Intelligent operation method and system based on large energy production model and readable storage medium

Abstract

The embodiment of the invention provides an intelligent operation method and system based on an energy production large model and a readable storage medium. The method comprises the steps of collecting energy production multi-source data for processing and cloud-side cooperative transmission, obtaining, training and optimizing an energy production large model, obtaining an application package, processing the energy production large model and the application package, obtaining control instruction data, executing production regulation and control and returning operation data, and processing according to the operation data. The method comprises the following steps: acquiring hierarchical early warning information and decision information, mapping, processing and updating an energy production large model according to operation data, dynamically adjusting computing power resources, optimizing data storage and transmission, and performing cloud-side transmission through global data acquisition and cloud-side transmission. According to the technical scheme of the invention, central model training and cloud development, edge intelligent reasoning and real-time control, intelligent decision early warning and business linkage and closed-loop measurement optimization and resource management are adopted, so that the monitoring, early warning and decision support of the whole energy production process can be realized, the production efficiency and safety can be improved, and the operation cost can be reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent operation technology in the energy industry, and more specifically, to intelligent operation methods, systems, and readable storage media based on large-scale energy production models. Background Technology

[0002] With the rapid development of the energy industry, the demand for intelligent operation in high-risk sectors such as mining is increasing. Traditional energy production suffers from problems such as low efficiency, numerous safety hazards, and resource waste. Although artificial intelligence technology has made some progress in the industrial field, challenges remain, including low model development efficiency, weak generalization ability, and complex deployment. Existing systems struggle to achieve integrated operation encompassing data fusion, edge-cloud collaboration, and intelligent decision-making.

[0003] Therefore, relevant technical solutions are urgently needed to address the above problems. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent operation method, system, and readable storage medium based on a large energy production model, which can realize intelligent monitoring, early warning, and decision support for the entire energy production process, improve production efficiency and safety, and reduce operating costs.

[0005] This application also provides an intelligent operation method based on a large-scale energy production model, including the following steps: Collect and process multi-source energy production data and transmit it via a cloud-edge collaborative network. The multi-source energy production data is processed to obtain a large-scale energy production model, which is then trained and optimized to obtain a lightweight application package. The energy production big model and lightweight application package are processed to obtain production control command data, production regulation is executed, and the operation data is transmitted back. The operational data is processed to obtain tiered early warning information and decision-making information, and then correlated and mapped. The operational data is processed to update the large-scale energy production model, dynamically adjust computing resources, and optimize data storage and transmission.

[0006] Optionally, in the intelligent operation method based on a large energy production model described in the embodiments of this application, the step of collecting and processing multi-source energy production data and transmitting it via a cloud-edge collaborative network includes: Collect multi-source data on energy production through pre-set devices, including data from field equipment and business systems; The energy production multi-source data is cleaned, standardized, and compressed preprocessed. The preprocessed multi-source energy production data is transmitted in real time to the central node and edge nodes.

[0007] Optionally, in the intelligent operation method based on a large energy production model described in the embodiments of this application, the step of processing the multi-source energy production data to obtain a large energy production model and training and optimizing it to obtain a lightweight application package includes: An energy industry database is constructed by desensitizing, associating, and storing the multi-source energy production data through a preset model. The data in the constructed energy industry database is processed by a preset learning model to obtain a large energy production model, which is then trained and optimized using a preset algorithm model. The energy production model is processed through a pre-defined application development platform to obtain a lightweight application package.

[0008] Optionally, in the intelligent operation method based on a large energy production model described in the embodiments of this application, the step of processing the large energy production model and the lightweight application package to obtain production control command data, executing production regulation, and transmitting the operation data back includes: The large-scale energy production model and lightweight application package are processed for transmission. The energy production big data model and lightweight application package are used to process the real-time collected multi-source energy production data to obtain production control command data. The production control command data is processed to perform on-site production control and the operational data is transmitted back. The operational data includes production control command data, control command execution status data, and abnormal data.

[0009] Optionally, in the intelligent operation method based on a large-scale energy production model described in this application embodiment, the step of processing the operational data to obtain hierarchical early warning information and decision information, and performing correlation mapping, includes: The operational data is processed by a preset decision-making model to obtain comprehensive evaluation results. The energy production big data model is used to process the comprehensive assessment results and historical data to correct the assessment results and obtain graded early warning information and decision-making information. The hierarchical early warning information and decision-making information are correlated and mapped.

[0010] Optionally, in the intelligent operation method based on a large-scale energy production model described in the embodiments of this application, the step of processing the operating data, updating the large-scale energy production model, dynamically adjusting computing resources, and optimizing data storage and transmission includes: The energy production model is processed by combining the preset algorithm model with the running data to obtain optimized parameter data and update the energy production model. The system collects computing power usage data in real time, processes it through a preset algorithm model, and dynamically adjusts computing power resources. Data on the system's computing power resource utilization efficiency, data transmission, and storage resources are collected and processed according to a preset time period to optimize data storage and transmission.

[0011] Secondly, embodiments of this application provide an intelligent operation system based on a large-scale energy production model. This system includes a memory and a processor. The memory includes a program for an intelligent operation method based on a large-scale energy production model. When the program for the intelligent operation method based on the large-scale energy production model is executed by the processor, it implements the following steps: Collect and process multi-source energy production data and transmit it via a cloud-edge collaborative network. The multi-source energy production data is processed to obtain a large-scale energy production model, which is then trained and optimized to obtain a lightweight application package. The energy production big model and lightweight application package are processed to obtain production control command data, production regulation is executed, and the operation data is transmitted back. The operational data is processed to obtain tiered early warning information and decision-making information, and then correlated and mapped. The operational data is processed to update the large-scale energy production model, dynamically adjust computing resources, and optimize data storage and transmission.

[0012] Optionally, in the intelligent operation system based on a large-scale energy production model described in this application embodiment, the step of collecting and processing multi-source energy production data and transmitting it via a cloud-edge collaborative network includes: Collect multi-source data on energy production through pre-set devices, including data from field equipment and business systems; The energy production multi-source data is cleaned, standardized, and compressed preprocessed. The preprocessed multi-source energy production data is transmitted in real time to the central node and edge nodes.

[0013] Optionally, in the intelligent operation system based on a large energy production model described in this application embodiment, the process of processing the multi-source energy production data to obtain a large energy production model and then training and optimizing it to obtain a lightweight application package includes: An energy industry database is constructed by desensitizing, associating, and storing the multi-source energy production data through a preset model. The data in the constructed energy industry database is processed by a preset learning model to obtain a large energy production model, which is then trained and optimized using a preset algorithm model. The energy production model is processed through a pre-defined application development platform to obtain a lightweight application package.

[0014] Thirdly, embodiments of this application also provide a computer-readable storage medium, which includes a smart operation method program based on a large-scale energy production model. When the smart operation method program based on the large-scale energy production model is executed by a processor, it implements the steps of the smart operation method based on the large-scale energy production model as described in any of the preceding claims.

[0015] As can be seen from the above, the intelligent operation method, system, and readable storage medium based on a large energy production model provided in this application obtain a large energy production model by collecting and processing multi-source energy production data and transmitting it via cloud-edge collaboration. This model is then trained and optimized to obtain an application package. The large energy production model and the application package are processed to obtain control command data. Production regulation is executed and the operating data is transmitted back. Based on the operating data, hierarchical early warning information and decision information are obtained and mapped. The large energy production model is updated based on the operating data. Computing resources are dynamically adjusted and data storage and transmission are optimized. Through full-domain data collection and cloud-edge transmission, central model training and cloud development, edge intelligent inference and real-time control, intelligent decision-making and early warning and business linkage, and closed-loop measurement optimization and resource management, intelligent monitoring, early warning, and decision support for the entire energy production process are achieved, thereby improving production efficiency and safety and reducing operating costs.

[0016] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing embodiments of this application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of an intelligent operation method based on a large energy production model provided in an embodiment of this application.

[0019] Figure 2 A flowchart illustrating the full-domain data acquisition and cloud-edge transmission process of the intelligent operation method based on a large energy production model, provided in the embodiments of this application.

[0020] Figure 3 The flowchart illustrates the central model training and cloud development process of the intelligent operation method based on a large energy production model, as provided in the embodiments of this application. Detailed Implementation

[0021] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely represents selected embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0022] It should be noted that similar reference numerals and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. Furthermore, in the description of this application, terms such as "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating intelligent operation based on a large-scale energy production model in some embodiments of this application. This intelligent operation method based on a large-scale energy production model is used in terminal devices, such as mobile phones and computers. The intelligent operation method based on a large-scale energy production model includes the following steps: S11. Collect and process multi-source energy production data and transmit it via a cloud-edge collaborative network. S12. Process the multi-source energy production data to obtain a large energy production model and train and optimize it to obtain a lightweight application package. S13. Process the energy production big model and lightweight application package to obtain production control command data, execute production regulation and control and send back the operation data; S14. Process the operational data to obtain hierarchical early warning information and decision information, and perform correlation mapping; S15. Process the operational data, update the energy production model, dynamically adjust computing resources, and optimize data storage and transmission.

[0024] This process involves collecting and processing multi-source energy production data and transmitting it via a cloud-edge collaborative network. The multi-source energy production data is processed to obtain a large-scale energy production model, which is then trained and optimized to generate a lightweight application package. The large-scale energy production model and the lightweight application package are then processed to obtain production control command data. Production regulation is executed, and operational data is fed back. Based on the operational data, tiered early warning and decision-making information is obtained and correlated. Based on the operational data, the large-scale energy production model is updated, and computing resources are dynamically adjusted and data storage and transmission are optimized. Through full-domain data collection and cloud-edge transmission, central model training and cloud development, edge intelligent inference and real-time control, intelligent decision-making and early warning with business linkage, and closed-loop measurement optimization and resource management, intelligent monitoring, early warning, and decision support for the entire energy production process are achieved, improving production efficiency and safety while reducing operating costs.

[0025] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating the full-domain data collection and cloud-edge transmission process for intelligent operation based on a large-scale energy production model, as shown in some embodiments of this application. According to embodiments of the present invention, the collection, processing, and cloud-edge collaborative network transmission of multi-source energy production data specifically includes: S21. Collect multi-source energy production data through preset devices, including field equipment data and business system data; S22. Clean, standardize, and compress the multi-source energy production data. S23. Transmit the preprocessed multi-source energy production data to the central node and edge nodes in real time.

[0026] In this process, various types of sensors, such as vibration sensors, temperature sensors, and pressure sensors, are installed on key equipment at energy production sites, including mining equipment, transportation equipment, ventilation equipment, and drainage equipment. These sensors are then integrated with the business systems of the production execution system, safety monitoring system, and equipment management system to build a comprehensive data acquisition network covering all aspects of equipment operation, environmental monitoring, production scheduling, and safety management. The acquisition terminals perform preliminary preprocessing on the acquired heterogeneous data, such as structured, semi-structured, and unstructured data. This includes data cleaning (removing outliers and missing values), data standardization (unifying data formats and units), and data compression (using lightweight compression algorithms to reduce transmission bandwidth usage) to ensure data quality. Relying on the cloud-edge collaborative network built on the industrial internet platform, a "edge-first, cloud-synchronized" transmission strategy is adopted. The preprocessed historical data and batch data used for model training and trend analysis are synchronized to the cloud central node through fragmented transmission and breakpoint resume technology. During transmission, encryption protocols (such as SSL / TLS) are used to ensure data security. At the same time, real-time control data (such as real-time equipment operating parameters and real-time environmental monitoring data) are transmitted to the nearest edge node.

[0027] Please refer to Figure 3 , Figure 3 This is a flowchart illustrating the central model training and cloud development process for intelligent operation based on a large-scale energy production model, as described in some embodiments of this application. According to embodiments of the present invention, the process of processing the multi-source energy production data to obtain a large-scale energy production model, and then training and optimizing it to obtain a lightweight application package, specifically involves: S31. The multi-source energy production data is desensitized, correlated, and stored using a preset model to construct an energy industry database. S32. The data in the constructed energy industry database is processed through a preset learning model to obtain a large energy production model, which is then trained and optimized through a preset algorithm model. S33. Process the large energy production model through a preset application development platform to obtain a lightweight application package.

[0028] The cloud-based central node uses pre-defined models, such as data fusion models, to desensitize (remove sensitive information), correlate (establish relationships between equipment data, environmental data, and business data), and store aggregated multi-source energy production data to build an energy industry database. Then, a pre-defined learning model processes the data in this database, employing transfer learning and incremental learning algorithms for continuous training and optimization. Specifically, this includes initializing model parameters, inputting labeled training data such as equipment failure samples, safety risk samples, and process optimization samples, adjusting model weights through backpropagation, iteratively optimizing model accuracy, and introducing a cross-validation mechanism to ultimately generate... The AI-based large-scale energy production model adapted to energy production scenarios includes equipment fault diagnosis models, safety risk early warning models, and process parameter optimization models. The cloud-based central node provides a visual programming interface and a library of energy-specific functional components, such as equipment monitoring components, early warning push components, and report generation components, through a pre-set application development platform. Through low-code methods such as drag-and-drop and configuration, the system operates equipment health management applications, safety risk early warning applications, and production scheduling optimization applications based on the trained large-scale model. Functional testing, performance testing, and compatibility testing are performed through the platform's built-in testing module. After passing the tests, the application is packaged to obtain a lightweight application package that can be deployed to edge nodes.

[0029] According to an embodiment of the present invention, the process of processing the large-scale energy production model and the lightweight application package to obtain production control command data, executing production regulation, and transmitting the operating data back specifically includes: The large-scale energy production model and lightweight application package are processed for transmission. The energy production big data model and lightweight application package are used to process the real-time collected multi-source energy production data to obtain production control command data. The production control command data is processed to perform on-site production control and the operational data is transmitted back. The operational data includes production control command data, control command execution status data, and abnormal data.

[0030] In this solution, the cloud-based central node transmits the trained energy production model and its packaged lightweight application to the edge nodes at the energy site via a cloud-edge collaborative network. Differential update technology is used during transmission, transmitting only the incremental parts of the model and application. The edge nodes utilize local computing resources, such as edge servers and edge gateways, to perform real-time inference analysis on multi-source energy production data collected in real time, including equipment operation data and environmental monitoring data. This includes equipment operating status assessment, fault and potential hazard identification, environmental risk judgment, and production parameter rationality verification. In this embodiment, the inference latency is controlled within 60ms. Based on the inference analysis results, the edge nodes obtain production control command data and issue these commands to the field execution equipment via an industrial bus or wireless communication module. For example, when an equipment temperature exceeds the limit, a cooling system is automatically triggered; when a gas concentration exceeds the limit, the power to the work area is immediately cut off and ventilation equipment is activated. The edge nodes feed back the production control commands, command execution status, and abnormal data to the cloud-based central node in real time for model iteration and subsequent analysis.

[0031] According to an embodiment of the present invention, the step of processing the operational data to obtain tiered early warning information and decision information, and performing correlation mapping, specifically includes: The operational data is processed by a preset decision-making model to obtain comprehensive evaluation results. The energy production big data model is used to process the comprehensive assessment results and historical data to correct the assessment results and obtain graded early warning information and decision-making information. The hierarchical early warning information and decision-making information are correlated and mapped.

[0032] In this system, the cloud-based central node processes the operational data fed back from the edge nodes using a preset decision model to obtain comprehensive evaluation results. The energy production big data model combines these comprehensive evaluation results with historical data to correct the evaluation results and obtain tiered early warning information and decision suggestions. For example, in this embodiment, standardized operational data is input into the preset decision model, and the equipment health status score is calculated to be 60 points (unqualified) and the environmental safety level score is calculated to be 50 points (unqualified). The comprehensive evaluation result is a level two early warning. Based on the big data model and historical failure cases, it is predicted that the failure may lead to a gas leakage risk, and the early warning level is corrected to a level one early warning. Decision information is generated (shut down the coal mining machine and surrounding equipment, increase ventilation, evacuate workers, and have rescue teams on standby). The tiered early warning information and decision information are correlated and mapped. The intelligent decision module is built through the application development module and linked with the energy business system to achieve the coordinated display of early warning information, video footage, equipment operation data, and control commands. For example, when an early warning is triggered, the video footage of the corresponding area is automatically retrieved, alarm information is pushed to relevant mobile terminals and the monitoring center's large screen, and the corresponding emergency handling process is triggered simultaneously to achieve the linkage of "early warning-judgment-handling".

[0033] According to an embodiment of the present invention, the step of processing the operational data, updating the energy production big data model, dynamically adjusting computing resources, and optimizing data storage and transmission specifically includes: The energy production model is processed by combining the preset algorithm model with the running data to obtain optimized parameter data and update the energy production model. The system collects computing power usage data in real time, processes it through a preset algorithm model, and dynamically adjusts computing power resources. Data on the system's computing power resource utilization efficiency, data transmission, and storage resources are collected and processed according to a preset time period to optimize data storage and transmission.

[0034] The cloud-based central node receives operational data from edge nodes, labels abnormal data, and adds it to the training dataset. It then retrains the large-scale energy production model using pre-defined algorithms, such as incremental learning, to optimize model parameters and improve its adaptability to complex scenarios. An iteration cycle is set based on actual production needs, and the large-scale model is periodically updated to establish a closed-loop optimization mechanism. The system also monitors the real-time utilization of computing resources and dynamically adjusts the allocation ratio of computing resources between the cloud-based central node and edge nodes using pre-defined algorithms, such as load balancing. Finally, it collects system computing resource utilization efficiency data at pre-defined time intervals, such as monthly. The data includes average utilization, peak utilization, and idle rate of computing resources; data transmission-related data, including transmission latency, packet loss rate, and bandwidth utilization; and storage resource-related data, including storage resource utilization, data read / write speed, and redundant data ratio. By comparing the data of this month with historical months, the changes in computing power allocation and data processing are assessed, and performance bottlenecks are identified, such as continuous overload of edge computing power during a certain period or excessively high latency of a certain type of data transmission. A standardized performance analysis report is obtained, which includes data statistical charts, performance evaluation results, and optimization direction suggestions. Adjustments are made to data storage and transmission to optimize data storage and transmission.

[0035] This invention also discloses an intelligent operation system based on a large-scale energy production model, including a memory and a processor. The memory includes an intelligent operation method program based on the large-scale energy production model. When the processor executes the intelligent operation method program based on the large-scale energy production model, it performs the following steps: Collect and process multi-source energy production data and transmit it via a cloud-edge collaborative network. The multi-source energy production data is processed to obtain a large-scale energy production model, which is then trained and optimized to obtain a lightweight application package. The energy production big model and lightweight application package are processed to obtain production control command data, production regulation is executed, and the operation data is transmitted back. The operational data is processed to obtain tiered early warning information and decision-making information, and then correlated and mapped. The operational data is processed to update the large-scale energy production model, dynamically adjust computing resources, and optimize data storage and transmission.

[0036] This process involves collecting and processing multi-source energy production data and transmitting it via a cloud-edge collaborative network. The data is processed to obtain a large-scale energy production model, which is then trained and optimized to generate a lightweight application package. This model and package are then processed to obtain production control command data. Production control is executed, and operational data is fed back. Based on this operational data, tiered early warning and decision-making information is obtained and correlated. The large-scale energy production model is updated, and computing resources are dynamically adjusted and data storage and transmission are optimized. Through comprehensive data collection and cloud-edge transmission, central model training and cloud development, edge intelligent inference and real-time control, intelligent decision-making and early warning with business linkage, and closed-loop measurement optimization and resource management, the system achieves comprehensive collection and efficient transmission of multi-source energy data, precise control of production processes, significantly improved efficiency, and ensures the continuous and stable operation of the system.

[0037] According to an embodiment of the present invention, the process of collecting, processing, and transmitting multi-source energy production data via a cloud-edge collaborative network specifically includes: Collect multi-source data on energy production through pre-set devices, including data from field equipment and business systems; The energy production multi-source data is cleaned, standardized, and compressed preprocessed. The preprocessed multi-source energy production data is transmitted in real time to the central node and edge nodes.

[0038] In this process, various types of sensors, such as vibration sensors, temperature sensors, and pressure sensors, are installed on key equipment at energy production sites, including mining equipment, transportation equipment, ventilation equipment, and drainage equipment. These sensors are then integrated with the business systems of the production execution system, safety monitoring system, and equipment management system to build a comprehensive data acquisition network covering all aspects of equipment operation, environmental monitoring, production scheduling, and safety management. The acquisition terminals perform preliminary preprocessing on the acquired heterogeneous data, such as structured, semi-structured, and unstructured data. This includes data cleaning (removing outliers and missing values), data standardization (unifying data formats and units), and data compression (using lightweight compression algorithms to reduce transmission bandwidth usage) to ensure data quality. Relying on the cloud-edge collaborative network built on the industrial internet platform, a "edge-first, cloud-synchronized" transmission strategy is adopted. The preprocessed historical data and batch data used for model training and trend analysis are synchronized to the cloud central node through fragmented transmission and breakpoint resume technology. During transmission, encryption protocols (such as SSL / TLS) are used to ensure data security. At the same time, real-time control data (such as real-time equipment operating parameters and real-time environmental monitoring data) are transmitted to the nearest edge node.

[0039] According to an embodiment of the present invention, the process of processing the multi-source energy production data to obtain a large-scale energy production model and then training and optimizing it to obtain a lightweight application package specifically includes: An energy industry database is constructed by desensitizing, associating, and storing the multi-source energy production data through a preset model. The data in the constructed energy industry database is processed by a preset learning model to obtain a large energy production model, which is then trained and optimized using a preset algorithm model. The energy production model is processed through a pre-defined application development platform to obtain a lightweight application package.

[0040] The cloud-based central node uses pre-defined models, such as data fusion models, to desensitize (remove sensitive information), correlate (establish relationships between equipment data, environmental data, and business data), and store aggregated multi-source energy production data to build an energy industry database. Then, a pre-defined learning model processes the data in this database, employing transfer learning and incremental learning algorithms for continuous training and optimization. Specifically, this includes initializing model parameters, inputting labeled training data such as equipment failure samples, safety risk samples, and process optimization samples, adjusting model weights through backpropagation, iteratively optimizing model accuracy, and introducing a cross-validation mechanism to ultimately generate... The AI-based large-scale energy production model adapted to energy production scenarios includes equipment fault diagnosis models, safety risk early warning models, and process parameter optimization models. The cloud-based central node provides a visual programming interface and a library of energy-specific functional components, such as equipment monitoring components, early warning push components, and report generation components, through a pre-set application development platform. Through low-code methods such as drag-and-drop and configuration, the system operates equipment health management applications, safety risk early warning applications, and production scheduling optimization applications based on the trained large-scale model. Functional testing, performance testing, and compatibility testing are performed through the platform's built-in testing module. After passing the tests, the application is packaged to obtain a lightweight application package that can be deployed to edge nodes.

[0041] According to an embodiment of the present invention, the process of processing the large-scale energy production model and the lightweight application package to obtain production control command data, executing production regulation, and transmitting the operating data back specifically includes: The large-scale energy production model and lightweight application package are processed for transmission. The energy production big data model and lightweight application package are used to process the real-time collected multi-source energy production data to obtain production control command data. The production control command data is processed to perform on-site production control and the operational data is transmitted back. The operational data includes production control command data, control command execution status data, and abnormal data.

[0042] In this solution, the cloud-based central node transmits the trained energy production model and its packaged lightweight application to the edge nodes at the energy site via a cloud-edge collaborative network. Differential update technology is used during transmission, transmitting only the incremental parts of the model and application. The edge nodes utilize local computing resources, such as edge servers and edge gateways, to perform real-time inference analysis on multi-source energy production data collected in real time, including equipment operation data and environmental monitoring data. This includes equipment operating status assessment, fault and potential hazard identification, environmental risk judgment, and production parameter rationality verification. In this embodiment, the inference latency is controlled within 60ms. Based on the inference analysis results, the edge nodes obtain production control command data and issue these commands to the field execution equipment via an industrial bus or wireless communication module. For example, when an equipment temperature exceeds the limit, a cooling system is automatically triggered; when a gas concentration exceeds the limit, the power to the work area is immediately cut off and ventilation equipment is activated. The edge nodes feed back the production control commands, command execution status, and abnormal data to the cloud-based central node in real time for model iteration and subsequent analysis.

[0043] According to an embodiment of the present invention, the step of processing the operational data to obtain tiered early warning information and decision information, and performing correlation mapping, specifically includes: The operational data is processed by a preset decision-making model to obtain comprehensive evaluation results. The energy production big data model is used to process the comprehensive assessment results and historical data to correct the assessment results and obtain graded early warning information and decision-making information. The hierarchical early warning information and decision-making information are correlated and mapped.

[0044] In this system, the cloud-based central node processes the operational data fed back from the edge nodes using a preset decision model to obtain comprehensive evaluation results. The energy production big data model combines these comprehensive evaluation results with historical data to correct the evaluation results and obtain tiered early warning information and decision suggestions. For example, in this embodiment, standardized operational data is input into the preset decision model, and the equipment health status score is calculated to be 60 points (unqualified) and the environmental safety level score is calculated to be 50 points (unqualified). The comprehensive evaluation result is a level two early warning. Based on the big data model and historical failure cases, it is predicted that the failure may lead to a gas leakage risk, and the early warning level is corrected to a level one early warning. Decision information is generated (shut down the coal mining machine and surrounding equipment, increase ventilation, evacuate workers, and have rescue teams on standby). The tiered early warning information and decision information are correlated and mapped. The intelligent decision module is built through the application development module and linked with the energy business system to achieve the coordinated display of early warning information, video footage, equipment operation data, and control commands. For example, when an early warning is triggered, the video footage of the corresponding area is automatically retrieved, alarm information is pushed to relevant mobile terminals and the monitoring center's large screen, and the corresponding emergency handling process is triggered simultaneously to achieve the linkage of "early warning-judgment-handling".

[0045] According to an embodiment of the present invention, the step of processing the operational data, updating the energy production big data model, dynamically adjusting computing resources, and optimizing data storage and transmission specifically includes: The energy production model is processed by combining the preset algorithm model with the running data to obtain optimized parameter data and update the energy production model. The system collects computing power usage data in real time, processes it through a preset algorithm model, and dynamically adjusts computing power resources. Data on the system's computing power resource utilization efficiency, data transmission, and storage resources are collected and processed according to a preset time period to optimize data storage and transmission.

[0046] The cloud-based central node receives operational data from edge nodes, labels abnormal data, and adds it to the training dataset. It then retrains the large-scale energy production model using pre-defined algorithms, such as incremental learning, to optimize model parameters and improve its adaptability to complex scenarios. An iteration cycle is set based on actual production needs, and the large-scale model is periodically updated to establish a closed-loop optimization mechanism. The system also monitors the real-time utilization of computing resources and dynamically adjusts the allocation ratio of computing resources between the cloud-based central node and edge nodes using pre-defined algorithms, such as load balancing. Finally, it collects system computing resource utilization efficiency data at pre-defined time intervals, such as monthly. The data includes average utilization, peak utilization, and idle rate of computing resources; data transmission-related data, including transmission latency, packet loss rate, and bandwidth utilization; and storage resource-related data, including storage resource utilization, data read / write speed, and redundant data ratio. By comparing the data of this month with historical months, the changes in computing power allocation and data processing are assessed, and performance bottlenecks are identified, such as continuous overload of edge computing power during a certain period or excessively high latency of a certain type of data transmission. A standardized performance analysis report is obtained, which includes data statistical charts, performance evaluation results, and optimization direction suggestions. Adjustments are made to data storage and transmission to optimize data storage and transmission.

[0047] A third aspect of the present invention provides a readable storage medium comprising a program for an intelligent operation method based on a large-scale energy production model, wherein when the program is executed by a processor, it implements the steps of the intelligent operation method based on the large-scale energy production model as described in any of the preceding claims.

[0048] This invention discloses an intelligent operation method, system, and readable storage medium based on a large-scale energy production model. By collecting and processing multi-source energy production data and transmitting it via cloud-edge collaboration, a large-scale energy production model is obtained, trained, and optimized to generate an application package. The large-scale energy production model and application package are then processed to obtain control command data. Production regulation is executed, and operational data is transmitted back. Based on the operational data, tiered early warning and decision information are obtained and mapped. The large-scale energy production model is updated based on the operational data, and computing resources are dynamically adjusted and data storage and transmission are optimized. Through comprehensive data collection and cloud-edge transmission, central model training and cloud development, edge intelligent inference and real-time control, intelligent decision-making and early warning with business linkage, and closed-loop measurement optimization and resource management, intelligent monitoring, early warning, and decision support for the entire energy production process are achieved, improving production efficiency and safety while reducing operating costs.

[0049] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0050] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0051] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0052] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0053] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

Claims

1. A smart operation method based on a large-scale energy production model, characterized in that: Includes the following steps: Collect and process multi-source energy production data and transmit it via a cloud-edge collaborative network. The multi-source energy production data is processed to obtain a large-scale energy production model, which is then trained and optimized to obtain a lightweight application package. The energy production big model and lightweight application package are processed to obtain production control command data, production regulation is executed, and the operation data is transmitted back. The operational data is processed to obtain tiered early warning information and decision-making information, and then correlated and mapped. The operational data is processed to update the large-scale energy production model, dynamically adjust computing resources, and optimize data storage and transmission.

2. The intelligent operation method based on a large-scale energy production model according to claim 1, characterized in that, The process of collecting, processing, and transmitting multi-source energy production data via a cloud-edge collaborative network includes: Collect multi-source data on energy production through pre-set devices, including data from field equipment and business systems; The energy production multi-source data is cleaned, standardized, and compressed preprocessed. The preprocessed multi-source energy production data is transmitted in real time to the central node and edge nodes.

3. The intelligent operation method based on a large-scale energy production model according to claim 2, characterized in that, The process of processing the multi-source energy production data to obtain a large-scale energy production model, and then training and optimizing it to obtain a lightweight application package, includes: An energy industry database is constructed by desensitizing, associating, and storing the multi-source energy production data through a preset model. The data in the constructed energy industry database is processed by a preset learning model to obtain a large energy production model, which is then trained and optimized using a preset algorithm model. The energy production model is processed through a pre-defined application development platform to obtain a lightweight application package.

4. The intelligent operation method based on a large-scale energy production model according to claim 1, characterized in that, The process of processing the large-scale energy production model and lightweight application package to obtain production control command data, executing production regulation, and transmitting the operating data back includes: The large-scale energy production model and lightweight application package are processed for transmission. The energy production big data model and lightweight application package are used to process the real-time collected multi-source energy production data to obtain production control command data. The production control command data is processed to perform on-site production control and the operational data is transmitted back. The operational data includes production control command data, control command execution status data, and abnormal data.

5. The intelligent operation method based on a large-scale energy production model according to claim 1, characterized in that, The step of processing the operational data to obtain tiered early warning information and decision information, and performing correlation mapping, includes: The operational data is processed by a preset decision-making model to obtain comprehensive evaluation results. The energy production big data model is used to process the comprehensive assessment results and historical data to correct the assessment results and obtain graded early warning information and decision-making information. The hierarchical early warning information and decision-making information are correlated and mapped.

6. The intelligent operation method based on a large-scale energy production model according to claim 1, characterized in that, The process of processing the operational data, updating the large-scale energy production model, dynamically adjusting computing resources, and optimizing data storage and transmission includes: The energy production model is processed by combining the preset algorithm model with the running data to obtain optimized parameter data and update the energy production model. The system collects computing power usage data in real time, processes it through a preset algorithm model, and dynamically adjusts computing power resources. Data on the system's computing power resource utilization efficiency, data transmission, and storage resources are collected and processed according to a preset time period to optimize data storage and transmission.

7. An intelligent operation system based on a large-scale energy production model, characterized in that: The system includes a memory and a processor. The memory contains a program for an intelligent operation method based on a large-scale energy production model. When the processor executes the program for the intelligent operation method based on the large-scale energy production model, it performs the following steps: Collect and process multi-source energy production data and transmit it via a cloud-edge collaborative network. The multi-source energy production data is processed to obtain a large-scale energy production model, which is then trained and optimized to obtain a lightweight application package. The energy production big model and lightweight application package are processed to obtain production control command data, production regulation is executed, and the operation data is transmitted back. The operational data is processed to obtain tiered early warning information and decision-making information, and then correlated and mapped. The operational data is processed to update the large-scale energy production model, dynamically adjust computing resources, and optimize data storage and transmission.

8. The intelligent operation system based on a large-scale energy production model according to claim 7, characterized in that, The process of collecting, processing, and transmitting multi-source energy production data via a cloud-edge collaborative network includes: Collect multi-source data on energy production through pre-set devices, including data from field equipment and business systems; The energy production multi-source data is cleaned, standardized, and compressed preprocessed. The preprocessed multi-source energy production data is transmitted in real time to the central node and edge nodes.

9. The intelligent operation system based on a large-scale energy production model according to claim 8, characterized in that, The process of processing the multi-source energy production data to obtain a large-scale energy production model, and then training and optimizing it to obtain a lightweight application package, includes: An energy industry database is constructed by desensitizing, associating, and storing the multi-source energy production data through a preset model. The data in the constructed energy industry database is processed by a preset learning model to obtain a large energy production model, which is then trained and optimized using a preset algorithm model. The energy production model is processed through a pre-defined application development platform to obtain a lightweight application package.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a smart operation method program based on a large-scale energy production model. When the smart operation method program based on the large-scale energy production model is executed by a processor, it implements the steps of the smart operation method based on the large-scale energy production model as described in any one of claims 1 to 6.

Images