Steel structure manufacturing intelligent optimization decision-making method and system based on digital technology

Abstract

The invention discloses an intelligent optimization decision-making method and system for steel structure manufacturing based on a digital technology, belongs to the technical field of steel structure manufacturing, and aims to solve the problems of limitation to single-link optimization, insufficient real-time data processing capability and poor system integration in the prior art, and the method comprises the following steps: S1, data acquisition and sensor arrangement; s2, data cleaning and fusion; s3, constructing a global optimization model; s4, establishing an intelligent decision support system; s5, real-time monitoring and feedback are carried out; s6, system integration and collaboration; s7, scheduling and resource management are optimized; by constructing the multi-link global optimization model, global optimization of the whole steel structure manufacturing process is achieved, links from data acquisition, optimization decision, resource scheduling to process feedback and the like are covered, optimization of the links can be coordinated by comprehensively considering the mutual relation between different production links, and the production efficiency is improved. Therefore, the overall production efficiency and quality are improved, and the method is not limited to optimization of a single link.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of steel structure manufacturing, and particularly relates to a steel structure manufacturing intelligent optimization decision method and system based on digital technology. BACKGROUND

[0002] Steel structure is widely used in engineering such as building, bridge and industrial plant due to its advantages of light weight, high strength, good corrosion resistance and short construction period. Steel structure manufacturing refers to the production of steel structure components meeting design requirements through processing and assembly of steel materials. With the increasing demand for steel structure in the construction industry and manufacturing industry, the manufacturing process of steel structure becomes more and more complex. Steel structure manufacturing involves multiple links, including design, material procurement, processing, assembly and quality control, etc. These links need to be closely coordinated to ensure the quality and production efficiency of the final product.

[0003] The traditional steel structure manufacturing process usually relies on manual experience and manual decision-making, which is not only susceptible to human factors, but also may lead to long production cycle, resource waste and high cost. In recent years, digital technology has gradually attracted widespread attention in the steel structure manufacturing industry. Through computer digital tools, the design, processing and quality control links in the manufacturing process can be managed and optimized more finely. However, although digital technology has achieved successful application in some fields, there are still the following deficiencies in practical application:

[0004] Firstly, it is limited to single-link optimization. Existing digital technologies are mostly focused on a single link in the steel structure manufacturing process, such as design optimization or processing path planning, which fails to achieve overall optimization of the entire manufacturing process, resulting in inability to comprehensively improve production efficiency and quality.

[0005] Secondly, real-time data processing capability is insufficient. Steel structure manufacturing process requires real-time monitoring of a large amount of data such as temperature, humidity, material state and processing progress. Existing systems often lack effective integration and processing capability of these real-time data, affecting the accuracy and timeliness of optimization decisions.

[0006] Thirdly, system integration is poor. Steel structure manufacturing process involves multiple links and systems such as design, manufacturing and assembly. Existing technologies lack good system integration, leading to difficulties in information exchange and collaboration between different links, and inability to achieve overall optimization of the process.

[0007] Therefore, a steel structure manufacturing intelligent optimization decision method and system based on digital technology is needed to solve the problems of single-link optimization limitation, insufficient real-time data processing capability and poor system integration in existing technologies. SUMMARY

[0008] The purpose of the present invention is to provide an intelligent optimization decision-making method and system for steel structure manufacturing based on digital technology to solve the problems raised in the above background technology.

[0009] To achieve the above objectives, the present invention provides the following technical solution: a steel structure manufacturing intelligent optimization decision-making method and system based on digital technology, comprising the following steps:

[0010] S1. Data acquisition and sensor placement: Place sensors in the steel structure manufacturing process to collect real-time data related to production, and design a data acquisition system to synchronize data from different links through wireless transmission;

[0011] S2. Data cleaning and fusion: Preprocess the collected raw data to remove noise and erroneous data, fill in missing values, and fuse data from different links and sources to establish a complete real-time data flow;

[0012] S3. Build a global optimization model: Build a multi-step global optimization model, use machine learning algorithms to train and optimize the model, and achieve global scheduling and decision-making through the optimization model;

[0013] S4. Establish an intelligent decision support system: Generate optimization decisions based on real-time data and optimization model results, integrate a visual interface, and automatically issue decision instructions for each production link based on the results of the optimization model;

[0014] S5. Real-time monitoring and feedback: A real-time monitoring system is established to continuously monitor key parameters in the steel structure manufacturing process. Intelligent sensors provide real-time feedback on any anomalies in the production process. The system automatically detects anomalies and provides adjustment suggestions based on the optimization model, forming a closed-loop feedback mechanism so that every decision is monitored and adjusted.

[0015] S6. System integration and collaboration: Integrate all aspects of steel structure manufacturing into a unified digital platform, and share departmental data and information in real time through the platform;

[0016] S7. Optimized Scheduling and Resource Management: Based on real-time data and optimized decision-making models, the system intelligently schedules production resources and rationally allocates resources by adjusting production plans based on real-time data.

[0017] S8. Predictive analysis and early warning mechanism: Use big data analysis and machine learning algorithms to model historical data and predict possible risk issues;

[0018] S9. Process optimization and continuous improvement: By continuously collecting feedback data during system operation, the optimization model is iteratively updated. Based on historical data and production experience, the optimization algorithm is continuously improved to enhance the accuracy and intelligence of decision-making.

[0019] S10. System deployment and maintenance: Deploy the intelligent optimization decision-making system into the production environment, perform software and hardware integration and system debugging, train operators, and perform regular maintenance and updates on the system.

[0020] It should be noted in the scheme that in the data collection and sensor arrangement steps, the sensor types include sensors for monitoring the status of steel structure production equipment, sensors for collecting environmental parameters such as temperature and humidity in the production environment, and sensors for collecting material status and quality data.

[0021] It is worth noting that, in the step of constructing a global optimization model, the global optimization model is:

[0022]

[0023] Where Z is the total production cost,

[0024] c i is the cost of the i-th production link,

[0025] x i is the resource usage of the i-th production link,

[0026] n is the total number of production links;

[0027] The constraints are:

[0028]

[0029] Where a ij is the consumption of resource j by production link i,

[0030] b j is the total supply of resource j,

[0031] m is the total number of resource types.

[0032] It should be further explained that in the optimization scheduling and resource management steps, the production resource optimization scheduling model is:

[0033]

[0034] Where, T idle is the total resource idle time,

[0035] R i (t) is the usage of the i-th resource at time t,

[0036] I i (t) is the idle state of the i-th resource at time t (1 indicates idle, 0 indicates used);

[0037] The state transition equation is:

[0038] I i (t)=min(I i (t-1)+R i (t)-C i (t),1)

[0039] Where C i (t) is the task consumption of the i-th resource at time t.

[0040] As a preferred embodiment, in the prediction analysis and early warning mechanism step, the risk prediction model is:

[0041] f(x)=ω T x+b

[0042] Where f(x) is the predicted risk value,

[0043] x is the input feature,

[0044] ω is the weight vector,

[0045] b is the bias term;

[0046] If f(x) exceeds a preset threshold θ, it indicates that there is a risk and the system triggers an early warning.

[0047] As a preferred embodiment, the method for realizing the above-mentioned intelligent optimization decision-making method for steel structure manufacturing based on digital technology includes:

[0048] Intelligent sensing and data acquisition module: Responsible for collecting real-time production data during the steel structure manufacturing process through sensors, IoT devices, and other means, including important parameters such as temperature, pressure, speed, and workpiece dimensions, and ensuring the accuracy and timeliness of the data, providing basic data support for subsequent analysis and optimization;

[0049] Data preprocessing and integration module: cleans, removes noise, and fills missing values ​​in the collected raw data, and integrates data from different data sources to ensure data integrity and consistency, providing high-quality input for further data analysis and decision-making;

[0050] Intelligent Optimization and Decision-Making Module: Based on pre-processed data, it uses artificial intelligence, machine learning and other technologies to establish optimization models, analyze production conditions in real time, formulate optimization plans, and generate intelligent decisions to guide scheduling, quality control, and resource allocation operations during the production process.

[0051] Monitoring and feedback module: real-time monitoring of key indicators and status in the production process to detect potential anomalies or problems;

[0052] Intelligent resource allocation module: Automatically dispatches and allocates production resources based on production needs and optimization decisions, ensuring optimal resource allocation and maximizing production capacity through intelligent means;

[0053] Risk prediction and early warning module: Analyzes potential risks in historical and real-time data to identify potential problems or safety hazards in production;

[0054] Platform integration and collaborative operation module: responsible for integrating each independent module with external systems, ensuring data sharing and collaborative work among various departments and production links, and improving the collaborative efficiency of various production links through a unified platform interface;

[0055] System implementation and continuous optimization module: responsible for the deployment, implementation and subsequent optimization of the entire system, ensuring the smooth operation of the system in the actual production environment, and regularly updating and improving it, optimizing algorithms, adjusting module functions, so that the system can adapt to changing needs in production.

[0056] As a preferred implementation, the data preprocessing and integration module also includes a data quality assessment function.

[0057] As a preferred embodiment, the platform integration and collaborative operation module further includes multi-level data sharing and authority management functions.

[0058] Compared with the existing technology, the steel structure manufacturing intelligent optimization decision-making method and system based on digital technology provided by the present invention have at least the following beneficial effects:

[0059] (1) By constructing a multi-link global optimization model, the global optimization of the entire steel structure manufacturing process is achieved, covering all links from data collection, optimization decision-making, resource scheduling to process feedback. By comprehensively considering the relationship between different production links, the optimization of each link can be coordinated, thereby improving the overall production efficiency and quality, rather than being limited to the optimization of a single link.

[0060] (2) Through data collection and sensor layout steps, a large amount of key data in the production process, such as temperature, humidity, material status, etc., can be collected in real time, and through data cleaning and fusion processing, the accuracy and completeness of the data can be ensured. With the help of real-time monitoring and feedback systems, abnormal situations in the production process can be detected immediately, and rapid responses can be made through optimization models to ensure the timeliness and accuracy of optimization decisions.

[0061] (3) Through the system integration and collaborative operation module, all links and systems in the steel structure manufacturing process are integrated into a unified digital platform to ensure information sharing and collaborative work between different departments and links. Through the unified data platform and intelligent resource allocation module, intelligent scheduling of production resources and full-process collaboration are realized, effectively eliminating information islands between links, improving the system's integration and collaborative efficiency, and ensuring the smoothness and efficiency of the overall production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 is a flow chart of the method of the present invention;

[0063] Figure 2 This is a system block diagram of the present invention. DETAILED DESCRIPTION

[0064] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0065] The present invention will be further described below with reference to the embodiments.

[0066] See also Figures 1-2 The present invention provides a steel structure manufacturing intelligent optimization decision-making method and system based on digital technology, including the following steps:

[0067] S1. Data acquisition and sensor placement: Place sensors in the steel structure manufacturing process to collect real-time data related to production, and design a data acquisition system to synchronize data from different links through wireless transmission;

[0068] S2. Data cleaning and fusion: Preprocess the collected raw data to remove noise and erroneous data, fill in missing values, and fuse data from different links and sources to establish a complete real-time data flow;

[0069] S3. Build a global optimization model: Build a multi-step global optimization model, use machine learning algorithms to train and optimize the model, and achieve global scheduling and decision-making through the optimization model;

[0070] S4. Establish an intelligent decision support system: Generate optimization decisions based on real-time data and optimization model results, integrate a visual interface, and automatically issue decision instructions for each production link based on the results of the optimization model;

[0071] S5. Real-time monitoring and feedback: A real-time monitoring system is established to continuously monitor key parameters in the steel structure manufacturing process. Intelligent sensors provide real-time feedback on any anomalies in the production process. The system automatically detects anomalies and provides adjustment suggestions based on the optimization model, forming a closed-loop feedback mechanism so that every decision is monitored and adjusted.

[0072] S6. System integration and collaboration: Integrate all aspects of steel structure manufacturing into a unified digital platform, and share departmental data and information in real time through the platform;

[0073] S7. Optimized Scheduling and Resource Management: Based on real-time data and optimized decision-making models, the system intelligently schedules production resources and rationally allocates resources by adjusting production plans based on real-time data.

[0074] S8. Predictive analysis and early warning mechanism: Use big data analysis and machine learning algorithms to model historical data and predict possible risk issues;

[0075] S9. Process optimization and continuous improvement: By continuously collecting feedback data during system operation, the optimization model is iteratively updated. Based on historical data and production experience, the optimization algorithm is continuously improved to enhance the accuracy and intelligence of decision-making.

[0076] S10. System deployment and maintenance: Deploy the intelligent optimization decision-making system into the production environment, perform software and hardware integration and system debugging, train operators, and perform regular maintenance and updates on the system.

[0077] Further as Figure 1 As shown, it is worth mentioning that in the data collection and sensor arrangement steps, the sensor types include sensors for monitoring the status of steel structure production equipment, sensors for collecting environmental parameters such as temperature and humidity in the production environment, and sensors for collecting material status and quality data. These sensors can collect various types of data related to the production process (such as temperature, pressure, humidity, etc.) in real time to ensure that the key parameters of each production link can be tracked in a timely manner, which helps to immediately discover potential problems, avoid production interruptions or equipment failures, and improve production efficiency. Through real-time monitoring of production equipment, environment and material status, more accurate data can be provided to support intelligent optimization decision-making models. In this way, the optimization model can perform more effective production scheduling and resource allocation based on accurate data, thereby reducing production costs and improving production efficiency.

[0078] Further as Figure 1 As shown, it is worth noting that in the step of building a global optimization model, the global optimization model is:

[0079]

[0080] Where Z is the total production cost,

[0081] c i is the cost of the i-th production link,

[0082] x i is the resource usage of the i-th production link,

[0083] n is the total number of production links;

[0084] The constraints are:

[0085]

[0086] Where a ij is the consumption of resource j by production link i,

[0087] b j is the total supply of resource j,

[0088] m is the total number of resource types. The global optimization model can effectively reduce unnecessary resource waste in the production process by accurately calculating the cost and resource consumption of each link. For example, by optimizing the resource usage of each link, it can avoid excessive resource consumption or idleness, thereby reducing overall production costs. Through the intelligent optimization decision-making model, it can quickly respond to resource bottlenecks that may arise in the production process, optimize scheduling and production plans, and thus reduce production downtime and cycles.

[0089] Further as Figure 1 As shown, it is worth noting that in the optimization scheduling and resource management steps, the production resource optimization scheduling model is:

[0090]

[0091] Where, T idle is the total resource idle time,

[0092] R i (t) is the usage of the i-th resource at time t,

[0093] I i (t) is the idle state of the i-th resource at time t (1 indicates idle, 0 indicates used);

[0094] The state transition equation is:

[0095] I i (t)=min(I i (t-1)+R i (t)-C i (t),1)

[0096] Where C i(t) is the task consumption of the i-th resource at time t, by optimizing the scheduling model, the system can intelligently adjust the allocation and use of resources, ensure that each resource is optimally utilized, reduce resource waste, and thus improve production efficiency. Reasonable resource scheduling can reduce the idle time and unnecessary consumption of resources in the production process, reduce unnecessary expenses, thereby reducing the overall production cost.

[0097] Further as Figure 1 illustrated, it is worth noting that in the risk prediction and early warning mechanism step, the risk prediction model is:

[0098] f(x) = ω T x + b

[0099] where f(x) is the predicted risk value,

[0100] x is the input feature,

[0101] ω is the weight vector,

[0102] b is the bias term;

[0103] f(x) exceeds a certain preset threshold θ, indicating that there is a risk, the system triggers an early warning, through in-depth analysis of historical data and real-time data, the risk prediction model can issue an early warning signal before potential problems occur, for example, by predicting production line equipment failure, resource shortage or quality problems, etc. Early detection of problems and preventive measures can prevent serious consequences; risk prediction and early warning mechanism helps to identify potential safety hazards or equipment failure in advance, and timely maintenance or replacement measures are taken to reduce production accidents and ensure the safety of employees and the production environment.

[0104] Further as Figure 2 illustrated, it is worth noting that for the above-mentioned steel structure manufacturing intelligent optimization decision method based on digital technology, it includes:

[0105] Intelligent perception and data acquisition module: responsible for real-time collection of production data in the steel structure manufacturing process through sensors, Internet of Things devices and other means, including temperature, pressure, speed, workpiece size and other important parameters, and ensuring the accuracy and timeliness of the data, providing basic data support for subsequent analysis and optimization;

[0106] Data preprocessing and integration module: clean, denoise and fill missing values of the collected raw data, and integrate data from different data sources to ensure data integrity and consistency, providing high-quality input for further data analysis and decision-making;

[0107] Intelligent optimization and decision-making module: Based on the pre-processed data, an optimization model is established using artificial intelligence, machine learning, etc. Real-time analysis of production conditions, formulation of optimization schemes, and generation of intelligent decisions guide the scheduling, quality control, and resource allocation operations in the production process.

[0108] Monitoring and feedback module: Real-time monitoring of key indicators and states in the production process detects potential abnormalities or problems.

[0109] Intelligent resource allocation module: According to production needs and optimization decisions, production resources are automatically scheduled and allocated to ensure optimal resource allocation and maximize production capacity.

[0110] Risk prediction and early warning module: Analyzing potential risks in historical and real-time data identifies potential problems or safety hazards in production.

[0111] Platform integration and collaborative operation module: Responsible for integrating individual modules with external systems to ensure data sharing and collaborative work among departments and production links. Through unified platform interfaces, the efficiency of production links is improved.

[0112] System implementation and continuous optimization module: Responsible for the deployment, implementation, and post-optimization of the entire system to ensure smooth operation in the actual production environment and regular updates and improvements. Optimize algorithms, adjust module functions, and make the system adapt to changing production needs.

[0113] Further as shown in Figure 2 , it is worth noting that the data preprocessing and integration module also includes a data quality assessment function. The data quality assessment function can detect the quality of collected data, identify and exclude inaccurate, erroneous, or missing data. In this way, it ensures that the data input into subsequent processing and analysis is reliable and reduces the risk of incorrect decisions due to data problems. In the process of data fusion from multiple sources and multiple links, different sources of data may have quality differences. The data quality assessment function can filter before fusion to ensure consistency and compatibility between different data sources, thereby improving the efficiency and accuracy of data integration.

[0114] Further as shown in Figure 2As shown, it is worth noting that the platform integration and collaborative operation module further includes multi-level data sharing and permission management function. Through multi-level permission management, only authorized users or departments can access specific data, thereby enhancing the security and confidentiality of data, sensitive information can be open only to relevant personnel, avoiding data leakage or misuse; through a unified data sharing platform, departments can access and share data in real time. This efficient data mobility helps to improve team collaboration and cross-department cooperation, ensuring that each link can obtain real-time and accurate information support.

[0115] The present scheme has the following working process:

[0116] Step one: arrange sensors at the steel structure manufacturing link to collect real-time data related to production, design a data collection system, and make the data from different links transmitted synchronously through wireless mode;

[0117] Step two: pre-process the collected raw data, remove noise, error data, and fill in missing values, fuse data from different links and different sources, and establish a complete real-time data stream;

[0118] Step three: build a multi-link global optimization model, train and optimize the model using machine learning algorithms, and realize global scheduling and decision-making through the optimized model;

[0119] Step four: generate optimization decisions based on real-time data and optimization model results, integrate a visualization interface, and according to the results of the optimization model, the intelligent decision-making system automatically issues decision instructions for each production link;

[0120] Step five: establish a real-time monitoring system to continuously monitor key parameters in the steel structure manufacturing process, feedback abnormal conditions in the production process through intelligent sensors, and the system automatically detects abnormalities and provides adjustment suggestions according to the optimization model, forming a closed-loop feedback mechanism, so that each decision is monitored and adjusted;

[0121] Step six: integrate each link of steel structure manufacturing into a unified digital platform, and share department data and information in real time through the platform;

[0122] Step seven: based on real-time data and optimization decision model, the system intelligently schedules production resources, and the system adjusts production plans and reasonably allocates resources according to real-time data;

[0123] Step eight: use big data analysis and machine learning algorithms to model historical data and predict possible risks;

[0124] Step nine: The optimization model is iteratively updated by continuously collecting feedback data during system operation, and the optimization algorithm is continuously improved based on historical data and production experience to improve decision accuracy and intelligent level;

[0125] Step ten: Deploy the intelligent optimization decision system to the production environment, integrate software and hardware, and debug the system. Train the operators, and regularly maintain and update the system.

[0126] In summary: By constructing a multi-link global optimization model, the global optimization of the whole process of steel structure manufacturing is realized, covering data collection, optimization decision, resource scheduling, process feedback and other links. By considering the mutual relationship between different production links, the optimization of each link can be coordinated to improve the overall production efficiency and quality, rather than being limited to single-link optimization. Through the data collection and sensor arrangement steps, a large amount of key data such as temperature, humidity, material state, etc. can be collected in real time during the production process, and through data cleaning and fusion processing, the accuracy and completeness of the data are ensured. With real-time monitoring and feedback system, abnormal conditions in the production process can be detected in real time, and the optimization model can respond quickly to ensure the timeliness and accuracy of the optimization decision. Through system integration and collaborative operation module, each link and system in the steel structure manufacturing process is integrated into a unified digital platform to ensure information sharing and collaborative work between different departments and links. Through a unified data platform and intelligent resource allocation module, intelligent scheduling and whole-process collaboration of production resources are realized, effectively eliminating information silos between links, improving the integration and collaboration efficiency of the system, and ensuring the smoothness and efficiency of the overall production process.

[0127] Although embodiments of the present application have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and alterations can be made thereto without departing from the principles and spirit of the present application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An intelligent optimization decision-making method for steel structure manufacturing based on digital technology, characterized by: The following steps are involved: S1. Data acquisition and sensor placement: Place sensors in the steel structure manufacturing process to collect real-time data related to production, and design a data acquisition system to synchronize data from different links through wireless transmission; S2. Data cleaning and fusion: Preprocess the collected raw data to remove noise and erroneous data, fill in missing values, and fuse data from different links and sources to establish a complete real-time data flow; S3. Build a global optimization model: Build a multi-step global optimization model, use machine learning algorithms to train and optimize the model, and achieve global scheduling and decision-making through the optimization model; S4. Establish an intelligent decision support system: Generate optimization decisions based on real-time data and optimization model results, integrate a visual interface, and automatically issue decision instructions for each production link based on the results of the optimization model; S5. Real-time monitoring and feedback: A real-time monitoring system is established to continuously monitor key parameters in the steel structure manufacturing process. Intelligent sensors provide real-time feedback on any anomalies in the production process. The system automatically detects anomalies and provides adjustment suggestions based on the optimization model, forming a closed-loop feedback mechanism so that every decision is monitored and adjusted. S6. System integration and collaboration: Integrate all aspects of steel structure manufacturing into a unified digital platform, and share departmental data and information in real time through the platform; S7. Optimized Scheduling and Resource Management: Based on real-time data and optimized decision-making models, the system intelligently schedules production resources and rationally allocates resources by adjusting production plans based on real-time data. S8. Predictive analysis and early warning mechanism: Use big data analysis and machine learning algorithms to model historical data and predict possible risk issues; S9. Process optimization and continuous improvement: By continuously collecting feedback data during system operation, the optimization model is iteratively updated. Based on historical data and production experience, the optimization algorithm is continuously improved to enhance the accuracy and intelligence of decision-making. S10. System deployment and maintenance: Deploy the intelligent optimization decision-making system into the production environment, perform software and hardware integration and system debugging, train operators, and perform regular maintenance and updates on the system.

2. The intelligent optimization decision-making method for steel structure manufacturing based on digital technology according to claim 1 is characterized by: In the data collection and sensor arrangement step, the sensor types include sensors for monitoring the status of steel structure production equipment, sensors for collecting environmental parameters such as temperature and humidity of the production environment, and sensors for collecting material status and quality data.

3. The intelligent optimization decision-making method for steel structure manufacturing based on digital technology according to claim 1 is characterized by: In the step of constructing a global optimization model, the global optimization model is: Where Z is the total production cost, c i is the cost of the i-th production link, x i is the resource usage of the i-th production link, n is the total number of production links; The constraints are: Where a ij is the consumption of resource j by production link i, b j is the total supply of resource j, m is the total number of resource types.

4. The intelligent optimization decision-making method for steel structure manufacturing based on digital technology according to claim 1 is characterized by: In the optimization scheduling and resource management step, the production resource optimization scheduling model is: Where, T idle is the total resource idle time, R i (t) is the usage of the i-th resource at time t, I i (t) is the idle state of the i-th resource at time t (1 indicates idle, 0 indicates used); The state transition equation is: I i (t)=min(I i (t-1)+R i (t)-C i (t),1) Where C i (t) is the task consumption of the i-th resource at time t.

5. The intelligent optimization decision-making method for steel structure manufacturing based on digital technology according to claim 1 is characterized by: In the prediction analysis and early warning mechanism step, the risk prediction model is: f(x)=ω T x+b Where f(x) is the predicted risk value, x is the input feature, ω is the weight vector, b is the bias term; If f(x) exceeds a preset threshold θ, it indicates that there is a risk and the system triggers an early warning.

6. The intelligent optimization decision-making system for steel structure manufacturing based on digital technology according to claim 1 is characterized by: The method for realizing intelligent optimization decision-making of steel structure manufacturing based on digital technology according to any one of claims 1 to 5 comprises: Intelligent sensing and data acquisition module: Responsible for collecting real-time production data during the steel structure manufacturing process through sensors, IoT devices, and other means, including important parameters such as temperature, pressure, speed, and workpiece dimensions, and ensuring the accuracy and timeliness of the data, providing basic data support for subsequent analysis and optimization; Data preprocessing and integration module: cleans, removes noise, and fills missing values ​​in the collected raw data, and integrates data from different data sources to ensure data integrity and consistency, providing high-quality input for further data analysis and decision-making; Intelligent Optimization and Decision-Making Module: Based on pre-processed data, it uses artificial intelligence, machine learning and other technologies to establish optimization models, analyze production conditions in real time, formulate optimization plans, and generate intelligent decisions to guide scheduling, quality control, and resource allocation operations during the production process. Monitoring and feedback module: real-time monitoring of key indicators and status in the production process to detect potential anomalies or problems; Intelligent resource allocation module: Automatically dispatches and allocates production resources based on production needs and optimization decisions, ensuring optimal resource allocation and maximizing production capacity through intelligent means; Risk prediction and early warning module: Analyzes potential risks in historical and real-time data to identify potential problems or safety hazards in production; Platform integration and collaborative operation module: responsible for integrating each independent module with external systems, ensuring data sharing and collaborative work among various departments and production links, and improving the collaborative efficiency of various production links through a unified platform interface; System implementation and continuous optimization module: responsible for the deployment, implementation and subsequent optimization of the entire system, ensuring the smooth operation of the system in the actual production environment, and regularly updating and improving it, optimizing algorithms, adjusting module functions, so that the system can adapt to changing needs in production.

7. The method and system for intelligent optimization decision-making in steel structure manufacturing based on digital technology according to claim 1, characterized in that: The data preprocessing and integration module also includes a data quality assessment function.

8. The method and system for intelligent optimization decision-making in steel structure manufacturing based on digital technology according to claim 1, characterized in that: The platform integration and collaborative operation module further includes multi-level data sharing and authority management functions.

Images