Power distribution cabinet safety early warning method and system

Abstract

The invention provides a power distribution cabinet safety early warning method and system, and belongs to the technical field of power distribution cabinet safety early warning. Monitoring areas are accurately divided, operation data of core components are monitored in real time, and comprehensive analysis of historical data and construction of a correlation influence network diagram are combined; according to the invention, deep understanding and intelligent prediction of the operation state of the power distribution cabinet are realized, a fault area can be timely found and pre-warned, a monitoring area associated with the fault area is automatically identified as a potential safety hazard monitoring area, a pre-warning notification is triggered, and in addition, the detection frequency can be dynamically adjusted according to the operation parameters of the potential safety hazard monitoring area. The use efficiency of monitoring resources is optimized, and the operation and maintenance efficiency and safety of the power distribution cabinet are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution cabinet safety early warning, and in particular to a power distribution cabinet safety early warning method and system. Background Art

[0002] In the power system, the distribution cabinet is a key device for power distribution and transmission. Its safe and stable operation is directly related to the reliability and safety of the entire power system. However, in actual applications, the distribution cabinet faces a variety of security threats and challenges, such as equipment aging, overload operation, short circuit failure, abnormal ambient temperature and humidity, etc. These problems may cause the distribution cabinet to fail, thus affecting the normal operation of the power system.

[0003] Traditional power distribution cabinet safety early warning technology mainly relies on manual inspection and regular maintenance, but this method has many shortcomings. First, manual inspection cannot monitor the operating status of the power distribution cabinet in real time, and it is difficult to detect potential safety hazards in time. Secondly, the safety early warning method of the traditional power distribution cabinet often lacks scientific and reasonable regional division, and requires long-term and continuous monitoring of all regional monitoring data of the power distribution cabinet, resulting in a waste of monitoring resources and time-consuming and labor-intensive monitoring. It is difficult to accurately reflect the actual operating status of each component in the long term, resulting in low early warning efficiency.

[0004] Therefore, it is necessary to provide a distribution cabinet safety early warning method and system to solve the above technical problems. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a distribution cabinet safety warning method and system for solving the problem that the traditional distribution cabinet safety warning method requires long-term and continuous monitoring of all area monitoring data of the distribution cabinet, resulting in waste of monitoring resources, time-consuming and labor-intensive monitoring, and low warning efficiency.

[0006] The present invention provides a power distribution cabinet safety early warning method, the safety early warning method comprising the following steps: The interior of the power distribution cabinet is divided into multiple monitoring areas, and the monitoring area to which the core components of the power distribution cabinet belong is divided into a primary core monitoring area; Collect historical data of the power distribution cabinet and obtain the mutual influence relationship between each monitoring area through data association analysis method. The historical data includes power operation data and temperature and humidity data. Based on the mutual influence relationship between the various monitoring areas, the final core monitoring area is further divided from the primary core monitoring area through data statistical methods; Build a safety prediction model based on historical data of power distribution cabinets; Monitor the operating data of each final core monitoring area in real time, input it into the safety prediction model after preprocessing, and output the estimated results of each final core monitoring area, so as to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area; The operating parameters of the safety hazard monitoring area are obtained in real time, and the operating parameters of the safety hazard monitoring area are judged according to the preset operating parameter safety standard threshold. If the judgment result exceeds the safety standard threshold, an early warning notification is triggered and the detection frequency is dynamically adjusted.

[0007] Preferably, the interior of the power distribution cabinet is divided into a plurality of monitoring areas, and the monitoring area to which the core components of the power distribution cabinet belong is divided into primary core monitoring areas, and the specific steps are: According to the functional layout and component distribution of the power distribution cabinet, the inside of the power distribution cabinet is divided into multiple independent monitoring areas, and the divided monitoring areas are specifically divided by electrical connection, heat conduction or physical location factors; After the divided monitoring areas are obtained, the monitoring areas to which the core components of the power distribution cabinet belong are determined, and the determined monitoring areas to which the core components of the power distribution cabinet belong are divided into primary core monitoring areas.

[0008] Preferably, the historical data of the power distribution cabinet is collected, and the mutual influence relationship between each monitoring area is obtained by a data association analysis method, wherein the historical data includes power operation data and temperature and humidity data, and the specific steps are: Determine the type of historical data to be collected from the power distribution cabinet and the time span of the historical data, where the type of historical data specifically includes power operation data and temperature and humidity data, and the time span of the historical data specifically is the past six months or one year; Based on determining the type of historical data to be collected from the power distribution cabinet and the time span of the historical data, the historical data of the power distribution cabinet is collected and preprocessed to obtain the preprocessed historical data, wherein the preprocessing specifically includes data cleaning and data conversion; The correlation coefficient in the data association analysis method analyzes the mutual influence relationship between each monitoring area and obtains the influence relationship between each monitoring area; The influence relationship between each monitoring area is output in the form of a chart or report.

[0009] Preferably, the method further divides the final core monitoring area from the primary core monitoring area by a data statistical method based on the mutual influence relationship between the obtained monitoring areas, and the specific steps are: Utilize the correlation coefficient, covariance analysis or regression analysis in the data statistics method to quantify the mutual influence degree between each monitoring area, and obtain the quantified mutual influence degree between each monitoring area; Based on the quantified mutual influence between each monitoring area, a correlation influence network diagram between each primary core monitoring area and other monitoring areas is constructed, and each primary core monitoring area is respectively associated with other monitoring areas; In the constructed association impact network diagram, the total impact of each primary core monitoring area on other monitoring areas is evaluated by calculating the sum of their impact coefficients, and the total impact of each monitoring area is obtained; An influence threshold is set, and each primary core monitoring area whose total influence exceeds the influence threshold is determined as the final core monitoring area.

[0010] Preferably, the safety prediction model is constructed based on the historical data of the power distribution cabinet, and the specific steps are: Obtain historical data of the power distribution cabinet, including current, voltage, temperature, operating time, or maintenance records, and pre-process it; Identify the mapping relationship between current, voltage, temperature, operating time and corresponding fault problems in maintenance records; A neural network model is selected as the architecture, and the mapping relationship between current, voltage, temperature, operating time and the corresponding fault problems in the maintenance records is used as the training set to train the neural network model to obtain a safety prediction model.

[0011] Preferably, the real-time monitoring of the operating data of each final core monitoring area is input into the safety prediction model after preprocessing to output the estimated results of each final core monitoring area, so as to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area, and the specific steps are: The operation data in the final core monitoring area is obtained through sensors and pre-processed; The pre-processed operation data in the final core monitoring area is standardized and converted into a format recognized by the safety prediction model, and then input into the safety prediction model to output the prediction results of each final core monitoring area; The final core monitoring area with a predicted result of failure is identified, and the monitoring areas associated with it are marked as safety hazard monitoring areas.

[0012] Preferably, the real-time acquisition of the operating parameters of the potential safety hazard monitoring area, the determination of the operating parameters of the potential safety hazard monitoring area according to the preset operating parameter safety standard threshold, if the determination result is that the safety standard threshold is exceeded, triggering an early warning notification and dynamically adjusting the detection frequency, the specific steps are: By collecting the operating parameters of the potential safety hazard monitoring area in real time and comparing them with the safety standard threshold after pre-processing, it is determined whether the operating parameters of each potential safety hazard monitoring area exceed the safety range and obtain the judgment result; When the judgment result is that the operating parameters exceed the safety standard threshold, the safety hazard monitoring area where the operating parameters exceed the safety standard threshold is marked, and an early warning notification is triggered at the same time, where the early warning notification specifically includes a sound alarm, flashing lights, SMS reminders or email notifications; Increase the detection frequency of safety hazard monitoring areas where operating parameters exceed the safety standard threshold, and continuously detect the operating parameters of the safety hazard monitoring areas.

[0013] A power distribution cabinet safety warning system, the safety warning system comprising: The area division module is used to divide the interior of the power distribution cabinet into multiple monitoring areas, and divide the monitoring area to which the core components of the power distribution cabinet belong into primary core monitoring areas; The data analysis module is used to collect historical data of the power distribution cabinet and obtain the mutual influence relationship between various monitoring areas through data association analysis methods, where the historical data includes power operation data and temperature and humidity data; A region identification module is used to further divide the final core monitoring area from the primary core monitoring area through a data statistical method based on the mutual influence relationship between the various monitoring areas obtained; Model building module, used to build a safety prediction model based on the historical data of the power distribution cabinet; The estimation processing module is used to monitor the operating data of each final core monitoring area in real time, input it into the safety prediction model after preprocessing, and output the estimation results of each final core monitoring area, so as to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area; The early warning adjustment module is used to obtain the operating parameters of the safety hazard monitoring area in real time, and judge the operating parameters of the safety hazard monitoring area according to the preset operating parameter safety standard threshold. If the judgment result exceeds the safety standard threshold, the early warning notification is triggered and the detection frequency is dynamically adjusted.

[0014] Compared with the related art, the power distribution cabinet safety early warning method and system provided by the present invention have the following beneficial effects: The present invention achieves an in-depth understanding and intelligent prediction of the operating status of the distribution cabinet by accurately dividing the monitoring area and monitoring the operating data of the core components in real time, combining the comprehensive analysis of historical data with the construction of the associated impact network diagram. It can timely discover and warn of fault areas, and automatically identify the monitoring areas associated with them as safety hazard monitoring areas, and trigger early warning notifications. In addition, it can also dynamically adjust the detection frequency according to the operating parameters of the safety hazard monitoring area, optimize the use efficiency of monitoring resources, and significantly improve the operation and maintenance efficiency and safety of the distribution cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1The present invention is a flow chart of a power distribution cabinet safety early warning method.

[0016] Figure 2 The system block diagram of a power distribution cabinet safety early warning system of the present invention. DETAILED DESCRIPTION

[0017] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes. Example

[0018] like Figure 1 As shown, a power distribution cabinet safety early warning method includes the following steps:.

[0019] S1. Divide the interior of the power distribution cabinet into multiple monitoring areas, and divide the monitoring area to which the core components of the power distribution cabinet belong into primary core monitoring areas.

[0020] In the specific implementation process, the specific steps of step S1 are: S101. Divide the interior of the distribution cabinet into multiple independent monitoring areas according to the functional layout and component distribution of the distribution cabinet to obtain the divided monitoring areas, which are specifically divided according to factors such as electrical connection, heat conduction or physical location.

[0021] Specifically, in this embodiment, components with similar electrical characteristics are divided into the same monitoring area. For example, all circuit breakers, disconnectors, etc. directly connected to the bus are divided into one monitoring area to monitor the operating status of the bus and its connected components; adjacent or similar components on the heat conduction path are divided into the same monitoring area. For example, components such as transformers and capacitors with large heat generation and the heat dissipation devices around them are divided into one monitoring area to monitor the temperature changes of these components; considering the physical position relationship of the components inside the distribution cabinet, adjacent or similar components are divided into the same monitoring area. For example, components such as circuit breakers and transformers located on the upper part of the distribution cabinet are divided into one monitoring area to monitor the physical status of these components.

[0022] S102: After obtaining the divided monitoring areas, determine the monitoring areas to which the core components of the power distribution cabinet belong, and divide the determined monitoring areas to which the core components of the power distribution cabinet belong into primary core monitoring areas.

[0023] Specifically, in this embodiment, the core components of the distribution cabinet are determined to include busbars, main circuit breakers or transformers. According to the divided monitoring areas, the monitoring area to which the core components belong is found, and the monitoring area to which the core components belong is divided into primary core monitoring areas.

[0024] S2. Collect historical data of the distribution cabinet and obtain the mutual influence relationship between each monitoring area through data association analysis method, where the historical data includes power operation data and temperature and humidity data.

[0025] In the specific implementation process, the specific steps of step S2 are: S201, determining the type of historical data collected from the power distribution cabinet and the time span of the historical data, wherein the type of historical data specifically includes power operation data and temperature and humidity data, and the time span of the historical data specifically is the past six months or one year; S202, based on determining the type of historical data to be collected from the power distribution cabinet and the time span of the historical data, collecting the historical data from the power distribution cabinet and preprocessing it to obtain preprocessed historical data, wherein the preprocessing specifically includes data cleaning and data conversion; Specifically, after collecting the historical data of the distribution cabinet, data cleaning is mainly to remove outliers, missing values ​​and duplicate values ​​in the data. Outliers are caused by sensor failure or data transmission errors, and they need to be eliminated or corrected; missing values ​​need to be filled according to the specific situation, by using interpolation or averaging method; duplicate values ​​need to be deleted to avoid interference with the analysis results.

[0026] S203, the correlation coefficient in the data association analysis method is used to analyze the mutual influence relationship between the various monitoring areas to obtain the influence relationship between the various monitoring areas; Specifically, the correlation coefficient matrix between each monitoring area is calculated, and then the correlation between each monitoring area is determined according to the value in the correlation coefficient matrix.

[0027] In this embodiment, if the correlation coefficient is greater than 0.8, it means that the mutual influence between the two monitoring areas is strong; if the correlation coefficient is less than 0.3, it means that the mutual influence between the two monitoring areas is weak. In addition, the direction of the mutual influence can be judged by observing the positive and negative signs in the correlation coefficient matrix: a positive correlation indicates that the change trend of one monitoring area is the same as the change trend of another monitoring area; a negative correlation indicates that the change trend of one monitoring area is opposite to the change trend of another monitoring area.

[0028] S204: Output the obtained influence relationship between the various monitoring areas in the form of a chart or report.

[0029] Specifically, various chart types are used to display the mutual influence relationship between the monitoring areas. In this embodiment, a heat map can be used to display the size and distribution of the values ​​in the correlation coefficient matrix; a network diagram can be used to display the connection relationship and the degree of mutual influence between the various monitoring areas; a scatter plot or line graph can also be used to display the changing trend between different monitoring areas over time; in addition, the chart can be combined with text descriptions to form a complete report to better present the analysis results and conclusions.

[0030] S3. Based on the mutual influence relationship between the various monitoring areas, the final core monitoring area is further divided from the primary core monitoring area through data statistical methods.

[0031] In the specific implementation process, the specific steps of step S3 are: S301, using correlation coefficient, covariance analysis or regression analysis in data statistical methods to quantify the mutual influence degree between various monitoring areas, and obtain the quantified mutual influence degree between various monitoring areas; In this embodiment, there are three monitoring areas A, B and C, which record their respective indicators, such as temperature, humidity or current; first, by calculating the correlation coefficients between A and B, A and C, and B and C, a series of numerical values ​​are obtained, and then, covariance analysis can be used to obtain whether the correlations between these monitoring areas are different in different time periods, such as day and night time. Finally, through regression analysis, a model is established to describe how changes in the indicators of area A affect the indicators of area B or C.

[0032] S302. Based on the quantified mutual influence degree between each monitoring area, construct a correlation influence network diagram between each primary core monitoring area and other monitoring areas, and associate each primary core monitoring area with other monitoring areas respectively.

[0033] Specifically, each monitoring area is taken as a node in the network diagram, and the connection relationship and influence degree between the nodes are determined according to the mutual influence degree between the quantified monitoring areas. The edge with a larger weight indicates that the mutual influence between the two monitoring areas is stronger. In this embodiment, the three monitoring areas A, B and C are taken as nodes, and the connection relationship and influence degree are determined according to the correlation coefficient or regression analysis results between them. Then, a network diagram is drawn using graphics software, in which the nodes represent the monitoring areas, the edges represent the connection relationship between them, and the thickness or color of the edges represents the size of the influence degree.

[0034] S303. In the constructed association influence network diagram, the total influence of each primary core monitoring area on other monitoring areas is evaluated by calculating the sum of its influence coefficients to obtain the total influence of each monitoring area.

[0035] Specifically, for each primary core monitoring area, the sum of the influence coefficients between it and all other monitoring areas is calculated to obtain the total influence of the area. For example, in the associated influence network diagram, all edges connected to monitoring area A and the corresponding influence degrees can be found, and then these influence degrees are added to obtain the total influence of area A.

[0036] S304: Set an influence threshold, and determine each primary core monitoring area whose total influence exceeds the influence threshold as a final core monitoring area.

[0037] Specifically, in this embodiment, the influence threshold is set to 10, and then the total influence of each primary core monitoring area is compared with this threshold. If the total influence of a primary core monitoring area is greater than 10, it is determined as the final core monitoring area; otherwise, it is excluded.

[0038] S4. Build a safety prediction model based on the historical data of the distribution cabinet.

[0039] In the specific implementation process, the specific steps of step S4 are: S401, obtaining historical data of a power distribution cabinet, specifically including current, voltage, temperature, operating time, or maintenance records, and preprocessing the data.

[0040] S402: Identify the mapping relationship between current, voltage, temperature, operating time and corresponding fault problems in the maintenance record.

[0041] Specifically, the association rule mining or cluster analysis method in the data mining technology is used to identify the mapping relationship between the combination of monitoring parameters among current, voltage, temperature, and operating time and the corresponding fault problems in the maintenance record.

[0042] S403, selecting a neural network model as the architecture, and training the neural network model using the mapping relationship between current, voltage, temperature, operating time and corresponding fault problems in maintenance records as a training set to obtain a safety prediction model.

[0043] Specifically, a multi-layer perceptron (MLP) model in the neural network model is selected for training. During the training process, the mapping relationship between the combination of monitoring parameters such as current, voltage, temperature, and operating time and the corresponding fault problems in the maintenance records is used as input features and target output. The multi-layer perceptron (MLP) model is trained using the back propagation algorithm. By continuously adjusting the parameters and structure of the model, a safe prediction model for predicting distribution cabinet failures is finally obtained.

[0044] S5. Monitor the operating data of each final core monitoring area in real time, input it into the safety prediction model after preprocessing, and output the estimated results of each final core monitoring area to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area.

[0045] In the specific implementation process, the specific steps of step S5 are: S501. Obtain operation data in the final core monitoring area through sensors and perform preprocessing.

[0046] Specifically, the operating data in the final core monitoring area is obtained through sensors for preprocessing, and the process includes data cleaning, data filtering, and data conversion steps.

[0047] S502: Standardize the pre-processed operation data in the final core monitoring area, convert it into a format recognized by the safety prediction model, and then input it into the safety prediction model to output the prediction results of each final core monitoring area.

[0048] Specifically, in this embodiment, before the pre-processed operating data in the final core monitoring area is input into the safety prediction model, the operating data in the final core monitoring area is first standardized, such as converting the temperature data and vibration data into numerical values ​​between 0 and 1, and then converting the operating data into a format that the model can recognize, such as a CSV file or a database table, and finally, the converted data is input into the trained safety prediction model. The safety prediction model predicts the operating status of the equipment based on the input operating data, and outputs the prediction results of each final core monitoring area.

[0049] S503: Identify the final core monitoring area with a prediction result of failure, and mark the monitoring area associated with it as a potential safety hazard monitoring area.

[0050] Specifically, if the prediction result is a fault or abnormal state, the corresponding final core monitoring area needs to be identified as a safety hazard monitoring area. At the same time, its associated monitoring areas also need to be identified as safety hazard monitoring areas. The specific identification is based on the associated impact network diagram to facilitate further monitoring and analysis.

[0051] S6. Obtain the operating parameters of the safety hazard monitoring area in real time, and judge the operating parameters of the safety hazard monitoring area according to the preset operating parameter safety standard threshold. If it is judged that it exceeds the safety standard threshold, trigger an early warning notification and dynamically adjust the detection frequency.

[0052] In the specific implementation process, the specific steps of step S6 are: S601. By collecting the operating parameters of the potential safety hazard monitoring area in real time and comparing them with the safety standard threshold after preprocessing, it is determined whether the operating parameters of each potential safety hazard monitoring area exceed the safety range to obtain a determination result.

[0053] Specifically, first, the operating parameters in the safety hazard monitoring area are collected in real time, including temperature, humidity, pressure, current, voltage and other types. It should be noted that the collected data should ensure accuracy and real-time performance so as to timely reflect the actual operating status of the equipment or area. After the operating parameters in the safety hazard monitoring area are collected, they need to be preprocessed. The preprocessing process includes data cleaning, data filtering, data conversion and other steps. After the preprocessing is completed, the operating parameters in the safety hazard monitoring area are compared with the safety standard thresholds respectively. According to the comparison results, it is judged whether the operating parameters of each safety hazard monitoring area exceed the safety range, and a judgment result is generated.

[0054] S602. When the judgment result is that the operating parameters exceed the safety standard threshold, the safety hazard monitoring area where the operating parameters exceed the safety standard threshold is marked, and an early warning notification is triggered at the same time, where the early warning notification specifically includes a sound alarm, flashing lights, SMS reminders or email notifications.

[0055] Specifically, when the result of the judgment is that the operating parameters exceed the safety standard threshold, the corresponding safety hazard monitoring area needs to be marked immediately. The marking can be through displaying a red warning box, flashing icon, etc. on the monitoring interface, so that the operator can quickly notice the problem; at the same time, trigger an early warning notification, which can be implemented in a variety of ways, including sound alarms (such as buzzers, alarms, etc.), flashing lights (such as red warning lights), SMS reminders or email notifications, etc. The content of the early warning notification should include the name of the safety hazard monitoring area and the type of parameters that exceed the safety standard threshold.

[0056] S603: Increase the detection frequency of the potential safety hazard monitoring area whose operating parameters exceed the safety standard threshold, and continue to detect the operating parameters of the potential safety hazard monitoring area.

[0057] Specifically, when a safety hazard monitoring area is found whose operating parameters exceed the safety standard threshold, its detection frequency needs to be immediately increased. It should be noted that the increased detection frequency should be determined based on the severity and urgency of the safety hazard to ensure that the operating status changes of the area can be monitored more frequently. After increasing the detection frequency, it is necessary to continuously detect the operating parameters of the safety hazard monitoring area, specifically by increasing the frequency of data collection, expanding the monitoring range or increasing monitoring parameters. This will help to promptly discover and resolve potential safety problems and prevent the situation from further deteriorating. Example

[0058] like Figure 2 As shown, a power distribution cabinet safety early warning system applied to a power distribution cabinet safety early warning method specifically includes: The area division module is used to divide the interior of the power distribution cabinet into multiple monitoring areas, and divide the monitoring area to which the core components of the power distribution cabinet belong into primary core monitoring areas; The data analysis module is used to collect historical data of the power distribution cabinet and obtain the mutual influence relationship between various monitoring areas through data association analysis methods, where the historical data includes power operation data and temperature and humidity data; A region identification module is used to further divide the final core monitoring area from the primary core monitoring area through a data statistical method based on the mutual influence relationship between the various monitoring areas obtained; Model building module, used to build a safety prediction model based on the historical data of the power distribution cabinet; The estimation processing module is used to monitor the operating data of each final core monitoring area in real time, input it into the safety prediction model after preprocessing, and output the estimation results of each final core monitoring area, so as to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area; The early warning adjustment module is used to obtain the operating parameters of the safety hazard monitoring area in real time, and judge the operating parameters of the safety hazard monitoring area according to the preset operating parameter safety standard threshold. If the judgment result exceeds the safety standard threshold, the early warning notification is triggered and the detection frequency is dynamically adjusted.

[0059] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0060] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0061] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A power distribution cabinet safety early warning method, characterized in that: The safety early warning method comprises the following steps: The interior of the power distribution cabinet is divided into multiple monitoring areas, and the monitoring area to which the core components of the power distribution cabinet belong is divided into a primary core monitoring area; Collect historical data of the power distribution cabinet and obtain the mutual influence relationship between each monitoring area through data association analysis method. The historical data includes power operation data and temperature and humidity data. Based on the mutual influence relationship between the various monitoring areas, the final core monitoring area is further divided from the primary core monitoring area through data statistical methods; Build a safety prediction model based on historical data of power distribution cabinets; Monitor the operating data of each final core monitoring area in real time, input it into the safety prediction model after preprocessing, and output the estimated results of each final core monitoring area, so as to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area; The operating parameters of the safety hazard monitoring area are obtained in real time, and the operating parameters of the safety hazard monitoring area are judged according to the preset operating parameter safety standard threshold. If the judgment result exceeds the safety standard threshold, an early warning notification is triggered and the detection frequency is dynamically adjusted.

2. A power distribution cabinet safety early warning method according to claim 1, characterized in that: The specific steps of dividing the interior of the power distribution cabinet into multiple monitoring areas and dividing the monitoring area to which the core components of the power distribution cabinet belong into primary core monitoring areas are as follows: According to the functional layout and component distribution of the power distribution cabinet, the inside of the power distribution cabinet is divided into multiple independent monitoring areas, and the divided monitoring areas are specifically divided by electrical connection, heat conduction or physical location factors; After the divided monitoring areas are obtained, the monitoring areas to which the core components of the power distribution cabinet belong are determined, and the determined monitoring areas to which the core components of the power distribution cabinet belong are divided into primary core monitoring areas.

3. A power distribution cabinet safety early warning method according to claim 1, characterized in that: The historical data of the power distribution cabinet is collected, and the mutual influence relationship between each monitoring area is obtained through the data association analysis method, wherein the historical data includes power operation data and temperature and humidity data, and the specific steps are as follows: Determine the type of historical data to be collected from the power distribution cabinet and the time span of the historical data, where the type of historical data specifically includes power operation data and temperature and humidity data, and the time span of the historical data specifically is the past six months or one year; Based on determining the type of historical data to be collected from the power distribution cabinet and the time span of the historical data, the historical data of the power distribution cabinet is collected and preprocessed to obtain the preprocessed historical data, wherein the preprocessing specifically includes data cleaning and data conversion; The correlation coefficient in the data association analysis method analyzes the mutual influence relationship between each monitoring area and obtains the influence relationship between each monitoring area; The influence relationship between each monitoring area is output in the form of a chart or report.

4. A power distribution cabinet safety early warning method according to claim 1, characterized in that: Based on the mutual influence relationship between the obtained monitoring areas, the final core monitoring area is further divided from the primary core monitoring area by a data statistical method, and the specific steps are: Utilize the correlation coefficient, covariance analysis or regression analysis in the data statistics method to quantify the mutual influence degree between each monitoring area, and obtain the quantified mutual influence degree between each monitoring area; Based on the quantified mutual influence between each monitoring area, a correlation influence network diagram between each primary core monitoring area and other monitoring areas is constructed, and each primary core monitoring area is respectively associated with other monitoring areas; In the constructed association impact network diagram, the total impact of each primary core monitoring area on other monitoring areas is evaluated by calculating the sum of their impact coefficients, and the total impact of each monitoring area is obtained; An influence threshold is set, and each primary core monitoring area whose total influence exceeds the influence threshold is determined as the final core monitoring area.

5. A power distribution cabinet safety early warning method according to claim 1, characterized in that: The specific steps of building a safety prediction model based on the historical data of the power distribution cabinet are as follows: Obtain historical data of the power distribution cabinet, including current, voltage, temperature, operating time, or maintenance records, and pre-process it; Identify the mapping relationship between current, voltage, temperature, operating time and corresponding fault problems in maintenance records; A neural network model is selected as the architecture, and the mapping relationship between current, voltage, temperature, operating time and the corresponding fault problems in the maintenance records is used as the training set to train the neural network model to obtain a safety prediction model.

6. A power distribution cabinet safety early warning method according to claim 1, characterized in that: The real-time monitoring of the operating data of each final core monitoring area is input into the safety prediction model after preprocessing to output the estimated results of each final core monitoring area, so as to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area, and the specific steps are as follows: The operation data in the final core monitoring area is obtained through sensors and pre-processed; The pre-processed operation data in the final core monitoring area is standardized and converted into a format recognized by the safety prediction model, and then input into the safety prediction model to output the prediction results of each final core monitoring area; The final core monitoring area with a predicted result of failure is identified, and the monitoring areas associated with it are marked as safety hazard monitoring areas.

7. A power distribution cabinet safety early warning method according to claim 1, characterized in that: The real-time acquisition of the operating parameters of the potential safety hazard monitoring area and the determination of the operating parameters of the potential safety hazard monitoring area according to the preset operating parameter safety standard threshold are performed. If the determination result is that the safety standard threshold is exceeded, an early warning notification is triggered and the detection frequency is dynamically adjusted. The specific steps are as follows: By collecting the operating parameters of the potential safety hazard monitoring area in real time and comparing them with the safety standard threshold after pre-processing, it is determined whether the operating parameters of each potential safety hazard monitoring area exceed the safety range and obtain the judgment result; When the result of the judgment is that the operating parameters exceed the safety standard threshold, the safety hazard monitoring area where the operating parameters exceed the safety standard threshold is marked, and an early warning notification is triggered at the same time, where the early warning notification specifically includes a sound alarm, flashing lights, SMS reminders or email notifications; Increase the detection frequency of safety hazard monitoring areas where operating parameters exceed the safety standard threshold, and continuously detect the operating parameters of the safety hazard monitoring areas.

8. A power distribution cabinet safety early warning system, applied to a power distribution cabinet safety early warning method according to any one of claims 1 to 7, characterized in that: The safety early warning system comprises: The area division module is used to divide the interior of the power distribution cabinet into multiple monitoring areas, and divide the monitoring area to which the core components of the power distribution cabinet belong into primary core monitoring areas; The data analysis module is used to collect historical data of the power distribution cabinet and obtain the mutual influence relationship between various monitoring areas through data association analysis methods, where the historical data includes power operation data and temperature and humidity data; A region identification module is used to further divide the final core monitoring area from the primary core monitoring area through a data statistical method based on the mutual influence relationship between the various monitoring areas obtained; Model building module, used to build a safety prediction model based on the historical data of the power distribution cabinet; The estimation processing module is used to monitor the operating data of each final core monitoring area in real time, input it into the safety prediction model after preprocessing, and output the estimation results of each final core monitoring area, so as to predict and identify the final core monitoring area of ​​the fault and its associated safety hazard monitoring area; The early warning adjustment module is used to obtain the operating parameters of the safety hazard monitoring area in real time, and judge the operating parameters of the safety hazard monitoring area according to the preset operating parameter safety standard threshold. If the judgment result exceeds the safety standard threshold, the early warning notification is triggered and the detection frequency is dynamically adjusted.

Images