effectively predict changes in product demand and production environment, and cannot monitor and early warning of abnormal situations in the production process in real time, resulting in low production efficiency and increased safety risks.
Using the production situation center scheduling method based on machine learning, a scheduling model is constructed by extracting data samples of production line indicators, monitoring production information in real time, early warning and dynamically orchestrating production tasks, and realizing intelligent production scheduling and resource scheduling.
Improve production efficiency and product quality, promptly detect and prevent abnormal situations, reduce costs and risks, and enhance the ability to respond to market demand.
Smart Images

Figure CN119090185A_ABST
Abstract
Description
Technical Field
[0001] The invention discloses a production situation center scheduling method and device based on machine learning, and relates to the technical field of data analysis. Background Art
[0002] With the increasing complexity and scale of industrial production, production line scheduling needs to improve production efficiency and focus on product quality, and the safety risks in the production process are also gradually increasing. However, there is currently no perfect method to predict changes in product demand and production environment. Based on real-time monitoring and early warning of abnormal situations that may occur in the production process, as well as real-time monitoring of key parameters in the production process, abnormal situations can be discovered in time to avoid accidents. Summary of the invention
[0003] In view of the problems of the prior art, the present invention provides a production situation center scheduling method and device based on machine learning, which realizes intelligent scheduling of production tasks and multi-dimensional real-time analysis of production data through the analysis and processing of station information data and early warning, greatly ensuring the efficient operation of the production line and real-time monitoring of the production line station data. Real-time monitoring of key parameters in the production process can timely detect abnormal situations and generate early warnings to avoid accidents. The production situation is fully displayed, and the real-time scheduling of production equipment is realized through platform arrangement, so that efficient production is carried out with the concept of digitalization.
[0004] The specific scheme proposed by the present invention is:
[0005] The present invention provides a production situation center scheduling method based on machine learning, comprising:
[0006] Step 1: The production situation center extracts data samples of different production line indicators based on real-time and historical data of production scheduling tasks, and uses the data samples to build scheduling models for each production line through machine learning algorithms.
[0007] Step 2: Use the scheduling model to manage production line scheduling through the production situation center:
[0008] The production situation center obtains real-time production information of the production line, and uses the scheduling model to process the real-time production information. If the production information triggers the preset alarm conditions, the production line will be warned.
[0009] The production scheduling plan is issued through the production situation center, the generated data collected and sent back according to the production scheduling plan is obtained, the production data is analyzed using the scheduling model, and the production scheduling plan is adjusted according to the production line warning status corresponding to the production data.
[0010] The Production Situation Center uses scheduling models to make forecasts or make production decisions without a clear production plan to execute tasks.
[0011] Furthermore, in step 1 of the production situation center scheduling method based on machine learning, data samples of different production line indicators are extracted, including: extracting global equipment efficiency OEE data, time utilization rate, product first-time qualified rate, and product performance efficiency as data samples of production line indicators.
[0012] Furthermore, in step 2 of the production situation center scheduling method based on machine learning, a scheduling model is used to predict or make decisions on production scheduling, including: scheduling production tasks according to the calendar based on specific granularity, dynamically scheduling factory production tasks based on real-time analysis of production line status, and performing collaborative scheduling of multiple tasks and multiple production lines in the factory based on real-time analysis of production line status.
[0013] Furthermore, in step 2 of the production situation center scheduling method based on machine learning, in the process of production line scheduling management performed by the production situation center using the scheduling model, changes in production line indicators of each production scenario are displayed, results of real-time production information processing using the scheduling model are displayed, and results of analyzing production data using the scheduling model are displayed.
[0014] The present invention also provides a production situation center scheduling device based on machine learning, comprising: a production situation management module and a scheduling module,
[0015] The production situation center uses the production situation management module to extract data samples of different production line indicators based on the real-time data and historical data of production scheduling tasks, and uses the data samples to build scheduling models for each production line through machine learning algorithms.
[0016] The production situation center uses the scheduling model through the scheduling module to manage production line scheduling:
[0017] The production situation center obtains real-time production information of the production line through the scheduling module, and uses the scheduling model to process real-time production information. If the production information triggers the preset alarm conditions, the production line will be warned.
[0018] The production situation center issues production scheduling plans through the scheduling module, obtains the generated data collected and transmitted back according to the production scheduling plan, uses the scheduling model to analyze the production data, and adjusts the production scheduling plan according to the production line warning status corresponding to the production data.
[0019] The Production Situation Center uses the scheduling model through the scheduling module to make predictions or make decisions on production scheduling without a clear production plan to perform tasks.
[0020] Furthermore, the production situation management module of the production situation center scheduling device based on machine learning extracts data samples of different production line indicators, including: extracting global equipment efficiency OEE data, time utilization rate, product first-time qualified rate, and product performance efficiency as data samples of production line indicators.
[0021] Furthermore, the scheduling module of the production situation center scheduling device based on machine learning uses a scheduling model to predict or make decisions on production scheduling, including: scheduling production tasks according to the calendar based on specific granularity, dynamically scheduling factory production tasks based on real-time analysis of production line status, and performing collaborative scheduling of multiple tasks and multiple production lines in the factory based on real-time analysis of production line status.
[0022] Furthermore, in the process of performing production line scheduling management using a scheduling model through a scheduling module, the production situation center of the production situation center scheduling device based on machine learning displays the changes in production line indicators of each production scenario, displays the results of real-time production information processing using the scheduling model, and displays the results of analyzing production data using the scheduling model.
[0023] The benefits of the present invention are:
[0024] The present invention uses advanced algorithms and models, based on the mathematical model of the sample data of the production line station information, and automatically performs intelligent production scheduling and resource scheduling according to real-time production data and user needs, thereby improving production efficiency and product quality. It can also adjust production plans and resource allocation in a timely manner through real-time monitoring and analysis, improve the ability to respond to market demand, and reduce costs and risks. Through machine learning, statistical analysis of production warnings and historical data, and comparative analysis of data change trends in the production process, the laws and potential problems in the production process can be discovered. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 It is a schematic diagram of the interaction flow between the parties in the application of the method of the present invention. DETAILED DESCRIPTION
[0026] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.
[0027] Example 1
[0028] The present invention provides a production situation center scheduling method based on machine learning, comprising:
[0029] Step 1: The production situation center extracts data samples of different production line indicators based on real-time data and historical data of production scheduling tasks, and uses the data samples to build scheduling models for each production line through machine learning algorithms. When collecting real-time data, RFID can also be used on products to use wireless radio frequency to perform non-contact two-way data transmission between the reader and the electronic tag to achieve the purpose of target identification, data transmission and control.
[0030] Extracting data samples of different production line indicators may include: extracting global equipment efficiency OEE data, time utilization rate, product first-time qualified rate, and product performance efficiency as data samples of production line indicators.
[0031] Step 2: Use the scheduling model to manage production line scheduling through the production situation center:
[0032] The production situation center obtains real-time production information of the production line, and uses the scheduling model to process the real-time production information. If the production information triggers the preset alarm conditions, the production line will be warned.
[0033] The production scheduling plan is issued through the production situation center, the generated data collected and sent back according to the production scheduling plan is obtained, the production data is analyzed using the scheduling model, and the production scheduling plan is adjusted according to the production line warning status corresponding to the production data.
[0034] The production situation center uses the scheduling model to make predictions or make production decisions without a clear production schedule to execute tasks. The use of the scheduling model for prediction or production scheduling can include: scheduling production tasks according to the calendar based on specific granularity, dynamically scheduling factory production tasks based on real-time analysis of production line status, and performing factory multi-task and multi-production line collaborative scheduling based on real-time analysis of production line status. Message middleware such as Kafka can also be used to reduce data processing pressure.
[0035] In step 2, the production situation center can also display the changes in production line indicators of each production scenario, the results of real-time production information processing using the scheduling model, and the results of analyzing production data using the scheduling model during the process of production line scheduling management using the scheduling model. Data can also be actively pushed from the back end to the front end interface for real-time display through the WebSocket service.
[0036] Example 2
[0037] The present invention also provides a production situation center scheduling device based on machine learning, comprising: a production situation management module and a scheduling module,
[0038] The production situation center uses the production situation management module to extract data samples of different production line indicators based on the real-time data and historical data of production scheduling tasks, and uses the data samples to build scheduling models for each production line through machine learning algorithms.
[0039] The production situation center uses the scheduling model through the scheduling module to manage production line scheduling:
[0040] The production situation center obtains real-time production information of the production line through the scheduling module, and uses the scheduling model to process real-time production information. If the production information triggers the preset alarm conditions, the production line will be warned.
[0041] The production situation center issues production scheduling plans through the scheduling module, obtains the generated data collected and transmitted back according to the production scheduling plan, uses the scheduling model to analyze the production data, and adjusts the production scheduling plan according to the production line warning status corresponding to the production data.
[0042] The Production Situation Center uses the scheduling model through the scheduling module to make predictions or make decisions on production scheduling without a clear production plan to perform tasks.
[0043] As the information interaction and execution process between the modules in the above-mentioned device are based on the same concept as the embodiment of the method of the present invention, the specific contents can be found in the description of the embodiment of the method of the present invention and will not be repeated here.
[0044] Similarly, the device of the present invention uses advanced algorithms and models, based on the mathematical model of the sample data of the production line station information, according to the real-time production data and user needs, to automatically perform intelligent production scheduling and resource scheduling, thereby improving production efficiency and product quality. It can also adjust production plans and resource allocation in a timely manner through real-time monitoring and analysis, improve the ability to respond to market demand, and reduce costs and risks. Through machine learning, statistical analysis of production warnings and historical data, and comparative analysis of data change trends in the production process, the laws and potential problems in the production process can be discovered.
[0045] It should be noted that not all steps and modules in the above-mentioned processes and device structures are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The system structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by multiple physical entities, or some components in multiple independent devices may be implemented together.
[0046] The above-described embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art based on the present invention are within the protection scope of the present invention. The protection scope of the present invention shall be subject to the claims.
Claims
1. A production situation center scheduling method based on machine learning, characterized by include: Step 1: The production situation center extracts data samples of different production line indicators based on real-time and historical data of production scheduling tasks, and uses the data samples to build scheduling models for each production line through machine learning algorithms. Step 2: Use the scheduling model to manage production line scheduling through the production situation center: The production situation center obtains real-time production information of the production line, and uses the scheduling model to process the real-time production information. If the production information triggers the preset alarm conditions, the production line will be warned. The production scheduling plan is issued through the production situation center, the generated data collected and sent back according to the production scheduling plan is obtained, the production data is analyzed using the scheduling model, and the production scheduling plan is adjusted according to the production line warning status corresponding to the production data. The Production Situation Center uses scheduling models to make forecasts or make production decisions without a clear production plan to execute tasks.
2. The method for scheduling a production situation center based on machine learning according to claim 1 is characterized in that In step 1, data samples of different production line indicators are extracted, including: extracting global equipment efficiency OEE data, time utilization rate, product first-time qualified rate, and product performance efficiency as data samples of production line indicators.
3. The method for scheduling a production situation center based on machine learning according to claim 1 is characterized in that In step 2, the scheduling model is used to make predictions or make decisions on production scheduling, including: scheduling production tasks according to the calendar based on specific granularity, dynamically scheduling factory production tasks based on real-time analysis of production line status, and performing collaborative scheduling of multiple tasks and multiple production lines in the factory based on real-time analysis of production line status.
4. The method for scheduling a production situation center based on machine learning according to claim 1, characterized in that In step 2, when the production situation center uses the scheduling model to perform production line scheduling management, the changes in production line indicators in each production scenario are displayed, the results of real-time production information processing using the scheduling model are displayed, and the results of analyzing production data using the scheduling model are displayed.
5. A production situation center scheduling device based on machine learning, characterized in that include: Production situation management module and scheduling module, The production situation center uses the production situation management module to extract data samples of different production line indicators based on the real-time data and historical data of production scheduling tasks, and uses the data samples to build scheduling models for each production line through machine learning algorithms. The production situation center uses the scheduling model through the scheduling module to manage production line scheduling: The production situation center obtains real-time production information of the production line through the scheduling module, and uses the scheduling model to process real-time production information. If the production information triggers the preset alarm conditions, the production line will be warned. The production situation center issues production scheduling plans through the scheduling module, obtains the generated data collected and transmitted back according to the production scheduling plan, uses the scheduling model to analyze the production data, and adjusts the production scheduling plan according to the production line warning status corresponding to the production data. The Production Situation Center uses the scheduling model through the scheduling module to make predictions or make decisions on production scheduling without a clear production plan to perform tasks.
6. The production situation center scheduling device based on machine learning according to claim 5 is characterized by: The production situation management module extracts data samples of different production line indicators, including: extracting global equipment efficiency OEE data, time utilization rate, product first-time qualified rate, and product performance efficiency as data samples of production line indicators.
7. The production situation center scheduling device based on machine learning according to claim 5 is characterized by: The scheduling module uses the scheduling model to make predictions or make decisions on production scheduling, including: scheduling production tasks according to the calendar based on specific granularity, dynamically scheduling factory production tasks based on real-time analysis of production line status, and performing collaborative scheduling of multiple tasks and multiple production lines in the factory based on real-time analysis of production line status.
8. The production situation center scheduling device based on machine learning according to claim 5 is characterized by: In the process of production line scheduling management using the scheduling model through the scheduling module, the Production Situation Center displays the changes in production line indicators in each production scenario, the results of real-time production information processing using the scheduling model, and the results of production data analysis using the scheduling model.
