Danger source identification and control method and device based on LECD method

Abstract

The invention belongs to the technical field of nuclear power, and particularly relates to a hazard source identification and control method and device based on an LECD method. The LECD risk assessment method is combined with the AI technology and the map technology, the color codes are introduced to display the risk level, a large amount of data can be automatically processed and analyzed, and manual intervention is not needed. Therefore, the processing efficiency and speed are greatly improved, the demand of human resources is reduced, and the time of manual processing and decision making is shortened. Risk grades are distinguished by colors, and the sensitivity and identification degree of color vision are utilized to help a user to quickly understand risk grade information of the hazard source, so that effective hazard source management is facilitated.

Description

Technical Field

[0001] The present invention belongs to the technical field of nuclear power, and particularly relates to a method and device for identifying and controlling hazard sources based on the LECD method. Background Art

[0002] With the development of society and the acceleration of the industrialization process, the number and scope of influence of various hazard sources have increased rapidly, causing more and more serious impacts on people's work and life. To effectively control these hazard sources and reduce the occurrence of personnel casualty accidents, it is necessary to identify and control hazard sources. In related technologies, hazard sources are mainly identified and controlled by personnel, which has a relatively high risk of human error and poses a hidden danger to nuclear power production. Therefore, there is an urgent need for a perfect method for identifying and managing hazard sources with better data visualization capabilities. Summary of the Invention

[0003] To overcome the problems existing in related technologies, a method and device for identifying and controlling hazard sources based on the LECD method are provided.

[0004] According to one aspect of the embodiments of the present disclosure, a method for identifying and controlling hazard sources based on the LECD method is provided. The method includes:

[0005] Step 11, collecting hazard source data: Collecting hazard source data for describing hazard sources, where the hazard source data includes the site, equipment, and personnel;

[0006] Step 12, preprocessing the hazard source data: Preprocessing the collected hazard source data to obtain preprocessed data, and the preprocessing includes text cleaning, word segmentation, and removing stop words;

[0007] Step 13, feature extraction: Extracting features from the preprocessed data for quantifying relevant attributes of the hazard source, where the features include accident type, loss degree, occurrence frequency, and potential impact;

[0008] Step 14, training the model: As Figure 2 shown, according to the LECD scoring system, using machine learning or deep learning algorithms to construct a model, the model includes the possibility of an accident occurring, the frequency of personnel being exposed to a dangerous environment, the consequences that an accident may cause, and the risk. For the preprocessed data, deep learning training is performed in combination with the LECD scoring standard to obtain a trained model;

[0009] Step 15, model evaluation and optimization: Evaluating the trained model using a test data set and optimizing the model according to the evaluation results;

[0010] Step 16, Automatic quantification and grading: Input the new hazard source data into the trained model, obtain the corresponding risk value through prediction, and assign the risk level corresponding to the risk value to the new hazard source data with this risk value.

[0011] In a possible implementation manner, the method of the present disclosure further includes:

[0012] Step 21, Perform color coding on the identified hazard sources. Different colors correspond to different hazard source levels. High risk corresponds to red, medium-high risk corresponds to orange, medium risk corresponds to blue, and low risk corresponds to green;

[0013] Step 22, Perform full-scale grid processing on the digital map of the nuclear power plant, establish an association relationship between the hazard sources and the map grids, and display each grid in the color of the hazard source level associated with the grid. Clicking on the grid can display the hazard source information associated with the grid.

[0014] According to another aspect of the embodiments of the present disclosure, there is provided a hazard source identification and control device based on the LECD method. The device includes:

[0015] A collection module, used for collecting hazard source data: Collect hazard source data used to describe hazard sources. The hazard source data includes the site, equipment, and personnel;

[0016] A preprocessing module, used for preprocessing hazard source data: Preprocess the collected hazard source data to obtain preprocessed data. The preprocessing includes text cleaning, word segmentation, and stop word removal;

[0017] An extraction module, used for feature extraction, extract features from the preprocessed data for quantifying relevant attributes of the hazard sources. The features include accident type, loss degree, occurrence frequency, and potential impact;

[0018] A construction module, used for training the model: As Figure 2 shown, according to the LECD scoring system, use machine learning or deep learning algorithms to construct a model. The model includes the possibility of an accident occurring, the frequency of personnel being exposed to the hazardous environment, the consequences that the accident may cause, and the risk. For the preprocessed data, perform deep learning training in combination with the LECD scoring standard to obtain a trained model;

[0019] An optimization module, used for model evaluation and optimization: Evaluate the trained model using the test data set, and optimize the model according to the evaluation results;

[0020] A grading module, used for automatic quantification and grading: Input the new hazard source data into the trained model, obtain the corresponding risk value through prediction, and assign the risk level corresponding to the risk value to the new hazard source data with this risk value.

[0021] In a possible implementation, the device of the present disclosure further includes:

[0022] An identification module, configured to perform color coding on the identified hazard sources, where different colors correspond to different hazard source levels, high risk corresponds to red, medium-high risk corresponds to orange, medium risk corresponds to blue, and low risk corresponds to green;

[0023] A display and interaction module, configured to perform full-scale grid processing on the digital map of the nuclear power plant, establish an association relationship between the hazard sources and the map grids, and each grid is displayed in the color of the hazard source level associated with the grid. Clicking on the grid can display the hazard source information associated with the grid.

[0024] According to another aspect of the embodiments of the present disclosure, there is provided a hazard source identification and control device based on the LECD method, where the device includes:

[0025] A processor;

[0026] A memory for storing instructions executable by the processor;

[0027] Wherein, the processor is configured to execute the above method.

[0028] According to another aspect of the embodiments of the present disclosure, there is provided a non-volatile computer-readable storage medium, on which computer program instructions are stored, and when the computer program instructions are executed by a processor, the above method is implemented.

[0029] The beneficial effects of the present disclosure are as follows: The present disclosure combines the LECD risk assessment method with AI technology and map technology, and introduces color coding to display the risk level, having the following advantages:

[0030] 1. Automation: AI technology can automatically process a large amount of data and perform analysis without manual intervention. This greatly improves the processing efficiency and speed, and reduces the demand for human resources;

[0031] 2. High efficiency: AI technology can quickly evaluate and grade hazard sources, reducing the time for manual processing and decision-making. This is particularly useful for large-scale data sets or situations that require real-time processing;

[0032] 3. Accuracy: Using an AI model for automatic quantitative grading can reduce the interference of subjective factors and improve the objectivity and accuracy of the assessment. The AI model can accurately predict and classify hazard sources based on a large amount of data and training experience;

[0033] 4. Unified standard: Through the LECD risk assessment method, AI technology can assign corresponding levels to different hazard sources, establishing a unified assessment standard. This helps to achieve consistency in risk comparison and risk management in different scenarios and organizations.

[0034] 5. Highly scalable: AI technology has good scalability and can adapt to datasets of different scales and complexities. Whether it is a small organization or a large enterprise, AI technology can be used for automatic quantitative grading to adapt to the changing risk environment;

[0035] 6. Continuous improvement: AI models can be improved through feedback mechanisms and continuous optimization to adapt to new data and situations. With the accumulation of data and the improvement of the models, the accuracy and reliability of automatic quantitative grading will continue to increase.

[0036] 7. Sensitivity: Color is used to distinguish risk levels, leveraging the sensitivity and recognition of color vision to help users quickly understand the risk level information of hazard sources, facilitating effective hazard source management. Description of the Drawings

[0037] Figure 1 is a flowchart of a hazard source identification and control method based on the LECD method shown according to an exemplary embodiment.

[0038] Figure 2 is a schematic diagram of the LECD scoring standard.

[0039] Figure 3 is a block diagram of a hazard source identification and control device based on the LECD method shown according to an exemplary embodiment. Detailed Implementation Manner

[0040] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] Figure 1 is a flowchart of a hazard source identification and control method based on the LECD method shown according to an exemplary embodiment. This method can be executed by a terminal device, where the terminal device can be a server, a desktop computer, a laptop computer, a tablet computer, etc. The terminal device can also be, for example, a user device, a vehicle-mounted device, or a wearable device, etc. The embodiments of the present disclosure do not limit the type of the terminal device. As Figure 1 shown, the method includes:

[0042] Step 11, hazard source data collection: Collect hazard source data used to describe hazard sources. The hazard source data can include the site, equipment, and personnel. The data can be collected and input through on-site investigations, or retrieved from relevant databases through retrieval strategies.

[0043] Step 12, preprocessing of hazard source data: Preprocess the collected hazard source data to obtain preprocessed data. The preprocessing can include, for example, text cleaning, word segmentation, stop word removal, etc. The preprocessed data is used for subsequent analysis and processing.

[0044] Step 13, Feature extraction: Extract features from the preprocessed data for quantifying relevant attributes of the hazard sources. The features may include accident type, loss degree, occurrence frequency, potential impact, etc. These features should be able to reflect the risk level of the hazard sources.

[0045] Step 14, Model training: As Figure 2 shown, according to the LECD scoring system, use machine learning or deep learning algorithms to build a model. The model includes the following features: L (likelihood, the possibility of an accident occurring), E (exposure, the frequency of personnel being exposed to the hazardous environment), C (consequence, the possible consequences once an accident occurs), D (danger, the degree of danger). For the preprocessed data, conduct deep learning training in combination with the LECD scoring criteria to obtain the trained model. The model can adopt classification algorithms such as decision trees, support vector machines (SVMs) or neural networks to predict the value of the danger D based on the features, and automatically identify, evaluate and grade the hazard sources;

[0046] Step 15, Model evaluation and optimization: Use the test data set to evaluate the trained model, and optimize the model according to the evaluation results. Metrics such as cross-validation and confusion matrices can be used to evaluate the accuracy and performance of the model.

[0047] Step 16, Automatic quantification and grading: Input the new hazard source data into the trained model, and obtain the corresponding danger D value through prediction. The AI model will automatically evaluate the danger value of the hazard source based on the input features, and assign the risk level corresponding to the danger value to the new hazard source data. For example, multiple threshold intervals of the danger values can be set, and different threshold intervals correspond to different risk levels.

[0048] In a possible implementation manner, the method of the present disclosure further includes: Hazard source control, which specifically includes the following implementation steps:

[0049] Step 21, Conduct color coding on the identified hazard sources. Different colors correspond to different hazard source levels. For example, high risk corresponds to red, medium-high risk corresponds to orange, medium risk corresponds to blue, and low risk corresponds to green.

[0050] Step 22, Conduct full-scale grid processing on the digital map of the nuclear power plant, and establish an association relationship between the hazard sources and the map grids; visually manage the hazard sources, and each grid is displayed in the color of the hazard source level associated with the grid. Clicking on the grid can display the hazard source information associated with the grid.

[0051] The present disclosure combines the LECD risk assessment method with AI technology and map technology, and introduces color coding to display the risk level, which has the following advantages:

[0052] 1. Automation: AI technology can automatically process and analyze a large amount of data without manual intervention. This greatly improves the processing efficiency and speed, and reduces the demand for human resources;

[0053] 2. High efficiency: AI technology can quickly evaluate and grade hazard sources, reducing the time for manual processing and decision-making. This is particularly useful for large-scale data sets or situations that require real-time processing;

[0054] 3. Accuracy: Using an AI model for automatic quantitative grading can reduce the interference of subjective factors and improve the objectivity and accuracy of the assessment. The AI model can accurately predict and classify hazard sources based on a large amount of data and training experience;

[0055] 4. Unified standard: Through the LECD risk assessment method, AI technology can assign corresponding levels to different hazard sources, establishing a unified assessment standard. This helps to achieve risk comparison and consistency in risk management in different scenarios and organizations.

[0056] 5. High scalability: AI technology has good scalability and can adapt to data sets of different scales and complexities. Whether it is a small organization or a large enterprise, AI technology can be used for automatic quantitative grading to adapt to the changing risk environment;

[0057] 6. Continuous improvement: The AI model can be improved through a feedback mechanism and continuous optimization to adapt to new data and situations. With the accumulation of data and the improvement of the model, the accuracy and reliability of automatic quantitative grading will continue to increase;

[0058] 7. Sensitivity: The risk level is distinguished by colors, and the sensitivity and recognition of color vision are used to help users quickly understand the risk level information of hazard sources, facilitating effective hazard source management.

[0059] According to another aspect of the embodiments of the present disclosure, a hazard source identification and control device based on the LECD method is provided. The device includes:

[0060] A collection module for collecting hazard source data: collecting hazard source data used to describe hazard sources, where the hazard source data includes the site, equipment, and personnel;

[0061] A preprocessing module for preprocessing hazard source data: preprocessing the collected hazard source data to obtain preprocessed data, and the preprocessing includes text cleaning, word segmentation, and stop word removal;

[0062] An extraction module, used for feature extraction, extracts features from the preprocessed data to quantify the relevant attributes of the hazard sources. The features include accident type, loss degree, occurrence frequency, and potential impact;

[0063] A construction module, used for training a model: As Figure 2 shown, according to the LECD scoring system, use machine learning or deep learning algorithms to construct a model. The model includes the possibility of an accident occurring, the frequency of personnel being exposed to the hazardous environment, the consequences that the accident may cause, and the hazard. For the preprocessed data, perform deep learning training in combination with the LECD scoring criteria to obtain the trained model;

[0064] An optimization module, used for model evaluation and optimization: Use the test data set to evaluate the trained model and optimize the model according to the evaluation results;

[0065] A grading module, used for automatic quantification and grading: Input the new hazard source data into the trained model, obtain the corresponding hazard value through prediction, and use this hazard value as the risk level corresponding to the new hazard source data to assign the risk level corresponding to this hazard value.

[0066] In a possible implementation manner, the device of the present disclosure further includes:

[0067] An identification module, used for color coding the identified hazard sources. Different colors correspond to different hazard source levels. High risk corresponds to red, medium-high risk corresponds to orange, medium risk corresponds to blue, and low risk corresponds to green;

[0068] A display and interaction module, used for performing full-scale grid processing on the digital map of the nuclear power plant, establishing an association relationship between the hazard sources and the map grids, and each grid is displayed in the color of the hazard source level associated with the grid. Clicking on the grid can display the hazard source information associated with the grid.

[0069] The description of the above device has been elaborated in detail in the description of the above method and will not be repeated here.

[0070] Figure 3 is a block diagram of a hazard source identification and control device based on the LECD method shown according to an exemplary embodiment. For example, the device 1900 can be provided as a server. Refer to Figure 3 , the device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by a memory 1932 for storing instructions executable by the processing component 1922, such as application programs. The application programs stored in the memory 1932 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0071] The apparatus 1900 may further include a power supply component 1926 configured to perform power management of the apparatus 1900, a wired or wireless network interface 1950 configured to connect the apparatus 1900 to a network, and an input / output (I / O) interface 1958. The apparatus 1900 may operate based on an operating system stored in the memory 1932, such as Windows ServerTM, MacOS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

[0072] In an exemplary embodiment, a non-transitory computer-readable storage medium is also provided, such as the memory 1932 including computer program instructions, and the computer program instructions may be executed by the processing component 1922 of the apparatus 1900 to complete the above method.

[0073] The present disclosure may be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0074] A computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as a punch card or raised structures in grooves storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not construed to be a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0075] The computer-readable program instructions described herein can be downloaded to various computing / processing devices from a computer-readable storage medium or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0076] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present disclosure.

[0077] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0078] These computer-readable program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus to produce a machine such that the instructions, when executed by the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more boxes of the flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that causes a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises a manufacture including instructions that implement various aspects of the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0079] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0080] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, and the module, segment of code, or portion of an instruction may include one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the boxes may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by special-purpose hardware-based systems that perform the specified functions or acts, or by combinations of special-purpose hardware and computer instructions.

[0081] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A hazard source identification and control method based on the LECD method, characterized in that, the method includes: Step 11, hazard source data collection: Collect hazard source data used to describe hazard sources. The hazard source data includes sites, equipment, and personnel; Step 12, hazard source data preprocessing: Preprocess the collected hazard source data to obtain preprocessed data. The preprocessing includes text cleaning, word segmentation, and stop word removal; Step 13, feature extraction: Extract features from the preprocessed data to quantify the relevant attributes of hazard sources. The features include accident types, loss degrees, occurrence frequencies, and potential impacts; Step 14, training the model: According to the LECD scoring system, use machine learning or deep learning algorithms to build a model. The model includes the possibility of an accident occurring, the frequency of personnel exposure to a dangerous environment, the consequences that an accident may cause, and the risk. For the preprocessed data, perform deep learning training in combination with the LECD scoring standard to obtain a trained model; Step 15, model evaluation and optimization: Use the test data set to evaluate the trained model and optimize the model according to the evaluation results; Step 16, automatic quantification and grading: Input the new hazard source data into the trained model, obtain the corresponding risk value through prediction, and assign the risk level corresponding to the risk value to the new hazard source data.

2. The method according to claim 1, characterized in that, the method of the present disclosure further includes: Step 21, perform color coding on the identified hazard sources. Different colors correspond to different hazard source levels. High risk corresponds to red, medium-high risk corresponds to orange, medium risk corresponds to blue, and low risk corresponds to green; Step 22, perform full-scale grid processing on the digital map of the nuclear power plant, establish an association relationship between the hazard sources and the map grids, and each grid is displayed in the color of the hazard source level associated with the grid. Clicking on the grid can display the hazard source information associated with the grid.

3. A hazard source identification and control device based on the LECD method, characterized in that, the device includes: A collection module for collecting hazard source data: Collect hazard source data used to describe hazard sources. The hazard source data includes sites, equipment, and personnel; A preprocessing module for preprocessing hazard source data: Preprocess the collected hazard source data to obtain preprocessed data. The preprocessing includes text cleaning, word segmentation, and stop word removal; An extraction module for feature extraction: Extract features from the preprocessed data to quantify the relevant attributes of hazard sources. The features include accident types, loss degrees, occurrence frequencies, and potential impacts; A construction module for training the model: According to the LECD scoring system, use machine learning or deep learning algorithms to build a model. The model includes the possibility of an accident occurring, the frequency of personnel exposure to a dangerous environment, the consequences that an accident may cause, and the risk. For the preprocessed data, perform deep learning training in combination with the LECD scoring standard to obtain a trained model; An optimization module for model evaluation and optimization: Use the test data set to evaluate the trained model and optimize the model according to the evaluation results; A grading module for automatic quantitative grading: Input the new hazard source data into the trained model, obtain the corresponding hazard value through prediction, and assign the risk level corresponding to the hazard value to the new hazard source data with this hazard value.

4. The device according to claim 1, wherein, the device of the present disclosure further includes: An identification module for color-coding the identified hazard sources, where different colors correspond to different hazard source levels, high risk corresponds to red, medium-high risk corresponds to orange, medium risk corresponds to blue, and low risk corresponds to green; A display and interaction module for performing full-scale grid processing on the digital map of the nuclear power plant, establishing an association relationship between the hazard sources and the map grids, and displaying each grid in the color of the hazard source level associated with the grid. Clicking on the grid can display the hazard source information associated with the grid.

5. A hazard source identification and control device based on the LECD method, wherein, the device includes: A processor; A memory for storing instructions executable by the processor; wherein, the processor is configured to execute the method according to claim 1 or 2.

6. A non-volatile computer-readable storage medium, on which computer program instructions are stored, wherein, when the computer program instructions are executed by the processor, the method according to claim 1 or 2 is implemented.

Images