Intelligent power plant safety inspection method and system

Abstract

The invention relates to the technical field of power plant inspection, in particular to an intelligent power plant safety inspection method and system, and the method comprises the steps: presetting the inspection path and time of an inspection robot in a power plant; controlling an inspection robot to inspect the line of the electrical equipment along the inspection path, and acquiring appearance data of the line of the electrical equipment by using an image acquisition device mounted on the inspection robot; analyzing the appearance data to identify and judge whether the line has a fault; when the fault of the line is identified, an alarm is given to an operator, and the position and the type of the fault are provided; and optimizing the inspection route on the basis of the fault position appearing in the historical data. Therefore, the operation and maintenance efficiency of a power plant can be improved, potential safety accidents can be effectively prevented, and stable operation of a power system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power plant inspection, and in particular to a smart power plant safety inspection method and system. Background Art

[0002] Power plant safety inspection is a key task to ensure the safe operation of power production facilities. This task usually includes regular inspections of various equipment and systems in the power plant to identify any abnormal conditions or safety hazards that may affect normal operation. Inspectors will carefully check the status of key components such as generators, transformers, transmission lines, cooling systems, and use advanced detection technologies and tools to evaluate the performance of equipment. In addition, they will monitor environmental conditions, such as changes in temperature and humidity, because these factors can also affect the safety and efficiency of equipment. Through continuous inspections, potential problems can be discovered and resolved in a timely manner, thereby preventing accidents from occurring, ensuring stable power supply to the power plant while protecting the lives of workers and the surrounding environment.

[0003] However, this method of manual inspection is affected by the manual working state, which makes the detection structure unstable and unreliable, and reduces the credibility of the detection structure. Summary of the invention

[0004] The purpose of the present invention is to provide a smart power plant safety inspection method and system, which aims to automatically inspect the lines of electrical equipment in the power plant to improve the inspection efficiency.

[0005] To achieve the above-mentioned object, in a first aspect, the present invention provides a smart power plant safety inspection method, comprising presetting an inspection path and time of an inspection robot in the power plant;

[0006] Controlling the inspection robot to inspect the circuit of the electrical equipment along the inspection path, and using an image acquisition device installed on the inspection robot to collect appearance data of the circuit of the electrical equipment;

[0007] Analyzing the appearance data to identify and determine whether there is a fault in the line;

[0008] When a fault is identified on the line, an alarm is issued to the operator, and the location and type of the fault are provided;

[0009] The inspection route is optimized based on the fault locations that have appeared in historical data.

[0010] The specific steps of presetting the inspection path and time of the inspection robot in the power plant include:

[0011] Obtain the electrical equipment and line layout data of the power plant;

[0012] Generate inspection routes based on electrical equipment and line layout data;

[0013] Set up inspection points at electrical equipment along the inspection route;

[0014] Set the daily inspection time.

[0015] The specific steps of controlling the inspection robot to inspect the circuit of the electrical equipment along the inspection path and using the image acquisition device installed on the inspection robot to collect the appearance data of the circuit of the electrical equipment include:

[0016] Turn on the inspection robot and initialize the system;

[0017] The robot automatically navigates according to the preset inspection route;

[0018] When the robot reaches the inspection point, it starts the image acquisition device to capture the circuit image of the electrical equipment;

[0019] The collected line image data is transmitted back to the host computer in real time.

[0020] The specific steps of analyzing the appearance data to identify and determine whether a line has a fault include:

[0021] Establish a support vector machine model for route recognition;

[0022] Preprocessing line image data;

[0023] Use the YOLO target recognition algorithm to segment each line from the background in the preprocessed line image data to obtain segmented line data;

[0024] Extracting identification features from segmented route data;

[0025] The segmented line data is classified based on the identification features using a support vector machine model to identify faults.

[0026] The specific steps of establishing the support vector machine model for line identification include:

[0027] Collecting pre-processed line image data;

[0028] Extract identification features from the image and label each fault image to distinguish the faults;

[0029] Divide the dataset into training and validation sets;

[0030] Use the training set data to train the SVM model to obtain a support vector machine model for line recognition;

[0031] The validation set is used to validate the support vector machine model.

[0032] The specific steps of preprocessing the line image data include:

[0033] Adjust all line image data to the same size;

[0034] Optimize the overall brightness and contrast of the resized line image;

[0035] Use a filter to reduce random noise in the line image.

[0036] Wherein, the identification features include color, texture and shape.

[0037] The specific steps of issuing an alarm to an operator and providing the location and type of the fault when a fault is identified in the line include:

[0038] Classifying the corresponding segmented line data according to the characteristics of the fault to obtain the fault type, wherein the fault type includes overheating, damage, and aging;

[0039] Generate notification information based on fault type and fault location;

[0040] Send notification information to designated operators through predetermined communication channels.

[0041] In a second aspect, the present invention further provides a smart power plant safety inspection system, including an inspection path setting module, a data acquisition module, a fault judgment module, a notification module and a line optimization module;

[0042] The inspection path setting module is used to pre-set the inspection path and time of the inspection robot in the power plant;

[0043] The data acquisition module is used to control the inspection robot to inspect the circuit of the electrical equipment along the inspection path, and use the image acquisition device installed on the inspection robot to collect the appearance data of the circuit of the electrical equipment;

[0044] The fault judgment module is used to analyze the appearance data to identify and judge whether there is a fault in the line;

[0045] The notification module is used to send an alarm to the operator when a fault is identified in the line, and provide the location and type of the fault;

[0046] The line optimization module is used to optimize the inspection route based on the fault locations that have appeared in the historical data.

[0047] A smart power plant safety inspection method and system of the present invention comprises: presetting the inspection path and time of the inspection robot in the power plant; controlling the inspection robot to inspect the line of the electrical equipment along the inspection path, and using the image acquisition device installed on the inspection robot to collect the appearance data of the line of the electrical equipment; analyzing the appearance data to identify and determine whether there is a fault in the line; when it is identified that there is a fault in the line, an alarm is issued to the operator, and the fault location and type are provided; and the inspection route is optimized based on the fault location that has appeared in the historical data. The travel path of the inspection robot is pre-planned according to the actual layout of the power plant, the distribution of important equipment, and safety requirements. This usually requires consideration of factors such as avoiding obstacles, ensuring coverage of all key areas, and minimizing inspection time. Combined with the work plan of the power plant, the operating status of the equipment, and the change of power load, a reasonable inspection schedule is formulated. For example, inspections are carried out when the equipment load is low or during non-peak hours to reduce the impact on normal operations. The inspection robot is started by a remote control system, and the lines of the electrical equipment are automatically inspected according to the preset path and time. During the inspection process, a high-resolution camera or other image acquisition device installed on the robot is used to take high-definition pictures or videos of the electrical equipment circuit to collect appearance data. Image processing technology, such as machine learning algorithms, is used to analyze the collected appearance data to identify whether there are abnormalities such as cracks, rust, and wear on the surface of the equipment. By analyzing the image features, it is determined whether these abnormalities constitute actual faults, such as wire breakage, insulation damage, etc., and the severity of the fault is evaluated. Once a fault is identified, the system will immediately send an alarm message to the operator to inform the specific fault location, type, and scope of impact. In addition to instant alarms, detailed fault reports are also generated to provide a reference for subsequent maintenance work. Based on the fault data in the historical inspection records, analyze which locations are more likely to have problems. According to the frequency and location of the fault, the inspection route is dynamically adjusted to increase the attention to the high-incidence areas of the fault, thereby improving the inspection efficiency and the timeliness of fault detection. This method can not only improve the operation and maintenance efficiency of the power plant, but also effectively prevent potential safety accidents and ensure the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0049] Figure 1 It is a flow chart of a smart power plant safety inspection method according to the first embodiment of the present invention.

[0050] Figure 2 This is a flow chart of presetting the inspection path and time of the inspection robot in a power plant according to the first embodiment of the present invention.

[0051] Figure 3 It is a flow chart of the first embodiment of the present invention for controlling the inspection robot to inspect the lines of the electrical equipment along the inspection path, and using the image acquisition device installed on the inspection robot to collect the appearance data of the lines of the electrical equipment.

[0052] Figure 4 It is a flowchart of analyzing the appearance data to identify and determine whether there is a fault in the line according to the first embodiment of the present invention.

[0053] Figure 5 It is a flowchart of establishing a support vector machine model for line recognition according to the first embodiment of the present invention.

[0054] Figure 6 It is a flowchart of preprocessing line image data according to the first embodiment of the present invention.

[0055] Figure 7 The first embodiment of the present invention is to send an alarm to the operator when a line fault is identified, and provide a flow chart of the fault location and type. DETAILED DESCRIPTION

[0056] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.

[0057] First embodiment

[0058] See also Figure 1 to Figure 7 , a smart power plant safety inspection method, comprising:

[0059] S101 pre-sets the inspection route and time of the inspection robot in the power plant;

[0060] The specific steps include:

[0061] S201 obtains the electrical equipment and line layout data of the power plant;

[0062] In this step, it is necessary to collect all relevant electrical equipment information and their location distribution. This usually involves extracting the necessary data from the power plant's CAD drawings, technical documents, and other relevant information sources. This data includes but is not limited to the location of key equipment such as generators, transformers, switchgear, and the layout of power transmission lines.

[0063] S202 generates an inspection route based on electrical equipment and line layout data;

[0064] With detailed electrical equipment and line layout data, the next task is to plan one or more inspection routes. This step requires the use of path planning algorithms, such as the A* algorithm or the Dijkstra algorithm, to ensure that the robot can inspect along the most optimized path. In addition, the importance of the equipment and the potential risk level need to be considered in order to reasonably allocate inspection resources.

[0065] S203 setting up inspection points at electrical equipment on the inspection route;

[0066] In this step, checkpoints are set up near each important electrical device. When the robot reaches these checkpoints, it performs a series of predefined actions.

[0067] S204 sets the daily inspection time.

[0068] Finally, determine the specific time for daily inspections. This requires considering the equipment's operating cycle, maintenance requirements, and peak load conditions. Usually, inspections are performed during periods of low load to reduce the impact on normal operations. At the same time, ensure that the inspection frequency is high enough to capture any abnormal changes in a timely manner. Specifically, inspections can be set during employees' rest and meal times.

[0069] Through the above steps, the automated management of the inspection robot can be effectively realized, thereby improving the inspection efficiency and reducing the risk of human error.

[0070] S102 controls the inspection robot to inspect the circuit of the electrical equipment along the inspection path, and uses an image acquisition device installed on the inspection robot to collect appearance data of the circuit of the electrical equipment;

[0071] The specific steps include:

[0072] S301 turns on the inspection robot and performs system initialization;

[0073] In this step, you first need to start the inspection robot and ensure that all system functions are working properly. System initialization usually includes but is not limited to:

[0074] Power Management: Make sure the robot battery is adequately charged.

[0075] Sensor calibration: Ensure the accuracy of various sensors (such as lidar, cameras, etc.).

[0076] Communication connection: Establish a stable connection with the remote monitoring system.

[0077] Safety Check: Perform a simple autonomous test to confirm that the robot has no mechanical failures.

[0078] The S302 robot automatically navigates according to the preset inspection route;

[0079] Once the system is initialized, the robot will begin to automatically navigate according to the previously set inspection route. The navigation system usually uses advanced positioning technology and sensors to accurately guide the robot to move. In this process, the robot needs to be able to identify and avoid obstacles to ensure that it reaches each inspection point safely. The specific robot used can be selected on the market.

[0080] S303 When the robot reaches the inspection point, the image acquisition device is started to capture the circuit image of the electrical equipment;

[0081] When the robot reaches a predetermined inspection point, it automatically activates an image acquisition device, such as a high-definition camera or infrared imager, to capture images of the wiring of the electrical equipment. These images are used to detect whether the equipment has physical damage, wear or other abnormalities. In addition, other types of data are collected, such as temperature distribution.

[0082] S304 transmits the collected line image data back to the host computer in real time.

[0083] The final step is to transmit the collected image data back to the host computer of the monitoring center in real time. This data will be further analyzed to evaluate the working status of the electrical equipment. Wireless communication technology is usually used to achieve real-time transmission to ensure the immediate availability of data. The staff of the monitoring center can judge whether maintenance measures are needed based on this information, thereby preventing potential failures.

[0084] S103 analyzes the appearance data to identify and determine whether there is a fault in the line;

[0085] The specific steps include:

[0086] S401 establishes a support vector machine model for line identification;

[0087] The specific steps include:

[0088] S501 collects pre-processed line image data;

[0089] First, we need to prepare a batch of preprocessed line image datasets. These images should clearly show the appearance of the electrical equipment lines and cover various types of fault conditions so that the model can learn comprehensive features.

[0090] S502 extracts identification features from the image and labels each fault image to distinguish the fault;

[0091] Next, useful identification features such as color, texture, and shape are extracted from each image. At the same time, each image containing a fault is labeled and tagged to distinguish different fault types.

[0092] S503 divides the data set into a training set and a validation set;

[0093] The collected image dataset is randomly divided into two parts: one part is used as a training set for training the model; the other part is used as a validation set for evaluating the performance of the model.

[0094] S504 uses the training set data to train the SVM model to obtain a support vector machine model for line recognition;

[0095] The image data in the training set is used to train the SVM model. By adjusting the model parameters, the model can accurately distinguish different types of faults and learn the effective boundary between faults and non-faults.

[0096] S505 uses the validation set to validate the support vector machine model.

[0097] Use the validation set to verify the trained SVM model and evaluate the model's accuracy, recall and other indicators to ensure that the model has good generalization ability.

[0098] S402 pre-processes the line image data;

[0099] In order to improve the effect of subsequent processing steps, it is necessary to preprocess the original line image data to make it more suitable for subsequent analysis. The specific steps include:

[0100] S601 adjusts all line image data to the same size;

[0101] Resize all images to the same resolution to ensure they are of consistent size for the model to process.

[0102] S602 optimizes the overall brightness and contrast of the resized line image;

[0103] Adjust the brightness and contrast of the image to make the image details more obvious and improve the recognizability of features.

[0104] S603 uses a filter to reduce random noise in the line image.

[0105] By applying filters (such as Gaussian filters) to reduce noise interference in the image and enhance image quality.

[0106] S403 uses the YOLO target recognition algorithm to separate each line from the background in the preprocessed line image data to obtain segmented line data;

[0107] The pre-processed image is processed using the YOLO (You Only Look Once) target detection algorithm to separate the electrical equipment lines from the background. This allows more focus on the information of the lines themselves and reduces background interference.

[0108] S404 extracts identification features from the segmented route data;

[0109] The identification features include color, texture and shape. The identification features are extracted from the segmented line image, and these features include but are not limited to color, texture and shape, etc. These features are helpful for subsequent fault identification.

[0110] S405 uses a support vector machine model to classify the segmented line data based on the identification features to identify faults.

[0111] Use the previously trained SVM model to classify the segmented line data to determine whether there is a fault. If there is a fault, the specific fault type is output; if no fault is found, the line is considered to be in good condition.

[0112] S104, when a fault is identified in the line, issues an alarm to the operator and provides the location and type of the fault;

[0113] The specific steps include:

[0114] S701 classifies the corresponding segmented line data according to the characteristics of the fault to obtain the fault type, wherein the fault type includes overheating, damage, and aging;

[0115] In this step, the system first needs to collect data about the power lines through sensors or monitoring equipment. This data includes but is not limited to parameters such as current, voltage, temperature, and line images captured by cameras. Next, a machine learning model is used to analyze this data to identify whether there is a fault and further determine the specific type of fault.

[0116] Failure-related features are extracted from the collected data. For example, overheating is manifested as an abnormal increase in temperature; breakage is manifested as current fluctuations or physical damage to the insulating material; and aging is a series of changes caused by the decline in material performance over time.

[0117] According to the above characteristics, the segmented line data is classified. Common fault types include but are not limited to:

[0118] Overheating: Usually local high temperature caused by excessive load, poor contact or poor heat dissipation.

[0119] Damage: includes mechanical damage, corrosion or physical damage to insulating materials.

[0120] Aging: refers to the gradual degradation of circuit materials over time, which can lead to reduced electrical performance.

[0121] The system will record each classification result and its corresponding line location information for subsequent processing.

[0122] S702 generates notification information based on the fault type and fault location;

[0123] After the fault classification is completed, the system needs to generate a detailed alarm notification based on the fault type and location. This notification should contain enough information so that the operator can quickly understand the situation and take appropriate actions.

[0124] The system combines the fault type and location information into an easy-to-understand format. Design a standardized notification template that includes key information such as fault type, fault location, and recommended inspection or repair steps. Fill the results of the previous classification into the notification template to form the final notification information.

[0125] S703 sends notification information to the designated operator through a predetermined communication channel.

[0126] The final step is to ensure that notification information is delivered to the operator responsible for handling the fault in a timely and accurate manner.

[0127] Depending on the actual needs and urgency, you can choose from a variety of communication channels, such as email, SMS, instant messaging applications or dedicated alarm systems. Determine which operators or maintenance team members need to receive these alarm information. This usually includes front-line operators, engineers and technical support teams. Notification information containing the fault type and location is sent to the designated operators via the selected communication channel. In addition, automatic reminders can be set up to ensure that relevant personnel are notified in a timely manner even during non-working hours.

[0128] Through the above steps, the system can respond quickly when a line fault is detected, which not only reduces the time for fault handling but also improves the overall safety of the power grid.

[0129] S105 optimizes the inspection route based on the fault locations that have appeared in the historical data.

[0130] First, all relevant historical fault data needs to be collected. This data is usually stored in a database and includes but is not limited to:

[0131] The specific location where the fault occurred: such as longitude and latitude coordinates, line number or specific geographical identifier.

[0132] Fault type: such as overheating, breakage, aging, etc.

[0133] Time when the fault occurred: including date and specific time.

[0134] Time to repair: The time span from when a fault is reported to when the repair is completed.

[0135] Equipment affected: Model and specifications of equipment affected by the failure.

[0136] Clean and preprocess the collected data to ensure its accuracy and completeness. Use the processed data to perform statistical analysis of the fault location to find areas or line sections with high fault frequencies. This can be achieved by:

[0137] Frequency statistics: Calculate the number of times each fault location occurs.

[0138] Hot spot analysis: Use spatial clustering techniques (such as DBSCAN or K-Means) to identify areas with high incidence of failures.

[0139] Then, based on the analysis results of the fault locations, an optimization model is built to plan the inspection route. The methods used in this model include Dijkstra algorithm or A* algorithm to find the shortest path from the starting point to each high-prone point of faults.

[0140] Then, the optimal inspection route is output based on the optimization model. The route planning is adjusted according to the test results until the optimal state is achieved. The verified optimized route is applied to daily inspection work and its effect is continuously monitored.

[0141] Second embodiment

[0142] The present invention provides a smart power plant safety inspection system, comprising an inspection path setting module, a data acquisition module, a fault judgment module, a notification module and a line optimization module; the inspection path setting module is used to pre-set the inspection path and time of the inspection robot in the power plant; the data acquisition module is used to control the inspection robot to inspect the line of electrical equipment along the inspection path, and use an image acquisition device installed on the inspection robot to collect appearance data of the electrical equipment line; the fault judgment module is used to analyze the appearance data to identify and judge whether there is a fault in the line; the notification module is used to issue an alarm to the operator when it is identified that there is a fault in the line, and provide the fault location and type; the line optimization module is used to optimize the inspection route based on the fault location that has appeared in historical data.

[0143] In this embodiment, the inspection path setting module pre-sets the inspection path and time of the inspection robot in the power plant. The inspection path should cover all key electrical equipment and their connection lines to ensure that the health of the entire power system can be fully checked. In addition, different inspection frequencies can be set according to different equipment categories and importance levels to meet the maintenance needs of different equipment.

[0144] The data acquisition module is used to control the inspection robot to inspect the lines of electrical equipment along the set inspection path, and use the image acquisition device installed on the inspection robot to collect the appearance data of the lines of electrical equipment. The image acquisition device can be a high-resolution camera or other type of sensor to capture clear images for subsequent analysis.

[0145] The fault judgment module analyzes the collected appearance data to identify and judge whether there is a fault in the line. This process includes but is not limited to:

[0146] Image processing: pre-process the collected images, such as denoising, contrast enhancement, etc.

[0147] Feature extraction: Extract key features such as color, texture, shape, etc. from the processed image.

[0148] Pattern recognition: Using machine learning algorithms, such as deep learning networks, to identify unusual features in images that indicate potential failures.

[0149] Fault classification: Classify faults into different types based on identified features, such as insulation damage, loose connections, etc.

[0150] When the fault diagnosis module identifies a fault in the line, the fault notification module will send an alarm to the operator and provide the specific location and type of the fault. The alarm can be sent in a variety of ways, such as SMS, email, mobile application notification, etc., to ensure that the operator can be informed of the fault information in time and take appropriate measures.

[0151] The route optimization module is used to optimize the inspection route based on the fault locations that have appeared in historical data.

[0152] Through the collaborative work of these modules, the smart power plant safety inspection system can effectively improve the efficiency and accuracy of inspection work, reduce labor costs, and also improve the safety and reliability of the power system.

[0153] What is disclosed above is only a preferred embodiment of the present invention, and it certainly cannot be used to limit the scope of rights of the present invention. Ordinary technicians in this field can understand that all or part of the processes of the above embodiment and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.

Claims

1. A smart power plant safety inspection method, characterized in that: include: Pre-set the inspection route and time of the inspection robot in the power plant; Controlling the inspection robot to inspect the circuit of the electrical equipment along the inspection path, and using an image acquisition device installed on the inspection robot to collect appearance data of the circuit of the electrical equipment; Analyzing the appearance data to identify and determine whether there is a fault in the line; When a fault is identified on the line, an alarm is issued to the operator, and the location and type of the fault are provided; The inspection route is optimized based on the fault locations that have appeared in historical data.

2. A smart power plant safety inspection method according to claim 1, characterized in that: The specific steps of presetting the inspection path and time of the inspection robot in the power plant include: Obtain the electrical equipment and line layout data of the power plant; Generate inspection routes based on electrical equipment and line layout data; Set up inspection points at electrical equipment along the inspection route; Set the daily inspection time.

3. A smart power plant safety inspection method as claimed in claim 2, characterized in that: The specific steps of controlling the inspection robot to inspect the circuit of the electrical equipment along the inspection path and using the image acquisition device installed on the inspection robot to collect the appearance data of the circuit of the electrical equipment include: Turn on the inspection robot and initialize the system; The robot automatically navigates according to the preset inspection route; When the robot reaches the inspection point, it starts the image acquisition device to capture the circuit image of the electrical equipment; The collected line image data is transmitted back to the host computer in real time.

4. A smart power plant safety inspection method as claimed in claim 3, characterized in that: The specific steps of analyzing the appearance data to identify and determine whether there is a fault in the line include: Establish a support vector machine model for route recognition; Preprocessing line image data; Use the YOLO target recognition algorithm to segment each line from the background in the preprocessed line image data to obtain segmented line data; Extracting identification features from segmented route data; The segmented line data is classified based on the identification features using a support vector machine model to identify faults.

5. A smart power plant safety inspection method as claimed in claim 4, characterized in that: The specific steps of establishing the support vector machine model for line identification include: Collecting pre-processed line image data; Extract identification features from the image and label each fault image to distinguish the faults; Divide the dataset into training and validation sets; Use the training set data to train the SVM model to obtain a support vector machine model for line recognition; The validation set is used to validate the support vector machine model.

6. A smart power plant safety inspection method as claimed in claim 5, characterized in that: The specific steps of preprocessing the line image data include: Adjust all line image data to the same size; Optimize the overall brightness and contrast of the resized line image; Use a filter to reduce random noise in the line image.

7. A smart power plant safety inspection method as claimed in claim 6, characterized in that: The identifying features include color, texture and shape.

8. A smart power plant safety inspection method as claimed in claim 7, characterized in that: The specific steps of issuing an alarm to an operator and providing the location and type of the fault when a fault is identified in the line include: Classifying the corresponding segmented line data according to the characteristics of the fault to obtain the fault type, wherein the fault type includes overheating, damage, and aging; Generate notification information based on fault type and fault location; Send notification information to designated operators through predetermined communication channels.

9. A smart power plant safety inspection system, characterized in that: It includes inspection route setting module, data acquisition module, fault judgment module, notification module and line optimization module; The inspection path setting module is used to pre-set the inspection path and time of the inspection robot in the power plant; The data acquisition module is used to control the inspection robot to inspect the circuit of the electrical equipment along the inspection path, and use the image acquisition device installed on the inspection robot to collect the appearance data of the circuit of the electrical equipment; The fault judgment module is used to analyze the appearance data to identify and judge whether there is a fault in the line; The notification module is used to send an alarm to the operator when a fault is identified in the line, and provide the location and type of the fault; The line optimization module is used to optimize the inspection route based on the fault locations that have appeared in the historical data.

Images