A smart power plant intelligent emergency drill system and emergency drill method thereof

Abstract

The present invention proposes an intelligent emergency drill system for a smart power plant and an emergency drill method thereof, and relates to the field of emergency drill technology. Aiming at the technical problem in the prior art that the prediction accuracy and evaluation effectiveness of the emergency drill system of a smart power plant are poor due to the lack of historical emergency drill data, the present invention determines the emergency drill keywords, and the model outputs the fault information of the emergency drill event and the estimated time required to repair the fault; then obtains the test data of the tester and the equipment operation data during the processing; outputs the evaluation test results; when training the model, by screening the existing power plant data that matches the installed capacity of the smart power plant to be drilled, it is ensured that the data for model training is highly relevant and representative, and the generalization ability of the model is improved; by comprehensively considering the predicted output of the model, the actual operation performance of the tester, and the key parameters of the equipment during the processing process, a comprehensive and accurate drill evaluation framework is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency drills, and in particular to an intelligent emergency drill system for a smart power plant and an emergency drill method thereof. Background Art

[0002] With the acceleration of industrialization and the growing demand for energy, the importance of safe operation of power plants as key energy supply facilities has become increasingly prominent. In order to cope with various possible emergencies, the intelligent emergency drill system of smart power plants has come into being. By integrating advanced information technologies such as the Internet of Things (IoT), big data analysis, artificial intelligence (AI) and virtual reality (VR), the emergency drill system of smart power plants can provide a close-to-real training environment, allowing employees to familiarize themselves with and practice emergency response processes without actual danger.

[0003] Although the intelligent emergency drill system of smart power plants has played an important role in improving safety awareness and response capabilities, the existing technology still has some shortcomings, such as:

[0004] 1. Small amount of historical emergency drill data. For a specific power plant, there is little historical fault data, which causes the model to over-learn specific noise and details in the training data and lose generalization ability, resulting in poor robustness of the model;

[0005] 2. Inaccurate evaluation results. Many systems lack effective evaluation methods, making it difficult to accurately measure the emergency response capabilities of testers and the actual effects of drills, thus failing to provide strong data support for continuous improvement.

[0006] These problems limit the potential of emergency drill systems in improving the safety management level of power plants. Therefore, there is still a need for continuous research on intelligent emergency drill systems for smart power plants. Summary of the invention

[0007] The present invention provides an intelligent emergency drill method for a smart power plant to solve the technical problem in the prior art that the prediction accuracy and evaluation effectiveness of the emergency drill system of a smart power plant are poor due to the lack of historical emergency drill data.

[0008] A smart power plant intelligent emergency drill method specifically includes the following steps:

[0009] Step S1, obtaining a BIM model of a smart power plant to be tested;

[0010] Step S2, determining emergency drill keywords;

[0011] Step S3, inputting the emergency drill keywords into the trained fault prediction model, and outputting the fault information of the emergency drill event and the estimated time required to repair the fault; the fault information includes: fault location and fault type;

[0012] Step S4, generating an emergency drill simulation scenario according to the fault information of the emergency drill event and the BIM model of the smart power plant to be drilled;

[0013] Step S5: Based on the emergency drill simulation scenario, the tester provides fault information and repairs the fault, and obtains the actual time required to repair the fault and the voltage, current and power of each device in the power plant during the repair process;

[0014] Step S6, evaluating the test according to the fault information output by the fault prediction model, the estimated time required to repair the fault, the fault information given by the tester, the actual time required to repair the fault, and the voltage, current and power of each device in the power plant during the repair process, and outputting the test results;

[0015] Step S7, storing the emergency drill data of this time into the historical emergency drill data.

[0016] Furthermore, in step S2, the emergency drill keywords include impact range, difficulty in finding the fault point, difficulty in repairing the fault and additional difficulty, wherein:

[0017] The impact range includes: a single area of ​​a power plant, multiple areas of a power plant, and a power plant and surrounding areas;

[0018] The difficulty of finding the fault point includes: obvious faults and hidden faults;

[0019] The fault repair difficulty includes: simple repair and complex repair;

[0020] The additional difficulty includes: urgency, resource requirements and security protection.

[0021] Furthermore, in step S3, the fault prediction model adopts a multilayer perceptron, the number of neurons in the input layer is 4, and the number of neurons in the output layer is 3.

[0022] Furthermore, in step S3, the fault prediction model training method is specifically as follows:

[0023] Step S31, obtaining the installed capacity of the smart power plant to be tested;

[0024] Step S32, obtaining the installed capacity of existing smart power plants, and selecting smart power plants with installed capacity within a preset range according to the installed capacity of the smart power plant to be tested;

[0025] Step S33, obtaining the fault information and fault repair time of the screened historical emergency drill events of the smart power plant;

[0026] Step S34, keyword tagging of the historical emergency drill events according to the impact scope, difficulty of finding the fault point, difficulty of fault repair and additional difficulty;

[0027] Step S35, taking the keywords of each emergency drill event as input, and the fault information and the time to repair the fault as output, the multilayer perceptron is trained to obtain a trained fault prediction model.

[0028] Furthermore, in step S32, the preset range is: GWtarget×(1-η) <GW≤GWtarget×(1+η);

[0029] Among them, GW is the installed capacity of the selected smart power plants, GWtarget is the installed capacity of the smart power plants to be tested, and η is the proportional factor.

[0030] Furthermore, the step S6 is specifically as follows:

[0031] Step S61, if the fault information provided by the tester is inconsistent with the fault information output by the fault prediction model, the test result is unqualified and the evaluation ends; if they are consistent, a score A1 is obtained;

[0032] If the tester completes troubleshooting, he / she will receive a score of A2;

[0033] If a device with a parameter exceeding the limit appears during the processing, score B will be deducted; the device with a parameter exceeding the limit means that at least one of the voltage, current and power of the device exceeds the rated value; if the device is damaged due to the operation of the tester, the test result is unqualified and the evaluation is terminated;

[0034] If the actual time required to repair the fault does not exceed the estimated time required to repair the fault, the score C is increased;

[0035] Step S62, calculating the difficulty coefficient ω according to the emergency drill keywords;

[0036] Step S63, calculating a comprehensive score, the calculation formula of the comprehensive score is: A=ω×(A1+A2-n×B+C), where n is the number of devices with parameters exceeding the limit;

[0037] Step S64, comparing the comprehensive score with a preset value, and providing an excellent, qualified, or unqualified test result.

[0038] Further, in step S62, the difficulty coefficient ω is obtained according to the emergency drill keywords, specifically:

[0039] Calculate the impact range difficulty coefficient ω r , if the impact range is a single area of ​​the power plant, then ω r =ω r1 ; If the impact range is multiple areas of the power plant, then ω r =ω r2 ; If the impact range is the power plant and surrounding areas, then ω r =ω r3 ; Among them, ω r1 ,ω r2 ,ω r3 is the preset value of the difficulty coefficient of the impact range, ω r1 <ω r2 <ω r3 ;

[0040] Calculate the difficulty coefficient of finding the fault point ω f , if the difficulty of finding the fault point is obvious, then ω f =ω f1 ; If the difficulty of finding the fault point is a hidden fault, then ω f =ω f2 ; Among them, ω f1 ,ω f2 Find the preset value of difficulty coefficient for the fault point, ω f1 <ω f2 ;

[0041] Calculate the fault repair difficulty coefficient ω h , if the fault repair difficulty is simple repair, then ω h =ω h1 ; If the fault repair difficulty is complex repair, then ω h =ω h2 ; Among them, ω h1 ,ω h2 is the preset value of the fault repair difficulty coefficient, ω h1 <ω h2 ;

[0042] Calculate the additional difficulty coefficient ω d , if each additional difficulty is added, the difficulty coefficient ω is increased d ; The additional difficulty includes urgency, resource requirements and safety protection;

[0043] The difficulty coefficient ω=ω r +ω f +ω h +m×ω d , where m is the number of items with additional difficulty.

[0044] A smart power plant intelligent emergency drill system, the system adopts the smart power plant intelligent emergency drill method as described in any one of the above items, and specifically includes the following modules:

[0045] The data acquisition module obtains the BIM model of the smart power plant to be tested; obtains the actual time required for testers to repair the fault, as well as the voltage, current and power of each device in the power plant during the repair process;

[0046] A keyword determination module, connected to the data acquisition module, for determining emergency drill keywords;

[0047] Emergency drill event generation module: connected to the data acquisition module and the keyword determination module, used to input the emergency drill keyword into the trained fault prediction model, output the fault information of the emergency drill event and the estimated time required to repair the fault; input the BIM model of the smart power plant to be drilled according to the fault location of the emergency drill event, and generate an emergency drill simulation scenario;

[0048] The user end is connected to the emergency drill event generation module, and the tester finds out the fault information and repairs the fault based on the emergency drill simulation scenario;

[0049] An evaluation module, connected to the emergency drill event generation module and the user terminal, is used to evaluate the test according to the fault information output by the fault prediction model, the estimated time required to repair the fault, the fault location found by the tester, the actual time required to repair the fault, and the voltage, current and power of each device in the power plant during the repair process, and output the test results;

[0050] The historical data module is connected to the evaluation module and is used to store historical emergency drill data.

[0051] Compared with the prior art, the beneficial effects of the present invention are:

[0052] First, the present invention ensures that the data used to train the fault prediction model is highly relevant and representative by screening existing power plant data that matches the installed capacity of the smart power plant to be drilled, thereby improving the generalization ability of the model and making it more accurate in generating fault information and estimating repair time, thereby improving the practicality and pertinence of emergency drills. In addition, it also helps to optimize resource allocation, ensure that drills are more efficient, and formulate more appropriate emergency response strategies for the specific scale and characteristics of power plants;

[0053] Secondly, the evaluation mechanism of the present invention provides a comprehensive and detailed exercise evaluation framework by comprehensively considering the predicted output of the fault prediction model, the actual operating performance of the testers, and the key parameters of the equipment during the processing. This evaluation can not only quantify the emergency handling capabilities of the testers, but also reveal the deficiencies and potential risk points in the exercise process. In this way, the power plant can obtain targeted feedback, adjust and optimize the emergency response plan in a timely manner, improve the safety awareness and operational skills of employees, and ensure that actions can be taken quickly and accurately in real emergency situations, thereby enhancing the overall safety management level and emergency response capabilities of the power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 This is a flow chart of an intelligent emergency drill method for a smart power plant;

[0056] Figure 2 This is a structural diagram of an intelligent emergency drill system for a smart power plant. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0058] The specific implementation of the present invention is described below with reference to the accompanying drawings (tables).

[0059] For the existing technology.

[0060] Example 1

[0061] like Figure 1 As shown, the present invention proposes an intelligent emergency drill method for a smart power plant, which specifically includes the following steps:

[0062] Step S1, obtaining the BIM model of the smart power plant to be tested.

[0063] BIM models can be used to generate emergency drill simulation scenarios, providing testers with a realistic operating platform so that they can become familiar with and practice emergency response processes without actual danger.

[0064] The model includes all key components and systems of the power plant, such as mechanical equipment, electrical systems, safety facilities, etc., as well as their interrelationships and operating logic.

[0065] Step S2, determining emergency drill keywords.

[0066] The key words for emergency drills include impact range, difficulty in finding fault points, difficulty in repairing faults, and additional difficulty.

[0067] The scope of impact includes: a single area of ​​a power plant, multiple areas of a power plant, and a power plant and surrounding areas; it refers to the size of the area that may be affected by the failure. This keyword determines the scale and complexity of the emergency response.

[0068] The difficulty of finding the fault point includes: obvious faults and hidden faults; this keyword involves whether the fault is easy to identify, which affects the speed at which the emergency team locates the problem.

[0069] The difficulty of fault repair includes: simple repair and complex repair; this keyword helps to accurately evaluate and simulate different types of fault conditions in emergency drills of smart power plants. "Simple repair" refers to faults that are easy to identify and can be solved quickly, such as replacing parts or adjusting settings, which usually require less time and technical skills. In contrast, "complex repair" involves deeper problems and may require more extensive diagnosis, professional skills or longer repairs. Such faults may affect the critical operations of the power plant and require more careful planning and coordination. By distinguishing between these two types of repair difficulty, the drill can more realistically reflect the response strategy and resource allocation of the power plant when facing different emergencies, thereby improving the practicality and educational effect of the drill.

[0070] The additional difficulty includes: urgency, resource requirements and safety protection; these keywords together constitute additional difficulty, which may increase the complexity and challenge of emergency response, requiring that these additional challenges must be considered when designing emergency drills to ensure the comprehensiveness and effectiveness of the drills. By simulating these additional difficulties in drills, employees can be better prepared and trained to face the multiple needs of real emergency situations.

[0071] In the intelligent emergency drill system of smart power plants, words that can represent the core content and key elements of the drill are selected according to the drill objectives and needs. These keywords usually cover the key variables and conditions in the drill, and are the basis for designing and executing drill scenarios, ensuring that the drill can simulate the various challenges that may be encountered in real emergency situations. By accurately defining these keywords, clear guidance and basis can be provided for the subsequent steps of the drill, such as the training of fault prediction models and the generation of drill events, thereby improving the effectiveness and pertinence of the drill.

[0072] Step S3, input the emergency drill keywords into the trained fault prediction model, and output the fault information of the emergency drill event and the estimated time required to repair the fault; the fault information includes: fault location and fault type.

[0073] The fault prediction model uses a multilayer perceptron, with 4 neurons in the input layer and 3 neurons in the output layer. Multilayer perceptron (MLP) is a basic feedforward neural network structure suitable for processing classification and regression tasks. In the present invention, the number of neurons in the input layer is set to 4, which matches the number of emergency drill keywords, ensuring that each keyword can be used independently as an input feature of the model. The number of neurons in the output layer is 3, corresponding to the three main outputs predicted by the model: fault location, fault type, and estimated repair time. Through such a structural design, the multilayer perceptron can learn the complex mapping relationship from keywords to fault predictions, thereby providing accurate fault predictions and time estimates in emergency drills of smart power plants, enhancing the pertinence and effectiveness of the drills.

[0074] The specific method for training the fault prediction model is as follows:

[0075] Step S31, obtaining the installed capacity of the smart power plant to be tested;

[0076] Step S32, obtaining the installed capacity of existing smart power plants, and selecting smart power plants with installed capacity within a preset range according to the installed capacity of the smart power plant to be tested; the preset range is: GWtarget×(1-η) <GW≤GWtarget×(1+η);

[0077] Among them, GW is the installed capacity of the selected smart power plants, GWtarget is the installed capacity of the smart power plants to be tested, and η is the proportional factor.

[0078] This step obtains more representative and relevant historical emergency drill data by matching smart power plants with similar installed capacity, ensuring that the data used to train the fault prediction model is consistent with the actual operating conditions and scale of the power plant to be tested, thereby improving the accuracy and reliability of the model prediction.

[0079] Step S33, obtaining the fault information and fault repair time of the screened historical emergency drill events of the smart power plant;

[0080] Step S34, keyword tagging of the historical emergency drill events according to the impact scope, difficulty of finding the fault point, difficulty of fault repair and additional difficulty;

[0081] Step S35, taking the keywords of each emergency drill event as input, and the fault information and the time to repair the fault as output, the multilayer perceptron is trained to obtain a trained fault prediction model.

[0082] The previously identified emergency drill keywords are input into a pre-trained fault prediction model, which analyzes these keywords to predict the possible fault type, location, and estimated repair time. The fault prediction model is trained based on historical data and machine learning algorithms, and can identify patterns and trends in fault occurrence. The output fault information and estimated repair time are crucial for generating emergency drill simulation scenarios, providing testers with a specific fault scenario that allows them to practice and improve their response capabilities to real emergencies in a controlled environment. This approach not only enhances the relevance and effectiveness of the drill, but also helps to evaluate and improve the emergency response skills of testers.

[0083] Step S4, generating an emergency drill simulation scenario according to the fault information of the emergency drill event and the BIM model of the smart power plant to be drilled.

[0084] This step uses the detailed 3D data and fault information of the BIM model to create a virtual power plant environment through software tools, in which real fault conditions are simulated. In this simulated scenario, testers can conduct practical operation exercises such as fault diagnosis, equipment repair and emergency response, thereby improving their skills and responsiveness without actual risks. This method has been widely used in the fields of construction and engineering for education and training purposes, and is now extended to emergency drills in smart power plants to improve the authenticity and effectiveness of the drills. In this way, smart power plants can ensure that employees have the necessary knowledge and skills to solve problems quickly and effectively when faced with actual emergencies.

[0085] Step S5: Based on the emergency drill simulation scenario, the tester provides fault information and repairs the fault, and obtains the actual time required to repair the fault and the voltage, current and power of each device in the power plant during the repair process.

[0086] Step S6, evaluate this test based on the fault information output by the fault prediction model, the estimated time required to repair the fault, the fault information given by the tester, the actual time required to repair the fault, and the voltage, current and power of each device in the power plant during the repair process, and output the test results. Specifically:

[0087] Step S61, if the fault information provided by the tester is inconsistent with the fault information output by the fault prediction model, the test result is unqualified and the evaluation ends; if they are consistent, a score A1 is obtained;

[0088] If the tester completes troubleshooting, he / she will receive a score of A2;

[0089] If a device with a parameter exceeding the limit appears during the processing, score B will be deducted; the device with a parameter exceeding the limit means that at least one of the voltage, current and power of the device exceeds the rated value; if the device is damaged due to the operation of the tester, the test result is unqualified and the evaluation is terminated;

[0090] If the actual time required to repair the fault does not exceed the estimated time required to repair the fault, the score C is increased;

[0091] Step S62, calculating the difficulty coefficient ω according to the emergency drill keywords; the calculation method of ω is:

[0092] Calculate the impact range difficulty coefficient ω r , if the impact range is a single area of ​​the power plant, then ω r =ω r1 ; If the impact range is multiple areas of the power plant, then ω r =ω r2 ; If the impact range is the power plant and surrounding areas, then ω r =ω r3 ; Among them, ω r1 ,ω r2 ,ω r3 is the preset value of the difficulty coefficient of the impact range, ω r1 <ω r2 <ω r3 ;

[0093] Calculate the difficulty coefficient of finding the fault point ω f , if the difficulty of finding the fault point is obvious, then ω f =ω f1 ; If the difficulty of finding the fault point is a hidden fault, then ω f =ω f2 ; Among them, ω f1 ,ω f2 Find the preset value of difficulty coefficient for the fault point, ω f1 <ω f2 ;

[0094] Calculate the fault repair difficulty coefficient ω h , if the fault repair difficulty is simple repair, then ω h =ω h1 ; If the fault repair difficulty is complex repair, then ω h =ω h2 ; Among them, ω h1 ,ω h2 is the preset value of the fault repair difficulty coefficient, ω h1 <ω h2 ;

[0095] Calculate the additional difficulty coefficient ω d , if each additional difficulty is added, the difficulty coefficient ω is increased d ; The additional difficulty includes urgency, resource requirements and safety protection;

[0096] The difficulty coefficient ω=ω r +ω f +ω h +m×ω d , where m is the number of items with additional difficulty.

[0097] The difficulty coefficient ω plays a key role in the intelligent emergency drill system of smart power plants. It quantifies the complexity and challenge of the drill event. By considering factors such as the scope of impact, the difficulty of finding the fault point, the difficulty of fault repair, and additional difficulty, the difficulty coefficient ω provides a comprehensive assessment of the difficulty of the drill event. This coefficient not only helps determine the difficulty level of the drill, but is also used to adjust the score when evaluating the test results to ensure that the test score can fairly reflect the performance of the tester when facing faults of different difficulty levels. In this way, the difficulty coefficient ω makes the drill evaluation more scientific and reasonable, and helps to more accurately measure and improve the emergency response capabilities of testers in real emergencies.

[0098] Step S63, calculating a comprehensive score, the calculation formula of the comprehensive score is: A=ω×(A1+A2-n×B+C), where n is the number of devices with parameters exceeding the limit;

[0099] Step S64, comparing the comprehensive score with a preset value, and providing an excellent, qualified, or unqualified test result.

[0100] Steps S5 and S6 are the evaluation process of the actual operation and response capabilities of the test personnel in the intelligent emergency drill system of the smart power plant. In step S5, the test personnel use the fault information provided in the simulation scenario to actually operate to identify and repair the fault, and record the actual time required to complete these tasks, as well as the voltage, current and power parameters of key equipment in the power plant such as generators and transformers during this process. These data are key indicators for evaluating the reaction speed and skill proficiency of the test personnel. Subsequently, in step S6, the evaluation module compares these actual operation data with the predicted output of the fault prediction model, including the fault type, location, the difference between the expected repair time and the actual repair time, and whether the equipment operating parameters meet the safety standards. Through this comparison, the system is able to output a comprehensive evaluation result, which not only quantifies the performance of the test personnel, but also reveals the deficiencies in the exercise process, providing a basis for further training and improvement.

[0101] Step S7, storing the emergency drill data of this time into the historical emergency drill data.

[0102] This step stores all relevant data of this emergency drill, including the BIM model of the smart power plant, emergency drill keywords, output of the fault prediction model, actual operation performance of testers, time for fault repair, equipment operating parameters and test results, in the historical emergency drill data, ensuring that the experience and data generated during the drill can be effectively preserved and accumulated, providing reference and comparison benchmarks for future drills. Through the accumulation of historical data, power plants can analyze drill trends, identify common problems, and evaluate the effectiveness of improvement measures, thereby continuously optimizing emergency response processes and improving employees' emergency handling capabilities. In addition, these data can also be used to further train and optimize fault prediction models to more accurately simulate real-world fault conditions and enhance the practicality and pertinence of drills.

[0103] Example 2

[0104] like Figure 2 As shown, the present invention also proposes an intelligent emergency drill system for a smart power plant, which adopts the intelligent emergency drill method for a smart power plant described in any one of Embodiment 1, and specifically includes the following modules:

[0105] The data acquisition module obtains the BIM model of the smart power plant to be tested; obtains the actual time required for testers to repair the fault, as well as the voltage, current and power of each device in the power plant during the repair process;

[0106] A keyword determination module, connected to the data acquisition module, for determining emergency drill keywords;

[0107] Emergency drill event generation module: connected to the data acquisition module and the keyword determination module, used to input the emergency drill keyword into the trained fault prediction model, output the fault information of the emergency drill event and the estimated time required to repair the fault; input the BIM model of the smart power plant to be drilled according to the fault location of the emergency drill event, and generate an emergency drill simulation scenario;

[0108] The user end is connected to the emergency drill event generation module, and the tester finds out the fault information and repairs the fault based on the emergency drill simulation scenario;

[0109] An evaluation module, connected to the emergency drill event generation module and the user terminal, is used to evaluate the test according to the fault information output by the fault prediction model, the estimated time required to repair the fault, the fault location found by the tester, the actual time required to repair the fault, and the voltage, current and power of each device in the power plant during the repair process, and output the test results;

[0110] The historical data module is connected to the evaluation module and is used to store historical emergency drill data.

[0111] Example 3

[0112] An electronic device, comprising:

[0113] Processor and memory;

[0114] The processor is used to execute the steps of an intelligent emergency drill method for a smart power plant as described in any one of Example 1 by calling the program or instructions stored in the memory.

[0115] Example 4

[0116] A computer-readable storage medium, the computer-readable storage medium comprising computer program instructions, the computer program instructions enabling a computer to execute the steps of a smart power plant intelligent emergency drill method as described in any one of Example 1.

[0117] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0118] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present invention. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0119] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A smart power plant intelligent emergency drill method, characterized in that: The steps include: Step S1, obtaining a BIM model of a smart power plant to be tested; Step S2, determining emergency drill keywords; the emergency drill keywords include impact scope, difficulty of finding fault point, difficulty of fault repair and additional difficulty; Step S3, inputting the emergency drill keywords into the trained fault prediction model, and outputting the fault information of the emergency drill event and the estimated time required to repair the fault; The fault information includes: fault location and fault type; Step S4, generating an emergency drill simulation scenario according to the fault information of the emergency drill event and the BIM model of the smart power plant to be drilled; Step S5: Based on the emergency drill simulation scenario, the tester provides fault information and repairs the fault, and obtains the actual time required to repair the fault and the voltage, current and power of each device in the power plant during the repair process; Step S6, scoring the test according to the fault information output by the fault prediction model, the estimated time required to repair the fault, the fault information given by the tester, the actual time required to repair the fault, and the voltage, current and power of each device in the power plant during the repair process; Calculate the difficulty coefficient ω according to the difficulty coefficient of the impact range, the difficulty coefficient of finding the fault point, the difficulty coefficient of fault repair, the additional difficulty coefficient and the number of additional difficulty items; Calculate the comprehensive score based on the difficulty coefficient and score; Evaluate based on the comprehensive score and output the test results; Step S7, storing the emergency drill data of this time into the historical emergency drill data.

2. The intelligent emergency drill method for a smart power plant according to claim 1 is characterized in that: In step S2, the emergency drill keywords include impact range, fault point finding difficulty, fault repair difficulty and additional difficulty, where: The impact scope includes: a single area of ​​a power plant, multiple areas of a power plant, and a power plant and surrounding areas; The difficulty of finding the fault point includes: obvious faults and hidden faults; The difficulty of fault repair includes: simple repair and complex repair; The additional difficulty includes: urgency, resource requirements and security protection.

3. The intelligent emergency drill method for a smart power plant according to claim 1 is characterized in that: In step S3, the fault prediction model adopts a multilayer perceptron, the number of neurons in the input layer is 4, and the number of neurons in the output layer is 3.

4. The intelligent emergency drill method for a smart power plant according to claim 3 is characterized in that: In step S3, the training method of the fault prediction model is specifically as follows: Step S31, obtaining the installed capacity of the smart power plant to be tested; Step S32, obtaining the installed capacity of existing smart power plants, and screening out smart power plants with installed capacity within a preset range according to the installed capacity of the smart power plant to be tested; Step S33, obtaining the fault information and fault repair time of the screened historical emergency drill events of the smart power plant; Step S34, keyword tagging of the historical emergency drill events according to the impact scope, difficulty of finding the fault point, difficulty of fault repair and additional difficulty; Step S35, taking the keywords of each emergency drill event as input, and the fault information and the time to repair the fault as output, the multilayer perceptron is trained to obtain a trained fault prediction model.

5. The intelligent emergency drill method for a smart power plant according to claim 4 is characterized in that: In step S32, the preset range is: GWtarget×(1-η) <GW≤GWtarget×(1+η); Among them, GW is the installed capacity of the selected smart power plants, GWtarget is the installed capacity of the smart power plants to be tested, and η is the proportional factor.

6. The intelligent emergency drill method for a smart power plant according to claim 1 is characterized in that: The step S6 is specifically: Step S61, if the fault information provided by the tester is inconsistent with the fault information output by the fault prediction model, the test result is unqualified and the evaluation ends; if they are consistent, a score A1 is obtained; If the tester completes troubleshooting, he / she will receive a score of A2; If a device with a parameter exceeding the limit appears during the processing, score B will be deducted; the device with a parameter exceeding the limit means that at least one of the voltage, current and power of the device exceeds the rated value; if the device is damaged due to the operation of the tester, the test result is unqualified and the evaluation is terminated; If the actual time required to repair the fault does not exceed the estimated time required to repair the fault, the score C is increased; Step S62, calculating the difficulty coefficient ω according to the emergency drill keywords; Step S63, calculating a comprehensive score, the calculation formula of the comprehensive score is: A=ω×(A1+A2-n×B+C), where n is the number of devices with parameters exceeding the limit; Step S64, comparing the comprehensive score with a preset value, and providing an excellent, qualified, or unqualified test result.

7. The intelligent emergency drill method for a smart power plant according to claim 6 is characterized in that: In step S62, the difficulty coefficient ω is obtained according to the emergency drill keywords, specifically: Calculate the impact range difficulty coefficient ω r , if the impact range is a single area of ​​the power plant, then ω r =ω r1 ; If the impact range is multiple areas of the power plant, then ω r =ω r2 ; If the impact range is the power plant and surrounding areas, then ω r =ω r3 ; Among them, ω r1 ,ω r2 ,ω r3 is the preset value of the difficulty coefficient of the impact range, ω r1 <ω r2 <ω r3 ; Calculate the difficulty coefficient of finding the fault point ω f , if the difficulty of finding the fault point is obvious, then ω f =ω f1 ; If the difficulty of finding the fault point is a hidden fault, then ω f =ω f2 ; Among them, ω f1 ,ω f2 Find the preset value of difficulty coefficient for the fault point, ω f1 <ω f2 ; Calculate the fault repair difficulty coefficient ω h , if the fault repair difficulty is simple repair, then ω h =ω h1 ; If the fault repair difficulty is complex repair, then ω h =ω h2 ; Among them, ω h1 ,ω h2 is the preset value of the fault repair difficulty coefficient, ω h1 <ω h2 ; Calculate the additional difficulty coefficient ω d , if each additional difficulty is added, the difficulty coefficient ω is increased d ; The additional difficulty includes urgency, resource requirements and safety protection; The difficulty coefficient ω=ω r +ω f +ω h +m×ω d , where m is the number of items with additional difficulty.

8. A smart power plant intelligent emergency drill system, characterized in that: The system adopts the intelligent emergency drill method for a smart power plant according to any one of claims 1 to 7, and specifically includes the following modules: The data acquisition module obtains the BIM model of the smart power plant to be tested; obtains the actual time required for testers to repair the fault, as well as the voltage, current and power of each device in the power plant during the repair process; A keyword determination module, connected to the data acquisition module, for determining emergency drill keywords; Emergency drill event generation module: connected to the keyword determination module, used to input the emergency drill keyword into the trained fault prediction model, and output the fault information of the emergency drill event and the estimated time required to repair the fault; Input the BIM model of the smart power plant to be drilled according to the fault location of the emergency drill event to generate an emergency drill simulation scenario; The user end is connected to the emergency drill event generation module, and the tester finds out the fault information and repairs the fault based on the emergency drill simulation scenario; An evaluation module, connected to the user terminal, is used to evaluate the test according to the fault information output by the fault prediction model, the estimated time required to repair the fault, the fault location found by the tester, the actual time required to repair the fault, and the voltage, current and power of each device in the power plant during the repair process, and output the test results; The historical data module is connected to the evaluation module and is used to store historical emergency drill data.

Images