A method and system for monitoring the operating state of a distribution box

Abstract

The application discloses a kind of distribution box operating state monitoring method and system, it is related to distribution box field, including: acquisition module, for collecting each loop current voltage signal in distribution box, cabinet surface temperature distribution and cabinet door opening and closing state signal, the analog signal collected is converted into digital signal sequence;Extraction module is used to receive digital signal sequence, extracts signal fluctuation characteristics, temperature field distribution characteristics and state signal change characteristics to generate three-dimensional feature set;The application can obtain loop electric parameter, cabinet temperature and cabinet door state in real time, accurately analyze operating characteristics to deduce state trend, quickly locate problem loop components and influence range when abnormal, scientific assessment health grade, timely early warning, simultaneously disconnect associated equipment power supply when serious, effectively reduce fault downtime, improve power safety and maintenance efficiency, guarantee distribution box stable operation.

Description

Technical Field

[0001] This invention relates to the field of distribution box technology, specifically to a method and system for monitoring the operating status of distribution boxes. Background Technology

[0002] Distribution boxes are core equipment in power systems, consisting of switching equipment, protective electrical appliances, etc. They are responsible for power distribution and circuit on / off control. Through circuit breakers, leakage current protectors, etc., they provide overload, short circuit, and leakage protection, ensuring safe and reliable power use. Currently, distribution boxes are transforming towards intelligence and modularization, integrating technologies such as the Internet of Things and AI, enabling remote monitoring of operating status, fault diagnosis, and predictive maintenance, adapting to the needs of smart grids and new energy sources.

[0003] The invention patent application with application number 202411555332.6 discloses a method for monitoring the operating status of a distribution box. This application aims to solve the problems that "manual detection of operating load relies on the professional skills of personnel, which is unreliable and affects operational safety; the analysis of the operating environment does not comprehensively consider the power distribution safety and operating efficiency, which is not comprehensive enough and makes it difficult to accurately judge the impact of the environment on the operating status; and warnings are often issued only after an anomaly occurs, making timely maintenance difficult. The anomaly warnings also use fixed thresholds, which do not consider the wear and tear of the equipment itself, making them prone to misjudgment and resulting in the monitoring not achieving the expected results."

[0004] For the daily operation and maintenance management and monitoring of distribution boxes, existing technologies rarely have comprehensive safety monitoring and simulation functions. Therefore, we propose a new method and system for monitoring the operating status of distribution boxes for daily operation and maintenance management and monitoring. Summary of the Invention

[0005] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a method and system for monitoring the operating status of a distribution box, which can effectively solve the problems of the existing technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions;

[0007] This invention discloses a power distribution box operation status monitoring system, comprising:

[0008] The system comprises the following modules: Acquisition module, Extraction module, and Analysis module. The Acquisition module collects current and voltage signals from each circuit within the distribution box, temperature distribution on the box surface, and door opening / closing status signals, converting the collected analog signals into digital signal sequences. Extraction module receives the digital signal sequences and extracts signal fluctuation characteristics, temperature field distribution characteristics, and status signal change characteristics to generate a three-dimensional feature set. Analysis module receives the three-dimensional feature set, analyzes the correlation between features, and analyzes the evolution trend of the distribution box's operating status, outputting the trend analysis results. Location module acquires the trend analysis results and, when the results indicate an abnormal tendency, locates the corresponding circuit, component, and associated impact range, generating a location message. Assessment module acquires the trend analysis results and location message, and, combined with the three-dimensional feature set, assesses the health level of the distribution box's current operating status. Monitoring module receives the current health level assessment results of the distribution box, continuously monitors the dynamic changes in the health level, and outputs a warning signal containing the warning level and associated abnormal information when the level falls below a preset threshold or the rate of change is abnormal.

[0009] The acquisition module is interactively connected to the extraction module via a wireless network. The extraction module is interactively connected to the inference module and the positioning module via a wireless network. The inference module and the positioning module are interactively connected to the evaluation module via a wireless network. The evaluation module is interactively connected to the monitoring module via a wireless network.

[0010] Furthermore, during the operation phase of the acquisition module, the current and voltage signals of each circuit are sampled at the same frequency by triggering a synchronous clock, so that the sampling time deviation is always controlled within a preset time range.

[0011] The acquisition module integrates a temperature acquisition array. The acquisition points of the temperature acquisition array are arranged in the heat accumulation area on the surface of the cabinet and the corresponding outer wall area of ​​each core component of the circuit. The coordinate information of each acquisition point and the model and installation position information of the corresponding circuit component are pre-stored inside the acquisition module. The acquisition module integrates a non-contact Hall sensor, which generates a cabinet door opening and closing status signal by detecting the change in magnetic flux between the cabinet door and the cabinet.

[0012] Furthermore, when performing feature extraction, the extraction module follows the following rules:

[0013] Short-time Fourier transforms are performed on the current and voltage signals in the digital signal sequence, and the frequency domain peak, characteristic frequency band energy ratio, and phase offset of adjacent sampling points are extracted from the transform results to form a feature subset of current and voltage fluctuations.

[0014] Spatial gradient calculation is performed on the digital signal of temperature distribution on the surface of the box to obtain the gradient amplitude and gradient direction characteristics of the temperature field. At the same time, density clustering algorithm is used to cluster the temperature values ​​of all temperature acquisition points, and the temperature values ​​of the cluster centers and the temperature variance within the cluster are extracted to form a subset of temperature field distribution characteristics.

[0015] The time sequence of cabinet door opening and closing status signals is labeled, and the opening and closing frequency, duration of a single opening and closing, and interval period between two adjacent opening and closing are extracted to form a subset of status signal change features.

[0016] Finally, the three feature subsets are input into the attention mechanism network. The network learns the matching degree between each feature vector and the abnormal features in the historical fault samples of the distribution box, and generates dynamic attention weights for each feature. The generation logic is that the higher the matching degree, the greater the weight. The feature vectors are then weighted and summed according to the weights to output the three-dimensional feature set.

[0017] Furthermore, the process by which the deduction module deduces the evolution trend of the operating state based on the correlation analysis between features is as follows:

[0018] Calculate the mutual information between any two features of different types in a 3D feature set:

[0019] ;

[0020] In the formula: The information entropy of the first feature sequence X; The information entropy of the second feature sequence Y; Let X be the joint information entropy of Y.

[0021] Calculate the grey relational degree between each feature sequence and the feature sequence of the standard operating state of the distribution box, where the feature sequence of the standard operating state of the distribution box is generated by statistical analysis of the distribution box's factory commissioning and long-term normal operation data:

[0022] ;

[0023] In the formula: Grey relational degree; The number of samples in the feature sequence; This represents the i-th sample value of the k-th feature sequence to be analyzed. This represents the i-th sample value of the standard feature sequence; The resolution coefficient, ∈ (0,1); This represents the minimum difference between all characteristic sequences and standard sequence samples; This represents the maximum value of the differences between all feature sequences and the standard sequence samples;

[0024] Again , Normalize them separately to bring them to the interval [0,1], denoted as . And configure weights to calculate the overall correlation between features:

[0025] ,in All are positive numbers and their sum is 1;

[0026] based on Construct a feature association network, where each network node is a single feature in a 3D feature set, and the weights of edges between nodes are taken from the weights of the corresponding two features. Then, the first-order difference is calculated for the feature time sequence of each node to obtain the feature change rate. Combined with the edge weight analysis, the synchronicity of changes between related features is analyzed. Then, by comparing the change trend of the current related features with the feature change trend under the standard operating state, the trend slope reflecting the speed of state evolution is quantified. A positive slope indicates evolution in the normal direction, and a negative slope indicates evolution in the abnormal direction. The larger the absolute value, the faster the evolution. At the same time, the proportion of the number of edges with edge weights lower than the preset correlation degree threshold in the network is counted. This proportion is used as the probability of abnormal risk. Finally, the trend inference result containing the trend slope and the probability of abnormal risk is output.

[0027] Furthermore, when the positioning module locates the circuit, component, and associated impact range corresponding to the anomaly, it follows the following rules:

[0028] Logic-step1: Determine whether there is an abnormal tendency based on the abnormal risk probability and trend slope in the trend extrapolation results; if the judgment result is that there is an abnormal tendency, then determine the feature type corresponding to the abnormal tendency based on the feature that is most strongly correlated with the abnormal risk probability and trend slope in the trend extrapolation process.

[0029] Logic-step 2: Construct the fault propagation matrix M of the distribution box. The matrix dimension is the number of circuit components × the number of circuit components, and the elements are... This represents the probability that a failure in the i-th loop component will propagate to the j-th loop component. The value is determined by the comprehensive correlation degree of the features corresponding to the i-th and j-th components. Mapping generation follows a higher degree of correlation. The larger;

[0030] Logic-step 3: Set a comprehensive correlation threshold, which will be related to the feature type corresponding to the abnormal tendency and Loop components corresponding to features that are not less than the comprehensive correlation threshold are marked as candidate anomaly sources;

[0031] Logic-step4: For each candidate anomaly source, calculate its fault impact degree within a preset time using the fault propagation matrix. The fault impact degree is the product of the sum of propagation probabilities within the preset time and the number of affected components. The candidate anomaly source with the highest impact degree and the unique starting point of the fault propagation path is determined as the core component of the anomaly.

[0032] Logic-step5: Determine the associated impact range of the anomaly based on the fault propagation path, and generate a location message containing the core component model, installation location identifier, corresponding circuit number, and impact range boundary.

[0033] Furthermore, the evaluation module assesses the health level of the current operating status of the distribution box using the following logic:

[0034] For each feature in the three-dimensional feature set , Represents the total number of features, and calculates their anomaly coefficient. In the formula for calculating the anomaly coefficient Take its actual sampled value, Representation of features Normal operating threshold, =0 indicates no abnormality. The larger the value, the more severe the abnormality.

[0035] according to Determine each Association weight , express The mean of the overall correlation with all other features;

[0036] Finally, calculate the current health index of the distribution box. ;

[0037] Where health thresholds H1, H2, and H3 are set, and they follow the order 1 > H1 > H2 > H3 > 0, then:

[0038] When H∈[H1,1], the health level is excellent, which means there is no abnormal risk.

[0039] When H∈[H2,H1), the health level is good, which means there is a slight abnormality and no need to stop the machine.

[0040] When H∈[H3,H2), the health level is medium, which means moderate abnormality and requires routine inspection;

[0041] When H∈[0,H3), the health level is poor, which means that there is a serious abnormality and the machine needs to be shut down for maintenance.

[0042] Furthermore, when the evaluation module outputs a poor health level for the current operating status of the distribution box, all electrical equipment connected to the distribution box will simultaneously disconnect from the power supply to the distribution box.

[0043] Furthermore, when the monitoring module continuously monitors the dynamic changes in the health level, it follows the following:

[0044] A sliding time window is used to continuously sample the health index H corresponding to the health level. The window length is a preset time T, and the number of samplings within the window is denoted as N. The rate of change of the health index within each sliding window is calculated. , This indicates the health index at the end of the window. The health index at the start of the window is represented by the positive or negative value of v, which indicates whether the health index is rising or falling. The absolute value indicates the rate of change. The exponential smoothing method is then used to predict the health index within a preset time period in the future to obtain the predicted health index.

[0045] Synchronously set health warning thresholds and rate thresholds. When any of the following conditions are met, an warning signal will be output:

[0046] The current H is less than the health warning threshold; the absolute value of v is greater than the rate threshold, which only applies when v is less than zero; the predicted health index is less than the health warning threshold.

[0047] The warning signal includes the warning level and associated anomaly information.

[0048] On the other hand, a method for monitoring the operating status of a distribution box includes:

[0049] The system collects current and voltage signals of each circuit in the distribution box, temperature distribution on the box surface, and door opening / closing status signals, converting analog signals into digital signal sequences. It receives these digital signal sequences, extracts fluctuation characteristics such as current and voltage frequency domain peak values, distribution characteristics such as temperature field gradients, and state change characteristics such as door opening / closing frequency, and generates a three-dimensional feature set through a weighted attention mechanism. It calculates the mutual information between the three-dimensional features and the grey relational degree between the features and standard operating features, obtains a comprehensive relational degree after normalization, and then constructs a feature association network to deduce the evolution trend of the operating status, outputting results including trend slope and abnormal risk probability. If the results show an abnormal tendency, it determines the corresponding feature type and constructs a fault propagation matrix, filters candidate abnormal sources and calculates the fault impact, locates the core abnormal components and the associated impact range, and simultaneously generates a location message. It calculates the abnormal coefficient and association weight of each feature, combines the three-dimensional feature set and other information to obtain a health index and classify health levels. When the health level is poor, it disconnects the power equipment connected to the distribution box. It uses a sliding time window to monitor the dynamic changes of the health index, calculates the rate of change and predicts the future health index, and outputs a warning signal containing the warning level and associated abnormal information when a threshold is triggered.

[0050] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects:

[0051] This invention provides a method and system for monitoring the operating status of a distribution box. During execution, this method and system accurately collect current and voltage signals of each circuit within the distribution box, temperature distribution on the box surface, and door opening / closing status signals, converting them into digital signal sequences. It also extracts signal fluctuations, temperature field distribution, and status change characteristics. Specific characteristic frequency bands are determined for different circuit components, and the accuracy of the feature set is optimized using an attention mechanism. Based on the correlation analysis between features, the evolution trend of the operating status is more reliably predicted. When an abnormal tendency exists, the corresponding circuit, core component, and associated impact range are accurately located. The current operating health level is reasonably assessed to clarify maintenance needs. The dynamic changes in the health level are continuously monitored and future trends are predicted. When early warning conditions are met, a signal containing the early warning level and abnormal information is output. When the health level is poor, the connection of associated power equipment is simultaneously disconnected. This effectively improves the comprehensiveness and accuracy of monitoring, promptly avoids fault risks, and ensures the long-term safe and stable operation of the distribution box. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0053] Figure 1 This is a schematic diagram of a power distribution box operation status monitoring system;

[0054] Figure 2 This is a flowchart illustrating a method for monitoring the operating status of a distribution box. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0056] The present invention will be further described below with reference to embodiments.

[0057] Example 1:

[0058] This embodiment provides a power distribution box operation status monitoring system, such as... Figure 1 As shown, it includes:

[0059] The acquisition module is used to acquire current and voltage signals of each circuit in the distribution box, temperature distribution on the surface of the box, and opening and closing status signals of the cabinet door, and convert the acquired analog signals into digital signal sequences.

[0060] During the operation of the acquisition module, it is triggered by a synchronous clock to sample the current and voltage signals of each circuit at the same frequency, so that the sampling time deviation is always controlled within the preset time range.

[0061] The acquisition module integrates a temperature acquisition array. The acquisition points of the temperature acquisition array are arranged in the heat accumulation area on the surface of the cabinet and the corresponding outer wall area of ​​each core component of the circuit. The coordinate information of each acquisition point and the model and installation position information of the corresponding circuit component are pre-stored inside the acquisition module. The acquisition module integrates a non-contact Hall sensor, which generates a cabinet door opening and closing status signal by detecting the change in magnetic flux between the cabinet door and the cabinet.

[0062] Among them, the heat accumulation area on the surface of the enclosure includes at least the outer wall corresponding to the circuit wiring terminals and the area where the heat dissipation holes are opened, and the core components include at least circuit breakers and contactors;

[0063] The extraction module is used to receive digital signal sequences and extract signal fluctuation features, temperature field distribution features, and state signal change features to generate a three-dimensional feature set.

[0064] When performing feature extraction, the extraction module follows the following rules:

[0065] Short-time Fourier transforms are performed on the current and voltage signals in the digital signal sequence, and the frequency domain peak, characteristic frequency band energy ratio, and phase offset of adjacent sampling points are extracted from the transform results to form a feature subset of current and voltage fluctuations.

[0066] The characteristic frequency band is determined as follows: electrical parameter signals of the distribution box are collected during the factory commissioning phase and within a preset period of continuous normal operation. The signals are then subjected to Fourier transform to obtain the frequency domain distribution data of the electrical parameters during normal operation. Frequency domain intervals in the frequency domain distribution data whose energy proportion exceeds the preset confidence level are statistically analyzed, and these intervals are taken as the "basic characteristic frequency band". Typical interference frequency bands (such as electromagnetic interference frequency bands in the environment where the distribution box is located and harmonic interference frequency bands of the power grid signal) are excluded from the basic characteristic frequency band, and the remaining frequency domain intervals are the "characteristic frequency bands" used for feature extraction. The above steps are repeated for different types of circuit components (such as circuit breakers, contactors, and relays) to generate exclusive characteristic frequency bands that match the component type.

[0067] Spatial gradient calculation is performed on the digital signal of temperature distribution on the surface of the box to obtain the gradient amplitude and gradient direction characteristics of the temperature field. At the same time, density clustering algorithm is used to cluster the temperature values ​​of all temperature acquisition points, and the temperature values ​​of the cluster centers and the temperature variance within the clusters are extracted to form a subset of temperature field distribution characteristics. The clustering parameters are preset through the uniformity analysis of the thermal field of the box.

[0068] The time sequence of cabinet door opening and closing status signals is labeled, and the opening and closing frequency, duration of a single opening and closing, and interval period between two adjacent opening and closing are extracted to form a subset of status signal change features.

[0069] Finally, the three feature subsets are input into the attention mechanism network. The network learns the matching degree between each feature vector and the abnormal features in the historical fault samples of the distribution box, generates dynamic attention weights for each feature, and follows the generation logic that the higher the matching degree, the greater the weight. The feature vectors are then weighted and summed according to the weights to output a three-dimensional feature set.

[0070] The deduction module is used to receive a three-dimensional feature set, analyze the correlation between features to deduce the evolution trend of the operating status of the distribution box, and output the trend deduction results.

[0071] The process of the deduction module, which analyzes the correlation between features to deduce the evolution trend of the operating state, is as follows:

[0072] Calculate the mutual information between any two features of different types in a 3D feature set:

[0073] ;

[0074] In the formula: The information entropy of the first feature sequence X; The information entropy of the second feature sequence Y; Let X be the joint information entropy of Y.

[0075] The above formula constructs a quantitative correlation between the three by introducing the information entropy of the first feature sequence, the information entropy of the second feature sequence, and the joint information entropy of the two. This operational logic distinguishes it from the limitations of traditional single feature analysis, provides basic data support for the subsequent comprehensive evaluation of feature correlation, and applies the concept of mutual information in information theory to the correlation analysis of distribution box operation features, realizing a quantitative expression of the correlation strength between features and avoiding the subjectivity and ambiguity of qualitative analysis.

[0076] in, , Let X and Y represent the total number of samples in the first feature sequence and the total number of samples in the second feature sequence, respectively. Let represent the probability of the i-th sample appearing in X. Let X represent the joint probability of the i-th sample in X and the j-th sample in Y;

[0077] Calculate the grey relational degree between each feature sequence and the feature sequence of the standard operating state of the distribution box, where the feature sequence of the standard operating state of the distribution box is generated by statistical analysis of the distribution box's factory commissioning and long-term normal operation data:

[0078] ;

[0079] In the formula: Grey relational degree; The number of samples in the feature sequence; This represents the i-th sample value of the k-th feature sequence to be analyzed. This represents the i-th sample value of the standard feature sequence; The resolution coefficient, ∈ (0,1), The value is determined based on the operational stability requirements of the distribution box. When higher sensitivity is needed to distinguish subtle differences between the characteristic sequence and the standard operating state characteristic sequence, the value is smaller; when lower sensitivity is permissible, the value is larger. This represents the minimum difference between all characteristic sequences and standard sequence samples; This represents the maximum value of the differences between all feature sequences and the standard sequence samples;

[0080] The above formula is based on the number of characteristic sequence samples. By introducing a resolution coefficient to adjust the analysis sensitivity, and combining the minimum and maximum values ​​of the differences between all characteristic sequences and standard sequence samples, a similarity quantification model of the characteristic sequence to be analyzed and the standard operating state characteristic sequence is constructed. Moreover, the resolution coefficient can be flexibly adjusted according to the stability requirements of the distribution box operation. When high sensitivity is required to distinguish subtle differences, a smaller value is taken, and when low sensitivity is allowed, a larger value is taken. It effectively solves the problem that traditional correlation analysis is difficult to adapt to different stability requirements. It can more accurately reflect the degree of deviation between the characteristic to be analyzed and the standard characteristic, and provide support for judging whether the characteristic is abnormal.

[0081] Again , Normalize them separately to bring them to the interval [0,1], denoted as . And configure weights to calculate the overall correlation between features:

[0082] ,in All are positive numbers and their sum is 1. When the correlation between different types of characteristics has a more critical impact on judging the evolution trend of the distribution box's operating status, The larger the value, the better; conversely, The smaller the value, the more critical the similarity between the feature to be analyzed and the standard operating state features of the distribution box is in determining the trend of the operating state evolution. The larger the value, the better; conversely, The smaller the value;

[0083] The above formula complements the advantages of the two correlation indicators, comprehensively considers the intrinsic correlation between features and the degree of fit between features and standard states, and lays the foundation for constructing feature correlation networks and accurately predicting the evolution trend of operating states.

[0084] based on Construct a feature association network, where each network node is a single feature in a 3D feature set, and the weights of edges between nodes are taken from the weights of the corresponding two features. Then, the first-order difference is calculated for the feature time sequence of each node to obtain the feature change rate. Combined with the edge weight analysis, the synchronicity of changes between related features is analyzed. Then, by comparing the change trend of the current related features with the feature change trend under the standard operating state, the trend slope reflecting the speed of state evolution is quantified. A positive slope indicates evolution in the normal direction, and a negative slope indicates evolution in the abnormal direction. The larger the absolute value, the faster the evolution. At the same time, the proportion of the number of edges with edge weights lower than the preset correlation degree threshold in the network is counted. This proportion is used as the probability of abnormal risk. Finally, the trend inference result containing the trend slope and the probability of abnormal risk is output.

[0085] The positioning module is used to obtain trend projection results. When the results show an abnormal trend, it locates the circuit, component and related impact range corresponding to the abnormality and generates a positioning message.

[0086] When the positioning module locates the circuit, component, and associated impact range corresponding to the anomaly, it follows the following rules:

[0087] Logic-step1: Determine whether there is an abnormal tendency based on the abnormal risk probability and trend slope in the trend extrapolation results; if the judgment result is that there is an abnormal tendency, then determine the feature type corresponding to the abnormal tendency based on the feature that is most strongly correlated with the abnormal risk probability and trend slope in the trend extrapolation process.

[0088] Logic-step 2: Construct the fault propagation matrix M of the distribution box. The matrix dimension is the number of circuit components × the number of circuit components, and the elements are... This represents the probability that a failure in the i-th loop component will propagate to the j-th loop component. The value is determined by the comprehensive correlation degree of the features corresponding to the i-th and j-th components. Mapping generation follows a higher degree of correlation. The larger;

[0089] Logic-step 3: Set a comprehensive correlation threshold, which will be related to the feature type corresponding to the abnormal tendency and Loop components corresponding to features that are not less than the comprehensive correlation threshold are marked as candidate anomaly sources;

[0090] Logic-step4: For each candidate anomaly source, calculate its fault impact within a preset time using the fault propagation matrix. The fault impact is the product of the sum of propagation probabilities within the preset time and the number of affected components. The candidate anomaly source with the highest impact and the unique starting point of the fault propagation path is identified as the core component of the anomaly.

[0091] Logic-step 5: Determine the scope of the anomaly's associated impact based on the fault propagation path (e.g., the circuit containing the core component and its propagation probability). For loops with a value of ≥0.5, a positioning message is generated that includes the core component model, installation location identifier, corresponding loop number, and boundary of the affected area.

[0092] The fault propagation path starts from the faulty core component and the propagation probability is selected based on the fault propagation matrix. The inter-component relationships are determined to be no less than a preset propagation probability threshold;

[0093] The assessment module is used to obtain trend projection results and location messages, and combined with the three-dimensional feature set, assess the health level of the current operating status of the distribution box;

[0094] The evaluation module assesses the health level of the distribution box's current operating status using the following logic:

[0095] For each feature in the three-dimensional feature set , Represents the total number of features, and calculates their anomaly coefficient. In the formula for calculating the anomaly coefficient Take its actual sampled value, Representation of features Normal operating threshold, =0 indicates no abnormality. The larger the value, the more severe the abnormality.

[0096] according to Determine each Association weight , express The mean of the overall correlation with all other features;

[0097] Finally, calculate the current health index of the distribution box. ;

[0098] Where health thresholds H1, H2, and H3 are set, and they follow the order 1 > H1 > H2 > H3 > 0, then:

[0099] When H∈[H1,1], the health level is excellent, which means there is no abnormal risk.

[0100] When H∈[H2,H1), the health level is good, which means there is a slight abnormality and no need to stop the machine.

[0101] When H∈[H3,H2), the health level is medium, which means moderate abnormality and requires routine inspection;

[0102] When H∈[0,H3), the health level is poor, which means a serious abnormality and requires shutdown for maintenance;

[0103] When the health level of the current operating status of the distribution box output by the evaluation module is poor, all electrical equipment connected to the distribution box will be disconnected from the power supply at the same time.

[0104] The monitoring module is used to receive the current health level assessment results of the distribution box, continuously monitor the dynamic changes of the health level, and output an early warning signal containing the warning level and related abnormal information when the level is lower than the preset threshold or the rate of change is abnormal.

[0105] When the monitoring module continuously monitors the dynamic changes in health level, it follows the following rules:

[0106] A sliding time window is used to continuously sample the health index H corresponding to the health level. The window length is a preset time T, and the number of samplings within the window is denoted as N. The rate of change of the health index within each sliding window is calculated. , This indicates the health index at the end of the window. The health index at the start of the window is represented by the positive or negative value of v, which indicates whether the health index is rising or falling. The absolute value indicates the rate of change. The exponential smoothing method is then used to predict the health index within a preset time period in the future to obtain the predicted health index.

[0107] The smoothing coefficient is preset based on the historical stability of the health index. The smoothing coefficient is preset based on the standard deviation of the historical health index series. That is, the smaller the ratio of the standard deviation to the coefficient of variation, the larger the smoothing coefficient, and vice versa.

[0108] Synchronously set health warning thresholds and rate thresholds. When any of the following conditions are met, an warning signal will be output:

[0109] The current H is less than the health warning threshold; the absolute value of v is greater than the rate threshold, which only applies when v is less than zero; the predicted health index is less than the health warning threshold.

[0110] The warning signal includes the warning level and related anomaly information;

[0111] The warning level is determined by setting the discrimination range based on the degree of deviation between H and the health warning threshold, and the degree of deviation between the absolute value of v and the rate threshold, so as to divide it into Level 1 warning, Level 2 warning, and Level 3 warning. The associated abnormal information includes the specific feature categories that cause health level abnormalities or warnings in the three-dimensional feature set, and the location information of the abnormal core components.

[0112] The data acquisition module is interconnected with the extraction module via a wireless network. The extraction module is interconnected with the deduction module and the positioning module via a wireless network. The deduction module and the positioning module are interconnected with the evaluation module via a wireless network. The evaluation module is interconnected with the monitoring module via a wireless network.

[0113] In this embodiment, the acquisition module collects current and voltage signals of each circuit in the distribution box, temperature distribution on the box surface, and door opening / closing status signals. It converts the collected analog signals into digital signal sequences. The extraction module then receives these digital signal sequences and extracts signal fluctuation characteristics, temperature field distribution characteristics, and status signal change characteristics to generate a three-dimensional feature set. The deduction module receives this three-dimensional feature set and, based on the correlation between features, deduces the evolution trend of the distribution box's operating status, outputting the trend deduction result. The positioning module further acquires the trend deduction result. When the result indicates an abnormal tendency, it locates the circuit, component, and associated impact range corresponding to the abnormality, generating a positioning message. The evaluation module acquires the trend deduction result and the positioning message, and, combined with the three-dimensional feature set, evaluates the health level of the distribution box's current operating status. Finally, the monitoring module receives the current health level evaluation result of the distribution box and continuously monitors the dynamic changes in the health level. When the level is below a preset threshold or the rate of change is abnormal, it outputs a warning signal containing the warning level and associated abnormal information.

[0114] In the above embodiments, the system can acquire circuit electrical parameters, box temperature and cabinet door status in real time in the operation scenario of the distribution box, accurately analyze the operating characteristics to deduce the status trend, quickly locate the problematic circuit components and the scope of impact when abnormalities occur, scientifically assess the health level, provide timely warnings, and simultaneously disconnect the power supply to related equipment when the situation is serious, effectively reducing downtime due to faults, improving power safety and maintenance efficiency, and ensuring the stable operation of the distribution box.

[0115] Example 2:

[0116] At the implementation level, based on Example 1, this example refers to... Figure 2 A further detailed description of the distribution box operation status monitoring system in Example 1 is provided below:

[0117] A method for monitoring the operating status of a distribution box, comprising:

[0118] Collect current and voltage signals of each circuit in the distribution box, temperature distribution on the surface of the box, and opening and closing status signals of the cabinet door, and convert the analog signals into digital signal sequences;

[0119] The system receives digital signal sequences, extracts fluctuation features such as peak values ​​in the frequency domain of current and voltage, distribution features such as temperature field gradient, and state change features such as cabinet door opening and closing frequency, and generates a three-dimensional feature set by weighting through an attention mechanism.

[0120] Calculate the mutual information between three-dimensional features and the grey correlation degree between features and standard operating features. After normalization, obtain the comprehensive correlation degree. Then, construct a feature correlation network to infer the evolution trend of the operating status and output the results including trend slope and abnormal risk probability.

[0121] If the results show an abnormal tendency, determine the corresponding feature type and construct a fault propagation matrix, screen candidate anomaly sources and calculate the fault impact, locate the core components of the anomaly and the associated impact range, and generate a location message simultaneously.

[0122] Calculate the anomaly coefficient and correlation weight of each feature, combine information such as the three-dimensional feature set to obtain the health index and classify the health level. When the health level is poor, disconnect the power equipment connected to the distribution box.

[0123] The system uses a sliding time window to monitor the dynamic changes in health indices, calculates the rate of change, predicts future health indices, and outputs an early warning signal containing the warning level and related abnormal information when a threshold is triggered.

[0124] In summary, the system and method in the above embodiments can accurately collect current and voltage signals of each circuit in the distribution box, temperature distribution on the box surface, and door opening and closing status signals during execution, and convert them into digital signal sequences. They also extract signal fluctuations, temperature field distribution, and state change characteristics, determine specific characteristic frequency bands for different circuit components, optimize the accuracy of feature sets using an attention mechanism, and more reliably deduce the evolution trend of operating status based on the correlation analysis between features. When an abnormal tendency exists, they accurately locate the circuit, core component, and related impact range corresponding to the abnormality, reasonably assess the current operating health level to clarify maintenance needs, continuously monitor the dynamic changes in the health level and predict future trends, output a signal containing the warning level and abnormal information when the warning conditions are met, and simultaneously disconnect the connection of related power equipment when the health level is poor. This effectively improves the comprehensiveness and accuracy of monitoring, timely avoids fault risks, and ensures the long-term safe and stable operation of the distribution box.

[0125] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A power distribution box operation status monitoring system, characterized in that, include: The data acquisition module is used to acquire current and voltage signals of each circuit in the distribution box, temperature distribution on the surface of the box, and opening and closing status signals of the cabinet door, and convert the acquired analog signals into digital signal sequences. The extraction module is used to receive digital signal sequences and extract signal fluctuation features, temperature field distribution features, and state signal change features to generate a three-dimensional feature set. The deduction module is used to receive a three-dimensional feature set, analyze the correlation between features to deduce the evolution trend of the operating status of the distribution box, and output the trend deduction results. The process of the deduction module, which analyzes the correlation between features to deduce the evolution trend of the operating state, is as follows: Calculate the mutual information between any two features of different types in a 3D feature set: ； In the formula: The information entropy of the first feature sequence X; The information entropy of the second feature sequence Y; Let X be the joint information entropy of Y. Calculate the grey relational degree between each feature sequence and the feature sequence of the standard operating state of the distribution box, where the feature sequence of the standard operating state of the distribution box is generated by statistical analysis of the distribution box's factory commissioning and long-term normal operation data: ； In the formula: Grey relational degree; The number of samples in the feature sequence; This represents the i-th sample value of the k-th feature sequence to be analyzed. This represents the i-th sample value of the standard feature sequence; The resolution coefficient, ∈ (0,1); This represents the minimum difference between all characteristic sequences and standard sequence samples; This represents the maximum value of the differences between all feature sequences and the standard sequence samples; Again , Normalize them separately to bring them to the interval [0,1], denoted as . And configure weights to calculate the overall correlation between features: ,in All are positive numbers and their sum is 1; based on Construct a feature association network, where each network node is a single feature in a 3D feature set, and the weights of edges between nodes are taken from the weights of the corresponding two features. Then, the first-order difference is calculated for the feature time sequence of each node to obtain the feature change rate. Combined with the edge weight analysis, the synchronicity of changes between related features is analyzed. Then, by comparing the change trend of the current related features with the feature change trend under the standard operating state, the trend slope reflecting the speed of state evolution is quantified. A positive slope indicates evolution in the normal direction, and a negative slope indicates evolution in the abnormal direction. The larger the absolute value, the faster the evolution. At the same time, the proportion of the number of edges with edge weights lower than the preset correlation degree threshold in the network is counted. This proportion is used as the probability of abnormal risk. Finally, the trend inference result containing the trend slope and the probability of abnormal risk is output. The positioning module is used to obtain trend projection results. When the results show an abnormal trend, it locates the circuit, component and related impact range corresponding to the abnormality and generates a positioning message. The assessment module is used to obtain trend projection results and location messages, and combined with the three-dimensional feature set, assess the health level of the current operating status of the distribution box; The monitoring module is used to receive the current health level assessment results of the distribution box, continuously monitor the dynamic changes in the health level, and output an early warning signal containing the warning level and related abnormal information when the level is lower than the preset threshold or the rate of change is abnormal.

2. The distribution box operation status monitoring system according to claim 1, characterized in that, During the operation phase, the acquisition module is triggered by a synchronous clock to sample the current and voltage signals of each circuit at the same frequency, so that the sampling time deviation is always controlled within a preset time range. The acquisition module integrates a temperature acquisition array. The acquisition points of the temperature acquisition array are arranged in the heat accumulation area on the surface of the cabinet and the corresponding outer wall area of ​​each core component of the circuit. The coordinate information of each acquisition point and the model and installation position information of the corresponding circuit component are pre-stored inside the acquisition module. The acquisition module integrates a non-contact Hall sensor, which generates a cabinet door opening and closing status signal by detecting the change in magnetic flux between the cabinet door and the cabinet.

3. The distribution box operation status monitoring system according to claim 1, characterized in that, When performing feature extraction, the extraction module follows the following rules: Short-time Fourier transforms are performed on the current and voltage signals in the digital signal sequence, and the frequency domain peak, characteristic frequency band energy ratio, and phase offset of adjacent sampling points are extracted from the transform results to form a feature subset of current and voltage fluctuations. Spatial gradient calculation is performed on the digital signal of temperature distribution on the surface of the box to obtain the gradient amplitude and gradient direction characteristics of the temperature field. At the same time, density clustering algorithm is used to cluster the temperature values ​​of all temperature acquisition points, and the temperature values ​​of the cluster centers and the temperature variance within the cluster are extracted to form a subset of temperature field distribution characteristics. The time sequence of cabinet door opening and closing status signals is labeled, and the opening and closing frequency, duration of a single opening and closing, and interval period between two adjacent opening and closing are extracted to form a subset of status signal change features. Finally, the three feature subsets are input into the attention mechanism network. The network learns the matching degree between each feature vector and the abnormal features in the historical fault samples of the distribution box, and generates dynamic attention weights for each feature. The generation logic is that the higher the matching degree, the greater the weight. The feature vectors are then weighted and summed according to the weights to output the three-dimensional feature set.

4. The distribution box operation status monitoring system according to claim 1, characterized in that, When the positioning module locates the circuit, component, and associated impact range corresponding to the anomaly, it follows the following rules: Logic-step1: Determine whether there is an abnormal tendency based on the abnormal risk probability and trend slope in the trend extrapolation results; if the judgment result is that there is an abnormal tendency, then determine the feature type corresponding to the abnormal tendency based on the feature that is most strongly correlated with the abnormal risk probability and trend slope in the trend extrapolation process. Logic-step 2: Construct the fault propagation matrix M of the distribution box. The matrix dimension is the number of circuit components × the number of circuit components, and the elements are... This represents the probability that a failure in the i-th loop component will propagate to the j-th loop component. The value is determined by the comprehensive correlation degree of the features corresponding to the i-th and j-th components. Mapping generation follows a higher degree of correlation. The larger; Logic-step 3: Set a comprehensive correlation threshold, which will be related to the feature type corresponding to the abnormal tendency and Loop components corresponding to features that are not less than the comprehensive correlation threshold are marked as candidate anomaly sources; Logic-step4: For each candidate anomaly source, calculate its fault impact degree within a preset time using the fault propagation matrix. The fault impact degree is the product of the sum of propagation probabilities within the preset time and the number of affected components. The candidate anomaly source with the highest impact degree and the unique starting point of the fault propagation path is determined as the core component of the anomaly. Logic-step5: Determine the associated impact range of the anomaly based on the fault propagation path, and generate a location message containing the core component model, installation location identifier, corresponding circuit number, and impact range boundary.

5. The distribution box operation status monitoring system according to claim 1, characterized in that, The evaluation module assesses the health level of the current operating status of the distribution box using the following logic: For each feature in the three-dimensional feature set , Represents the total number of features, and calculates their anomaly coefficient. In the formula for calculating the anomaly coefficient Take its actual sampled value, Representation of features Normal operating threshold, =0 indicates no abnormality. The larger the value, the more severe the abnormality. according to Determine each Association weight , express The mean of the overall correlation with all other features; Finally, calculate the current health index of the distribution box. ; Where health thresholds H1, H2, and H3 are set, and they follow the order 1 > H1 > H2 > H3 > 0, then: When H∈[H1,1], the health level is excellent, which means there is no abnormal risk. When H∈[H2,H1), the health level is good, which means there is a slight abnormality and no need to stop the machine. When H∈[H3,H2), the health level is medium, which means moderate abnormality and requires routine inspection; When H∈[0,H3), the health level is poor, which means that there is a serious abnormality and the machine needs to be shut down for maintenance.

6. The distribution box operation status monitoring system according to claim 5, characterized in that, When the evaluation module outputs a poor health level for the current operating status of the distribution box, all electrical equipment connected to the distribution box will simultaneously disconnect from the power supply.

7. The distribution box operation status monitoring system according to claim 1, characterized in that, When the monitoring module continuously monitors the dynamic changes in health level, it follows the following rules: A sliding time window is used to continuously sample the health index H corresponding to the health level. The window length is a preset time T, and the number of samplings within the window is denoted as N. The rate of change of the health index within each sliding window is calculated. , This indicates the health index at the end of the window. The health index at the start of the window is represented by the positive or negative value of v, which indicates whether the health index is rising or falling. The absolute value indicates the rate of change. The exponential smoothing method is then used to predict the health index within a preset time period in the future to obtain the predicted health index. Synchronously set health warning thresholds and rate thresholds. When any of the following conditions are met, an warning signal will be output: The current H is less than the health warning threshold; the absolute value of v is greater than the rate threshold, which only applies when v is less than zero; the predicted health index is less than the health warning threshold. The warning signal includes the warning level and associated anomaly information.

8. The distribution box operation status monitoring system according to claim 1, characterized in that, The acquisition module is interactively connected to the extraction module via a wireless network. The extraction module is interactively connected to the inference module and the positioning module via a wireless network. The inference module and the positioning module are interactively connected to the evaluation module via a wireless network. The evaluation module is interactively connected to the monitoring module via a wireless network.

9. A method for monitoring the operating status of a distribution box, wherein the method is an implementation method of a distribution box operating status monitoring system as described in any one of claims 1-8, characterized in that, include: Collect current and voltage signals of each circuit in the distribution box, temperature distribution on the surface of the box, and opening and closing status signals of the cabinet door, and convert the analog signals into digital signal sequences; The system receives digital signal sequences, extracts fluctuation features such as peak values ​​in the frequency domain of current and voltage, distribution features such as temperature field gradient, and state change features such as cabinet door opening and closing frequency, and generates a three-dimensional feature set by weighting through an attention mechanism. Calculate the mutual information between three-dimensional features and the grey correlation degree between features and standard operating features. After normalization, obtain the comprehensive correlation degree. Then, construct a feature correlation network to infer the evolution trend of the operating status and output the results including trend slope and abnormal risk probability. If the results show an abnormal tendency, determine the corresponding feature type and construct a fault propagation matrix, screen candidate anomaly sources and calculate the fault impact, locate the core components of the anomaly and the associated impact range, and generate a location message simultaneously. Calculate the anomaly coefficient and correlation weight of each feature, combine information such as the three-dimensional feature set to obtain the health index and classify the health level. When the health level is poor, disconnect the power equipment connected to the distribution box. The system uses a sliding time window to monitor the dynamic changes in health indices, calculates the rate of change, predicts future health indices, and outputs an early warning signal containing the warning level and related abnormal information when a threshold is triggered.

Images