Risk control identification method based on artificial intelligence technology

Abstract

The invention provides a risk control identification method based on an artificial intelligence technology, and belongs to the field of safety production. The method includes identifying risks that may be encountered during the operation process, including personnel, equipment, materials, methods, environments, and management; carrying out quantitative evaluation on the identified risk factors, and determining the possibility and severity of the identified risk factors; constructing a risk database containing a plurality of risk factors based on a risk identification and evaluation result; corresponding prevention and control measures are made for risk factors in the risk library; the risk is dynamically evaluated by monitoring the change of the working environment and condition in real time, and early warning is given out and countermeasures are taken in time when necessary; optimizing a project management process according to a risk assessment and control result; and continuously updating and perfecting the risk library to adapt to the change of the working environment and condition. According to the method, the risk management and control of the whole operation process can be realized, the risk prevention capability is greatly improved, and the high efficiency and safety of the production process are ensured.

Description

Technical Field

[0001] The present invention relates to the field of safe production technology, and in particular to a risk control identification method based on artificial intelligence technology. Background Art

[0002] The digital and intelligent transformation of power systems has been an important development trend in the power industry in recent years. From the initial manual operation to automation and informatization, to the current digitalization and intelligence, every technological upgrade of the power system has greatly improved production efficiency and reduced safety risks.

[0003] In the existing power production process, production safety is becoming more and more important. On the one hand, more and more laws and regulations have made provisions for law-based public security, requiring the implementation of more stringent and standardized safety production standards. In the face of new situations and new requirements, it is necessary to promote law-based public security and ensure that safety production management and behavior comply with the law. On the other hand, the existing production site operation risk control capabilities are not strong, the on-site operation safety level is not high, and the production site operation risk control system is not sound. It is impossible to strengthen source prevention and hierarchical control, and it is difficult to effectively improve the level of production site operation risk control. At the same time, there are difficulties in platform application deployment and data access, making it difficult to further improve risk control measures. Summary of the invention

[0004] The purpose of the present invention is to provide a risk control identification method based on artificial intelligence technology, which can realize risk control of the entire operation process, greatly improve the risk prevention capability, and ensure the efficiency and safety of the production process.

[0005] In order to achieve the above object, the present invention provides a risk control identification method based on artificial intelligence technology, the method comprising:

[0006] Identify the risks that may be encountered during the operation, including personnel, equipment, materials, methods, environment and management;

[0007] Quantitatively assess the identified risk factors to determine their likelihood and severity;

[0008] Build a risk database containing various risk factors based on the results of risk identification and assessment;

[0009] Formulate corresponding prevention and control measures for the risk factors in the risk database;

[0010] By monitoring the changes in the working environment and conditions in real time, we can dynamically assess the risks, issue early warnings and take timely response measures when necessary;

[0011] Optimize project management processes based on the results of risk assessment and control;

[0012] The risk library is continuously updated and improved to adapt to changes in the operating environment and conditions.

[0013] Preferably, the risks that may be encountered during the identification operation include:

[0014] Construct risk prediction models based on artificial intelligence machine learning technology, including deep learning algorithms, integrated learning using neural network integration technology, stacking models in deep learning, using feature engineering technology to build multidimensional risk factor indicator groups, big data analysis, and using data mining technology to discover hidden patterns or relationships in the data.

[0015] Preferably, the quantitative assessment of the identified risk factors includes:

[0016] Integrate the risk prediction model into the operation risk control card application, carry out safety risk assessment and analysis of substation maintenance, transmission line maintenance, and distribution maintenance production operations, combine the typical risk database of transmission, transformation, and distribution operations and the whole process control links as well as the safety management requirements of the whole process from planning to archiving of data at the end of work.

[0017] Preferably, a risk database containing multiple risk factors is constructed based on the results of risk identification and assessment, including:

[0018] Collect relevant data from the typical risk database and typical violation database of transmission, transformation and distribution operations, clean and organize the data, extract key features, build a data set for operation risk identification, and use the collected data set to pre-train or fine-tune the large safety supervision model.

[0019] Preferably, after the operation plan is generated, the system synchronously generates an operation risk control card, based on the plan content information, collects data from each stage in real time during the operation, and inputs the data into the trained model for risk identification. Based on the output results of the model, it determines whether there is a risk in the current operation and gives corresponding warning information.

[0020] Preferably, when the large model identifies a risk, similar risk cases are searched from the typical risk library to analyze the possible causes and consequences of the current risk. At the same time, the records in the typical violation library are compared to check whether there are any violations in the current operation, or whether there are any violation features in the current operation that need to be checked, and whether the violation may lead to risks.

[0021] Preferably, the risk control card is used to integrate data, processes, and interfaces with the digital work ticket, and the automatic flow of each link of the risk control card is promoted through intelligent verification of business data, assisting management personnel, on-the-job personnel, safety inspectors, and front-line operators to control risks throughout the entire operation process.

[0022] Preferably, use risk control cards for pre-emptive prevention, including plan preparation, release and receipt; use risk control cards for in-process management, including job preparation and job implementation; use risk control cards for post-event improvement, including job evaluation and improvement.

[0023] According to the above technical scheme, the present invention designs a fusion scheme of multi-professional operation risk control cards and risk control cards-digital work tickets-risk management and control platforms. Through the demonstration application of operation risk control cards, the risk management of the entire production operation process is improved, and risks are controllable and safety hazards are eliminated.

[0024] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0026] Figure 1 It is the business process diagram of the risk control card;

[0027] Figure 2 It is a schematic diagram of the business process and data sources of the risk control card;

[0028] Figure 3 It is a schematic diagram of the verification process. DETAILED DESCRIPTION

[0029] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0030] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0031] See also Figures 1 to 3 The present invention provides a risk control identification method based on artificial intelligence technology. The method includes designing multi-professional operation risk control cards for substation maintenance, transmission line maintenance, and distribution maintenance, combining risk prediction models to carry out safety risk assessment and analysis of substation maintenance, transmission line maintenance, and distribution maintenance production operations, and building a typical risk library for transmission, transformation, and distribution operations. The specific steps include:

[0032] Step 1: Identify risks. Identify the risks that may be encountered during the operation, including personnel, equipment, materials, methods, environment and management;

[0033] Step 2: Assess risk, conduct quantitative assessment of identified risk factors and determine their likelihood and severity;

[0034] Step 3: Build a risk database, based on the results of risk identification and assessment, to build a risk database containing multiple risk factors;

[0035] Step 4: Develop risk control measures and formulate corresponding prevention and control measures for the risk factors in the risk database;

[0036] Step 5: Risk monitoring and early warning: through real-time monitoring of changes in the operating environment and conditions, dynamic assessment of risks is carried out, and early warning is issued when necessary so that timely response measures can be taken;

[0037] Step 6: Optimize the risk management process and optimize the project management process based on the results of risk assessment and control;

[0038] Step 7: Continuously improve and constantly update and improve the risk library to adapt to changes in the operating environment and conditions.

[0039] In this embodiment, artificial intelligence machine learning technology is used to construct an operation risk prediction model, including the use of deep learning algorithms (such as convolutional neural networks CNN, recurrent neural networks RNN), neural network integration technology (such as integrated learning, stacking models in deep learning, etc.), feature engineering technology (used to build multidimensional risk factor indicator groups) and big data analysis technology. In addition, data mining technology may also be involved to discover hidden patterns or relationships in the data. The multidimensional risk factor indicator group and the operation risk prediction model are constructed. The overall solution consists of two parts of prediction capabilities, real-time monitoring and query of the risk verification of the operation link, and the short-term risk prediction model is supported by the multidimensional risk matrix of the production operation and the multidimensional risk factor dynamic time series model to predict the risks that may occur in the subsequent links. In addition, based on the historical operation violations and risk identification of the same type, the prone risks of the current operation are predicted.

[0040] In this embodiment, the risk prediction model constructed above is integrated into the operation risk control card application to carry out safety risk assessment and analysis of substation maintenance, transmission line maintenance, and distribution maintenance production operations. Combined with the typical risk library of transmission, transformation, and distribution operations and the whole process control links, the safety management requirements of the whole process from planning to archiving of data at the end of work are fully considered.

[0041] Among them, the focus is on collecting relevant data from the typical risk database and typical violation database of transmission, transformation and distribution operations, including historical risk events, violation records, operating procedures and safety regulations, and cleaning and organizing the data, extracting key features, and building a data set for operational risk identification. The collected data set is used to pre-train or fine-tune the large safety supervision model to improve its accuracy in identifying key patterns and features in operational risks.

[0042] In this embodiment, after the operation plan is generated, the system synchronously generates an operation risk control card, based on the plan content information, and collects data from each stage in real time during the operation process, including load-bearing capacity analysis, on-site investigation, plan compilation and approval, work ticket preparation, safety measures arrangement and environmental conditions; and inputs the data into the trained model for risk identification, and judges whether there is a risk in the current operation based on the output results of the model and gives corresponding early warning information.

[0043] When the big model identifies a risk, it searches for similar risk cases in the typical risk library and analyzes the possible causes and consequences of the current risk. At the same time, it compares the records in the typical violation library to check whether there are any violations in the current operation, or whether there are any violation features in the current operation that need to be checked, and whether the violation may lead to risks.

[0044] In addition, in this implementation, the risk control card takes the operation plan as the starting point and runs through the entire operation process. It is integrated with the digital work ticket data, process integration, and interface integration. Through intelligent verification of business data, it promotes the automatic flow of each link of the risk control card, assisting management personnel, on-the-job personnel, safety inspectors and front-line operators to control the risks of the entire operation process; at the same time, it implements the supervision of the performance of personnel in each link, gradually realizes the automatic evaluation of personnel performance, and promotes the transformation of operation management to the "pre-prevention, in-process control, and post-event improvement" mode.

[0045] Specifically, the pre-prevention in the above-mentioned risk control card includes plan preparation, namely plan compilation, release and receipt; in-process control includes operation preparation and operation implementation, among which operation preparation includes on-site inspection, risk assessment, carrying capacity analysis, plan, execution card preparation and approval, supplementary inspection, two-level pre-shift meetings and work ticket preparation; operation implementation includes pre-operation inspection, permission to start work, station shift meeting briefing, operation execution risk and work completion; post-event improvement includes operation evaluation and improvement improvement, among which operation evaluation is problem assessment and improvement improvement is rectification improvement.

[0046] In this embodiment, the risk assessment in job preparation includes a typical risk library, risk classification and risk publicity; the approval of plans and execution cards includes the qualification review of registered personnel of the "people, machines, objects and materials" matching job team; the two-level pre-shift meetings include the work area-level pre-shift meetings and the team-level pre-shift meetings; the job execution risks in job implementation include personal risks, power grid risks, equipment risks and network risks; the termination of work includes the restoration of measures of "work completed, materials cleaned and site cleared" and completion acceptance; the problem assessment in job evaluation includes the work summary and evaluation of risk control implementation after the class meeting; the rectification and improvement in improvement and improvement include improving documents, rules and regulations for evaluation, and improving processes.

[0047] In summary, in combination with the risk prediction model, the safety risk assessment and analysis of substation maintenance, transmission line maintenance, and distribution maintenance production operations are carried out, the typical risk library of transmission, transformation, and distribution operations is studied, and the risk control card design of multiple professions is carried out. The safety management requirements of the whole process from planning to the end of work are fully considered. The relationship between risk and different professions and different operation contents is studied, and how to combine artificial intelligence natural language processing technology to analyze the direct relationship between operation content and risk, for personal, equipment, power grid and other risks, combined with the professional management requirements and typical risk library, a set of operation risk control cards is designed on the basis of exploring the integration of risk control and professional operation business, studying the integration method of risk control card with risk control platform and digital work ticket application, and designing the integration solution of operation risk control business application. Break through the application boundaries between different professions, call each other within the system platform, and study the interface integration and data fusion technology between applications. In addition, in view of the characteristics of wide data sources and diverse data structures in the risk control link, the automatic extraction of link data and the analysis and verification method of link data management requirements are studied, and a set of digital application of operation risk control cards is designed. At the same time, explore the digital application of operation risk control cards and the deployment combined with existing application platforms, cross-application function call technology and cross-professional and cross-system data integration access technology. Combined with the actual personnel situation, equipment level, environmental characteristics, management and other related influencing factors, explore the practical application of risk evolution spatiotemporal transmission mechanism and risk prediction model, and provide scientific and technological support for local production operation risk prediction. Test whether the risk assessment and risk identification are accurate, and adjust and optimize the risk identification and early warning methods according to the demonstration application. Finally, through the application of operation risk control cards, for major risks in substation maintenance, transmission line maintenance, and distribution maintenance operations, through the application of artificial intelligence semantic understanding technology and risk factor prediction models, the risks of electric shock, high fall, equipment, power grid, etc. are predicted, and the high-incidence risk identification and early warning methods are used to control risks and eliminate safety hazards. According to the pilot demonstration application, design risk control and improvement measures for the entire operation process for the application unit, realize the verification and optimization of the method content, and form a complete closed loop as a whole.

[0048] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0049] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0050] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0051] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0052] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0053] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0054] Computer readable media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0055] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0056] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A risk control identification method based on artificial intelligence technology, characterized in that: The method comprises: Identify the risks that may be encountered during the operation, including personnel, equipment, materials, methods, environment and management; Quantitatively assess the identified risk factors to determine their likelihood and severity; Build a risk database containing various risk factors based on the results of risk identification and assessment; Formulate corresponding prevention and control measures for the risk factors in the risk database; By monitoring the changes in the working environment and conditions in real time, we can dynamically assess the risks, issue early warnings and take timely response measures when necessary; Optimize project management processes based on the results of risk assessment and control; The risk library is continuously updated and improved to adapt to changes in the operating environment and conditions.

2. The risk control identification method based on artificial intelligence technology according to claim 1 is characterized in that: Identify the risks that may be encountered during the operation, including: Construct risk prediction models based on artificial intelligence machine learning technology, including deep learning algorithms, integrated learning using neural network integration technology, stacking models in deep learning, using feature engineering technology to build multidimensional risk factor indicator groups, big data analysis, and using data mining technology to discover hidden patterns or relationships in the data.

3. The risk control identification method based on artificial intelligence technology according to claim 2 is characterized in that: Quantitative assessment of identified risk factors includes: Integrate the risk prediction model into the operation risk control card application, carry out safety risk assessment and analysis of substation maintenance, transmission line maintenance, and distribution maintenance production operations, combine the typical risk database of transmission, transformation, and distribution operations and the whole process control links as well as the safety management requirements of the whole process from planning to archiving of data at the end of work.

4. The risk control identification method based on artificial intelligence technology according to claim 3 is characterized in that: Based on the results of risk identification and assessment, a risk database containing various risk factors is constructed, including: Collect relevant data from the typical risk database and typical violation database of transmission, transformation and distribution operations, clean and organize the data, extract key features, build a data set for operation risk identification, and use the collected data set to pre-train or fine-tune the large safety supervision model.

5. The risk control identification method based on artificial intelligence technology according to claim 4 is characterized in that: After the operation plan is generated, the system will simultaneously generate an operation risk control card. Based on the plan content information, it will collect data from each stage in real time during the operation process, and input the data into the trained model for risk identification. Based on the output results of the model, it will determine whether there is a risk in the current operation and give corresponding early warning information.

6. The risk control identification method based on artificial intelligence technology according to claim 5 is characterized in that: When the big model identifies a risk, it searches for similar risk cases in the typical risk library and analyzes the possible causes and consequences of the current risk. At the same time, it compares the records in the typical violation library to check whether there are any violations in the current operation, or whether there are any violation features in the current operation that need to be checked, and whether the violation may lead to risks.

7. The risk control identification method based on artificial intelligence technology according to claim 5 or 6, characterized in that: Use risk control cards to integrate data, processes, and interfaces with digital work tickets, and promote automatic circulation of each link of the risk control card through intelligent verification of business data, to assist management personnel, on-the-job personnel, safety inspectors, and front-line operators in risk control of the entire operation process.

8. The risk control identification method based on artificial intelligence technology according to claim 7 is characterized in that: Use risk control cards for pre-emptive prevention, including plan preparation, release and receipt; use risk control cards for in-process management, including job preparation and implementation; use risk control cards for post-event improvement, including job evaluation and improvement.

Images