A kind of intelligent monitoring system and method of power distribution cabinet

Abstract

The present invention belongs to the technical field of intelligent monitoring of distribution cabinets, and specifically relates to an intelligent monitoring system and method for distribution cabinets. The invention constructs a fault database by performing orderly analysis and correlation screening on the historical operation data of the distribution cabinet, and realizes accurate monitoring and prediction of the real-time operation status of the distribution cabinet. First, by classifying and processing the historical operation data, it is possible to accurately distinguish between fault parameters and normal parameters, and then determine the fault category according to the regularity of the fault parameters, providing a basis for subsequent correlation analysis and prediction. Secondly, by performing correlation screening analysis on the historical operation data under conventional faults, it is possible to determine the parameters closely related to the fault, construct a fault database, and improve the accuracy and efficiency of fault identification. Finally, through real-time monitoring and predictive analysis, it is possible to timely discover the abnormal operation status of the distribution cabinet, and determine the abnormal level according to the abnormal difference, trigger the alarm mechanism, and ensure the safe and stable operation of the distribution cabinet.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent monitoring of power distribution cabinets, and in particular relates to an intelligent monitoring system and method for power distribution cabinets. Background Art

[0002] With the development of the power industry, the distribution cabinet, as an indispensable part of the power system, its operating status is directly related to the stability and safety of the power system. However, the traditional distribution cabinet monitoring method often relies on manual inspection, which has problems such as low monitoring efficiency and untimely fault detection. Therefore, it is particularly important to develop an efficient and accurate distribution cabinet intelligent monitoring system and method.

[0003] Most of the intelligent monitoring systems and methods for distribution cabinets in the prior art can only realize simple data collection and fault alarm, but cannot intelligently analyze and predict the operating status of the distribution cabinet, resulting in a lack of foresight and pertinence in fault handling. In addition, the existing intelligent monitoring systems for distribution cabinets also have certain limitations in fault classification. They often only consider fault parameters and ignore normal parameters that exist at the same time as the fault parameters. This may undoubtedly lead to insufficient comprehensive analysis of the cause of the fault. Based on this, this solution provides an intelligent monitoring method for distribution cabinets to solve the above problems. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent monitoring system and method for a power distribution cabinet, which can realize comprehensive monitoring, intelligent analysis and prediction of the operating status of the power distribution cabinet, improve the monitoring efficiency and the pertinence of fault handling.

[0005] The technical solution adopted by the present invention is as follows:

[0006] An intelligent monitoring method for a power distribution cabinet, comprising:

[0007] Acquire historical operation data of the power distribution cabinet, wherein the historical operation data includes current parameters, voltage parameters, power parameters and temperature parameters;

[0008] Classify and process the historical operation data to obtain fault parameters and normal parameters, and then perform an orderly analysis based on the fault parameters to determine the fault category of the fault parameters, wherein the fault category includes occasional faults and regular faults;

[0009] Performing correlation screening and analysis on the historical operation data under the conventional fault to determine the fault database corresponding to the conventional fault;

[0010] Collecting real-time operation data of the power distribution cabinet, and comparing and analyzing with the fault database, to determine the real-time operation status of the power distribution cabinet, wherein the real-time operation status includes a normal operation status and an abnormal operation status;

[0011] Summarize the real-time operation data under the normal operation state, and perform prediction analysis to determine the predicted state of the power distribution cabinet within the required operation period;

[0012] In the abnormal operation state, the abnormal level is determined according to the abnormal difference, and the alarm mechanism is immediately triggered to send out an alarm signal.

[0013] In a preferred solution, after the historical operation data of the power distribution cabinet is output, preprocessing is performed synchronously, and the preprocessing step includes:

[0014] De-noising the historical operation data to eliminate abnormal values ​​and noise interference in the historical operation data.

[0015] Normalizing the denoised historical operation data so that the historical operation data are at the same level;

[0016] A timestamp is added to the normalized historical operation data and the data is aggregated into a historical operation data set with time characteristics.

[0017] In a preferred solution, the step of classifying the historical operation data to obtain fault parameters and normal parameters includes:

[0018] Obtaining threshold ranges of current parameters, voltage parameters, power parameters, and temperature parameters in the historical operation data;

[0019] Comparing the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data within the threshold range;

[0020] If the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data exceed the corresponding threshold interval, the corresponding current parameter, voltage parameter, power parameter and temperature parameter are determined as fault parameters;

[0021] If the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data belong to the corresponding threshold interval, the corresponding current parameter, voltage parameter, power parameter and temperature parameter are determined to be normal parameters.

[0022] In a preferred solution, the step of performing an orderliness analysis based on the fault parameters to determine the fault category of the fault parameters includes:

[0023] Obtain fault parameters and perform classification processing simultaneously to obtain multiple classification subsets;

[0024] Record the occurrence nodes of the fault parameters in each classification subset as reference nodes, and reversely construct the monitoring period based on the reference nodes, and synchronously collect the normal parameters in the monitoring period;

[0025] Obtain a conditional function, and input the normal parameters within the monitoring period into the conditional function one by one according to the acquisition order, and record the output result of the conditional function as the conditional parameter;

[0026] Obtaining a verification function, inputting the conditional parameters into the verification function to perform verification processing, and recording the output result of the verification function as a verification difference;

[0027] Obtaining a verification threshold, and comparing the verification difference with the verification threshold;

[0028] When the verification difference is greater than or equal to the verification threshold, it indicates that the fault parameter corresponding to the verification difference does not have regularity, and the fault type corresponding to the verification difference is recorded as an occasional fault;

[0029] When the verification difference is less than the verification threshold, it indicates that the fault parameter corresponding to the verification difference has regularity, and the fault type corresponding to the verification difference is recorded as a conventional fault.

[0030] In a preferred solution, the step of performing correlation screening and analysis on the historical operation data under the conventional fault includes:

[0031] Obtaining normal parameters in the historical operation data under the same conventional fault, and recording them as first-level parameters to be evaluated;

[0032] Performing an offset process on each of the first-level parameters to be evaluated to obtain a plurality of evaluation intervals, wherein the offset mode of the first-level parameters to be evaluated is a bidirectional equidistant offset;

[0033] Counting the number of first-level parameters to be evaluated covered by each evaluation interval, and recording them as second-level parameters to be evaluated;

[0034] Calculate the proportion of the second-level parameter to be evaluated in all the first-level parameters to be evaluated, and record it as an associated condition parameter;

[0035] Obtaining an association evaluation threshold, and comparing the association condition parameter with the association evaluation threshold;

[0036] When the associated condition parameter is greater than or equal to the associated evaluation threshold, the normal parameter corresponding to the associated condition parameter is recorded as the associated parameter under the corresponding conventional fault;

[0037] When the associated condition parameter is less than the associated evaluation threshold, the normal parameter corresponding to the associated condition parameter is recorded as a non-associated parameter under the corresponding conventional fault;

[0038] The fault parameters and associated parameters under the conventional faults are summarized together into a fault database.

[0039] In a preferred solution, the step of collecting the real-time operation data of the power distribution cabinet and comparing and analyzing it with the fault database to determine the real-time operation status of the power distribution cabinet includes:

[0040] Acquire the real-time operation data, and compare it with the fault parameters and associated parameters in the fault database;

[0041] If the real-time operation data is the same as any fault parameter or associated parameter in the fault database, it indicates that the power distribution cabinet is in an abnormal operation state;

[0042] If the real-time operation data is different from the fault parameters and the associated parameters in the fault database, it indicates that the power distribution cabinet is currently in a normal operation state, and the real-time operation data continues to be monitored.

[0043] In a preferred solution, the step of determining the predicted state of the power distribution cabinet within the required operation period includes:

[0044] Obtaining the execution time period of the power distribution cabinet under the normal operating state, and the real-time operation data within the execution time period;

[0045] Obtain a prediction function, input the required operation time period and the real-time operation data into the prediction function, and record the output result of the prediction function as a prediction parameter;

[0046] The predicted parameters are compared with the fault parameters and associated parameters in the fault database, and the predicted state of the power distribution cabinet is output according to the comparison result.

[0047] In a preferred embodiment, the step of determining the abnormality level according to the abnormal difference comprises:

[0048] Obtaining an abnormal difference under the abnormal operating state;

[0049] Obtaining an evaluation interval, wherein a plurality of evaluation intervals are provided, and each evaluation interval corresponds to an abnormality level;

[0050] Compare the evaluation interval with the abnormal difference, determine the abnormal level of the abnormal difference, and simultaneously issue an alarm signal of a corresponding level;

[0051] The higher the abnormality level is, the higher the urgency of the corresponding alarm signal is.

[0052] The present invention also provides an intelligent monitoring system for a power distribution cabinet, using the above-mentioned intelligent monitoring method for a power distribution cabinet, comprising:

[0053] A data acquisition module, wherein the data acquisition module is used to obtain historical operation data of the power distribution cabinet, wherein the historical operation data includes current parameters, voltage parameters, power parameters and temperature parameters;

[0054] A fault classification module, the fault classification module is used to classify the historical operation data to obtain fault parameters and normal parameters, and then perform an orderly analysis based on the fault parameters to determine the fault category of the fault parameters, wherein the fault category includes occasional faults and regular faults;

[0055] A correlation analysis module, the correlation analysis module is used to perform correlation screening analysis on the historical operation data under the conventional fault, and determine the fault database corresponding to the conventional fault;

[0056] A status output module, the status output module is used to collect real-time operation data of the power distribution cabinet, and compare and analyze it with the fault database to determine the real-time operation status of the power distribution cabinet, wherein the real-time operation status includes a normal operation status and an abnormal operation status;

[0057] A prediction module, the prediction module is used to summarize the real-time operation data under the normal operation state, and perform prediction analysis to determine the predicted state of the distribution cabinet within the required operation period;

[0058] The alarm module is used to determine the abnormal level according to the abnormal difference in the abnormal operation state, and immediately trigger the alarm mechanism to send an alarm signal.

[0059] And, an electronic device, the electronic device comprising:

[0060] at least one processor;

[0061] and a memory communicatively coupled to the at least one processor;

[0062] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned intelligent monitoring method for distribution cabinets.

[0063] The technical effects achieved by the present invention are:

[0064] The present invention constructs a fault database by performing orderly analysis and correlation screening on the historical operation data of the distribution cabinet, thereby realizing accurate monitoring and prediction of the real-time operation status of the distribution cabinet. Firstly, through the classification and processing of the historical operation data, it is possible to accurately distinguish between fault parameters and normal parameters, and then determine the fault category according to the regularity of the fault parameters, thereby providing a basis for subsequent correlation analysis and prediction. Secondly, through the correlation screening analysis of the historical operation data under conventional faults, it is possible to determine the parameters closely related to the fault, construct a fault database, and improve the accuracy and efficiency of fault identification. Finally, through real-time monitoring and predictive analysis, it is possible to timely discover the abnormal operation status of the distribution cabinet, determine the abnormal level according to the abnormal difference, trigger the alarm mechanism, and ensure the safe and stable operation of the distribution cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic flow chart of the method of the present invention;

[0066] Figure 2 It is a schematic diagram of the system module of the present invention;

[0067] Figure 3 It is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION

[0068] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0069] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0070] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0071] See also Figure 1 As shown, the present invention provides a method for intelligent monitoring of a power distribution cabinet, comprising:

[0072] S1. Obtain historical operation data of the power distribution cabinet, where the historical operation data includes current parameters, voltage parameters, power parameters, and temperature parameters;

[0073] In step S1, before performing real-time monitoring on the power distribution cabinet, the historical operation data of the power distribution cabinet is first fully acquired. The historical operation data covers multiple key parameters, including but not limited to current parameters, voltage parameters, power parameters and temperature parameters, so as to ensure the comprehensiveness and accuracy of the data. After the historical operation data of the power distribution cabinet is output, preprocessing is performed synchronously. The preprocessing steps include:

[0074] Perform denoising on historical operation data to eliminate outliers and noise interference in historical operation data.

[0075] Normalize the denoised historical operation data to make them at the same level;

[0076] Add timestamps to the normalized historical operation data and aggregate them into a historical operation data set with time characteristics;

[0077] Specifically, after the historical operation data of the distribution cabinet is successfully output, it needs to be preprocessed synchronously. First, the historical operation data is denoised, that is, denoising is performed to remove various outliers and random noises mixed in the historical operation data to ensure the purity of the data for subsequent analysis. Then, the denoised historical operation data is normalized so that the originally uneven data is uniformly mapped to the same numerical range, thereby eliminating the difference between different dimensions and laying the foundation for subsequent data analysis. Finally, in order to enhance the time series characteristics of the data, the standardized data are timestamped one by one, and then compiled into a historical operation data set that contains both the original values ​​and time information, so as to facilitate subsequent time series analysis and trend tracking.

[0078] S2. Classify and process the historical operation data to obtain fault parameters and normal parameters, and then perform an orderly analysis based on the fault parameters to determine the fault categories of the fault parameters, where the fault categories include occasional faults and regular faults;

[0079] In step S2, after the historical operation data is preprocessed, the present embodiment performs detailed classification processing on the acquired historical operation data, and divides it into two categories: fault parameters and normal parameters. Then, an orderly analysis is performed on the fault parameters to accurately determine the specific fault category to which the fault parameters belong. The fault category is mainly divided into two types: occasional faults and conventional faults. In addition, the steps of classifying the historical operation data to obtain the fault parameters and the normal parameters include:

[0080] Obtaining threshold ranges of current parameters, voltage parameters, power parameters, and temperature parameters in historical operation data;

[0081] Compare the current parameters, voltage parameters, power parameters and temperature parameters in the historical operation data of the threshold interval;

[0082] If the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data exceed the corresponding threshold range, the corresponding current parameter, voltage parameter, power parameter and temperature parameter are determined as fault parameters;

[0083] If the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data belong to the corresponding threshold interval, the corresponding current parameter, voltage parameter, power parameter and temperature parameter are determined to be normal parameters;

[0084] Specifically, when the historical operation data is carefully classified and processed to accurately distinguish between fault parameters and normal parameters, all kinds of key parameters contained in the historical operation data are comprehensively obtained, including current parameters, voltage parameters, power parameters and temperature parameters, and the threshold ranges of the current parameters, voltage parameters, power parameters and temperature parameters are clearly defined. The threshold ranges are set according to the standard range of normal operation of the equipment and are an important basis for judging whether the parameters are abnormal. Then, the current parameters, voltage parameters, power parameters and temperature parameters in the historical operation data are compared in detail with the pre-set threshold ranges one by one. During the comparison process, if it is found that any one or more of the current parameters, voltage parameters, power parameters and temperature parameters in the historical operation data exceed the corresponding threshold ranges, then the out-of-range parameters will be clearly determined as fault parameters. On the contrary, if the current parameters, voltage parameters, power parameters and temperature parameters in the historical operation data all belong to the corresponding threshold ranges, then they will be determined as normal parameters, thereby realizing the classification processing of the historical operation data, accurately distinguishing between fault parameters and normal parameters, and providing reliable data support for equipment maintenance and optimization;

[0085] In addition, the steps of performing an orderly analysis based on the fault parameters and determining the fault category of the fault parameters include:

[0086] Obtain fault parameters and perform classification processing simultaneously to obtain multiple classification subsets;

[0087] Record the occurrence nodes of the fault parameters in each classification subset as reference nodes, and reversely construct the monitoring period based on the reference nodes, and synchronously collect the normal parameters in the monitoring period;

[0088] Obtain a conditional function, and input the normal parameters within the monitoring period into the conditional function one by one according to the acquisition order, and record the output result of the conditional function as the conditional parameter;

[0089] Obtain a verification function, input the conditional parameters into the verification function to perform verification processing, and record the output result of the verification function as the verification difference;

[0090] Obtaining a calibration threshold, and comparing the calibration difference with the calibration threshold;

[0091] When the check difference is greater than or equal to the check threshold, it indicates that the fault parameter corresponding to the check difference does not have regularity, and the fault type corresponding to the check difference is recorded as an occasional fault;

[0092] When the check difference is less than the check threshold, it indicates that the fault parameter corresponding to the check difference has regularity, and the fault type corresponding to the check difference is recorded as a conventional fault;

[0093] In the above, when performing orderliness analysis based on fault parameters, it is first necessary to obtain all fault parameters, and further subdivide these fault parameters to form multiple classification subsets with similar characteristics. Each classification subset represents a certain type of specific fault mode. Then, for each classification subset, determine the time node when the fault parameter appears, that is, the fault occurrence node, as the reference node. Based on the reference node, backtrack to build a monitoring period. The monitoring period includes a period of time before the fault occurs, which is used to capture the normal parameters before the fault occurs for subsequent analysis. At the same time, a pre-set conditional function is obtained, and the normal parameters in the monitoring period are input into the conditional function one by one according to the acquisition order for processing. At the same time, the output result of the conditional function is recorded as the conditional parameter, where the expression of the conditional function is: , where Represents the conditional parameters, Indicates the length of the monitoring period. Indicates the number of normal parameter collections during the monitoring period. and It represents the normal parameters of adjacent acquisition nodes during the monitoring period. Subsequently, the corresponding verification function is obtained, and the obtained conditional parameters are input into the verification function to perform verification processing, and the output result of the verification function is accurately recorded as the verification difference. Here, it should be noted that the known normal parameters are input into the verification function together with the conditional parameters, and the acquisition nodes of the normal parameters are adjacent, and multiple groups are set to avoid the accidental output result of the verification function. The calculation formula of the verification function is: , where and Indicates the normal parameters of the adjacent acquisition nodes. Indicates the sampling interval between adjacent normal parameters. It represents the number of normal parameters. After that, the preset verification threshold is obtained, and the obtained verification difference is compared with the verification threshold for analysis. When the value of the verification difference is greater than or equal to the verification threshold, it indicates that the fault parameter corresponding to the verification difference does not have obvious regular characteristics. At this time, the fault category corresponding to the verification difference should be recorded as an occasional fault. This type of fault is generally irregular and will occur randomly during the operation of the equipment. The causes and manifestations of the fault are relatively diverse, making it difficult to predict and prevent. Specifically, it can be discovered and handled in a timely manner by strengthening the monitoring frequency. On the contrary, when the value of the verification difference is less than the verification threshold, it indicates that the fault parameter corresponding to the verification difference has certain regular characteristics. At this time, the fault category corresponding to the verification difference is recorded as a regular fault for routine maintenance and processing.

[0094] S3. Perform correlation screening and analysis on historical operation data under conventional faults to determine the fault database corresponding to conventional faults;

[0095] In step S3, for conventional faults, the corresponding historical operation data will be subjected to corresponding correlation screening analysis, so as to accurately determine the fault database corresponding to the conventional faults, so as to provide data support for subsequent real-time monitoring. The step of performing correlation screening analysis on the historical operation data under conventional faults includes:

[0096] Obtain normal parameters from historical operating data under the same conventional fault and record them as first-level parameters to be evaluated;

[0097] Performing offset processing on each first-level parameter to be evaluated to obtain multiple evaluation intervals, wherein the offset mode of the first-level parameter to be evaluated is bidirectional equidistant offset;

[0098] Count the number of first-level parameters to be evaluated covered in each evaluation interval and record them as second-level parameters to be evaluated;

[0099] Calculate the proportion of the second-level parameters to be evaluated in all the first-level parameters to be evaluated, and record them as associated condition parameters;

[0100] Obtaining an association evaluation threshold, and comparing the association condition parameter with the association evaluation threshold;

[0101] When the associated condition parameter is greater than or equal to the associated evaluation threshold, the normal parameter corresponding to the associated condition parameter is recorded as the associated parameter under the corresponding conventional fault;

[0102] When the associated condition parameter is less than the associated evaluation threshold, the normal parameter corresponding to the associated condition parameter is recorded as a non-associated parameter under the corresponding conventional fault;

[0103] The fault parameters and related parameters under conventional faults are summarized into a fault database;

[0104] Specifically, when performing correlation screening analysis on historical operating data under routine fault conditions, it is first necessary to obtain the normal parameters recorded in the historical operating data when the same type of routine fault occurs, and record them as first-level parameters to be evaluated. Then, each first-level parameter to be evaluated is offset. The specific operation is to offset each parameter value in a bidirectional equidistant manner to generate multiple evaluation intervals. This offset processing method aims to expand the evaluation range of the parameter so as to capture data changes more comprehensively. Then, the number of first-level parameters to be evaluated covered in each evaluation interval is counted and recorded as second-level parameters to be evaluated. In this way, the distribution of the first-level parameters to be evaluated in the evaluation interval is determined. Subsequently, the proportion of the second-level parameters to be evaluated in all the first-level parameters to be evaluated is calculated and recorded as correlation condition parameters. After that, the pre-set A determined correlation evaluation threshold is determined, and the calculated correlation condition parameter is compared with the correlation evaluation threshold to determine whether there is correlation between the first-level parameter to be evaluated and the fault parameter. When the value of the correlation condition parameter is greater than or equal to the correlation evaluation threshold, it means that the corresponding first-level parameter to be evaluated has a strong correlation with the conventional fault. At this time, the normal parameter corresponding to the correlation condition parameter will be recorded and used as the correlation parameter under the corresponding conventional fault. On the contrary, when the value of the correlation condition parameter is less than the correlation evaluation threshold, it means that its correlation with the conventional fault is weak. At this time, the normal parameter corresponding to the correlation condition parameter will be recorded as the non-correlated parameter under the corresponding conventional fault. Finally, the fault parameters under the conventional fault and the determined correlation parameters are summarized together to form a complete fault database, which provides important data support for subsequent fault diagnosis and prevention.

[0105] S4, collecting real-time operation data of the power distribution cabinet, and comparing and analyzing it with the fault database to determine the real-time operation status of the power distribution cabinet, wherein the real-time operation status includes normal operation status and abnormal operation status;

[0106] In step S4, when it is necessary to perform monitoring operations on the distribution cabinet, firstly, the operation data of the distribution cabinet is collected in real time, and the real-time operation data is compared and analyzed with the pre-established fault database to determine the real-time operation status of the distribution cabinet, wherein the real-time operation status is divided into two situations: normal operation status and abnormal operation status. The step of collecting the real-time operation data of the distribution cabinet and comparing and analyzing it with the fault database to determine the real-time operation status of the distribution cabinet includes:

[0107] Obtain real-time operating data and compare it with fault parameters and associated parameters in the fault database;

[0108] If the real-time operation data is the same as any fault parameter or associated parameter in the fault database, it indicates that the power distribution cabinet is in an abnormal operation state;

[0109] If the real-time operation data is different from the fault parameters and associated parameters in the fault database, it indicates that the power distribution cabinet is currently in a normal operation state, and the real-time operation data continues to be monitored;

[0110] Specifically, when determining the real-time operating status of the distribution cabinet, it is first necessary to collect the real-time operating data of the distribution cabinet, and compare and analyze the real-time operating data with the fault parameters and related parameters in the pre-established fault database. If, during the comparison process, it is found that the real-time operating data matches any fault parameter or related parameter in the fault database, it can be determined that the distribution cabinet is currently in an abnormal operating state, and corresponding fault troubleshooting and handling measures must be taken immediately. On the contrary, if the real-time operating data does not match all the fault parameters and related parameters in the fault database, that is, there is no similarity or similarity, it can be confirmed that the distribution cabinet is currently in a normal operating state. In this case, the real-time operating data of the distribution cabinet will continue to be monitored to ensure its stable operation and to promptly discover and handle any abnormal situations that may arise.

[0111] S5. Summarize the real-time operation data under normal operation and perform forecast analysis to determine the forecast state of the power distribution cabinet during the required operation period;

[0112] In step S5, when the power distribution cabinet is in a normal operating state, the real-time operating data is aggregated and processed, and a prediction analysis is performed on this basis to determine the predicted state of the power distribution cabinet in the future demand operation period, providing a basis for preventive maintenance. The step of determining the predicted state of the power distribution cabinet in the demand operation period includes:

[0113] Obtain the execution period of the power distribution cabinet under normal operating conditions, as well as the real-time operation data during the execution period;

[0114] Obtain a prediction function, input the required operation time period and the real-time operation data into the prediction function, and record the output result of the prediction function as a prediction parameter;

[0115] Compare the predicted parameters with the fault parameters and associated parameters in the fault database, and output the predicted state of the power distribution cabinet according to the comparison result;

[0116] Specifically, when determining the predicted state of the distribution cabinet in the required operation period, it is first necessary to obtain the execution period of the distribution cabinet in the normal operation state, and record the real-time operation data in the execution period, and then obtain the prediction function applicable to the current distribution cabinet. The expression of the prediction function is: , where represents the prediction parameter, Indicates the real-time operation data of the current node of the power distribution cabinet. Indicates the required operating time period, Indicates the length of the execution period. express, and It represents the real-time operating data of adjacent nodes within the execution period. By inputting the required operating period and the collected real-time operating data into the prediction function, after calculation and processing, the prediction parameters for subsequent analysis can be obtained. The obtained prediction parameters are then compared and analyzed in detail with various fault parameters and related parameters in the fault database. Through comparative analysis, the predicted status of the distribution cabinet within the required operating period can be determined.

[0117] S6. Under abnormal operation conditions, the abnormal level is determined according to the abnormal difference, and the alarm mechanism is immediately triggered to send out an alarm signal;

[0118] In step S6, when the power distribution cabinet is in an abnormal operating state, the system determines the abnormal level according to the size of the abnormal difference, and immediately triggers the alarm mechanism after confirming the abnormality, and sends an alarm signal so that relevant personnel can take timely measures to ensure the safe and stable operation of the power distribution cabinet. The step of determining the abnormal level according to the abnormal difference includes:

[0119] Obtain abnormal difference under abnormal operation state;

[0120] Obtaining an evaluation interval, wherein a plurality of evaluation intervals are set, and each evaluation interval corresponds to an abnormality level;

[0121] Compare the evaluation interval with the abnormal difference, determine the abnormal level of the abnormal difference, and simultaneously issue an alarm signal of the corresponding level;

[0122] Among them, the higher the abnormality level, the higher the urgency of the corresponding alarm signal.

[0123] Specifically, when determining the abnormality level based on the abnormal difference, it is first necessary to obtain the abnormal difference under the abnormal operating state. The abnormal difference is the absolute value of the difference between the fault parameter and the normal parameter under the minimum tolerance under the abnormal operating state, and then obtain the pre-set evaluation interval, and each evaluation interval corresponds to a specific abnormality level, so as to facilitate subsequent matching and judgment. After that, the obtained abnormal difference and the evaluation interval are compared and analyzed in detail. Based on this, the abnormality level corresponding to the abnormal difference can be finally determined. While determining the abnormality level, an alarm signal of the level corresponding to the abnormality level will be issued synchronously to ensure that relevant personnel and systems can respond and handle it in time. It should be noted that the setting of the abnormality level is hierarchical. The higher the abnormality level, the higher the severity and urgency of the problem. Therefore, the urgency of the corresponding alarm signal will also increase accordingly to ensure that high-level abnormalities can be handled preferentially and quickly.

[0124] See also Figure 2 , an intelligent monitoring system for a power distribution cabinet, using the above-mentioned intelligent monitoring method for a power distribution cabinet, comprising:

[0125] Data acquisition module, the data acquisition module is used to obtain the historical operation data of the power distribution cabinet, the historical operation data includes current parameters, voltage parameters, power parameters and temperature parameters;

[0126] Fault classification module: The fault classification module is used to classify the historical operation data to obtain fault parameters and normal parameters, and then conduct an orderly analysis based on the fault parameters to determine the fault category of the fault parameters, where the fault category includes occasional faults and regular faults;

[0127] The correlation analysis module is used to perform correlation screening analysis on the historical operation data under conventional faults to determine the fault database corresponding to the conventional faults;

[0128] The status output module is used to collect the real-time operation data of the power distribution cabinet, and compare and analyze it with the fault database to determine the real-time operation status of the power distribution cabinet, wherein the real-time operation status includes the normal operation status and the abnormal operation status;

[0129] The prediction module is used to summarize the real-time operation data under normal operation and perform prediction analysis to determine the predicted state of the distribution cabinet during the required operation period;

[0130] The alarm module is used to determine the abnormal level according to the abnormal difference under abnormal operating conditions, and immediately trigger the alarm mechanism to send out an alarm signal.

[0131] In the above, the monitoring system includes a data acquisition module, a fault classification module, a correlation analysis module, a status output module, a prediction module and an alarm module. The main function of the data acquisition module is to obtain the historical operation data accumulated during the operation of the distribution cabinet. The historical operation data covers multiple key parameters, including current parameters, voltage parameters, power parameters and temperature parameters, etc., to ensure the comprehensiveness and accuracy of the data. The role of the fault classification module is to perform detailed classification processing on the collected historical operation data. Through this process, fault parameters and normal parameters can be distinguished, and then an orderly analysis is performed based on these fault parameters, so as to accurately determine the fault category to which the fault parameters belong. Among them, the fault categories are mainly divided into two categories: occasional faults and conventional faults. The main task of the correlation analysis module is to perform correlation screening analysis on the historical operation data under conventional fault conditions, so as to In order to determine the fault database corresponding to conventional faults and provide data support for subsequent analysis, the status output module is responsible for real-time collection of the operating data of the distribution cabinet, and conducts detailed comparative analysis of the real-time operating data with the previously determined fault database, so as to accurately judge the real-time operating status of the distribution cabinet, where the real-time operating status includes two conditions: normal operating status and abnormal operating status. The function of the prediction module is to systematically summarize the real-time operating data under normal operating conditions, and perform predictive analysis on this basis, aiming to determine the predicted status of the distribution cabinet in the future demand operation period, and provide a basis for preventive maintenance. The role of the alarm module is to determine the level of the abnormality according to the size of the abnormal difference when the distribution cabinet is detected to be in an abnormal operating state, and immediately trigger the alarm mechanism after confirming the abnormality, and send out an alarm signal so as to promptly notify relevant personnel to take corresponding countermeasures.

[0132] See also Figure 3 , an electronic device, the electronic device comprising:

[0133] at least one processor;

[0134] and a memory communicatively coupled to the at least one processor;

[0135] The memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned intelligent monitoring method for distribution cabinets.

[0136] The processor of the above-mentioned electronic device can be a central processing unit (CPU), a microprocessor (MCU), a digital signal processor (DSP), etc., which has powerful computing power and data processing capabilities, and can efficiently perform various tasks in the intelligent monitoring method of the distribution cabinet, including data acquisition, fault classification, correlation analysis, state prediction, and alarm triggering, etc., while the memory is used to store the historical operation data, fault database, program instructions, and various intermediate results and final results of the distribution cabinet to ensure the integrity and traceability of the data. At the same time, the memory can also provide a fast data access speed to meet the needs of real-time monitoring and early warning. In addition, the electronic device can also include various input and output devices, such as a display screen, a keyboard, a mouse, a network interface, etc., to facilitate user interactive operations and data transmission. In summary, the electronic device realizes real-time monitoring and intelligent early warning of the operating status of the distribution cabinet by integrating advanced hardware components such as processors and memories, as well as efficient intelligent monitoring software for distribution cabinets, and provides a strong technical guarantee for the safe and stable operation of the power system.

[0137] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0138] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.

Claims

1. A method for intelligent monitoring of a power distribution cabinet, characterized in that: include: Acquire historical operation data of the power distribution cabinet, wherein the historical operation data includes current parameters, voltage parameters, power parameters and temperature parameters; Classify and process the historical operation data to obtain fault parameters and normal parameters, and then perform an orderly analysis based on the fault parameters to determine the fault category of the fault parameters, wherein the fault category includes occasional faults and regular faults; Performing correlation screening and analysis on the historical operation data under the conventional fault to determine the fault database corresponding to the conventional fault; Collecting real-time operation data of the power distribution cabinet, and comparing and analyzing with the fault database, to determine the real-time operation status of the power distribution cabinet, wherein the real-time operation status includes a normal operation status and an abnormal operation status; Summarize the real-time operation data under the normal operation state, and perform prediction analysis to determine the predicted state of the power distribution cabinet within the required operation period; In the abnormal operation state, the abnormal level is determined according to the abnormal difference, and the alarm mechanism is immediately triggered to send out an alarm signal; The step of performing an orderly analysis based on the fault parameters to determine the fault category of the fault parameters includes: Obtain fault parameters and perform classification processing simultaneously to obtain multiple classification subsets; Record the occurrence nodes of the fault parameters in each classification subset as reference nodes, and reversely construct the monitoring period based on the reference nodes, and synchronously collect the normal parameters in the monitoring period; Obtain a conditional function, and input the normal parameters within the monitoring period into the conditional function one by one according to the acquisition order, and record the output result of the conditional function as the conditional parameter; Obtaining a verification function, inputting the conditional parameters into the verification function to perform verification processing, and recording the output result of the verification function as a verification difference; Obtaining a verification threshold, and comparing the verification difference with the verification threshold; When the verification difference is greater than or equal to the verification threshold, it indicates that the fault parameter corresponding to the verification difference does not have regularity, and the fault type corresponding to the verification difference is recorded as an occasional fault; When the verification difference is less than the verification threshold, it indicates that the fault parameter corresponding to the verification difference has regularity, and the fault type corresponding to the verification difference is recorded as a conventional fault.

2. The intelligent monitoring method for a power distribution cabinet according to claim 1 is characterized in that: After the historical operation data of the power distribution cabinet is output, preprocessing is performed synchronously, and the preprocessing steps include: De-noising the historical operation data to eliminate abnormal values ​​and noise interference in the historical operation data. Normalizing the denoised historical operation data so that the historical operation data are at the same level; A timestamp is added to the normalized historical operation data and the data is aggregated into a historical operation data set with time characteristics.

3. The intelligent monitoring method for a power distribution cabinet according to claim 1 is characterized in that: The step of classifying and processing the historical operation data to obtain fault parameters and normal parameters includes: Obtaining threshold ranges of current parameters, voltage parameters, power parameters, and temperature parameters in the historical operation data; Comparing the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data within the threshold range; If the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data exceed the corresponding threshold interval, the corresponding current parameter, voltage parameter, power parameter and temperature parameter are determined as fault parameters; If the current parameter, voltage parameter, power parameter and temperature parameter in the historical operation data belong to the corresponding threshold interval, the corresponding current parameter, voltage parameter, power parameter and temperature parameter are determined to be normal parameters.

4. The intelligent monitoring method for a power distribution cabinet according to claim 1 is characterized in that: The step of performing correlation screening and analysis on the historical operation data under the conventional fault comprises: Obtaining normal parameters in the historical operation data under the same conventional fault, and recording them as first-level parameters to be evaluated; Performing an offset process on each of the first-level parameters to be evaluated to obtain a plurality of evaluation intervals, wherein the offset mode of the first-level parameters to be evaluated is a bidirectional equidistant offset; Counting the number of first-level parameters to be evaluated covered by each evaluation interval, and recording them as second-level parameters to be evaluated; Calculate the proportion of the second-level parameter to be evaluated in all the first-level parameters to be evaluated, and record it as an associated condition parameter; Obtaining an association evaluation threshold, and comparing the association condition parameter with the association evaluation threshold; When the associated condition parameter is greater than or equal to the associated evaluation threshold, the normal parameter corresponding to the associated condition parameter is recorded as the associated parameter under the corresponding conventional fault; When the associated condition parameter is less than the associated evaluation threshold, the normal parameter corresponding to the associated condition parameter is recorded as a non-associated parameter under the corresponding conventional fault; The fault parameters and associated parameters under the conventional faults are summarized together into a fault database.

5. The intelligent monitoring method for a power distribution cabinet according to claim 4 is characterized in that: The step of collecting the real-time operation data of the power distribution cabinet and comparing and analyzing it with the fault database to determine the real-time operation status of the power distribution cabinet includes: Acquire the real-time operation data, and compare it with the fault parameters and associated parameters in the fault database; If the real-time operation data is the same as any fault parameter or associated parameter in the fault database, it indicates that the power distribution cabinet is in an abnormal operation state; If the real-time operation data is different from the fault parameters and the associated parameters in the fault database, it indicates that the power distribution cabinet is currently in a normal operation state, and the real-time operation data continues to be monitored.

6. The intelligent monitoring method for a power distribution cabinet according to claim 4 is characterized in that: The step of determining the predicted state of the power distribution cabinet within the required operation period includes: Obtaining the execution time period of the power distribution cabinet under the normal operating state, and the real-time operation data within the execution time period; Obtain a prediction function, input the required operation time period and the real-time operation data into the prediction function, and record the output result of the prediction function as a prediction parameter; The predicted parameters are compared with the fault parameters and associated parameters in the fault database, and the predicted state of the power distribution cabinet is output according to the comparison result.

7. The intelligent monitoring method for a power distribution cabinet according to claim 1 is characterized in that: The step of determining the abnormality level according to the abnormal difference comprises: Obtaining an abnormal difference under the abnormal operating state; Obtaining an evaluation interval, wherein a plurality of evaluation intervals are provided, and each evaluation interval corresponds to an abnormality level; Compare the evaluation interval with the abnormal difference, determine the abnormal level of the abnormal difference, and simultaneously issue an alarm signal of a corresponding level; The higher the abnormality level is, the higher the urgency of the corresponding alarm signal is.

8. An intelligent monitoring system for a power distribution cabinet, characterized in that: The intelligent monitoring method for a power distribution cabinet according to any one of claims 1 to 7 comprises: A data acquisition module, wherein the data acquisition module is used to obtain historical operation data of the power distribution cabinet, wherein the historical operation data includes current parameters, voltage parameters, power parameters and temperature parameters; A fault classification module, the fault classification module is used to classify the historical operation data to obtain fault parameters and normal parameters, and then perform an orderly analysis based on the fault parameters to determine the fault category of the fault parameters, wherein the fault category includes occasional faults and regular faults; A correlation analysis module, the correlation analysis module is used to perform correlation screening analysis on the historical operation data under the conventional fault, and determine the fault database corresponding to the conventional fault; A status output module, the status output module is used to collect real-time operation data of the power distribution cabinet, and compare and analyze it with the fault database to determine the real-time operation status of the power distribution cabinet, wherein the real-time operation status includes a normal operation status and an abnormal operation status; A prediction module, the prediction module is used to summarize the real-time operation data under the normal operation state, and perform prediction analysis to determine the predicted state of the distribution cabinet within the required operation period; The alarm module is used to determine the abnormal level according to the abnormal difference in the abnormal operation state, and immediately trigger the alarm mechanism to send an alarm signal.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the intelligent monitoring method for a distribution cabinet according to any one of claims 1 to 7.

Images