Power plant safety detection method, device, computer equipment and storage medium
Data is collected through infrared radiation and gas detectors, features are extracted and detection data bodies are constructed, and the safety detection model is used to perform power plant safety inspection, which solves the problems of low accuracy and lag of traditional methods, and realizes advanced detection and early warning of power plant safety status.
Patent Information
- Application Number
- CN202410570298.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-09
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-05-09
AI Technical Summary
The accuracy of power plant safety inspection is low, traditional methods rely on manual inspections and simple sensors, cannot conduct comprehensive evaluation, and fire alarms are lagging.
Infrared radiation detectors and gas detectors are used to collect data, extract time and space characteristics, build detection data bodies, and conduct comprehensive analysis through safety detection models to realize multi-dimensional data mining and fire risk prediction.
It improves the accuracy and early warning capabilities of power plant safety inspections, can detect abnormalities before fires occur, and reduce errors and dangers.
Smart Images

Figure CN118500471B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of safety detection technology, and in particular to a power plant safety detection method, device, computer equipment and storage medium. Background Art
[0002] A power plant is a factory that converts some form of raw energy, such as thermal power, hydraulic power, steam, diesel or nuclear power, into electrical energy for fixed facilities or transportation. As a power supply unit, power plants play an important role in social production and life, and the safe operation and safety detection of power plants are also of great significance.
[0003] Power plants often have complex environments, such as extreme environments such as high temperature and high pressure, so fire safety detection in power plants is very important. In terms of fire prevention, traditional power plant safety detection mainly relies on manual inspection or simple sensor detection. However, manual inspection requires a lot of manpower and time costs. For some hidden or extreme environments, manual inspection has high risks and errors. Traditional sensor detection often only focuses on specific parameters and cannot perform comprehensive evaluation; and when the alarm is issued based on sensor parameters such as temperature, the fire has often occurred, which has a lag. Summary of the invention
[0004] The purpose of the embodiments of the present application is to provide a power plant safety detection method, device, computer equipment and storage medium to solve the problem of low accuracy of power plant safety detection.
[0005] In order to solve the above technical problems, the present application embodiment provides a power plant safety detection method, which adopts the following technical solution:
[0006] For each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors in the detection area;
[0007] Extracting a first time feature and a first space feature of the infrared radiation detection data, and extracting a second time feature and a second space feature of the gas detection data;
[0008] Constructing a detection data volume of the detection area according to the infrared radiation detection data and the first time feature and the first space feature corresponding thereto, and the gas detection data and the second time feature and the second space feature corresponding thereto;
[0009] The detection data bodies of each detection area in the power plant are input into the safety detection model to obtain the safety detection results of the power plant.
[0010] Furthermore, the step of extracting the first time feature and the first space feature of the infrared radiation detection data includes:
[0011] Organizing the infrared radiation detection data according to collection time;
[0012] extracting a first number of first sub-features from the organized infrared radiation detection data, and determining the extracted first sub-features as first time features of the infrared radiation detection data;
[0013] The coverage information and distribution density information of the infrared radiation detector are acquired from a database, and the coverage information and the distribution density information are determined as the first spatial features of the infrared radiation detection data.
[0014] Furthermore, the step of extracting the second time feature and the second space feature of the gas detection data includes:
[0015] Organizing the gas detection data according to collection time;
[0016] extracting a second number of second sub-features from the organized gas detection data, and determining the extracted second sub-features as second time features of the gas detection data;
[0017] Based on the gas detection data, the uniformity of gas distribution and the gas concentration gradient in the detection area are calculated, and the uniformity and the gas concentration gradient are determined as the second spatial features of the gas detection data.
[0018] Furthermore, the step of constructing the detection data volume of the detection area according to the infrared radiation detection data and the first time feature and the first space feature corresponding thereto, and the gas detection data and the second time feature and the second space feature corresponding thereto comprises:
[0019] Adding the first time feature and the first space feature to the infrared radiation detection data to obtain infrared radiation enhancement data;
[0020] adding the second time feature and the second space feature to the gas detection data to obtain gas enhancement data;
[0021] The infrared radiation enhancement data and the gas enhancement data are fused by Kalman filtering to obtain a detection data volume of the detection area.
[0022] Furthermore, the step of inputting the detection data of each detection area in the power plant into the safety detection model to obtain the safety detection result of the power plant includes:
[0023] Obtaining importance factors and historical safety factors of each detection area in the power plant;
[0024] Calculate the weight of each detection area according to the obtained importance factor and historical safety factor;
[0025] Adding weights corresponding to the respective detection areas to the detection data volumes of the respective detection areas;
[0026] Each detection data body with weight is input into the safety detection model to obtain the safety detection result of the power plant.
[0027] Furthermore, the security detection model is constructed based on a recurrent neural network, a long short-term memory network or a gated recurrent unit.
[0028] Furthermore, after the step of obtaining the safety detection result of the power plant, the method further includes:
[0029] When it is determined according to the safety detection result that the power plant has a safety hazard, determining a target area having the safety hazard according to the safety detection result;
[0030] Acquire a monitoring image of the target area by an image collector associated with the target area;
[0031] The monitoring image and the security detection result are sent to the terminal corresponding to the target account.
[0032] In order to solve the above technical problems, the embodiment of the present application also provides a power plant safety detection device, which adopts the following technical solution:
[0033] A data acquisition module, for collecting infrared radiation detection data and gas detection data of each detection area in the power plant through infrared radiation detectors and gas detectors in the detection area;
[0034] A feature extraction module, used to extract a first time feature and a first space feature of the infrared radiation detection data, and to extract a second time feature and a second space feature of the gas detection data;
[0035] A data volume construction module, used for constructing a detection data volume of the detection area according to the infrared radiation detection data and the first time feature and the first space feature corresponding thereto, and the gas detection data and the second time feature and the second space feature corresponding thereto;
[0036] The safety detection module is used to input the detection data of each detection area in the power plant into the safety detection model to obtain the safety detection result of the power plant.
[0037] In order to solve the above technical problems, an embodiment of the present application further provides a computer device, which includes a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the power plant safety detection method as described above are implemented.
[0038] In order to solve the above technical problems, an embodiment of the present application further provides a computer-readable storage medium, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the steps of the power plant safety detection method as described above are implemented.
[0039] Compared with the prior art, the embodiments of the present application mainly have the following beneficial effects: for each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors; infrared radiation detection data reflects the thermal radiation characteristics of the object, which is conducive to discovering abnormalities before a fire or high temperature event occurs; gas detection data reflects the gas composition in the detection area, and the concentration change of a specific gas can be used as an early indicator of the occurrence of a fire; infrared radiation detection data and gas detection data have time and space attributes, and the first time feature and the first space feature of the infrared radiation detection data, as well as the second time feature and the second space feature of the gas detection data can be extracted, thereby obtaining more feature data; according to the infrared radiation detection data, the first time feature, the first space feature, the gas detection data, the second time feature and the second space feature, a detection data body of the detection area is constructed, and the detection data body contains data in specific time, space and attribute dimensions, and can realize multi-dimensional analysis and mining of infrared radiation detection data and gas detection data; the detection data body of each detection area is input into the safety detection model, and the model can integrate the data of each dimension, automatically predict and identify areas where fire risks may exist or have occurred, realize advanced detection and early warning of the safety status of the power plant, and improve the accuracy of safety detection of the power plant. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0041] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;
[0042] Figure 2 is a flow chart of an embodiment of a power plant safety detection method according to the present application;
[0043] Figure 3 is a structural schematic diagram of an embodiment of a power plant safety detection device according to the present application;
[0044] Figure 4 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION
[0045] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.
[0046] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0047] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
[0048] like Figure 1 As shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0049] The terminal devices 101, 102, 103 can collect relevant data of each detection area in the power plant, obtain infrared radiation detection data and gas detection data, and interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 can be, but are not limited to, various industrial computers, personal computers, laptops, sensors, etc. The server 105 can be provided with a power plant safety detection system.
[0050] It should be noted that the power plant safety detection method provided in the embodiment of the present application is generally executed by a server, and accordingly, the power plant safety detection device is generally set in the server.
[0051] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to the implementation requirements.
[0052] Continue to refer Figure 2 , shows a flow chart of an embodiment of a power plant safety detection method according to the present application. The power plant safety detection method comprises the following steps:
[0053] Step S201 : for each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors in the detection area.
[0054] In this embodiment, the power plant safety detection method is executed on the electronic device (eg Figure 1 The server shown in the figure) can communicate with the terminal device through a wired connection or a wireless connection. It should be noted that the above wireless connection method may include but is not limited to 3G / 4G / 5G connection, Wi-Fi connection, Bluetooth connection, Wi MAX connection, Zigbee connection, UWB (Ultra Wi-Fi Band) connection, and other wireless connection methods currently known or to be developed in the future.
[0055] Specifically, the power plant is divided into multiple detection areas in advance, and infrared radiation detectors and gas detectors can be set in each area. Among them, the infrared radiation detector can detect the thermal radiation of objects in the preset area and obtain infrared radiation detection data. The use of infrared radiation detection technology can detect abnormal conditions in time before a fire or high temperature event occurs. Compared with traditional temperature sensors, infrared radiation detection technology can detect signs of temperature rise more quickly.
[0056] Gas detectors can detect the gas composition in a preset area, such as oxygen, carbon dioxide, carbon monoxide, etc., and obtain gas detection data. Changes in the concentration of certain gases can be used as early indicators of fire. By detecting changes in these gases, potential fire risks can be discovered earlier.
[0057] The infrared radiation detector and the gas detector may be instruments having a detection function, such as sensors.
[0058] Step S202, extracting the first time feature and the first space feature of the infrared radiation detection data, and extracting the second time feature and the second space feature of the gas detection data.
[0059] Specifically, it is easy to understand that the infrared radiation detection data and the gas detection data have timestamps, and time-related features can be extracted based on the timestamps; for the infrared radiation detection data, the first time feature can be extracted; for the gas detection data, the second time feature can be extracted. Among them, the first time feature and the second time feature can both contain multiple sub-features.
[0060] Since the infrared radiation detection data and the gas detection data correspond to a certain detection area, which is a certain spatial area in the power plant, the spatial features of the infrared radiation detection data and the gas detection data can also be extracted based on the spatial attributes; for the infrared radiation detection data, the first spatial feature can be extracted; for the gas detection data, the second spatial feature can be extracted. The first spatial feature and the second spatial feature can both contain multiple sub-features.
[0061] By extracting the temporal and spatial characteristics of infrared radiation detection data and gas detection data, we can mine more characteristic data contained in the infrared radiation detection data and gas detection data, and apply these data to power plant safety detection, which is conducive to improving the richness of data and the accuracy of detection.
[0062] Step S203, constructing a detection data volume of the detection area according to the infrared radiation detection data and its corresponding first time feature and first space feature, and the gas detection data and its corresponding second time feature and second space feature.
[0063] Specifically, the detection data body is a multidimensional data structure used to store and analyze relevant data of the detection area. It integrates time, space and attribute information together to facilitate multidimensional data analysis and mining.
[0064] The attribute information in the detection data body comes from infrared radiation detection data and gas detection data. The attribute information includes detection data on multiple attributes, such as temperature-related data and gas concentration-related data. Each attribute corresponds to an attribute slice in the detection data body.
[0065] The time information comes from the first time feature of the infrared radiation detection data and the second time feature of the gas detection data. The time information can be in days, hours, minutes, seconds, etc. as time units, and each time point corresponds to a time slice in the detection data volume.
[0066] The spatial information comes from the first spatial feature of the infrared radiation detection data and the second spatial feature of the gas detection data. The spatial information can be three-dimensional, and it can be based on the geographic spatial coordinates within the power plant. Each detection data volume corresponds to a spatial slice of the power plant.
[0067] The detection data body contains data in specific time, space and attribute dimensions, which can realize multi-dimensional analysis and mining of infrared radiation detection data and gas detection data, such as spatiotemporal trend analysis, anomaly detection, predictive modeling, etc.
[0068] Step S204: input the detection data of each detection area in the power plant into the safety detection model to obtain the safety detection result of the power plant.
[0069] Specifically, the present application pre-trains a safety detection model, which can be constructed based on a neural network. The safety detection model can comprehensively detect data of various dimensions in the data body, analyze, predict, and identify areas where fire risks may exist or have already occurred, and achieve advanced detection and early warning of the safety status of the power plant, which helps to take timely measures to prevent the occurrence of fires in the power plant.
[0070] In this embodiment, for each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors; the infrared radiation detection data reflects the thermal radiation characteristics of the object, which is conducive to discovering abnormalities before a fire or high temperature event occurs; the gas detection data reflects the gas composition in the detection area, and the concentration change of a specific gas can be used as an early indicator of the occurrence of a fire; the infrared radiation detection data and the gas detection data have time and space attributes, and the first time feature and the first space feature of the infrared radiation detection data, as well as the second time feature and the second space feature of the gas detection data can be extracted, thereby obtaining more feature data; according to the infrared radiation detection data, the first time feature, the first space feature, the gas detection data, the second time feature and the second space feature, a detection data body of the detection area is constructed, and the detection data body contains data in specific time, space and attribute dimensions, and can realize multi-dimensional analysis and mining of the infrared radiation detection data and the gas detection data; the detection data body of each detection area is input into the safety detection model, and the model can integrate the data of each dimension, automatically predict and identify areas where there may be or have been fire risks, realize advanced detection and early warning of the safety status of the power plant, and improve the accuracy of safety detection of the power plant.
[0071] Furthermore, the above-mentioned step of extracting the first time feature and the first spatial feature of the infrared radiation detection data may include: organizing the infrared radiation detection data according to the collection time; extracting a first number of first sub-features from the organized infrared radiation detection data, and determining the extracted first sub-features as the first time feature of the infrared radiation detection data; obtaining the coverage information and distribution density information of the infrared radiation detector from the database, and determining the coverage information and distribution density information as the first spatial feature of the infrared radiation detection data.
[0072] Specifically, the infrared radiation detection data has a timestamp, and the timestamp corresponds to the collection time of the infrared radiation detection data. By organizing the infrared radiation detection data according to the collection time, a time series can be obtained. A first number of first sub-features are extracted from the time series (organized infrared radiation detection data). The type and quantity of the first sub-features can be predetermined. For example, the infrared radiation detection data under each timestamp is used as a slice to calculate the mean, standard value, maximum value, minimum value, trend characteristics, periodic characteristics, etc. of various radiation indicators in the infrared radiation detection data. In addition, the lag features can also be calculated by sliding windows and the like, such as the data change trend within the past few timestamps. It is explained here that the infrared radiation detection data can contain data of multiple radiation indicators, and calculations can be performed separately for each radiation indicator. The various first sub-features extracted are determined as the first time features of the infrared radiation detection data.
[0073] The infrared radiation detector also has coverage information and distribution density information. When the infrared radiation detector is arranged, this information can be determined and stored in the database. Coverage information refers to the spatial range that the infrared radiation detector can detect, which depends on the detection capability and installation location of the infrared radiation detector. For example, assuming that an infrared radiation detector is installed at point P in a power plant with a detection range of 20 meters, its coverage will be a spherical area with a radius of 20 meters centered on the infrared radiation detector.
[0074] Multiple infrared radiation detectors can be deployed in a power plant. The number and distribution of infrared radiation detectors determine the distribution density information of infrared radiation detectors, which can be used to evaluate the balance and coverage of fire risks in the detection area. For example, assuming that there are 50 infrared radiation detectors in a power plant, which are evenly distributed throughout the power plant, the distribution density of infrared radiation detectors will be relatively high because each area has infrared radiation detectors for detection.
[0075] The coverage information and distribution density information are determined as the first spatial feature of the infrared radiation detection data. In one embodiment, if the arrangement position of the infrared radiation detector is changed, the coverage information and distribution density information of the infrared radiation detector can be calculated in time.
[0076] In this embodiment, the infrared radiation detection data is organized according to the collection time, and then the first quantity of the first sub-feature is extracted from the time series as the first time feature of the infrared radiation detection data; the coverage information and distribution density information of the infrared radiation detector are obtained from the database as the first spatial feature of the infrared radiation detection data, thereby realizing feature mining of the time and space dimensions of the infrared radiation detection data.
[0077] Furthermore, the above-mentioned step of extracting the second time feature and the second spatial feature of the gas detection data may include: organizing the gas detection data according to the collection time; extracting a second number of second sub-features from the organized gas detection data, and determining the extracted second sub-features as the second time feature of the gas detection data; based on the gas detection data, calculating the uniformity of gas distribution and the gas concentration gradient in the detection area, and determining the uniformity and the gas concentration gradient as the second spatial feature of the gas detection data.
[0078] Specifically, the gas detection data has a timestamp, and the timestamp corresponds to the collection time of the gas detection data. By organizing the gas detection data according to the collection time, another time series can be obtained. A second number of second sub-features are extracted from the time series (organized gas detection data), and the type and quantity of the second sub-features can be predetermined. For example, the gas detection data under each timestamp is used as a slice to calculate the mean, standard value, maximum value, minimum value, trend characteristics, periodic characteristics, etc. of various gas indicators in the gas detection data. In addition, the lag characteristics can also be calculated by sliding windows and the like, such as the data change trend within the past few timestamps. It is explained here that the gas detection data can contain data of multiple gas indicators, and calculations can be performed separately for each gas indicator. The various second sub-features extracted are determined as the second time characteristics of the gas detection data.
[0079] It can be understood that the types and quantities of sub-features included in the first time feature and the second time feature may be the same or different. The above is a typical description of the extraction of the first time feature and the second time feature.
[0080] Multiple gas detectors can be arranged in each detection area, and each gas detector can detect and evaluate the uniformity of gas distribution and gas concentration gradient characteristics at different positions in the detection area. The uniformity and gas concentration gradient here can be the uniformity and gas concentration gradient of a specified type of gas, or the uniformity and gas concentration gradient of the entire air.
[0081] Among them, the gas concentration data collected by the gas detector can be used to evaluate the gas distribution in the detection area. If the change of gas concentration in the detection area is relatively uniform, that is, the difference in gas concentration at each position is small, it can be considered that the gas distribution is relatively uniform. For example, if the gas detector measures similar gas concentration values at different positions in the detection area, it can be inferred that the gas distribution in the detection area is relatively uniform.
[0082] The gas concentration gradient refers to the rate of change of gas concentration in space. By analyzing the gas concentration data collected by gas detectors at different locations, the gas concentration gradient between different locations can be calculated. For example, if the gas concentration in a certain direction within the detection area shows a clear increasing or decreasing trend, that is, the rate of change of the gas concentration is large, it means that there is a large gas concentration gradient.
[0083] The degree of uniformity and gas concentration gradient are determined as the second spatial features of the gas detection data.
[0084] In this embodiment, the gas detection data is organized according to the collection time, and then the second number of second sub-features are extracted from the time series as the second time feature of the gas detection data; the uniformity of gas distribution and the gas concentration gradient in the detection area are calculated as the second spatial feature of the gas detection data, thereby realizing feature mining of the time and space dimensions of the gas detection data.
[0085] Furthermore, the above-mentioned step S203 may include: adding the first time feature and the first space feature to the infrared radiation detection data to obtain infrared radiation enhancement data; adding the second time feature and the second space feature to the gas detection data to obtain gas enhancement data; performing Kalman filtering fusion on the infrared radiation enhancement data and the gas enhancement data to obtain a detection data body of the detection area.
[0086] Specifically, the first time feature and the first space feature are added to the infrared radiation detection data, thereby expanding the infrared radiation detection data to obtain infrared radiation enhancement data. The second time feature and the second space feature are added to the gas detection data, thereby expanding the gas detection data to obtain gas enhancement data.
[0087] The present application fuses the infrared radiation enhancement data and the gas enhancement data to form more comprehensive feature data. Data fusion can be performed by simple weighted average, data concatenation or data superposition, or by using a data fusion algorithm. In one embodiment, the fusion algorithm can use Kalman filter fusion to obtain a detection data volume of the detection area.
[0088] The Kalman filter fusion in this application uses the Kalman filter algorithm to fuse the infrared radiation enhancement data and the gas enhancement data. The Kalman filter fusion can combine the information of the infrared radiation detector and the gas detector in the detection area, and improve the estimation accuracy and robustness of the target state through fusion processing.
[0089] Since infrared radiation enhancement data and gas enhancement data contain temporal and spatial features, the information richness of the data is increased. Kalman filter fusion can make more comprehensive use of various information and improve the accuracy of target state estimation. Infrared radiation enhancement data and gas enhancement data have different characteristics and advantages. Through Kalman filter fusion, their advantages can be comprehensively utilized to improve the accuracy of subsequent safety detection. The fusion of multiple features can enhance the resistance of power plant safety detection system to interference and noise. If the data of a certain sensor is interfered, the information of other sensors can make up for its shortcomings. Kalman filter fusion can use the correlation between infrared radiation enhancement data and gas enhancement data to improve the stability and reliability of the system.
[0090] At the same time, the Kalman filter algorithm can dynamically adjust the weights of various feature data in the fusion process according to the reliability and accuracy of the data. The addition of time and space features can also make the weight adjustment more flexible and intelligent.
[0091] In this embodiment, the first time feature and the first space feature are added to the infrared radiation detection data to obtain infrared radiation enhancement data; the second time feature and the second space feature are added to the gas detection data to obtain gas enhancement data; Kalman filtering is performed on the infrared radiation enhancement data and the gas enhancement data to comprehensively utilize the data of the infrared radiation detector and the gas detector, thereby improving the accuracy of subsequent power plant safety detection.
[0092] Furthermore, the above step S204 may include: obtaining the importance factor and historical safety factor of each detection area in the power plant; calculating the weight of each detection area according to the obtained importance factor and historical safety factor; adding the weight corresponding to each detection area to the detection data body of each detection area; inputting each detection data body with weight into the safety detection model to obtain the safety detection result of the power plant.
[0093] Specifically, the power plant has multiple detection areas, and the importance and impact of different detection areas may be different, which can be reflected by the weight of the detection area. Obtain the importance factor and historical safety factor of each detection area. Among them, the importance factor reflects the importance of the detection area through the material / physical properties of the detection area. For example, if there are important equipment or dangerous substances in the detection area, the importance of the detection area is high; if the detection area is relatively empty, the importance of the detection area is low. The historical safety factor evaluates the importance of the detection area based on the fires or hidden dangers that have occurred in the detection area in history. For example, if according to historical data, there have been multiple fires or hidden dangers in detection area A, the importance of the detection area is high; if there has never been a fire or hidden danger in detection area A, the importance of the detection area is low.
[0094] The weight of each detection area is calculated based on the obtained importance factor and historical safety factor. For example, for each detection area, its importance factor and historical safety factor can be weighted averaged to obtain the weight of the detection area; the weight of the detection area can also be calculated by other weight calculation algorithms.
[0095] After obtaining the weight of the detection area, the weight is added to the detection data volume of the detection area. Then, each detection data volume with weight is input into the safety detection model, which can consider the correlation and influence between different detection areas, accurately predict and identify the fire risk in the power plant, and output the safety detection results.
[0096] In this embodiment, the importance factor and historical safety factor of each detection area in the power plant are obtained to calculate the weight of each detection area; the weight represents the importance and influence of the detection area, and the corresponding weight of each detection area is added to the detection data body of each detection area, so as to distinguish the importance and influence of the detection data body; each detection data body with weight is input into the safety detection model, and the model can consider the correlation and influence between different detection areas, can accurately predict and identify the fire risk in the power plant, and improve the accuracy of the power plant safety detection.
[0097] Furthermore, the above security detection model is constructed based on a recurrent neural network, a long short-term memory network or a gated recurrent unit.
[0098] Specifically, the present application aims to achieve advanced detection of potential safety hazards, and the established safety detection model can adopt an algorithm that has the ability to process time series data and can make future predictions. For example, the safety detection model can be constructed based on recurrent neural networks (RNN), long short-term memory networks (LSTM), gated recurrent units (GRU), etc. These algorithms can capture the time dependency in the data, thereby achieving the prediction of future safety hazards.
[0099] In this embodiment, the safety detection model can be constructed based on a recurrent neural network, a long short-term memory network or a gated recurrent unit. A safety detection model that can achieve advanced prediction can be constructed to discover potential safety hazards in advance, which is conducive to taking timely measures to prevent the occurrence of danger.
[0100] Furthermore, after the above-mentioned step of obtaining the safety inspection results of the power plant, it may also include: when it is determined that the power plant has safety hazards based on the safety inspection results, determining the target area where the safety hazards exist based on the safety inspection results; collecting a monitoring image of the target area through an image collector associated with the target area; and sending the monitoring image and the safety inspection results to the terminal corresponding to the target account.
[0101] Specifically, when it is determined according to the safety detection result that a safety hazard exists in the power plant (has occurred or will occur), a target area where the safety hazard exists is determined according to the safety detection result.
[0102] The target area is the detection area in the power plant, and the detection area is also associated with an image collector. The image collector is a device that collects real-time images, such as a camera. The power plant safety detection system can call the image collector associated with the target area to collect monitoring images of the target area. The power plant safety detection system sends the monitoring images and safety detection results to the terminal corresponding to the target account, where the target account can be the account of the power plant safety manager. The power plant safety manager can understand the safety hazards in the power plant based on the safety detection results, and understand the on-site conditions of the target area in real time through the monitoring images, which is beneficial to the safety management of the power plant and to taking timely measures to prevent the occurrence of danger.
[0103] In this embodiment, when it is determined that a power plant has safety hazards based on the safety inspection results, a target area where the safety hazards exist is determined, monitoring images of the target area are collected, and the monitoring images and safety inspection results are sent to a terminal corresponding to a target account; the target account is the account of a power plant safety manager. The power plant safety manager can understand the safety hazards existing in the power plant based on the safety inspection results, and understand the on-site conditions of the target area in real time through monitoring images, which is beneficial to the safety management of the power plant and to taking timely measures to prevent the occurrence of danger.
[0104] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).
[0105] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.
[0106] Further references Figure 3 , as a response to the above Figure 2 In order to realize the method shown in the figure, the present application provides an embodiment of a power plant safety detection device, and the device embodiment is Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.
[0107] like Figure 3 As shown, the power plant safety detection device 300 described in this embodiment includes: a data acquisition module 301, a feature extraction module 302, a data body construction module 303 and a safety detection module 304, wherein:
[0108] The data collection module 301 is used to collect infrared radiation detection data and gas detection data of each detection area in the power plant through the infrared radiation detectors and gas detectors in the detection area.
[0109] The feature extraction module 302 is used to extract the first time feature and the first space feature of the infrared radiation detection data, and to extract the second time feature and the second space feature of the gas detection data.
[0110] The data volume construction module 303 is used to construct the detection data volume of the detection area according to the infrared radiation detection data and its corresponding first time feature and first space feature, the gas detection data and its corresponding second time feature and second space feature.
[0111] The safety detection module 304 is used to input the detection data of each detection area in the power plant into the safety detection model to obtain the safety detection result of the power plant.
[0112] In this embodiment, for each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors; the infrared radiation detection data reflects the thermal radiation characteristics of the object, which is conducive to discovering abnormalities before a fire or high temperature event occurs; the gas detection data reflects the gas composition in the detection area, and the concentration change of a specific gas can be used as an early indicator of the occurrence of a fire; the infrared radiation detection data and the gas detection data have time and space attributes, and the first time feature and the first space feature of the infrared radiation detection data, as well as the second time feature and the second space feature of the gas detection data can be extracted, thereby obtaining more feature data; according to the infrared radiation detection data, the first time feature, the first space feature, the gas detection data, the second time feature and the second space feature, a detection data body of the detection area is constructed, and the detection data body contains data in specific time, space and attribute dimensions, and can realize multi-dimensional analysis and mining of the infrared radiation detection data and the gas detection data; the detection data body of each detection area is input into the safety detection model, and the model can integrate the data of each dimension, automatically predict and identify areas where there may be or have been fire risks, realize advanced detection and early warning of the safety status of the power plant, and improve the accuracy of safety detection of the power plant.
[0113] In some optional implementations of this embodiment, the feature extraction module 302 may include: an infrared tissue submodule, a first time extraction submodule, and a first space extraction submodule, wherein:
[0114] The infrared organization submodule is used to organize the infrared radiation detection data according to the acquisition time.
[0115] The first time extraction submodule is used to extract a first number of first sub-features from the organized infrared radiation detection data, and determine the extracted first sub-features as first time features of the infrared radiation detection data.
[0116] The first space extraction submodule is used to obtain coverage information and distribution density information of the infrared radiation detector from the database, and determine the coverage information and distribution density information as the first spatial feature of the infrared radiation detection data.
[0117] In this embodiment, the infrared radiation detection data is organized according to the collection time, and then the first quantity of the first sub-feature is extracted from the time series as the first time feature of the infrared radiation detection data; the coverage information and distribution density information of the infrared radiation detector are obtained from the database as the first spatial feature of the infrared radiation detection data, thereby realizing feature mining of the time and space dimensions of the infrared radiation detection data.
[0118] In some optional implementations of this embodiment, the feature extraction module 302 may further include: a gas organization submodule, a second time extraction submodule, and a second space extraction submodule, wherein:
[0119] The gas organization submodule is used to organize the gas detection data according to the collection time.
[0120] The second time extraction submodule is used to extract a second number of second sub-features from the organized gas detection data, and determine the extracted second sub-features as second time features of the gas detection data.
[0121] The second space extraction submodule is used to calculate the uniformity of gas distribution and the gas concentration gradient in the detection area based on the gas detection data, and determine the uniformity and the gas concentration gradient as the second space characteristics of the gas detection data.
[0122] In this embodiment, the gas detection data is organized according to the collection time, and then the second number of second sub-features are extracted from the time series as the second time feature of the gas detection data; the uniformity of gas distribution and the gas concentration gradient in the detection area are calculated as the second spatial feature of the gas detection data, thereby realizing feature mining of the time and space dimensions of the gas detection data.
[0123] In some optional implementations of this embodiment, the data volume construction module 303 may include: a first adding submodule, a second adding submodule and a filtering fusion submodule, wherein:
[0124] The first adding submodule is used to add the first time feature and the first space feature to the infrared radiation detection data to obtain infrared radiation enhancement data.
[0125] The second adding submodule is used to add the second time feature and the second space feature to the gas detection data to obtain gas enhancement data.
[0126] The filtering fusion submodule is used to perform Kalman filtering fusion on the infrared radiation enhancement data and the gas enhancement data to obtain the detection data volume of the detection area.
[0127] In this embodiment, the first time feature and the first space feature are added to the infrared radiation detection data to obtain infrared radiation enhancement data; the second time feature and the second space feature are added to the gas detection data to obtain gas enhancement data; Kalman filtering is performed on the infrared radiation enhancement data and the gas enhancement data to comprehensively utilize the data of the infrared radiation detector and the gas detector, thereby improving the accuracy of subsequent power plant safety detection.
[0128] In some optional implementations of this embodiment, the security detection module 304 may include: a factor acquisition submodule, a weight calculation submodule, a weight addition submodule and a security detection submodule, wherein:
[0129] The factor acquisition submodule is used to obtain the importance factor and historical safety factor of each detection area in the power plant.
[0130] The weight calculation submodule is used to calculate the weight of each detection area according to the obtained importance factor and historical safety factor.
[0131] The weight adding submodule is used to add the weights corresponding to each detection area to the detection data volume of each detection area.
[0132] The safety detection submodule is used to input each detection data body with weight into the safety detection model to obtain the safety detection result of the power plant.
[0133] In this embodiment, the importance factor and historical safety factor of each detection area in the power plant are obtained to calculate the weight of each detection area; the weight represents the importance and influence of the detection area, and the corresponding weight of each detection area is added to the detection data body of each detection area, so as to distinguish the importance and influence of the detection data body; each detection data body with weight is input into the safety detection model, and the model can consider the correlation and influence between different detection areas, can accurately predict and identify the fire risk in the power plant, and improve the accuracy of the power plant safety detection.
[0134] In some optional implementations of this embodiment, the security detection model is constructed based on a recurrent neural network, a long short-term memory network, or a gated recurrent unit.
[0135] In this embodiment, the safety detection model can be constructed based on a recurrent neural network, a long short-term memory network or a gated recurrent unit. A safety detection model that can achieve advanced prediction can be constructed to discover potential safety hazards in advance, which is conducive to taking timely measures to prevent the occurrence of danger.
[0136] In some optional implementations of this embodiment, the power plant safety detection device 300 may further include: a region determination module, an image acquisition module, and a sending module, wherein:
[0137] The area determination module is used to determine the target area where the safety hazard exists according to the safety detection result when it is determined that the power plant has a safety hazard according to the safety detection result.
[0138] The image acquisition module is used to acquire the monitoring image of the target area through an image collector associated with the target area.
[0139] The sending module is used to send the monitoring images and security detection results to the terminal corresponding to the target account.
[0140] In this embodiment, when it is determined that a power plant has safety hazards based on the safety inspection results, a target area where the safety hazards exist is determined, monitoring images of the target area are collected, and the monitoring images and safety inspection results are sent to a terminal corresponding to a target account; the target account is the account of a power plant safety manager. The power plant safety manager can understand the safety hazards existing in the power plant based on the safety inspection results, and understand the on-site conditions of the target area in real time through monitoring images, which is beneficial to the safety management of the power plant and to taking timely measures to prevent the occurrence of danger.
[0141] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.
[0142] The computer device 4 includes a memory 41, a processor 42, and a network interface 43 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 4 with components 41-43, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital processors (DSPs), embedded devices, etc.
[0143] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.
[0144] The memory 41 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 41 can be an internal storage unit of the computer device 4, such as a hard disk or memory of the computer device 4. In other embodiments, the memory 41 can also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 4. Of course, the memory 41 can also include both the internal storage unit of the computer device 4 and its external storage device. In this embodiment, the memory 41 is generally used to store the operating system and various application software installed on the computer device 4, such as computer-readable instructions of the power plant safety detection method, etc. In addition, the memory 41 can also be used to temporarily store various types of data that have been output or are to be output.
[0145] The processor 42 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 42 is generally used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is used to run computer-readable instructions or process data stored in the memory 41, such as computer-readable instructions for running the power plant safety detection method.
[0146] The network interface 43 may include a wireless network interface or a wired network interface. The network interface 43 is generally used to establish a communication connection between the computer device 4 and other electronic devices.
[0147] The computer device provided in this embodiment can execute the above power plant safety detection method. The power plant safety detection method here can be the power plant safety detection method of each of the above embodiments.
[0148] In this embodiment, for each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors; the infrared radiation detection data reflects the thermal radiation characteristics of the object, which is conducive to discovering abnormalities before a fire or high temperature event occurs; the gas detection data reflects the gas composition in the detection area, and the concentration change of a specific gas can be used as an early indicator of the occurrence of a fire; the infrared radiation detection data and the gas detection data have time and space attributes, and the first time feature and the first space feature of the infrared radiation detection data, as well as the second time feature and the second space feature of the gas detection data can be extracted, thereby obtaining more feature data; according to the infrared radiation detection data, the first time feature, the first space feature, the gas detection data, the second time feature and the second space feature, a detection data body of the detection area is constructed, and the detection data body contains data in specific time, space and attribute dimensions, and can realize multi-dimensional analysis and mining of the infrared radiation detection data and the gas detection data; the detection data body of each detection area is input into the safety detection model, and the model can integrate the data of each dimension, automatically predict and identify areas where there may be or have been fire risks, realize advanced detection and early warning of the safety status of the power plant, and improve the accuracy of safety detection of the power plant.
[0149] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores computer-readable instructions, and the computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the power plant safety detection method as described above.
[0150] In this embodiment, for each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors; the infrared radiation detection data reflects the thermal radiation characteristics of the object, which is conducive to discovering abnormalities before a fire or high temperature event occurs; the gas detection data reflects the gas composition in the detection area, and the concentration change of a specific gas can be used as an early indicator of the occurrence of a fire; the infrared radiation detection data and the gas detection data have time and space attributes, and the first time feature and the first space feature of the infrared radiation detection data, as well as the second time feature and the second space feature of the gas detection data can be extracted, thereby obtaining more feature data; according to the infrared radiation detection data, the first time feature, the first space feature, the gas detection data, the second time feature and the second space feature, a detection data body of the detection area is constructed, and the detection data body contains data in specific time, space and attribute dimensions, and can realize multi-dimensional analysis and mining of the infrared radiation detection data and the gas detection data; the detection data body of each detection area is input into the safety detection model, and the model can integrate the data of each dimension, automatically predict and identify areas where there may be or have been fire risks, realize advanced detection and early warning of the safety status of the power plant, and improve the accuracy of safety detection of the power plant.
[0151] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.
[0152] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.
Claims
1. A power plant safety detection method, characterized in that: The steps include: For each detection area in the power plant, infrared radiation detection data and gas detection data of the detection area are collected through infrared radiation detectors and gas detectors in the detection area; Extracting a first time feature and a first space feature of the infrared radiation detection data, and extracting a second time feature and a second space feature of the gas detection data; Constructing a detection data volume of the detection area according to the infrared radiation detection data and the first time feature and the first space feature corresponding thereto, and the gas detection data and the second time feature and the second space feature corresponding thereto; Inputting the detection data of each detection area in the power plant into a safety detection model to obtain a safety detection result of the power plant; The infrared radiation detection data has a timestamp, and the timestamp corresponds to the collection time of the infrared radiation detection data; The step of extracting the first time feature and the first space feature of the infrared radiation detection data comprises: Organizing the infrared radiation detection data according to collection time; Extracting a first number of first sub-features from the organized infrared radiation detection data, and determining the extracted first sub-features as first time features of the infrared radiation detection data; the number and types of the first sub-features are predetermined; the infrared radiation detection data includes data of multiple radiation indicators, and calculations are performed for each radiation indicator to obtain the first sub-features; Acquire coverage information and distribution density information of the infrared radiation detector from a database, and determine the coverage information and the distribution density information as the first spatial feature of the infrared radiation detection data; the coverage information is the spatial range detected by the infrared radiation detector, which depends on the detection capability and installation location of the infrared radiation detector; the number and distribution of the infrared radiation detectors determine the distribution density information of the infrared radiation detectors, and the distribution density information is used to evaluate the balance and coverage of fire risks in the detection area; The extraction process of the first sub-feature includes: The infrared radiation detection data at each timestamp is taken as slices, and the mean, standard value, maximum value, minimum value, trend characteristics and periodic characteristics of various radiation indicators in each slice are calculated; Calculating the hysteresis characteristics of the infrared radiation detection data through a sliding window, wherein the hysteresis characteristics include a data change trend; The gas detection data has a timestamp, and the timestamp of the gas detection data corresponds to the collection time of the gas detection data; the step of extracting the second time feature and the second space feature of the gas detection data includes: Organizing the gas detection data according to collection time; Extracting a second number of second sub-features from the organized gas detection data, and determining the extracted second sub-features as second time features of the gas detection data; the number and type of the second sub-features are predetermined; the gas detection data includes data of multiple gas indicators, and each gas indicator is calculated separately to obtain the second sub-feature; Based on the gas detection data, the uniformity of gas distribution and the gas concentration gradient in the detection area are calculated, and the uniformity and the gas concentration gradient are determined as the second spatial characteristics of the gas detection data; a plurality of gas detectors are arranged in each detection area, and each gas detector detects and evaluates the uniformity of gas distribution and the gas concentration gradient at different positions in the detection area; the uniformity and the gas concentration gradient are the uniformity and gas concentration gradient of a specified type of gas or air as a whole; the gas distribution in the detection area is evaluated through the gas concentration data collected by the gas detector; the gas concentration gradient is the rate of change of gas concentration in space, and the gas concentration gradient between different positions is calculated through the gas concentration data collected by the gas detectors at different positions; The extraction process of the second sub-feature includes: The gas detection data at each timestamp is taken as slices, and the mean, standard value, maximum value, minimum value, trend characteristics and periodic characteristics of various gas indicators in each slice are calculated; The hysteresis characteristics of the gas detection data are calculated through a sliding window, and the hysteresis characteristics include a data change trend.
2. The power plant safety detection method according to claim 1, characterized in that: The step of constructing the detection data volume of the detection area according to the infrared radiation detection data and the first time feature and the first space feature corresponding thereto, and the gas detection data and the second time feature and the second space feature corresponding thereto comprises: Adding the first time feature and the first space feature to the infrared radiation detection data to obtain infrared radiation enhancement data; adding the second time feature and the second space feature to the gas detection data to obtain gas enhancement data; The infrared radiation enhancement data and the gas enhancement data are fused by Kalman filtering to obtain a detection data volume of the detection area.
3. The power plant safety detection method according to claim 1, characterized in that: The step of inputting the detection data of each detection area in the power plant into the safety detection model to obtain the safety detection result of the power plant includes: Obtaining importance factors and historical safety factors of each detection area in the power plant; Calculate the weight of each detection area according to the obtained importance factor and historical safety factor; Adding weights corresponding to the respective detection areas to the detection data volumes of the respective detection areas; Each detection data body with a weight is input into the safety detection model to obtain the safety detection result of the power plant.
4. The power plant safety detection method according to claim 3, characterized in that: The security detection model is constructed based on a recurrent neural network, a long short-term memory network or a gated recurrent unit.
5. The power plant safety detection method according to claim 1, characterized in that: After the step of obtaining the safety detection result of the power plant, the method further includes: When it is determined according to the safety detection result that the power plant has a potential safety hazard, determining a target area having the potential safety hazard according to the safety detection result; Acquire a monitoring image of the target area by an image collector associated with the target area; The monitoring image and the security detection result are sent to the terminal corresponding to the target account.
6. A power plant safety detection device, characterized in that: include: A data acquisition module, for collecting infrared radiation detection data and gas detection data of each detection area in the power plant through infrared radiation detectors and gas detectors in the detection area; A feature extraction module, used to extract a first time feature and a first space feature of the infrared radiation detection data, and to extract a second time feature and a second space feature of the gas detection data; A data volume construction module, used for constructing a detection data volume of the detection area according to the infrared radiation detection data and the first time feature and the first space feature corresponding thereto, and the gas detection data and the second time feature and the second space feature corresponding thereto; A safety detection module, used to input the detection data of each detection area in the power plant into a safety detection model to obtain the safety detection result of the power plant; The infrared radiation detection data has a timestamp, and the timestamp corresponds to the collection time of the infrared radiation detection data; The extracting of the first time feature and the first space feature of the infrared radiation detection data comprises: Organizing the infrared radiation detection data according to collection time; Extracting a first number of first sub-features from the organized infrared radiation detection data, and determining the extracted first sub-features as first time features of the infrared radiation detection data; the number and types of the first sub-features are predetermined; the infrared radiation detection data includes data of multiple radiation indicators, and calculations are performed for each radiation indicator to obtain the first sub-features; Acquire coverage information and distribution density information of the infrared radiation detector from a database, and determine the coverage information and the distribution density information as the first spatial feature of the infrared radiation detection data; the coverage information is the spatial range detected by the infrared radiation detector, which depends on the detection capability and installation location of the infrared radiation detector; the number and distribution of the infrared radiation detectors determine the distribution density information of the infrared radiation detectors, and the distribution density information is used to evaluate the balance and coverage of fire risks in the detection area; The extraction process of the first sub-feature includes: The infrared radiation detection data at each timestamp is taken as slices, and the mean, standard value, maximum value, minimum value, trend characteristics and periodic characteristics of various radiation indicators in each slice are calculated; Calculating the hysteresis characteristics of the infrared radiation detection data through a sliding window, wherein the hysteresis characteristics include a data change trend; The gas detection data has a timestamp, and the timestamp of the gas detection data corresponds to the collection time of the gas detection data; and extracting the second time feature and the second space feature of the gas detection data includes: Organizing the gas detection data according to collection time; Extracting a second number of second sub-features from the organized gas detection data, and determining the extracted second sub-features as second time features of the gas detection data; the number and type of the second sub-features are predetermined; the gas detection data includes data of multiple gas indicators, and each gas indicator is calculated separately to obtain the second sub-feature; Based on the gas detection data, the uniformity of gas distribution and the gas concentration gradient in the detection area are calculated, and the uniformity and the gas concentration gradient are determined as the second spatial characteristics of the gas detection data; a plurality of gas detectors are arranged in each detection area, and each gas detector detects and evaluates the uniformity of gas distribution and the gas concentration gradient at different positions in the detection area; the uniformity and the gas concentration gradient are the uniformity and gas concentration gradient of a specified type of gas or air as a whole; the gas distribution in the detection area is evaluated through the gas concentration data collected by the gas detector; the gas concentration gradient is the rate of change of gas concentration in space, and the gas concentration gradient between different positions is calculated through the gas concentration data collected by the gas detectors at different positions; The extraction process of the second sub-feature includes: The gas detection data at each timestamp is taken as slices, and the mean, standard value, maximum value, minimum value, trend characteristics and periodic characteristics of various gas indicators in each slice are calculated; The hysteresis characteristics of the gas detection data are calculated through a sliding window, and the hysteresis characteristics include a data change trend.
7. A computer device, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the power plant safety detection method according to any one of claims 1 to 5 when executing the computer-readable instructions.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps of the power plant safety detection method according to any one of claims 1 to 5 are implemented.
