An unmanned intelligent power monitoring method and system

Abstract

The present invention relates to the field of power monitoring and discloses an unmanned intelligent power monitoring method and system. The method and system pre-process and extract features of collected equipment operation status data, power system data and environmental data, monitor and analyze environmental parameters and environmental behaviors in the substation in real time based on the environmental data to perform abnormality detection, and then, after eliminating substation failures caused by environmental reasons, further detect and issue early warnings for abnormal conditions in the equipment operation status and power transmission process. When no abnormal conditions are detected, the method continues to analyze and evaluate the safety risks in the substation, classifies the risk levels based on the evaluation results, and provides early warning feedback. The method can timely discover environmental anomalies and issue early warnings, which is conducive to quickly locking the cause of the failure, preventing equipment failures and safety accidents caused by the environment, and taking countermeasures to the risks existing in the substation as soon as possible.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and more particularly to an unmanned intelligent power monitoring method and system. Background Art

[0002] With the rapid development of information technology, Internet of Things technology, artificial intelligence and big data analysis technology, the automation level of power systems continues to improve. As an important part of the power system, the monitoring methods of smart substations are also constantly innovating to meet the growing demand for electricity and ensure the safe, stable and efficient operation of the power grid. Traditional substation monitoring systems often rely on manual operation and monitoring, which is not only inefficient but also poses safety risks. Therefore, the method of intelligent monitoring of substation power by using artificial intelligence technology has emerged. It mainly uses advanced sensors, actuators and communication technologies to realize automatic monitoring and control of substation equipment, and uses big data analysis and artificial intelligence algorithms to process and analyze substation operation data in real time, so as to realize remote monitoring and fault diagnosis of substations.

[0003] However, the above process still has the following disadvantages:

[0004] First, existing intelligent power monitoring methods mainly use data collected by sensors directly for power monitoring and analysis, which increases the amount of data calculations, slows data processing speed, and increases operation and maintenance costs.

[0005] Second, existing intelligent power monitoring methods lack the ability to analyze substation environmental data independently. They are unable to eliminate problems caused by environmental anomalies and further detect abnormalities in substation equipment operation and power transmission. This inability to quickly identify the cause of a fault may lead to errors in the diagnosis of substation power failures.

[0006] Third, the existing intelligent power monitoring methods lack the ability to further assess the potential safety risks of substations after detecting equipment operation and power transmission, resulting in the inability to take timely response measures to the risks existing in substations. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides an unmanned intelligent power monitoring method and system to solve the problems existing in the above-mentioned background technology.

[0008] The present invention provides the following technical solution: an unmanned intelligent power monitoring method, comprising:

[0009] S1: used to collect equipment operating status data, power system data and environmental data in real time, and pre-process the collected equipment operating status data, power system data and environmental data;

[0010] S2: It is used to monitor the environmental parameters and environmental behaviors in the substation. It monitors and analyzes the environmental status in the substation in real time through environmental data, and determines whether the environmental changes in the substation are normal. If not, it will immediately issue an early warning.

[0011] S3: Based on normal environmental conditions, analyze the equipment operating status data and environmental data to determine whether there are any abnormalities in the equipment's operating status under normal environmental conditions;

[0012] S4: Based on normal environmental conditions, analyze the power transmission data of the power system in combination with the environmental data to determine whether the power transmission of the power system under normal environmental conditions has abnormal behavior;

[0013] S5: Based on the analysis of the safety risks in the substation, a safety risk assessment coefficient is calculated to assess the potential safety risks in the substation, and the safety risks are classified into different levels according to the assessment results;

[0014] S6: Used to display the analysis results on the management personnel terminal in real time and automatically generate the substation monitoring report based on the analysis process.

[0015] Preferably, the S1 monitors and collects operating status data of various devices in the substation, including device temperature, device vibration, device current, and device voltage, through sensors and built-in intelligent components of the devices;

[0016] The current, voltage, active power, reactive power, and frequency of the power system are collected through power meters, and the status information and fault records of the protection relays are read through the communication interface of the relay protection device;

[0017] By using sensors and high-definition cameras in the substation, the environmental parameters and environmental behavior data in the substation are collected in real time;

[0018] The collected data is pre-processed, including data cleaning, data conversion, data synchronization and data integration. The pre-processed data is then classified according to the data type and stored in the database.

[0019] Preferably, the S2 analyzes the temperature change value, humidity change value, gas concentration change value and wind speed change value of the substation over a period of time through the environmental parameters collected by the sensor, and comprehensively calculates the environmental state detection coefficient, and sets a preset environmental state threshold value, and compares the environmental state detection coefficient with the preset environmental state threshold value to detect whether there is any abnormality in the environmental parameter changes in the substation;

[0020] When the environmental status detection coefficient is less than or equal to the preset environmental status threshold, no abnormal changes in environmental parameters in the substation are detected, and the environmental status continues to be monitored;

[0021] When the environmental status detection coefficient is greater than the preset environmental status threshold, an environmental abnormality warning prompt is issued to the management terminal, and the management personnel are prompted to conduct on-site inspections of the equipment operation and power transmission of the power system in the substation;

[0022] By detecting anomalies in environmental behavior patterns, using image processing technology to analyze the collected video streams, and using machine learning algorithms to learn from historical data, a normal environmental pattern is established and compared with real-time environmental behavior data to detect whether there are any anomalies in the environmental behavior pattern within the substation. If the real-time environmental behavior data does not match the normal behavior pattern, it is determined to be abnormal and the detected abnormal behavior is immediately sent to the management terminal for early warning.

[0023] Meanwhile, if no abnormal environmental changes in the substation are detected, the analysis process of S3 and S4 is continued.

[0024] Preferably, the S3 is used to perform feature extraction on the equipment status operation data and environmental data, extracting key characteristic parameters affecting the equipment operation, including power, maximum vibration value, temperature change rate, and speed fluctuation, analyzing the equipment operation status under normal environmental conditions based on the extracted key characteristic parameters, and calculating the equipment operation detection index;

[0025] By comparing the device operation detection index with the preset device operation threshold, it is used to monitor and judge the operation status of the device and visualize it in a graphical form. When the value of the device operation detection index is greater than the preset device operation threshold, it is considered that there is an abnormality in the operation status of the device under normal environmental conditions, and the detected abnormality is immediately sent to the management terminal for early warning; if no abnormality is detected, S5 is continued to analyze the security risk.

[0026] Preferably, S4 extracts key characteristic parameters that affect power transmission of the power system from the power transmission data and the environmental data respectively, and fuses the extracted key characteristic parameters to form a power transmission feature set, analyzes the power transmission process under normal environmental conditions based on the power transmission feature set, and calculates the power transmission detection index;

[0027] By comparing the power transmission detection index with the preset power transmission threshold, when the value of the power transmission detection index is greater than the preset power transmission threshold, it is considered that the power transmission state of the power system under normal environmental conditions has abnormal transmission behavior, and the abnormal detection result is immediately given as an early warning feedback; if no abnormal transmission behavior is detected, S5 is continued to analyze the safety risk.

[0028] Preferably, the S5 collects substation environmental data, equipment operating status data, power transmission data and historical safety accident records over a period of historical time, pre-processes the historical data, uses the historical data to establish a risk assessment model, evaluates the potential safety risks in the substation according to the risk assessment model, and outputs the value of the safety risk assessment coefficient. Then, low-risk thresholds and high-risk thresholds are set based on historical experience, and the assessed potential safety risks are classified into levels.

[0029] Preferably, the S6 feeds back the comprehensive power detection results and assessed risk levels of the substation to the management terminal, and displays them in the form of graphics and tables on the management terminal, and automatically generates a substation monitoring report based on the environmental analysis results, equipment operation status analysis results, power transmission analysis results and safety risk assessment results, and sends it to the management terminal together with the detected abnormal results.

[0030] To achieve the above objectives, the present invention provides the following technical solutions: an unmanned intelligent power monitoring system, which implements the above unmanned intelligent power monitoring method, comprising:

[0031] Data acquisition module: used to collect equipment operation status data, power system data and environmental data in real time, and pre-process the collected equipment operation status data, power system data and environmental data;

[0032] Environmental status monitoring module: used to monitor environmental parameters and environmental behaviors within the substation. It monitors and analyzes the environmental status within the substation in real time through environmental data, and determines whether the environmental changes within the substation are normal. If not, it immediately issues an early warning.

[0033] Equipment operation detection module: Based on normal environmental conditions, the module analyzes the equipment operation status data and environmental data to determine whether there are any abnormalities in the equipment's operation status under normal environmental conditions;

[0034] Power transmission detection module: Based on normal environmental conditions, it analyzes the power transmission data of the power system and the environmental data to determine whether the power transmission of the power system under normal environmental conditions has abnormal behavior;

[0035] Safety risk assessment module: Based on the analysis of safety risks within the substation, the safety risk assessment coefficient is calculated to assess the potential safety risks within the substation and the safety risks are classified into different levels according to the assessment results;

[0036] Result feedback module: used to display the analysis results on the management personnel terminal in real time, and automatically generate substation monitoring reports based on the analysis process.

[0037] Technical effects and advantages of the present invention:

[0038] (1) The present invention provides a method for preprocessing and extracting characteristic parameters based on the collected equipment operation status data, power system data, and environmental data, which is beneficial to reducing the amount of calculation, improving the data processing speed, and further reducing the operation and maintenance costs.

[0039] (2) The present invention provides a method for first detecting abnormalities in the environmental status of the substation, and then, on the basis of eliminating problems in the substation caused by environmental abnormalities, continuing to analyze abnormalities in the equipment operation and power transmission of the substation separately. It can timely discover environmental abnormalities and issue early warnings, which is conducive to quickly locking the cause of the fault, preventing equipment failures and safety accidents caused by the environment, and solving the problem of errors in the judgment of power faults in the substation.

[0040] (3) The present invention provides a method for further evaluating the potential safety risks of substations based on the detection of equipment operation and power transmission, and classifying the potential safety risks into different levels, which provides a quantitative basis for risk management and is conducive to taking early response measures to the risks existing in substations. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A diagram showing the steps of the method of the present invention.

[0042] Figure 2 This is a system structure diagram of the present invention.

[0043] Figure 3 This is a flow chart of the method of this embodiment. DETAILED DESCRIPTION

[0044] The technical solutions of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. In addition, the forms of the various structures described in the following embodiments are merely examples. The unmanned intelligent power monitoring method and system involved in the present invention are not limited to the various structures described in the following embodiments. All other implementations obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0045] like Figure 1 This embodiment provides an unmanned intelligent power monitoring method, including:

[0046] S1: used to collect equipment operation status data, power system data and environmental data in real time, and pre-process the collected equipment operation status data, power system data and environmental data.

[0047] In this embodiment, the S1 monitors and collects operating status data of various devices in the substation, including device temperature, device vibration, device current, and device voltage, through sensors and built-in intelligent components of the devices.

[0048] The current, voltage, active power, reactive power, and frequency of the power system are collected through power meters, and the status information and fault records of the protection relays are read through the communication interface of the relay protection device;

[0049] By using sensors and high-definition cameras in the substation, the environmental parameters and environmental behavior data in the substation are collected in real time;

[0050] The collected data is pre-processed, including data cleaning, data conversion, data synchronization and data integration. The pre-processed data is then classified according to the data type and stored in the database.

[0051] It should be specifically noted that the method for collecting equipment operating status data is as follows:

[0052] Through sensors and built-in intelligent components of the equipment, the operating status data of various equipment in the substation is monitored and collected, including equipment temperature, equipment vibration, equipment current and equipment voltage. The data collected by the sensors and intelligent components is input into the data collection terminal through the wireless communication interface;

[0053] The method for collecting power system data is as follows:

[0054] By connecting the wireless communication interface of the power meter to the data acquisition terminal, the current, voltage, active power, reactive power and frequency of the power system are collected, and the status information and fault records of the protection relay are read through the communication interface of the relay protection device. The power meter includes smart meters and power meters;

[0055] The methods for collecting environmental data are as follows:

[0056] By using temperature and humidity sensors, smoke sensors, gas sensors and wind speed sensors to collect environmental parameters in the substation in real time, and installing high-definition cameras at key locations in the substation to collect environmental behavior data in real time, the sensor data is input into the data acquisition terminal through the wireless communication interface of the sensor, and the video data recorded by the camera is automatically uploaded to the data acquisition terminal through the wireless network, thereby collecting environmental data in the substation.

[0057] S2: Used to monitor the environmental parameters and environmental behaviors in the substation. It monitors and analyzes the environmental status in the substation in real time through environmental data to determine whether the environmental changes in the substation are normal. If not, it will immediately issue an early warning.

[0058] In this embodiment, the S2 analyzes the temperature change value, humidity change value, gas concentration change value and wind speed change value of the substation over a period of time through the environmental parameters collected by the sensor, and comprehensively calculates the environmental state detection coefficient, and sets a preset environmental state threshold value. The environmental state detection coefficient is compared with the preset environmental state threshold value to detect whether there is any abnormality in the environmental parameter changes in the substation;

[0059] When the environmental status detection coefficient is less than or equal to the preset environmental status threshold, no abnormal changes in environmental parameters in the substation are detected, and the environmental status continues to be monitored;

[0060] When the environmental status detection coefficient is greater than the preset environmental status threshold, an environmental abnormality warning prompt is issued to the management terminal, and the management personnel are prompted to conduct on-site inspections of the equipment operation and power transmission of the power system in the substation;

[0061] By detecting anomalies in environmental behavior patterns, using image processing technology to analyze the collected video streams, and using machine learning algorithms to learn from historical data, a normal environmental pattern is established and compared with real-time environmental behavior data to detect whether there are any anomalies in the environmental behavior pattern within the substation. If the real-time environmental behavior data does not match the normal behavior pattern, it is determined to be abnormal and the detected abnormal behavior is immediately sent to the management terminal for early warning.

[0062] Meanwhile, if no abnormal environmental changes in the substation are detected, the analysis process of S3 and S4 is continued.

[0063] It should be noted that the specific analysis method for the changes in environmental parameters in the substation is as follows:

[0064] Step S211: Synchronously record the temperature data, humidity data, CO2 concentration data and wind speed data of the substation over a period of time through the temperature sensor, humidity sensor, gas sensor and wind speed sensor in the substation;

[0065] Step S212: Calculate the temperature change value within a period of time , humidity change value , CO2 concentration change And wind speed change value , the specific calculation formula is , , , ,in, represents the final temperature value recorded, Indicates the initial temperature value recorded, Indicates the final humidity value recorded, Indicates the initial humidity value recorded, Indicates the final CO2 concentration value recorded, Indicates the initial CO2 concentration value recorded, Indicates recording the final wind speed value in the substation. Indicates recording the initial wind speed value in the substation;

[0066] Step S213: Based on the temperature change value, humidity change value, CO2 concentration change value and wind speed change value, the environmental detection coefficient is calculated as follows: ,in, They represent weight coefficients respectively, and the specific values ​​are determined according to the importance of each parameter on the environmental state;

[0067] Step S214: Compare the calculated environmental state detection coefficient R with the preset environmental state threshold Comparison is used to detect whether there is any abnormality in the environmental parameter changes in the substation. , then no abnormal changes in environmental parameters in the substation are detected, and S3 is continued to detect the operating status of the equipment and S4 is continued to detect the power changes of the power system. If , it detects that the environmental parameters in the substation have changed beyond the normal range, and immediately sends an early warning of environmental anomalies to the management terminal. At the same time, it prompts the management to conduct on-site inspections of the equipment operation and power transmission of the power system in the substation;

[0068] The specific analysis method for the changes in the environmental behavior pattern in the substation is as follows:

[0069] Step S221: Real-time video data from the substation is collected through surveillance cameras, and the video images are pre-processed. A human body detection algorithm is used to identify the human outline in the video, and the detected human body is tracked and its motion trajectory is analyzed.

[0070] Step S222: The process of establishing a normal environment model using a machine learning algorithm is as follows: annotating historical video data to mark normal behavior and intrusion behavior, extracting features such as human position, speed, and direction from video frames, using a supervised learning algorithm to classify normal and intrusion behaviors to construct a normal behavior model, and cross-validating to ensure the accuracy and generalization ability of the model;

[0071] Step S223: The real-time video stream is input into the trained normal behavior model. The model will extract key features from the video stream, including human body outline or shape, movement direction and speed, target size, appearance time and appearance location, and compare the extracted real-time data features with the normal environment pattern learned during previous training, and set intrusion rules. If the real-time data does not match the normal behavior pattern and triggers the intrusion rule, the model will judge it as abnormal behavior. Once the model detects intrusion behavior, the system will immediately send an early warning prompt to the management terminal.

[0072] S3: Based on normal environmental conditions, the device operating status data and environmental data are combined for analysis to determine whether there are any abnormalities in the operating status of the device under normal environmental conditions.

[0073] In this embodiment, S3 is used to extract features from the device status operation data and environmental data, extracting key characteristic parameters that affect device operation, including power, maximum vibration value, temperature change rate, and speed fluctuation. The device operation status under normal environmental conditions is analyzed based on the extracted key characteristic parameters, and the device operation detection index is calculated.

[0074] By comparing the device operation detection index with the preset device operation threshold, it is used to monitor and judge the operation status of the device and visualize it in a graphical form. When the value of the device operation detection index is greater than the preset device operation threshold, it is considered that there is an abnormality in the operation status of the device under normal environmental conditions, and the detected abnormality is immediately sent to the management terminal for early warning; if no abnormality is detected, S5 is continued to analyze the security risk.

[0075] It should be noted that the analysis process of the equipment operating status includes:

[0076] Step S311: extract key characteristic parameters from the equipment status operation data and environmental data to perform data fusion, and fuse them into a characteristic parameter set as ;

[0077] Step S312: Calculate the equipment operation detection index based on the extracted characteristic parameter set. The specific calculation formula is: ,in, represents the jth extracted feature parameter value, represents the maximum value of the jth characteristic parameter, represents the minimum value of the jth characteristic parameter, represents the weight coefficient of the jth feature parameter, and M represents the number of extracted feature parameters;

[0078] Step S313: Set the equipment operation threshold according to historical data and expert knowledge, and compare the equipment operation detection index D with the preset equipment operation threshold. Compare to determine whether there is any abnormality in the operation status of the equipment under normal environmental conditions. , the equipment is considered to be operating normally under normal environmental conditions, and the safety risk assessment for the substation is continued. If , it is considered that the equipment is operating abnormally under normal environmental conditions, and an early warning message is immediately generated and sent to the management terminal.

[0079] S4: Based on normal environmental conditions, the power transmission data of the power system is combined with the environmental data for analysis to determine whether abnormal behavior occurs in the power transmission of the power system under normal environmental conditions.

[0080] In this embodiment, S4 extracts key characteristic parameters that affect power transmission in the power system from the power transmission data and the environmental data, fuses the extracted key characteristic parameters, and forms a power transmission feature set. The power transmission process under normal environmental conditions is analyzed based on the power transmission feature set, and a power transmission detection index is calculated.

[0081] By comparing the power transmission detection index with the preset power transmission threshold, when the value of the power transmission detection index is greater than the preset power transmission threshold, it is considered that the power transmission state of the power system under normal environmental conditions has abnormal transmission behavior, and the abnormal detection result is immediately given as an early warning feedback; if no abnormal transmission behavior is detected, S5 is continued to analyze the safety risk.

[0082] It should be noted that the power transmission detection index is calculated and analyzed by the extracted characteristic parameter set, and the specific calculation formula is: , where I represents the actual current value of power transmission, and V represents the actual voltage value of power transmission. represents the power transmission data function, T represents the actual temperature, H represents the actual humidity, V represents the actual wind speed, and C represents the pollutant concentration. A function representing environmental data, is the weight coefficient.

[0083] S5: Based on the analysis of the safety risks in the substation, a safety risk assessment coefficient is calculated to assess the potential safety risks in the substation, and the safety risks are graded according to the assessment results.

[0084] In this embodiment, the S5 collects substation environmental data, equipment operating status data, power transmission data and historical safety accident records over a period of historical time, pre-processes the historical data, uses the historical data to establish a risk assessment model, evaluates the potential safety risks in the substation according to the risk assessment model, and outputs the value of the safety risk assessment coefficient. Then, low-risk thresholds and high-risk thresholds are set based on historical experience, and the assessed potential safety risks are classified into levels.

[0085] It should be noted that the specific steps for security risk assessment are as follows:

[0086] Step S511: performing data cleaning, data standardization, and data integration on the collected historical substation environmental data, equipment operating status data, power transmission data, and historical safety accident records;

[0087] Step S512: Based on the characteristics of the substation, select indicators in terms of environment, equipment, power transmission, etc., and choose an appropriate risk assessment method, such as the analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method, to build a risk assessment model.

[0088] Step S513: Calculate the weight of each indicator according to the risk assessment model, and score each indicator to obtain a scoring matrix. Based on the weight of each indicator and the scoring matrix, calculate the security risk assessment coefficient: , where W represents the weight vector and Q represents the rating matrix;

[0089] For example, taking the analytic hierarchy process as an example, the calculation formula for establishing the judgment matrix is ​​as follows:

[0090]

[0091] in, Indicates the comparison of the importance of index p and index q;

[0092] Calculate the weight vector W: , represents the eigenvalue of the judgment matrix Q, represents the corresponding eigenvector;

[0093] According to the safety risk assessment coefficient S and the low risk threshold and high risk thresholds , divide the security risks into the following levels: , then the potential security risk is classified as low risk. , then the potential security risk is classified as medium risk. , the potential security risk is classified as high risk.

[0094] S6: Used to display the analysis results on the management personnel terminal in real time and automatically generate the substation monitoring report based on the analysis process.

[0095] In this embodiment, the S6 feeds back the comprehensive power detection results and assessed risk levels of the substation to the management terminal, and displays them in the form of graphics and tables on the management terminal. It automatically generates a substation monitoring report based on the environmental analysis results, equipment operation status analysis results, power transmission analysis results and safety risk assessment results, and sends it to the management terminal together with the detected abnormal results.

[0096] like Figure 2 The embodiment shown provides an implementation system corresponding to an unattended intelligent power monitoring method, including a data acquisition module, an environmental status monitoring module, an equipment operation detection module, a power transmission detection module, a safety risk assessment module and a result feedback module. The data acquisition module is connected to the environmental status monitoring module, the environmental status monitoring module is connected to the equipment operation detection module, the environmental status monitoring module is connected to the power transmission detection module, the equipment operation detection module is connected to the safety risk assessment module, the power transmission detection module is connected to the safety risk assessment module, and the safety risk assessment module is connected to the result feedback module.

[0097] The data acquisition module is used to collect equipment operating status data, power system data and environmental data in real time, and pre-process the collected equipment operating status data, power system data and environmental data;

[0098] The environmental status monitoring module is used to monitor the environmental parameters and environmental behavior in the substation, monitor and analyze the environmental status in the substation in real time through environmental data, and determine whether the environmental changes in the substation are normal. If not, an early warning process is immediately carried out;

[0099] The device operation detection module analyzes the device operation status data and the environmental data under normal environmental conditions to determine whether there is any abnormality in the operation status of the device under normal environmental conditions;

[0100] The power transmission detection module analyzes the power transmission data of the power system in combination with the environmental data under normal environmental conditions to determine whether the power transmission of the power system under normal environmental conditions has abnormal behavior;

[0101] The safety risk assessment module calculates a safety risk assessment coefficient based on the analysis of the safety risks in the substation, which is used to assess the potential safety risks in the substation and classify the safety risks into levels according to the assessment results;

[0102] The result feedback module is used to display the analysis results on the management personnel terminal in real time and automatically generate a substation monitoring report based on the analysis process.

[0103] like Figure 3 The embodiment provides a method for unattended intelligent power monitoring, and the corresponding process includes:

[0104] Collect equipment operating status data, power system data, and environmental data, and perform preprocessing and feature extraction;

[0105] Analyze environmental parameters and abnormal environmental behaviors within the substation to determine whether the environmental changes within the substation are normal;

[0106] Analyze the equipment's operating status under normal environmental conditions and determine whether there are any abnormalities in the equipment's operating status under normal environmental conditions;

[0107] Analyze the power transmission of the power system under normal environmental conditions and determine whether the power transmission of the power system under normal environmental conditions has abnormal behavior;

[0108] Based on the assessment and risk level classification of safety risks within the substation;

[0109] The analysis results are displayed in real time on the management terminal.

[0110] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0111] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. An unmanned intelligent power monitoring method, characterized in that: include: S1: used to collect equipment operating status data, power system data and environmental data in real time, and pre-process the collected equipment operating status data, power system data and environmental data; S2: It is used to monitor the environmental parameters and environmental behaviors in the substation. It monitors and analyzes the environmental status in the substation in real time through environmental data, and determines whether the environmental changes in the substation are normal. If not, it will immediately issue an early warning. The specific analysis method for the changes in environmental parameters in the substation is as follows: Step S211: Synchronously record the temperature data, humidity data, CO2 concentration data and wind speed data of the substation over a period of time through the temperature sensor, humidity sensor, gas sensor and wind speed sensor in the substation; Step S212: Calculate the temperature change value within a period of time , humidity change value , CO2 concentration change And wind speed change value , the specific calculation formula is , , , ,in, represents the final temperature value recorded, Indicates the initial temperature value recorded, represents the final humidity value recorded, Indicates the initial humidity value recorded, Indicates the final CO2 concentration value recorded, Indicates the initial CO2 concentration value recorded, Indicates recording the final wind speed value in the substation. Indicates recording the initial wind speed value in the substation; Step S213: Based on the temperature change value, humidity change value, CO2 concentration change value and wind speed change value, the environmental detection coefficient is calculated as follows: ,in, They represent weight coefficients respectively, and the specific values ​​are determined according to the importance of each parameter on the environmental state; Step S214: Compare the calculated environmental state detection coefficient R with the preset environmental state threshold Comparison is used to detect whether there is any abnormality in the environmental parameter changes in the substation. , then no abnormal changes in environmental parameters in the substation are detected, and S3 is continued to detect the operating status of the equipment and S4 is continued to detect the power changes of the power system. If , it detects that the environmental parameters in the substation have changed beyond the normal range, and immediately sends an early warning of environmental anomalies to the management terminal. At the same time, it prompts the management to conduct on-site inspections of the equipment operation and power transmission of the power system in the substation; The specific analysis method for the changes in the environmental behavior pattern in the substation is as follows: Step S221: Real-time video data from the substation is collected through surveillance cameras, and the video images are pre-processed. A human body detection algorithm is used to identify the human outline in the video, and the detected human body is tracked and its motion trajectory is analyzed. Step S222: The process of establishing a normal environment model using a machine learning algorithm is as follows: annotating historical video data to mark normal behavior and intrusion behavior, extracting human position, speed, and direction from video frames, using a supervised learning algorithm to classify normal and intrusion behaviors to construct a normal behavior model, and cross-validating to ensure the accuracy and generalization ability of the model; Step S223: The real-time video stream is input into the trained normal behavior model. The model extracts key features from the video stream, including human outline or shape, movement direction and speed, target size, appearance time, and appearance location. The extracted real-time data features are compared with the normal environment patterns learned during previous training, and intrusion rules are set. If the real-time data does not match the normal behavior pattern and triggers the intrusion rules, the model will determine it as abnormal behavior. Once the model detects intrusion behavior, the system will immediately send an early warning prompt to the administrator terminal; S3: Based on normal environmental conditions, analyze the equipment operating status data and environmental data to determine whether there are any abnormalities in the equipment's operating status under normal environmental conditions; S4: Based on normal environmental conditions, analyze the power transmission data of the power system in combination with the environmental data to determine whether the power transmission of the power system under normal environmental conditions has abnormal behavior; S5: Based on the analysis of the safety risks in the substation, a safety risk assessment coefficient is calculated to assess the potential safety risks in the substation, and the safety risks are classified into different levels according to the assessment results; The S5 collects substation environmental data, equipment operating status data, power transmission data, and historical safety accident records over a period of time, pre-processes the historical data, and uses the historical data to establish a risk assessment model. The S5 then assesses the potential safety risks in the substation based on the risk assessment model and outputs the value of the safety risk assessment coefficient. The S5 then sets low-risk and high-risk thresholds based on historical experience and classifies the assessed potential safety risks into different levels. The specific steps for security risk assessment are as follows: Step S511: performing data cleaning, data standardization, and data integration on the collected historical substation environmental data, equipment operating status data, power transmission data, and historical safety accident records; Step S512: Based on the characteristics of the substation, select indicators of the environment, equipment, and power transmission, and choose an appropriate risk assessment method to construct a risk assessment model; Step S513: Calculate the weight of each indicator according to the risk assessment model, and score each indicator to obtain a scoring matrix. Based on the weight of each indicator and the scoring matrix, calculate the security risk assessment coefficient: , where W represents the weight vector and Q represents the rating matrix; The analytic hierarchy process is selected as the risk assessment method, and the calculation formula for establishing the judgment matrix is ​​as follows: in, Indicates the comparison of the importance of index p and index q; Calculate the weight vector W: , represents the eigenvalue of the judgment matrix Q, represents the corresponding eigenvector; According to the safety risk assessment coefficient S and the low risk threshold and high risk thresholds , divide the security risks into the following levels: , then the potential security risk is classified as low risk. , then the potential security risk is classified as medium risk. , then the potential security risk is classified as high risk; S6: Used to display the analysis results on the management personnel terminal in real time and automatically generate the substation monitoring report based on the analysis process.

2. The unmanned intelligent power monitoring method according to claim 1, characterized in that: The S1 uses sensors and built-in intelligent components to monitor and collect operating status data of various devices in the substation, including device temperature, device vibration, device current, and device voltage; The current, voltage, active power, reactive power, and frequency of the power system are collected through power meters, and the status information and fault records of the protection relays are read through the communication interface of the relay protection device; By using sensors and high-definition cameras in the substation, the environmental parameters and environmental behavior data in the substation are collected in real time; The collected data is pre-processed, including data cleaning, data conversion, data synchronization and data integration. The pre-processed data is then classified according to the data type and stored in the database.

3. The unmanned intelligent power monitoring method according to claim 2, characterized in that: The S2 analyzes the temperature change value, humidity change value, gas concentration change value and wind speed change value of the substation over a period of time through the environmental parameters collected by the sensor, and comprehensively calculates the environmental state detection coefficient, and sets a preset environmental state threshold value, and compares the environmental state detection coefficient with the preset environmental state threshold value to detect whether there is any abnormality in the environmental parameter changes in the substation; When the environmental status detection coefficient is less than or equal to the preset environmental status threshold, no abnormal changes in environmental parameters in the substation are detected, and the environmental status continues to be monitored; When the environmental status detection coefficient is greater than the preset environmental status threshold, an environmental abnormality warning prompt is issued to the management terminal, and the management personnel are prompted to conduct on-site inspections of the equipment operation and power transmission of the power system in the substation; By detecting anomalies in environmental behavior patterns, using image processing technology to analyze the collected video streams, and using machine learning algorithms to learn from historical data, a normal environmental pattern is established and compared with real-time environmental behavior data to detect whether there are any anomalies in the environmental behavior pattern within the substation. If the real-time environmental behavior data does not match the normal behavior pattern, it is determined to be abnormal and the detected abnormal behavior is immediately sent to the management terminal for early warning. Meanwhile, if no abnormal environmental changes in the substation are detected, the analysis process of S3 and S4 is continued.

4. The unmanned intelligent power monitoring method according to claim 3, characterized in that: S3 is used to extract features from the equipment status operation data and environmental data, extract key characteristic parameters that affect equipment operation, including power, maximum vibration value, temperature change rate, and speed fluctuation, analyze the equipment operation status under normal environmental conditions based on the extracted key characteristic parameters, and calculate the equipment operation detection index; By comparing the device operation detection index with the preset device operation threshold, it is used to monitor and judge the operation status of the device and visualize it in a graphical form. When the value of the device operation detection index is greater than the preset device operation threshold, it is considered that there is an abnormality in the operation status of the device under normal environmental conditions, and the detected abnormality is immediately sent to the management terminal for early warning; if no abnormality is detected, S5 is continued to analyze the security risk.

5. The unmanned intelligent power monitoring method according to claim 3, characterized in that: S4 extracts key characteristic parameters that affect power transmission in the power system from the power transmission data and the environmental data, fuses the extracted key characteristic parameters to form a power transmission feature set, analyzes the power transmission process under normal environmental conditions based on the power transmission feature set, and calculates a power transmission detection index; By comparing the power transmission detection index with the preset power transmission threshold, when the value of the power transmission detection index is greater than the preset power transmission threshold, it is considered that the power transmission state of the power system under normal environmental conditions has abnormal transmission behavior, and the abnormal detection result is immediately given as an early warning feedback; If no abnormal transmission behavior is detected, continue to perform S5 to analyze the security risks.

6. The unmanned intelligent power monitoring method according to claim 1, characterized in that: The S6 feeds back the comprehensive power detection results and assessed risk levels of the substation to the management terminal, and displays them in the form of graphics and tables on the management terminal. It automatically generates a substation monitoring report based on the environmental analysis results, equipment operation status analysis results, power transmission analysis results and safety risk assessment results, and sends it to the management terminal together with the detected abnormal results.

7. An unmanned intelligent power monitoring system, implementing an unmanned intelligent power monitoring method according to any one of claims 1 to 6, characterized in that: include: Data acquisition module: used to collect equipment operation status data, power system data and environmental data in real time, and pre-process the collected equipment operation status data, power system data and environmental data; Environmental status monitoring module: used to monitor environmental parameters and environmental behaviors within the substation. It monitors and analyzes the environmental status within the substation in real time through environmental data, and determines whether the environmental changes within the substation are normal. If not, it immediately issues an early warning. Equipment operation detection module: Based on normal environmental conditions, the module analyzes the equipment operation status data and environmental data to determine whether there are any abnormalities in the equipment's operation status under normal environmental conditions; Power transmission detection module: Based on normal environmental conditions, it analyzes the power transmission data of the power system and the environmental data to determine whether the power transmission of the power system under normal environmental conditions has abnormal behavior; Safety risk assessment module: Based on the analysis of safety risks within the substation, the safety risk assessment coefficient is calculated to assess the potential safety risks within the substation and the safety risks are classified into different levels according to the assessment results; Result feedback module: used to display the analysis results on the management personnel terminal in real time, and automatically generate substation monitoring reports based on the analysis process.

Images