High-low voltage power distribution cabinet separation brake control system and method based on internet of things

Abstract

The present application relates to the technical field of switch control of power distribution cabinet, and particularly relates to a high-low voltage power distribution cabinet switch control system and method based on the Internet of Things, which combines electrical operation data and environmental state data of the high-low voltage power distribution cabinet to analyze abnormal conditions of electrical energy reception and distribution of the high-low voltage power distribution cabinet, thereby analyzing abnormal conditions of electrical operation of the high-low voltage power distribution cabinet, combining switch state data and environmental state data of the high-low voltage power distribution cabinet to analyze abnormal operation risks of the switch in the high-low voltage power distribution cabinet, based on the analysis results of abnormal conditions of electrical operation of the high-low voltage power distribution cabinet and the analysis results of abnormal operation risks of the switch, evaluating the global safety situation of the high-low voltage power distribution cabinet, based on the evaluation results of the global safety situation of the high-low voltage power distribution cabinet, executing a differentiated switch control scheme, thereby early discovering potential fault risks of the switch and improving the operation reliability of the power distribution system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of switch control of power distribution cabinet, and particularly relates to a switch control system and method of high-low voltage power distribution cabinet based on Internet of Things. BACKGROUND

[0002] As the core equipment of power distribution and control in the power system, the operation reliability of high-low voltage power distribution cabinet is directly related to the power safety and production stability of the power supply area. As the key component of the power distribution cabinet for executing the on-off operation of the circuit, the control performance of the switch directly affects the operation safety of the entire power distribution system. During the long-term operation of the power distribution cabinet, the switch will not only be subjected to the continuous impact of the electrical load, resulting in problems such as contact wear and mechanism aging; moreover, environmental factors such as temperature change, humidity erosion and mechanical vibration will also accelerate the deterioration of the components; if the performance degradation trend of the switch cannot be found in time, it may cause operation refusal, misoperation or even equipment explosion, which not only causes large-area power loss, but also endangers the safety of the operation and maintenance personnel.

[0003] However, the prior art does not correlate the electrical operation abnormality and the switch mechanism state when monitoring and controlling the switch of the power distribution cabinet, for example, when the voltage sag or current impact occurs in the power grid, it is difficult to accurately evaluate the operation success probability of the switch under the fault condition without considering the current mechanical characteristics and operation history of the switch, thereby leading to misjudgment of the operation risk. At the same time, the prior art also lacks quantitative evaluation of the influence range of the switch, which makes it difficult to accurately match the actual risk level for the control strategy, and cannot provide a comprehensive basis for differentiated safety control.

[0004] In order to solve these problems, the present application designs a switch control system and method of high-low voltage power distribution cabinet based on Internet of Things. SUMMARY

[0005] In order to overcome the defects and deficiencies of the prior art, the present application provides a switch control system and method of high-low voltage power distribution cabinet based on Internet of Things, which collects the electrical operation, environmental state and switch mechanism data of the power distribution cabinet in real time through the Internet of Things sensor, analyzes the abnormality of electrical energy reception and distribution and the operation risk of the switch by using a deep learning model, constructs a global safety situation assessment system, and finally executes a differentiated switch control scheme based on the risk level.

[0006] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0007] In the first aspect, the present application provides a switch control method of high-low voltage power distribution cabinet based on Internet of Things, which includes the following steps:

[0008] S1, through the Internet of Things sensor deployed in the high and low voltage power distribution cabinet, the electrical operation data, the environmental state data and the separation gate state data of the high and low voltage power distribution cabinet are synchronously collected;

[0009] S2, the electrical energy receiving and distribution abnormality of the high and low voltage power distribution cabinet is analyzed in combination with the electrical operation data and the environmental state data of the high and low voltage power distribution cabinet, and the electrical operation abnormality of the high and low voltage power distribution cabinet is analyzed according to the electrical energy receiving and distribution abnormality analysis result;

[0010] S3, the operation abnormal risk of the separation gate in the high and low voltage power distribution cabinet is analyzed in combination with the separation gate state data and the environmental state data of the high and low voltage power distribution cabinet;

[0011] S4, the global safety situation of the high and low voltage power distribution cabinet is evaluated based on the electrical operation abnormality analysis result and the separation gate operation abnormal risk analysis result of the high and low voltage power distribution cabinet;

[0012] S5, a differentiated separation gate control scheme is executed based on the global safety situation evaluation result of the high and low voltage power distribution cabinet.

[0013] As an implementation manner of the present application, the electrical energy receiving and distribution abnormality of the high and low voltage power distribution cabinet is analyzed in combination with the electrical operation data and the environmental state data of the high and low voltage power distribution cabinet in step S2, including the following specific steps:

[0014] S21, the electrical operation data and the environmental state data of the high and low voltage power distribution cabinet are extracted, wherein the electrical operation data includes an input side electrical operation characteristic parameter sequence and an output side electrical operation characteristic parameter sequence; the environmental state data includes an environmental state monitoring parameter sequence;

[0015] S22, based on a long short-term memory network autoencoder model, the input side electrical operation characteristic parameter sequence and the environmental state monitoring parameter sequence in the current monitoring period are taken as input side original sequences and introduced into an electrical energy receiving abnormality detection model, the input side electrical operation characteristic parameter sequence and the environmental state monitoring parameter sequence are reconstructed, and an input side reconstruction sequence including an input side electrical operation characteristic parameter reconstruction sequence and an environmental state monitoring parameter reconstruction sequence is obtained.

[0016] S23, the input side reconstruction error between the input side reconstruction sequence and the input side original sequence is calculated, a preset input side error threshold value is taken, and the ratio of the input side reconstruction error to the input side error threshold value is taken as the electrical energy receiving abnormality state in the current monitoring period.

[0017] As an implementation manner of the present application, the electrical operation abnormality of the high and low voltage power distribution cabinet is analyzed according to the electrical energy receiving and distribution abnormality analysis result in step S2, and the following specific contents are further included:

[0018] S24, based on the long short-term memory network autoencoder model, the output side electrical operation characteristic parameter sequence and the environment state monitoring parameter sequence in the current monitoring period are taken as the output side original sequence and introduced into the electric energy distribution anomaly detection model, the output side electrical operation characteristic parameter sequence and the environment state monitoring parameter sequence are reconstructed, and the output side reconstructed sequence containing the output side electrical operation characteristic parameter reconstructed sequence and the environment state monitoring parameter reconstructed sequence is obtained;

[0019] S25, the output side reconstruction error between the output side reconstructed sequence and the output side original sequence is calculated, a preset output side error threshold is set, and the ratio of the output side reconstruction error to the output side error threshold is taken as the electric energy distribution abnormal state in the current monitoring period;

[0020] S26, the electric energy receiving abnormal state and the electric energy distribution abnormal state in the current monitoring period are weighted and summed, and the electrical operation abnormality of the high-low voltage power distribution cabinet in the current monitoring period is obtained.

[0021] As an implementation manner of the present application, the operation abnormal risk of the disconnecting switch in the high-low voltage power distribution cabinet is analyzed in step S3 in combination with the disconnecting switch state data and the environment state data of the high-low voltage power distribution cabinet, including the following specific steps:

[0022] S31, the disconnecting switch state data and the environment state data in the high-low voltage power distribution cabinet are obtained, the cumulative operation times of the disconnecting switch, the average time of the last three operations, and the motor driving current peak value in the disconnecting switch state data are taken as the disconnecting switch state feature vector set, the cabinet temperature, the cabinet humidity, and the cabinet vibration amplitude in the environment state data are taken as the environment state feature vector set, the disconnecting switch state feature vector set and the environment state feature vector set are taken as the abnormal detection data set, and the abnormal detection data set is divided into an abnormal detection training set and an abnormal detection verification set;

[0023] S32, a support vector data description model is constructed, the cumulative operation times of the disconnecting switch, the average time of the last three operations, the motor driving current peak value, the cabinet temperature, the cabinet humidity, and the cabinet vibration amplitude in the abnormal detection training set are taken as the input features of the support vector data description model, the input features are mapped to a high-dimensional feature space through a kernel function, a smallest hypersphere containing the most normal samples is found in the high-dimensional feature space, the support vector data description model is trained, and an initial abnormal detection model is obtained;

[0024] S33, the initial abnormal detection model is verified through the abnormal detection verification set, and the initial abnormal detection model with a value greater than or equal to a preset model accuracy is output as the disconnecting switch operation abnormal detection model.

[0025] As an implementation manner of the present application, the operation abnormality risk of the disconnecting switch in the high-low voltage power distribution cabinet is analyzed in combination with the disconnecting switch state data and the environment state data of the high-low voltage power distribution cabinet, and the following specific contents are further included:

[0026] The disconnecting switch state feature vector set and the environment state feature vector set in the current monitoring period are acquired, the average distance from all vectors in the disconnecting switch state feature vector set and the environment state feature vector set in the current monitoring period to the center of the disconnecting switch operation abnormality detection model hypersphere is calculated respectively based on the disconnecting switch operation abnormality detection model, the disconnecting switch operation abnormality detection model hypersphere radius is extracted, and the ratio of the average distance to the disconnecting switch operation abnormality detection model hypersphere radius is taken as the operation abnormality risk of the disconnecting switch in the high-low voltage power distribution cabinet in the current monitoring period.

[0027] As an implementation manner of the present application, the global security situation of the high-low voltage power distribution cabinet is evaluated based on the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet and the operation abnormality risk analysis result of the disconnecting switch in step S4, and the following specific steps are included:

[0028] S41, the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet in the current monitoring period and the operation abnormality risk analysis result of each disconnecting switch in the high-low voltage power distribution cabinet in the current monitoring period are acquired, and the number of all load devices downstream of each disconnecting switch in the high-low voltage power distribution cabinet is acquired at the same time;

[0029] S42, the number of all load devices downstream of all disconnecting switches is summed, and the ratio of the number of all load devices downstream of each disconnecting switch to the sum result is taken as the operation abnormality risk weight of each disconnecting switch;

[0030] S43, the operation abnormality risk analysis result of each disconnecting switch in the current monitoring period is multiplied by the corresponding operation abnormality risk weight to obtain the global operation abnormality risk component of each disconnecting switch in the current monitoring period, and the global operation abnormality risk components of all disconnecting switches in the current monitoring period are summed to obtain the disconnecting switch global operation abnormality risk of the high-low voltage power distribution cabinet in the current monitoring period;

[0031] S44, the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet in the current monitoring period and the disconnecting switch global operation abnormality risk are weighted and summed to obtain the global security situation evaluation result of the high-low voltage power distribution cabinet in the current monitoring period.

[0032] As an implementation manner of the present application, the differentiated disconnecting switch control scheme is executed based on the global security situation evaluation result of the high-low voltage power distribution cabinet in step S5, and the following specific steps are included:

[0033] S51, obtain the global safety situation evaluation result of the high-low voltage power distribution cabinet in the current monitoring period, and preset a global safety situation threshold value;

[0034] S52, when the global safety situation evaluation result is less than or equal to the global safety situation threshold value, perform the separation gate operation according to the default operation process; when the global safety situation evaluation result is greater than the global safety situation threshold value, arrange the separation gate orders in descending order according to the operation abnormal risk analysis result of each separation gate in the current monitoring period, take the descendingly arranged separation gate orders as the separation gate priority maintenance sequence, and perform safety maintenance on each separation gate in the high-low voltage power distribution cabinet according to the separation gate priority maintenance sequence.

[0035] In a second aspect, the embodiments of the present application also provide a high-low voltage power distribution cabinet separation gate control system based on the Internet of Things, comprising:

[0036] A data acquisition module is configured to synchronously acquire electrical operation data, environmental state data and separation gate state data of the high-low voltage power distribution cabinet through the Internet of Things sensors deployed in the high-low voltage power distribution cabinet.

[0037] An electrical abnormality monitoring module is configured to analyze the electrical energy receiving and distribution abnormality of the high-low voltage power distribution cabinet in combination with the electrical operation data and the environmental state data of the high-low voltage power distribution cabinet, and analyze the electrical operation abnormality of the high-low voltage power distribution cabinet according to the electrical energy receiving and distribution abnormality analysis result.

[0038] A separation gate abnormality judgment module is configured to analyze the operation abnormal risk of the separation gate in the high-low voltage power distribution cabinet in combination with the separation gate state data and the environmental state data of the high-low voltage power distribution cabinet.

[0039] A global safety detection module is configured to evaluate the global safety situation of the high-low voltage power distribution cabinet based on the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet and the operation abnormal risk analysis result of the separation gate.

[0040] A separation gate control module is configured to execute a differentiated separation gate control scheme based on the global safety situation evaluation result of the high-low voltage power distribution cabinet.

[0041] A control module is configured to control the operation of the data acquisition module, the electrical abnormality monitoring module, the separation gate abnormality judgment module, the global safety detection module and the separation gate control module.

[0042] Compared with the prior art, the present application has the following advantages and beneficial effects:

[0043] 1. The present application realizes accurate perception of the power distribution system operation state by deeply analyzing the electrical energy receiving and distribution abnormality, can early discover potential fault hidden dangers, and improves the operation reliability of the power distribution system.

[0044] 2、The application realizes the leap from single device monitoring to system security situation assessment by quantitatively evaluating the risk of isolation gate operation abnormality, combining the importance of the device and the influence range, and provides a scientific basis for preventive maintenance;

[0045] 3、The application realizes the transition from passive response to active protection by constructing a global security situation assessment system and implementing a differentiated control strategy, significantly improves the safety management and control level of the power distribution system, and effectively prevents the expansion of accidents. BRIEF DESCRIPTION OF DRAWINGS

[0046] Other features, objects and advantages of the application will become more apparent from the following detailed description of non-limiting embodiments made with reference to the accompanying drawings:

[0047] Figure 1 The whole flowchart of the high-low voltage power distribution cabinet isolation gate control method based on the Internet of Things of the application;

[0048] Figure 2 The work flowchart of step S2 in the high-low voltage power distribution cabinet isolation gate control method based on the Internet of Things of the application;

[0049] Figure 3 The work flowchart of step S3 in the high-low voltage power distribution cabinet isolation gate control method based on the Internet of Things of the application;

[0050] Figure 4 The structure schematic diagram of the high-low voltage power distribution cabinet isolation gate control system based on the Internet of Things of the application. DETAILED DESCRIPTION

[0051] The technical scheme of the application will be described in detail below with reference to the drawings and specific embodiments. It should be understood that the embodiments of the application and the specific features in the embodiments are detailed descriptions of the technical scheme of the application, rather than limitations of the technical scheme of the application. In the case of no conflict, the technical features in the embodiments of the application and the embodiments can be combined with each other.

[0052] Embodiment 1

[0053] As shown in the figure, the embodiment provides a high-low voltage power distribution cabinet isolation gate control method based on the Internet of Things, which specifically includes the following steps: Figure 1

[0054] S1, synchronously collecting electrical operation data, environmental state data and isolation gate state data of the high-low voltage power distribution cabinet through the Internet of Things sensor deployed in the high-low voltage power distribution cabinet;

[0055] ​S2, analyze the abnormal situation of the power receiving and distribution of the high-low voltage power distribution cabinet based on the electrical operation data and the environmental state data of the high-low voltage power distribution cabinet; and analyze the electrical operation abnormal situation of the high-low voltage power distribution cabinet according to the analysis result of the power receiving and distribution abnormal situation;

[0056] S3, analyze the operation abnormal risk of the disconnecting switch in the high-low voltage power distribution cabinet based on the disconnecting switch state data and the environmental state data of the high-low voltage power distribution cabinet;

[0057] S4, evaluate the global safety situation of the high-low voltage power distribution cabinet based on the analysis result of the electrical operation abnormal situation and the analysis result of the operation abnormal risk of the disconnecting switch;

[0058] S5, execute the differentiated disconnecting switch control scheme based on the global safety situation evaluation result of the high-low voltage power distribution cabinet.

[0059] In this embodiment, as shown in Figure 2 The step S2 analyzes the abnormal situation of the power receiving and distribution of the high-low voltage power distribution cabinet based on the electrical operation data and the environmental state data of the high-low voltage power distribution cabinet, including the following specific steps:

[0060] S21, extract the electrical operation data and the environmental state data of the high-low voltage power distribution cabinet, wherein the electrical operation data includes the input side electrical operation characteristic parameter sequence and the output side electrical operation characteristic parameter sequence; the environmental state data includes the environmental state monitoring parameter sequence; wherein the input side electrical operation characteristic parameter sequence includes but is not limited to the input side voltage, the input side current, the input active power, and the input reactive power, which are used to reflect the operation state of the power receiving link. The output side electrical operation characteristic parameter sequence includes but is not limited to the output side voltage, the output side current, the load power, and the power factor, which are used to reflect the operation state of the power distribution link. The environmental state monitoring parameter sequence includes but is not limited to the cabinet temperature, the cabinet humidity, and the cabinet vibration amplitude.

[0061] S22, based on the long short-term memory network autoencoder model, the input side electrical operation characteristic parameter sequence and the environment state monitoring parameter sequence in the current monitoring period are taken as input side original sequence and introduced into the electric energy receiving abnormality detection model, the input side electrical operation characteristic parameter sequence and the environment state monitoring parameter sequence are reconstructed, and the input side reconstructed sequence containing the input side electrical operation characteristic parameter reconstructed sequence and the environment state monitoring parameter reconstructed sequence is obtained; it should be noted that the electric energy receiving abnormality detection model needs to be constructed first in the embodiment, the model adopts the long short-term memory network autoencoder structure and is composed of an encoder and a decoder. The encoder part is stacked by multiple LSTM units, which is used to learn the time dependence characteristics of the input data and compress the high-dimensional input sequence into a low-dimensional latent space representation. The decoder part is also composed of LSTM units, which is responsible for reconstructing the output sequence with the same dimension as the original input sequence from the latent space representation. The training process of the model uses the data under the normal state as the training set, optimizes the model parameters by minimizing the reconstruction error, and makes the model learn the data distribution pattern under the normal state. The input side electrical operation characteristic parameter sequence and the environment state monitoring parameter sequence collected in the current monitoring period are input into the trained model, and the corresponding reconstructed sequence is output. The embodiment captures the normal operation mode of the electric energy receiving link through the deep learning model, provides a reference for subsequent abnormality detection, can automatically learn complex time sequence characteristics, does not need to define abnormal rules manually, has strong adaptability, and also has certain detection ability for unknown types of abnormalities.

[0062] S23, the input side reconstruction error between the input side reconstructed sequence and the input side original sequence is calculated, a preset input side error threshold value is taken, and the ratio of the input side reconstruction error to the input side error threshold value is taken as the electric energy receiving abnormality state in the current monitoring period. In the embodiment, the reconstruction error is calculated by the mean square error method, the difference between the original value and the reconstructed value is calculated for each time step and each feature dimension of the input side electrical operation characteristic parameter sequence and the environment state monitoring parameter sequence, then the errors of all time steps and feature dimensions are averaged, and the comprehensive reconstruction error value is taken as the input side reconstruction error. The setting of the input side error threshold value is based on the statistical distribution of the historical normal data reconstruction error, and the 95% quantile of the historical normal data input side reconstruction error is taken as the input side error threshold value in the embodiment. Further, the error threshold value can be updated periodically in the embodiment, and a sliding window is used to recalculate the threshold value using the historical data in the recent period. The ratio obtained by comparing the real-time calculated reconstruction error with the threshold value directly reflects the abnormality degree of the electric energy receiving link, and when the ratio is greater than 1, it indicates that there is an abnormality, and the greater the ratio, the more serious the abnormality.

[0063] In this embodiment, the electrical operation abnormality of the high-low voltage power distribution cabinet is analyzed according to the analysis result of the power receiving and distribution abnormality in step S2, and the following specific contents are further included:

[0064] S24, based on the long short-term memory network autoencoder model, the output side electrical operation feature parameter sequence and the environment state monitoring parameter sequence in the current monitoring period are introduced into the power distribution abnormality detection model as the output side original sequence, and the output side electrical operation feature parameter sequence and the environment state monitoring parameter sequence are reconstructed to obtain the output side reconstruction sequence including the output side electrical operation feature parameter reconstruction sequence and the environment state monitoring parameter reconstruction sequence; in this embodiment, the construction process of the power distribution abnormality detection model is similar to that of the power receiving abnormality detection model, but the training data uses the output side electrical operation feature parameter sequence and the environment state monitoring parameter sequence in the historical normal state. The model structure also adopts the encoder-decoder architecture, and the encoder is composed of multiple layers of LSTM units, which is used to extract the time features of the output side data and encode the sequence into a latent space representation. The decoder reconstructs the output side data sequence according to the latent space representation. In the model training process, the model parameters are optimized through the back propagation algorithm, so that the model can accurately reconstruct the output side data sequence in the normal state. The real-time collected output side electrical operation feature parameter sequence and environment state monitoring parameter sequence are input into the model to obtain the corresponding reconstruction sequence. This embodiment establishes a normal operation benchmark for the power distribution link, and identifies the abnormality of the distribution link by comparing the differences between real-time data and reconstruction data. It can consider the comprehensive influence of electrical parameters and environmental parameters, capture complex nonlinear relationships, and has high sensitivity in detecting load abnormalities and uneven distribution problems.

[0065] S25, the output side reconstruction error between the output side reconstruction sequence and the output side original sequence is calculated, a preset output side error threshold is set, and the ratio of the output side reconstruction error to the output side error threshold is taken as the power distribution abnormality state in the current monitoring period; in this embodiment, the calculation of the output side reconstruction error and the output side error threshold is the same as the calculation method of the input side reconstruction error and the input side error threshold, and will not be repeated here.

[0066] S26, the power receiving abnormality state and the power distribution abnormality state in the current monitoring period are weighted and summed to obtain the electrical operation abnormality of the high-low voltage power distribution cabinet in the current monitoring period. In this embodiment, the weight setting is calculated based on the entropy weight method, and the electrical operation abnormality reflects the abnormality degree of the overall electrical operation state of the power distribution cabinet.

[0067] In this embodiment, as shown in Figure 3 , in step S3, the operation abnormality risk of the disconnecting switch in the high-low voltage power distribution cabinet is analyzed in combination with the disconnecting switch state data and the environment state data of the high-low voltage power distribution cabinet, including the following specific steps:

[0068] S31, obtain the separation gate state data and the environment state data in the high-low voltage power distribution cabinet, take the separation gate cumulative operation times, the average time length of the last three operations, and the motor drive current peak value in the separation gate state data as a separation gate state feature vector set, take the cabinet temperature, the cabinet humidity, and the cabinet body vibration amplitude in the environment state data as an environment state feature vector set, take the separation gate state feature vector set and the environment state feature vector set as an anomaly detection data set, and divide the anomaly detection data set into an anomaly detection training set and an anomaly detection verification set; in this embodiment, when the separation gate operation anomaly detection model is constructed, the separation gate state feature vector set (including the separation gate cumulative operation times, the average time length of the last three operations, and the motor drive current peak value) and the environment state feature vector set (including the cabinet temperature, the cabinet humidity, and the cabinet body vibration amplitude) need to be standardized. First, all feature data in the historical normal operation period is collected, and the mean and standard deviation of each feature are calculated. Since these features have different dimensions and value ranges, for example, the operation times may reach thousands of times, the temperature value is usually in the range of dozens of degrees, the drive current may be dozens of amperes, and the vibration amplitude may be only a few millimeters, therefore, the Z-score standardization method is adopted to convert the data of each feature dimension to a standard normal distribution with a mean of 0 and a standard deviation of 1, so as to realize the standardization processing of the original data. It is ensured that the support vector data description model can correctly calculate the distance between samples in a high-dimensional feature space, avoids the problem that some features are dominant in distance calculation due to large values, and improves the accuracy of anomaly detection.

[0069] S32, construct a support vector data description model, take the separation gate cumulative operation times, the average time length of the last three operations, the motor drive current peak value, the cabinet temperature, the cabinet humidity, and the cabinet body vibration amplitude in the anomaly detection training set as the input features of the support vector data description model, map the input features to a high-dimensional feature space through a kernel function, find a smallest hyper-sphere containing the most normal samples in the high-dimensional feature space, train the support vector data description model, and obtain an initial anomaly detection model; the support vector data description model in this embodiment is a single classification algorithm, which is suitable for anomaly detection scenarios where only normal samples are available. In the model construction process of this embodiment, a Gaussian kernel function is selected as the kernel function of the model. Further, the model training in this embodiment is realized by solving a quadratic programming problem, the training target of which is to find a hyper-sphere with the smallest volume, so that as many normal samples as possible are contained in the hyper-sphere, and the center point and radius of the hyper-sphere are obtained, and the support vectors are determined. This embodiment establishes a benchmark model of the normal operation state of the separation gate, provides a judgment basis for subsequent anomaly risk identification, and can process complex data distribution that is not linearly separable through the kernel function skill.

[0070] S33, model verification is performed on the initial anomaly detection model by using the anomaly detection verification set, and an initial anomaly detection model with a model accuracy greater than or equal to a preset model accuracy is output as a disconnecting switch operation anomaly detection model.

[0071] In this embodiment, the operating abnormality risk of the disconnecting switch in the high-low voltage power distribution cabinet is analyzed in combination with the disconnecting switch state data and the environmental state data of the high-low voltage power distribution cabinet, and the following specific contents are further included:

[0072] The disconnecting switch state feature vector set and the environmental state feature vector set in the current monitoring period are obtained, the average distance of all vectors in the disconnecting switch state feature vector set and the environmental state feature vector set in the current monitoring period to the center of the disconnecting switch operation anomaly detection model hypersphere is calculated based on the disconnecting switch operation anomaly detection model, the radius of the disconnecting switch operation anomaly detection model hypersphere is extracted, and the ratio of the average distance to the radius of the disconnecting switch operation anomaly detection model hypersphere is taken as the operating abnormality risk of the disconnecting switch in the high-low voltage power distribution cabinet in the current monitoring period. In this embodiment, the feature vectors collected in the current monitoring period are standardized, the same standardization parameters as in the training stage are used, and the consistency of the data distribution is ensured when calculating the operating abnormality risk. The distance of each feature vector to the center of the hypersphere is calculated, and the distance calculation formula depends on the type of the kernel function used. In this embodiment, the Gaussian kernel function is used as the kernel function of the model, so the Euclidean distance calculation formula is used for distance calculation. The average distance of all feature vectors is taken to obtain the average deviation degree of the current state from the normal state benchmark. Comparing the average distance with the radius of the hypersphere directly reflects the risk level of the operating abnormality. When the ratio is less than or equal to 1, it indicates that the current state is within the normal range; when the ratio is greater than 1, it indicates that there is an abnormal risk, and the greater the ratio, the higher the risk. In this embodiment, the abstract model output is converted into a direct risk indicator, which provides a quantitative basis for operation and maintenance decision-making. The risk degree is continuously quantified through the distance ratio, which can not only determine whether there is an abnormality, but also evaluate the severity of the abnormality, so as to facilitate the sorting and comparison of the risk states of different disconnecting switches.

[0073] In this embodiment, the global safety situation of the high-low voltage power distribution cabinet is evaluated based on the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet and the operating abnormality risk analysis result of the disconnecting switch in step S4, including the following specific steps:

[0074] S41, the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet in the current monitoring period and the operating abnormality risk analysis result of each disconnecting switch in the high-low voltage power distribution cabinet in the current monitoring period are obtained; and the number of all load devices downstream of each disconnecting switch in the high-low voltage power distribution cabinet is obtained;

[0075] S42, sum all the numbers of load devices downstream of all the separation gates, and take the ratio of the number of load devices downstream of each separation gate to the sum as the operation abnormal risk weight of each separation gate; specifically, the sum of the numbers of load devices downstream of all the separation gates is calculated to reflect the total load size in the power supply range of the power distribution system; for each separation gate, the ratio of the number of load devices downstream of the separation gate to the sum is calculated to represent the relative importance of the separation gate in the power supply range. This embodiment links the operation abnormal risk of the separation gate to its impact range, so that the separation gate with a large impact range obtains a higher weight in the comprehensive evaluation, ensuring the rationality and practicality of the safety situation assessment result.

[0076] S43, multiply the operation abnormal risk analysis result of each separation gate in the current monitoring period by the corresponding operation abnormal risk weight to obtain the global operation abnormal risk component of each separation gate in the current monitoring period; sum the global operation abnormal risk components of all separation gates in the current monitoring period to obtain the global operation abnormal risk of the separation gate of the high-low voltage power distribution cabinet in the current monitoring period; specifically, the operation abnormal risk analysis result reflects the probability of abnormality, and the operation abnormal risk weight reflects the severity of the abnormality. The risk component obtained by multiplying the two comprehensively reflects the risk contribution of each separation gate in the global safety. Summing the risk components of all separation gates obtains the overall global operation abnormal risk of the separation gate, which can reflect the comprehensive operation risk level of all separation gates of the power distribution cabinet. This embodiment aggregates the dispersed single separation gate risk indicators into a unified overall risk, highlights the risk contribution of the high-impact-range separation gate through weighted aggregation, and makes the risk assessment result more in line with the actual safety demand.

[0077] S44, weighted sum the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet in the current monitoring period and the global operation abnormal risk of the separation gate to obtain the global safety situation assessment result of the high-low voltage power distribution cabinet in the current monitoring period, wherein the weight setting is based on historical data analysis; in this embodiment, different types of safety risks are integrated into a unified situation assessment result, which provides a direct basis for the development of differentiated control strategies, balances the influence of different types of risks through reasonable weight allocation, and ensures the comprehensiveness and accuracy of the safety situation assessment.

[0078] In this embodiment, based on the global safety situation assessment result of the high-low voltage power distribution cabinet, a differentiated separation gate control scheme is executed in step S5, including the following specific steps:

[0079] S51, obtain the global safety situation assessment result of the high-low voltage power distribution cabinet in the current monitoring period, and preset a global safety situation threshold; wherein the setting of the global safety situation threshold is based on historical operation data analysis and safety specification requirements;

[0080] S52, when the global security situation assessment result is less than or equal to the global security situation threshold, the separation gate operation is carried out according to the default operation process; when the global security situation assessment result is greater than the global security situation threshold, the separation gate order is arranged in descending order according to the operation abnormal risk analysis result of each separation gate in the current monitoring period, and the descendingly arranged separation gate order is taken as the separation gate priority maintenance sequence, and the safety maintenance is carried out on each separation gate in the high-low voltage power distribution cabinet according to the separation gate priority maintenance sequence. Specifically, in the safe state, the separation gate operation is carried out according to the normal operation rules, and no special control measures are needed. When the security situation deteriorates beyond the threshold, the differentiated control strategy is started, the separation gates are sorted according to the operation abnormal risk first, and the separation gates with high risk are arranged in the priority maintenance position. Then, the maintenance work is arranged according to this priority sequence, and the separation gate with the highest risk is processed first. The maintenance measures include but are not limited to strengthening monitoring, limiting operation, planned maintenance, and taking corresponding control intensity according to the risk degree. The embodiment realizes the optimization of safety resources, preferentially uses the limited maintenance resources for the equipment with the highest risk, and improves the efficiency and effect of safety management. The advantage is that through the risk sorting and priority processing mechanism, the key risks are ensured to be controlled in time, and the blindness and randomness of safety management are avoided.

[0081] Embodiment 2

[0082] As shown in Figure 4 , the embodiment provides a high-low voltage power distribution cabinet separation gate control system based on Internet of Things, which comprises:

[0083] A data acquisition module is configured to synchronously acquire electrical operation data, environmental state data and separation gate state data of the high-low voltage power distribution cabinet through the Internet of Things sensors deployed in the high-low voltage power distribution cabinet.

[0084] An electrical abnormality monitoring module is configured to analyze the electrical energy receiving and distribution abnormality of the high-low voltage power distribution cabinet in combination with the electrical operation data and the environmental state data of the high-low voltage power distribution cabinet, and analyze the electrical operation abnormality of the high-low voltage power distribution cabinet according to the electrical energy receiving and distribution abnormality analysis result.

[0085] A separation gate abnormality judgment module is configured to analyze the operation abnormal risk of the separation gate in the high-low voltage power distribution cabinet in combination with the separation gate state data and the environmental state data of the high-low voltage power distribution cabinet.

[0086] A global security detection module is configured to evaluate the global security situation of the high-low voltage power distribution cabinet based on the electrical operation abnormality analysis result of the high-low voltage power distribution cabinet and the operation abnormal risk analysis result of the separation gate.

[0087] The isolation gate control module is used for executing a differentiated isolation gate control scheme based on the global safety situation evaluation result of the high-low voltage power distribution cabinet.

[0088] The control module is used for controlling the operation of the data acquisition module, the electrical abnormality monitoring module, the isolation gate abnormality judgment module, the global safety detection module and the isolation gate control module.

[0089] The steps of implementing the corresponding functions of the parameters and the unit modules in the high-low voltage power distribution cabinet isolation gate control system based on the Internet of Things according to the present application can refer to the parameters and steps in the embodiments of the high-low voltage power distribution cabinet isolation gate control method based on the Internet of Things, which will not be repeated here.

[0090] Each embodiment in the present application is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other. Each embodiment mainly describes the differences from other embodiments. In particular, the Internet of Things device and medium embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can refer to the part of the method embodiments.

[0091] The system and medium provided by the embodiments of the present application are one-to-one corresponding with the method, so the system and medium also have similar beneficial technical effects as the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0092] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer usable program code.

[0093] The present application is described with reference to flowcharts and / or block diagrams according to the method, device (system), and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks Figure 1 one flow or multiple flows and / or blocks

[0094] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The flow diagram(s) depict the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments. In this regard, each flow diagram can represent a method or portion of a method according to an embodiment. Each block of the flow diagram(s) can represent a computer- executable procedure, a logical component, a process, and / or a portion of a process that can be implemented in hardware, software, and / or firmware. Each block can also represent a flow of data between other blocks of the flow diagram(s). The flow diagrams can also represent a flow of control from one block to another block of the flow diagram(s). The flow diagrams can further represent a flow of data between other devices or components of an embodiment. Figure 1 The flow diagram(s) depict the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments. In this regard, each flow diagram can represent a method or portion of a method according to an embodiment. Each block of the flow diagram(s) can represent a computer- executable procedure, a logical component, a process, and / or a portion of a process that can be implemented in hardware, software, and / or firmware. Each block can also represent a flow of data between other blocks of the flow diagram(s). The flow diagrams can also represent a flow of control from one block to another block of the flow diagram(s). The flow diagrams can further represent a flow of data between other devices or components of an embodiment.

[0095] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0096] The memory can include non-persistent memory and / or persistent memory, such as flash memory, read-only memory (ROM), and / or volatile or non-volatile random access memory (RAM), among others. The memory is an example of computer-readable media.

[0097] Computer-readable media includes permanent and non-permanent, removable and non-removable media, which can be implemented by any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible to a computing device. According to the definition herein, computer-readable media does not include transitory media, such as modulated data signals and carrier waves.

[0098] It should also be noted that the terms "comprising", "including", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article or apparatus that includes a list of elements does not include only those elements recited, but can also include other elements not expressly listed or inherent to such process, method, article or apparatus. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article or apparatus that includes the element.

[0099] The above merely illustrates the embodiments of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. within the spirit and principles of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for controlling the disconnection of high and low voltage distribution cabinets based on the Internet of Things, characterized in that, Includes the following steps: S1. Through IoT sensors deployed in high and low voltage distribution cabinets, electrical operation data, environmental status data, and disconnection switch status data of high and low voltage distribution cabinets are collected synchronously. S2. Based on the electrical operation data and environmental status data of the high and low voltage distribution cabinets, analyze the abnormal situations of power reception and distribution of the high and low voltage distribution cabinets; and based on the analysis results of the abnormal situations of power reception and distribution, analyze the abnormal electrical operation situations of the high and low voltage distribution cabinets. S3. Based on the disconnector status data and environmental status data of high and low voltage distribution cabinets, analyze the operational abnormality risk of disconnectors in high and low voltage distribution cabinets; S4. Based on the analysis results of abnormal electrical operation of high and low voltage switchgear and the analysis results of abnormal operation risk of disconnecting switch, assess the overall safety status of high and low voltage switchgear. S5. Based on the overall security situation assessment results of high and low voltage distribution cabinets, implement a differentiated disconnection control scheme; Step S2 combines the electrical operation data and environmental status data of the high and low voltage distribution cabinets to analyze abnormal situations in the power reception and distribution of the high and low voltage distribution cabinets, including the following specific steps: S21. Extract electrical operation data and environmental status data from high and low voltage switchgear. The electrical operation data includes the input-side electrical operation characteristic parameter sequence and the output-side electrical operation characteristic parameter sequence; the environmental status data includes the environmental status monitoring parameter sequence. S22. Based on the long short-term memory network autoencoder model, the input side electrical operation characteristic parameter sequence and environmental status monitoring parameter sequence within the current monitoring period are used as the input side original sequence and imported into the power receiving anomaly detection model. The input side electrical operation characteristic parameter sequence and environmental status monitoring parameter sequence are reconstructed to obtain the input side reconstructed sequence containing the input side electrical operation characteristic parameter reconstructed sequence and the environmental status monitoring parameter reconstructed sequence. S23. Calculate the input-side reconstruction error between the input-side reconstructed sequence and the input-side original sequence, preset the input-side error threshold, and use the ratio of the input-side reconstruction error to the input-side error threshold as the abnormal state of power reception in the current monitoring period. Step S2 analyzes the abnormal electrical operation of the high and low voltage distribution cabinets based on the analysis results of abnormal power reception and distribution, and includes the following specific content: S24. Based on the long short-term memory network autoencoder model, the output side electrical operation characteristic parameter sequence and environmental status monitoring parameter sequence within the current monitoring period are imported into the power distribution anomaly detection model as the original output side sequence. The output side electrical operation characteristic parameter sequence and environmental status monitoring parameter sequence are reconstructed to obtain the output side reconstructed sequence containing the output side electrical operation characteristic parameter reconstructed sequence and the environmental status monitoring parameter reconstructed sequence. S25. Calculate the output-side reconstruction error between the output-side reconstructed sequence and the output-side original sequence, preset the output-side error threshold, and use the ratio of the output-side reconstruction error to the output-side error threshold as the abnormal state of power distribution in the current monitoring cycle. S26. Weighted summation of abnormal power reception and abnormal power distribution states within the current monitoring period to obtain the abnormal electrical operation status of the high and low voltage distribution cabinets within the current monitoring period.

2. The IoT-based high and low voltage distribution cabinet disconnection control method according to claim 1, characterized in that, In step S3, the operational risks of the disconnectors in the high and low voltage distribution cabinets are analyzed by combining the disconnector status data and environmental status data. This includes the following specific steps: S31. Obtain the status data of the disconnect switch and the environmental status data in the high and low voltage distribution cabinet. Take the cumulative number of disconnect switch operations, the average duration of the last three operations, and the peak value of the motor drive current in the disconnect switch status data as the disconnect switch status feature vector set. Take the cabinet temperature, cabinet humidity, and cabinet vibration amplitude in the environmental status data as the environmental status feature vector set. Take the disconnect switch status feature vector set and the environmental status feature vector set as the anomaly detection dataset. Divide the anomaly detection dataset into an anomaly detection training set and an anomaly detection verification set. S32. Construct a support vector data description model. Take the cumulative number of opening gate operations, the average duration of the last three operations, the peak value of the motor drive current, the temperature inside the cabinet, the humidity inside the cabinet, and the vibration amplitude of the cabinet in the anomaly detection training set as input features of the support vector data description model. Map the input features to a high-dimensional feature space through a kernel function. Find the smallest hypersphere containing the most normal samples in the high-dimensional feature space. Train the support vector data description model to obtain the initial anomaly detection model. S33. The initial anomaly detection model is validated using the anomaly detection validation set, and the initial anomaly detection model with an accuracy greater than or equal to the preset model is used as the anomaly detection model for the separation gate operation.

3. The IoT-based high and low voltage distribution cabinet disconnection control method according to claim 2, characterized in that, The analysis of operational anomalies of the disconnectors in high and low voltage distribution cabinets, combining disconnector status data and environmental status data, also includes the following specific content: Obtain the set of feature vectors for the disconnect gate status and the set of feature vectors for the environmental status within the current monitoring period; Based on the switchgear operation anomaly detection model, the average distance from all vectors in the switchgear state feature vector set and the environmental state feature vector set to the center of the switchgear operation anomaly detection model hypersphere is calculated in the current monitoring period. The radius of the switchgear operation anomaly detection model hypersphere is extracted, and the ratio of the average distance to the radius of the switchgear operation anomaly detection model hypersphere is taken as the risk of switchgear operation anomaly in high and low voltage distribution cabinets in the current monitoring period.

4. The IoT-based high and low voltage distribution cabinet disconnection control method according to claim 3, characterized in that, Step S4, based on the analysis results of abnormal electrical operation of the high and low voltage switchgear and the analysis results of abnormal operation risks of the disconnector, assesses the overall safety status of the high and low voltage switchgear, including the following specific steps: S41. Obtain the analysis results of electrical operation anomalies of high and low voltage distribution cabinets during the current monitoring period, as well as the analysis results of operational anomalies of each disconnector in the high and low voltage distribution cabinets during the current monitoring period; at the same time, obtain the number of all load devices downstream of each disconnector in the high and low voltage distribution cabinets. S42. Sum the number of all load devices downstream of all separation gates, and use the ratio of the number of all load devices downstream of each separation gate to the summation result as the operational anomaly risk weight of each separation gate. S43. Multiply the operational anomaly risk analysis results of each disconnector in the current monitoring period with the corresponding operational anomaly risk weight to obtain the overall operational anomaly risk component of each disconnector in the current monitoring period. The total operational anomaly risk of all disconnectors in the current monitoring period is obtained by summing the components of the overall operational anomaly risk of the high and low voltage switchgear in the current monitoring period. S44. The analysis results of electrical operation anomalies of high and low voltage switchgear during the current monitoring period and the risk of operation anomalies of the disconnect switch across the entire area are weighted and summed to obtain the overall safety status assessment results of high and low voltage switchgear during the current monitoring period.

5. The IoT-based high and low voltage distribution cabinet disconnection control method according to claim 4, characterized in that, Step S5, based on the overall security situation assessment results of the high and low voltage distribution cabinets, implements a differentiated disconnection control scheme, including the following specific steps: S51. Obtain the overall security status assessment results of high and low voltage distribution cabinets within the current monitoring period, and preset the overall security status threshold. S52. When the overall security situation assessment result is less than or equal to the overall security situation threshold, the disconnection switch operation is performed according to the default operation procedure; when the overall security situation assessment result is greater than the overall security situation threshold, the disconnection switches are arranged in descending order according to the operational anomaly risk analysis results of each disconnection switch in the current monitoring period, and the order of each disconnection switch after descending order is used as the priority maintenance sequence of the disconnection switches. Safety maintenance is performed on each disconnection switch in the high and low voltage distribution cabinet according to the priority maintenance sequence of the disconnection switches.

6. A high- and low-voltage distribution cabinet disconnection control system based on the Internet of Things, implemented based on any one of claims 1-5, characterized in that, The system includes: The data acquisition module is used to synchronously collect electrical operation data, environmental status data, and disconnection switch status data of high and low voltage switchgear through IoT sensors deployed in the switchgear. The electrical anomaly monitoring module is used to analyze abnormal situations in the power reception and distribution of high and low voltage distribution cabinets by combining electrical operation data and environmental status data; and to analyze abnormal electrical operation situations of high and low voltage distribution cabinets based on the analysis results of abnormal power reception and distribution. The disconnect switch anomaly judgment module is used to analyze the operational anomaly risk of the disconnect switch in the high and low voltage distribution cabinet by combining the disconnect switch status data and environmental status data. The overall safety monitoring module is used to assess the overall safety status of high and low voltage switchgear based on the analysis results of abnormal electrical operation of high and low voltage switchgear and the analysis results of abnormal operation risks of disconnectors. The disconnection switch control module is used to execute differentiated disconnection switch control schemes based on the overall security situation assessment results of high and low voltage distribution cabinets. The control module is used to control the operation of the data acquisition module, the electrical anomaly monitoring module, the disconnector anomaly judgment module, the global safety detection module, and the disconnector control module.

Images