Remote maintenance system of intelligent power distribution cabinet

Abstract

The invention relates to the technical field of remote maintenance of a power distribution cabinet, in particular to a remote maintenance system of an intelligent power distribution cabinet, which constructs a component operation parameter matrix by collecting current, voltage, component temperature, starting time and internal and external environment data of the power distribution cabinet in real time, and combines environment parameters of the power distribution cabinet to maintain the power distribution cabinet. And carrying out deep learning training by using a residual neural network algorithm. The method not only can detect common fault modes, but also can identify abnormal conditions caused by component aging, so that the problems of false alarm and missing alarm in a traditional fault detection method are solved. Through the residual neural network, the system can automatically learn normal and abnormal operation modes from historical data, and the accuracy of fault detection is improved. And the exception type is further pushed to the operation and maintenance personnel and is visually displayed, so that the judgment time and the round-trip times of the operation and maintenance personnel on the maintenance component are saved, and the maintenance efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of remote maintenance of power distribution cabinets, and in particular to a remote maintenance system of an intelligent power distribution cabinet. Background Art

[0002] As a vital equipment in the power system, the power distribution cabinet undertakes multiple functions such as power distribution, control, and protection. With the continuous increase in power demand, traditional power distribution cabinet equipment is increasingly difficult to meet the requirements of efficient, stable, and safe operation. Traditional power distribution cabinets usually rely on manual inspections, regular maintenance, and manual recording of equipment operation status, which is not only inefficient, but also prone to problems such as missed detection and false detection, which in turn leads to equipment failure or power outage accidents, affecting the safety and reliability of power supply.

[0003] The fault detection method in the existing distribution cabinet monitoring system relies on simple threshold judgments and fails to fully utilize advanced artificial intelligence technology to conduct in-depth analysis of equipment status. Especially in large distribution cabinet environments, simple rules cannot effectively deal with various potential abnormal patterns, often resulting in high false alarm rates or missed alarms. In addition, when the staff of the existing distribution cabinet monitoring system do not arrive at the abnormal distribution cabinet, they cannot intuitively discover the problems in the distribution cabinet and determine the component models that need to be replaced or repaired, which leads to an increase in the number of round trips and reduces maintenance efficiency. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a remote maintenance system for an intelligent distribution cabinet, which performs residual neural network learning and judgment based on operating parameters and environmental parameters of the distribution cabinet, and re-updates the component management module through maintenance records to adjust the operating parameters, thereby effectively improving the accuracy of abnormal mode judgment and improving maintenance efficiency by visualizing abnormal modes.

[0005] To achieve the above object, the technical solution adopted by the present invention is: A remote maintenance system for an intelligent power distribution cabinet comprises a component management module, an abnormality monitoring module, a model building module and a remote maintenance module connected in sequence, and also comprises an in-cabinet environment monitoring module, wherein the in-cabinet environment monitoring module is connected to the abnormality monitoring module, and the remote maintenance module is connected to the component management module; The component management module is used to update and record component attribute parameters and component operation parameters in the power distribution cabinet in real time, and the component operation parameters include current and voltage, component temperature and component activation time; The cabinet environment monitoring module is used to obtain the environmental parameters of the power distribution cabinet in real time, including the cabinet environment humidity and the cabinet external environment temperature and humidity; The abnormal monitoring module is used to construct an operating parameter matrix on a time series based on the component operating parameters in the power distribution cabinet, perform residual neural network training based on the operating parameter matrix and the power distribution cabinet environmental parameters, and perform abnormal judgment on the real-time component operating parameters through the trained residual neural network to generate a real-time judgment result; The model building module is used to build a three-dimensional framework of the power distribution cabinet, and the three-dimensional framework of the power distribution cabinet is combined according to the component category, component model and component connection relationship matching preset component library to obtain a real-time three-dimensional model of the power distribution cabinet; the model building module is also used to synchronously map the three-dimensional model of the power distribution cabinet based on the environmental parameters of the power distribution cabinet and the real-time judgment results; The remote maintenance module is used to receive the three-dimensional model of the power distribution cabinet from the model building module and visualize it, and is also used to receive maintenance record information to update the component management module.

[0006] Furthermore, the component attribute parameters include component category, component model and component connection relationship.

[0007] Furthermore, the operating parameter matrix includes a current and voltage matrix, a component temperature matrix, and a component activation time matrix.

[0008] Furthermore, constructing an operating parameter matrix on a time series based on the operating parameters of components in the power distribution cabinet comprises the following steps: Obtaining component operation parameters from the component management module; Presetting the filling area for the current voltage matrix, the component temperature matrix and the component activation time matrix based on the component connection relationship; Remove outliers and noise from component operating parameters and perform standardization to obtain standardized values; The standardized values ​​are correspondingly filled in the value filling areas of the current and voltage matrix, the component temperature matrix, and the component activation time matrix.

[0009] Furthermore, the residual neural network training based on the operating parameter matrix and the distribution cabinet environmental parameters includes the following steps: Construct a training data set by obtaining the operating parameter matrix and the distribution cabinet environmental parameters; Construct a residual neural network model, take the training data set as input, extract features of the training data through the convolution layer, and obtain a multi-dimensional feature map; The multi-dimensional feature map is input into the residual module, and the high-dimensional features are extracted through the residual connection mechanism; The extracted high-dimensional features are input into the fully connected layer, and the judgment results are output through the activation function.

[0010] Furthermore, the determination result includes whether the power distribution cabinet is normal, whether the power distribution cabinet is abnormal, and whether the component is abnormal.

[0011] Furthermore, the calculation formula of the residual neural network model is as follows: ; in, is the prediction result of the distribution cabinet at time t; is the input feature at time t, including the operating parameter matrix and the distribution cabinet environmental parameters; For the The convolution kernel parameters of the layer; is the bias term; is the convolution kernel weight matrix of the output layer; is the bias term of the output layer; is the activation function; is the residual neural network The output of the layer at the previous moment; is the number of network layers.

[0012] Furthermore, the loss function of the residual neural network model is as follows: ; in, is the total loss function; is the real judgment result of the distribution cabinet at time t; is the prediction result of the distribution cabinet at time t; is the mean square error between the predicted value and the true value; For the The convolution kernel parameters of the layer; is the regularization coefficient; is the number of samples in the training data set; is the number of network layers.

[0013] Furthermore, the remote maintenance module includes a cloud end and a maintenance personnel end; The remote maintenance module is used to receive a plurality of three-dimensional models of power distribution cabinets and send the three-dimensional models of the power distribution cabinets to the maintenance personnel according to the abnormality determination results, and is also used to receive the maintenance record information uploaded by the personnel and synchronously update it to the component management module; The maintenance personnel end is used to receive the three-dimensional model of the distribution cabinet and perform AR visualization, and is also used to receive maintenance record information and upload it to the remote maintenance module in a standardized manner.

[0014] The beneficial effect of the present invention is that the present invention collects the current and voltage, component temperature, component activation time and internal and external environmental data of the distribution cabinet in real time. Compared with the traditional manual inspection and regular maintenance, the system can monitor the working status of the distribution cabinet at any time, avoid the missed detection and false detection of manual inspection, and ensure the timeliness and accuracy of equipment operation. By introducing the residual neural network algorithm, by constructing the component operation parameter matrix and combining the distribution cabinet environmental parameters for deep learning training, not only daily faults are considered, but also the aging problem caused by long-term use of components is considered, which effectively solves the problem of low accuracy and serious false alarms and missed reports of traditional fault detection methods based on threshold judgment. The residual neural network can automatically learn the normal mode and abnormal mode of equipment operation from a large amount of historical data. When encountering complex faults or abnormal situations, it can accurately identify and timely warn, reduce the false alarm rate and missed report rate, obtain the maintenance record data and re-update it to the component management module, realize the recalculation of component usage time, and further improve the accuracy and synchronization of model judgment. Through intelligent analysis of the abnormal monitoring module, this solution can not only detect potential faults in the distribution cabinet, but also push warning information to operation and maintenance personnel according to the fault type and display it visually, saving the operation and maintenance personnel's judgment time and number of round trips for maintenance components, and improving maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a structural schematic diagram of a remote maintenance system for an intelligent power distribution cabinet in the present invention.

[0016] Figure 2 It is a flowchart of the steps of residual neural network training based on the operating parameter matrix and the distribution cabinet environmental parameters in the present invention. DETAILED DESCRIPTION

[0017] See also Figure 1-2 As shown, the present invention relates to a remote maintenance system for an intelligent power distribution cabinet, comprising a component management module, an abnormality monitoring module, a model building module and a remote maintenance module connected in sequence, and also comprising an in-cabinet environment monitoring module, wherein the in-cabinet environment monitoring module is connected to the abnormality monitoring module, and the remote maintenance module is connected to the component management module; The component management module is used to update and record component attribute parameters and component operation parameters in the power distribution cabinet in real time, and the component operation parameters include current and voltage, component temperature and component activation time; The cabinet environment monitoring module is used to obtain the environmental parameters of the power distribution cabinet in real time, including the cabinet environment humidity and the cabinet external environment temperature and humidity; The abnormal monitoring module is used to construct an operating parameter matrix on a time series based on the component operating parameters in the power distribution cabinet, perform residual neural network training based on the operating parameter matrix and the power distribution cabinet environmental parameters, and perform abnormal judgment on the real-time component operating parameters through the trained residual neural network to generate a real-time judgment result; The model building module is used to build a three-dimensional framework of the power distribution cabinet, and the three-dimensional framework of the power distribution cabinet is combined according to the component category, component model and component connection relationship matching preset component library to obtain a real-time three-dimensional model of the power distribution cabinet; the model building module is also used to synchronously map the three-dimensional model of the power distribution cabinet based on the environmental parameters of the power distribution cabinet and the real-time judgment results; The remote maintenance module is used to receive the three-dimensional model of the power distribution cabinet from the model building module and visualize it, and is also used to receive maintenance record information to update the component management module.

[0018] In some embodiments, the core hardware components of the system include a component management module, an abnormality monitoring module, a model building module, a remote maintenance module, and an in-cabinet environment monitoring module. First, the component management module is responsible for real-time acquisition and recording of the operating parameters inside the power distribution cabinet. The components may include circuit breakers, switches, contactors, disconnectors, transformers, relays, and cables. The module is equipped with high-precision current and voltage sensors and infrared temperature sensors, which can monitor the operating status of each component in the power distribution cabinet in real time. The data collected by the sensor includes the current, voltage, and temperature parameters of each electrical component. The monitoring component activation time is inserted through the interface, and these data are transmitted to the central processing unit of the system in real time via a wired or wireless network. The central processing unit updates the attribute parameters and operating status of each component in the power distribution cabinet in real time based on these data.

[0019] Furthermore, the component attribute parameters include component category, component model and component connection relationship.

[0020] Specifically, the component category is the type of component in the power distribution cabinet, such as circuit breakers, switches, contactors, disconnectors, transformers, protection devices, relays, etc. This parameter can help the system identify the functions and working principles of each component, and provide basic information for subsequent fault diagnosis and maintenance. The component model refers to the specific model or specification of each component, for example, the rated current and rated voltage of a certain model of circuit breaker. This parameter plays an important role in identifying the technical standards, performance range and compatibility of the component. By recording the model information, the system can conduct targeted analysis based on the model when a fault occurs, and determine whether a specific type of component needs to be replaced or repaired. Component connection relationship: refers to the physical connection and logical relationship between each component in the power distribution cabinet. This parameter describes the electrical connection mode and dependency relationship between different components. For example, a switch may be directly connected to a circuit breaker, while a transformer is connected to multiple switches. By recording these connection relationships, the system can better understand the structure of the internal circuit of the power distribution cabinet and provide a clear electrical diagram for troubleshooting and system optimization. In addition, this parameter can also help the system quickly locate other components that may be affected when a fault occurs, and perform linkage detection and remote maintenance.

[0021] Furthermore, the operating parameter matrix includes a current and voltage matrix, a component temperature matrix, and a component activation time matrix.

[0022] Specifically, the current and voltage matrix: This matrix is ​​used to record the current and voltage data of each component in the power distribution cabinet. Each matrix element represents the current and voltage value of a component at a specific time point (or time period). Through the current and voltage matrix, the system can monitor the working status of electrical components in real time and determine whether there are abnormal conditions such as overload and short circuit. The current and voltage matrix can not only help the system identify potential faults, but also be used for the analysis of historical data and predict the future working trend of the equipment. Component temperature matrix: This matrix is ​​used to record the temperature data of each component in the power distribution cabinet. Component temperature is one of the key factors affecting its normal operation. Excessive temperature may cause equipment damage or failure. Each element in the temperature matrix corresponds to the temperature value of a component at a certain moment. The system can analyze whether the equipment is in an overheating state through these data, and provide a basis for subsequent fault warning and maintenance. The accumulation of long-term temperature data can also help the system identify signs of aging or potential safety hazards of the equipment. Component activation time matrix: This matrix is ​​used to record the activation time or working time of each component in the power distribution cabinet. The activation time of each component is usually used to measure its service life. The system can evaluate the aging degree of the component or the time when it is close to scrapping by monitoring the activation time matrix. The matrix provides an important time reference for fault prediction and equipment maintenance. Especially when performing periodic maintenance, enabling the time matrix can help the system decide which components need to be inspected or replaced.

[0023] Furthermore, constructing an operating parameter matrix on a time series based on the operating parameters of components in the power distribution cabinet comprises the following steps: Obtaining component operation parameters from the component management module; Presetting the filling area for the current voltage matrix, the component temperature matrix and the component activation time matrix based on the component connection relationship; Remove outliers and noise from component operating parameters and perform standardization to obtain standardized values; The standardized values ​​are correspondingly filled in the value filling areas of the current and voltage matrix, the component temperature matrix, and the component activation time matrix.

[0024] In some embodiments, first, the system obtains the operating parameters of each component in the power distribution cabinet from the component management module, including current, voltage, component temperature, and component activation time. Data acquisition is performed through various sensors and acquisition modules to ensure the real-time and accuracy of the data. The collected raw data usually presents a time series form and may contain some abnormal values ​​and noise, which requires the subsequent processing link to clean and standardize the data. Next, the system presets the filling area of ​​different operating parameter matrices according to the component connection relationship. Specifically, the current and voltage matrix, the component temperature matrix, and the component activation time matrix need to predefine the corresponding filling area at the beginning of construction so that the parameters of each component can be accurately mapped to the corresponding matrix position. In this process, the component connection relationship provides a reference for the structural setting of each parameter matrix. For example, the electrical wiring diagram can determine which components The current and voltage data should be mapped to the same matrix area. The purpose of this is to ensure the logical consistency of the data and facilitate subsequent matrix processing and analysis. Before data filling, the system removes abnormal values ​​and noise from all acquired component operating parameters. To this end, the system uses an outlier detection algorithm, such as the Z-Score method or the interquartile range method, to detect and remove abnormal data that exceeds the normal range. In addition, in order to eliminate the differences between data of different dimensions and improve the accuracy of data analysis, all component operating parameters will be standardized after removing outliers. The purpose of standardization is to convert data of different dimensions into a unified standard format so that each parameter has equal weight in subsequent analysis, avoiding the disproportionate impact of some parameters on the analysis results due to large or small values. After standardization, the system fills the obtained standardized values ​​into the corresponding filling areas in the current and voltage matrix, component temperature matrix, and component activation time matrix respectively. This process is achieved through efficient matrix operations, ensuring that the real-time data of each component is accurately inserted into the corresponding matrix according to the time series, and forms a complete time series data set with the operating data of other components. The construction of these matrices provides data support for subsequent anomaly detection and fault diagnosis based on deep learning models.

[0025] Furthermore, the residual neural network training based on the operating parameter matrix and the distribution cabinet environmental parameters includes the following steps: Construct a training data set by obtaining the operating parameter matrix and the distribution cabinet environmental parameters; Construct a residual neural network model, take the training data set as input, extract features of the training data through the convolution layer, and obtain a multi-dimensional feature map; The multi-dimensional feature map is input into the residual module, and the high-dimensional features are extracted through the residual connection mechanism; The extracted high-dimensional features are input into the fully connected layer, and the judgment results are output through the activation function.

[0026] In some embodiments, first, the system obtains the real-time operation data of each component in the power distribution cabinet from the component management module, including operating parameters such as current, voltage, component temperature and activation time, and forms an operation parameter matrix with these data. At the same time, environmental data inside and outside the power distribution cabinet, such as temperature and humidity, external environmental temperature and humidity, etc., are collected as environmental parameters. After preliminary cleaning, these data form the original data set for neural network training. During the data set construction process, the system will uniformly format and preprocess the data to ensure the dimensional consistency of each parameter and the accuracy of the data. Then, based on the above training data set, the system constructs a residual neural network model. In the neural network model, the input data is firstly extracted through the convolutional layer. The convolutional layer uses different convolution kernels to perform multi-dimensional sliding window processing on the data, which can extract local features in the data, such as current and voltage fluctuation characteristics and the changing trend of ambient temperature. Through multiple convolution operations, the network can gradually learn high-level abstract features, thereby obtaining dynamic feature maps (Feature Maps) of the power distribution cabinet components. Then, these multi-dimensional feature maps are input into the residual module. The core idea of ​​the residual module is to establish a direct path between different layers of the network through the residual connection mechanism to avoid the gradient vanishing problem of deep networks during training. The residual connection allows information to be transmitted layer by layer in the network, ensuring the retention of key features and the effective extraction of deep features. The residual module can effectively capture complex time series features, such as gradual changes caused by component aging or instantaneous fluctuations caused by sudden failures. Next, the extracted high-dimensional features will be passed to the fully connected layers. In the fully connected layers, the neural network compresses and integrates the multi-dimensional feature vectors to further abstract the global features of the distribution cabinet operation status. At this time, the features are nonlinearly mapped through activation functions (such as ReLU or Sigmoid) to enhance the network's expression and prediction capabilities. The activation function helps to introduce nonlinear features and ensure that the model can learn the complex laws in the data, especially in complex distribution cabinet failure modes, which can improve the accuracy and generalization of the system. Finally, the output after activation is optimized through a loss function (such as cross entropy or mean square error) to adjust the weights of the neural network. Through the backpropagation algorithm, the network continuously updates weights and biases until the output of the model can accurately reflect the normal operation status and potential faults of the distribution cabinet. After this process is completed, the residual neural network model can efficiently detect various abnormal conditions in the distribution cabinet, thereby achieving accurate fault warning and remote maintenance of the distribution cabinet.

[0027] Furthermore, the determination result includes whether the power distribution cabinet is normal, whether the power distribution cabinet is abnormal, and whether the component is abnormal.

[0028] Specifically, the power distribution cabinet is normal: when the operating parameters of all components are within the predetermined safety threshold range and the environmental parameters of the power distribution cabinet are also in a normal state, the residual neural network will output the judgment result of "the power distribution cabinet is normal". This result indicates that the overall operating status of the power distribution cabinet is good and no further intervention measures are required. At this time, the remote maintenance module only needs to upload and store daily data for subsequent status monitoring and trend analysis. The power distribution cabinet is abnormal: when the system detects that the overall parameters of the power distribution cabinet (such as overtemperature, current overload, etc.) exceed the safety threshold, and the abnormal trend involves multiple key components, the residual neural network will output the judgment result of "the power distribution cabinet is abnormal". This situation usually reflects that there may be potential risks in the power distribution cabinet as a whole, such as overheating, overload or other systemic failures. The judgment result will be pushed to the operation and maintenance personnel in real time through the remote maintenance module, accompanied by the AR visualization display of the three-dimensional model, so that the operation and maintenance personnel can view the abnormal situation of the power distribution cabinet from a global perspective, quickly locate the potential source of the problem, and arrange maintenance or repair operations in time. Component abnormality: When the operating parameters of one or a few specific components deviate from the normal range, while other components remain normal, the residual neural network will separately identify the component as a "component abnormality" and generate a corresponding judgment result. For example, the system may detect that the temperature of a circuit breaker rises abnormally or the voltage is unstable, while the operating status of other components remains within the normal range. In this case, the remote maintenance module will push the abnormal information and related operating parameters of the specific component to the maintenance personnel through AR visualization, and highlight the location and numerical information of the faulty component, so that the operation and maintenance personnel can accurately identify the problem component and conduct targeted inspections and maintenance to avoid affecting the overall function of the distribution cabinet.

[0029] Furthermore, the calculation formula of the residual neural network model is as follows: ; in, is the prediction result of the distribution cabinet at time t; is the input feature at time t, including the operating parameter matrix and the distribution cabinet environmental parameters; For the The convolution kernel parameters of the layer; is the bias term; is the convolution kernel weight matrix of the output layer; is the bias term of the output layer; is the activation function; is the residual neural network The output of the layer at the previous moment; is the number of network layers.

[0030] Specifically, the network uses convolutional layers to transform input features. Perform feature extraction layer by layer to form a residual path of inter-layer accumulation. The output of each layer is not only affected by the current input features, but also superimposed with the output features of the previous layer to ensure the effective transmission of deep information. The weight matrix of the final output layer is The final judgment result is generated by weighting the accumulated features. This residual connection mechanism avoids the gradient vanishing problem by accumulating features across layers, and enhances the stability and recognition ability of the model when dealing with high-dimensional complex fault modes. Finally, after the residual features accumulated by multiple layers are input to the Lth layer, they are processed by the activation function to generate the final prediction judgment result of the distribution cabinet at time t. .

[0031] Furthermore, the loss function of the residual neural network model is as follows: ; in, is the total loss function; is the real judgment result of the distribution cabinet at time t; is the prediction result of the distribution cabinet at time t; is the mean square error between the predicted value and the true value; For the The convolution kernel parameters of the layer; is the regularization coefficient; is the number of samples in the training data set; is the number of network layers.

[0032] Specifically, the loss function combines the mean square error term and the regularization term to optimize the prediction accuracy of the model by minimizing the mean square error. At the same time, the convolution kernel parameters are constrained by the regularization term to prevent the model from overfitting. During the training process of the residual neural network, the weights and bias terms are continuously adjusted to minimize the loss function, thereby achieving high-precision prediction and anomaly detection of the distribution cabinet status.

[0033] Furthermore, the remote maintenance module includes a cloud end and a maintenance personnel end; The remote maintenance module is used to receive a plurality of three-dimensional models of power distribution cabinets and send the three-dimensional models of the power distribution cabinets to the maintenance personnel according to the abnormality determination results, and is also used to receive the maintenance record information uploaded by the personnel and synchronously update it to the component management module; The maintenance personnel end is used to receive the three-dimensional model of the distribution cabinet and perform AR visualization, and is also used to receive maintenance record information and upload it to the remote maintenance module in a standardized manner.

[0034] It should be noted that the remote maintenance module is designed to consist of a cloud and a maintenance personnel end to achieve efficient remote monitoring and maintenance support for the distribution cabinet. The remote maintenance module ensures that the real-time status of the distribution cabinet can be communicated and visualized in a timely manner through the combination of cloud computing and augmented reality (AR) technology, and supports real-time synchronization and updating of maintenance records. In the daily operation process, the cloud of the remote maintenance module is responsible for receiving and storing the three-dimensional models of multiple distribution cabinets. These models are generated by the model building module and cover the real-time operating status and spatial distribution information of all components in the distribution cabinet. Whenever the abnormal monitoring module detects an abnormality in the operating parameters or environmental parameters of the distribution cabinet and generates the corresponding abnormal judgment result, the cloud will immediately push the three-dimensional model of the corresponding distribution cabinet and the judgment result to the maintenance personnel end. This real-time synchronization mechanism enables operation and maintenance personnel to quickly obtain abnormal information of the distribution cabinet, and intuitively understand the specific location and fault details of the components in the distribution cabinet without arriving at the site, thereby improving the maintenance response speed. On the maintenance personnel side, the received three-dimensional model of the power distribution cabinet will be presented in an AR visualization way, so that the maintenance personnel can see the component distribution and fault location inside the power distribution cabinet on augmented reality devices (such as smart glasses, tablets or mobile phones). Through AR technology, operation and maintenance personnel can accurately locate the faulty component in the model and observe the relevant parameters of the component, such as current, voltage, temperature, etc., so as to provide effective decision support. For example, when a circuit breaker in the power distribution cabinet has an abnormal temperature rise, the AR visualization on the maintenance personnel side will highlight the circuit breaker and display the temperature value and other related parameters in real time, which is convenient for operation and maintenance personnel to evaluate the specific situation. In addition, after handling the fault or completing the maintenance operation, the maintenance personnel can enter detailed maintenance record information through the maintenance personnel side. These record information includes maintenance content, operation steps, component replacement status and test results. After entering, the system will standardize the maintenance record to ensure the uniformity and standardization of the data. The processed maintenance record information will be uploaded to the cloud and synchronized to the component management module through the cloud. After receiving the updated maintenance record, the component management module will combine the information with the component's historical record and archive it to provide a reference for subsequent equipment monitoring and maintenance. This design of the remote maintenance module ensures the complete traceability and recording of maintenance information, and can be updated in real time after a component fails or is replaced, so that the system can effectively accumulate the maintenance history data of the distribution cabinet in the long-term operation, thereby providing more reliable support in future fault prediction and operation and maintenance decisions. Through efficient data transmission and information synchronization, this module realizes remote monitoring, fault diagnosis, AR visualization and automated management of maintenance records of the distribution cabinet, greatly improving the intelligence level and maintenance efficiency of the system.

[0035] The above implementation modes are merely descriptions of the preferred implementation modes of the present invention, and are not intended to limit the scope of the present invention. Without departing from the design spirit of the present invention, various modifications and improvements made to the technical solutions of the present invention by ordinary engineering and technical personnel in the field shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A remote maintenance system for an intelligent power distribution cabinet, characterized in that: It includes a component management module, an abnormality monitoring module, a model building module and a remote maintenance module connected in sequence, and also includes an in-cabinet environment monitoring module, the in-cabinet environment monitoring module is connected to the abnormality monitoring module, and the remote maintenance module is connected to the component management module; The component management module is used to update and record component attribute parameters and component operation parameters in the power distribution cabinet in real time, and the component operation parameters include current and voltage, component temperature and component activation time; The cabinet environment monitoring module is used to obtain the environmental parameters of the power distribution cabinet in real time, including the cabinet environment humidity and the cabinet external environment temperature and humidity; The abnormal monitoring module is used to construct an operating parameter matrix on a time series based on the component operating parameters in the power distribution cabinet, perform residual neural network training based on the operating parameter matrix and the power distribution cabinet environmental parameters, and perform abnormal judgment on the real-time component operating parameters through the trained residual neural network to generate a real-time judgment result; The model building module is used to build a three-dimensional framework of the power distribution cabinet, and the three-dimensional framework of the power distribution cabinet is combined according to the component category, component model and component connection relationship matching preset component library to obtain a real-time three-dimensional model of the power distribution cabinet; the model building module is also used to synchronously map the three-dimensional model of the power distribution cabinet based on the environmental parameters of the power distribution cabinet and the real-time judgment results; The remote maintenance module is used to receive the three-dimensional model of the power distribution cabinet from the model building module and visualize it, and is also used to receive maintenance record information to update the component management module.

2. The remote maintenance system of an intelligent power distribution cabinet according to claim 1 is characterized in that: The component attribute parameters include component category, component model and component connection relationship.

3. The remote maintenance system of an intelligent power distribution cabinet according to claim 2 is characterized in that: The operating parameter matrix includes a current and voltage matrix, a component temperature matrix, and a component enable time matrix.

4. The remote maintenance system of an intelligent power distribution cabinet according to claim 3 is characterized in that: The method of constructing an operating parameter matrix on a time series based on the operating parameters of components in the power distribution cabinet comprises the following steps: Obtaining component operation parameters from the component management module; Presetting the filling area for the current voltage matrix, the component temperature matrix and the component activation time matrix based on the component connection relationship; Remove outliers and noise from component operating parameters and perform standardization to obtain standardized values; The standardized values ​​are correspondingly filled in the value filling areas of the current and voltage matrix, the component temperature matrix, and the component activation time matrix.

5. The remote maintenance system of an intelligent power distribution cabinet according to claim 1, characterized in that: The residual neural network training based on the operating parameter matrix and the distribution cabinet environmental parameters includes the following steps: Construct a training data set by obtaining the operating parameter matrix and the distribution cabinet environmental parameters; Construct a residual neural network model, take the training data set as input, extract features of the training data through the convolution layer, and obtain a multi-dimensional feature map; The multi-dimensional feature map is input into the residual module, and the high-dimensional features are extracted through the residual connection mechanism; The extracted high-dimensional features are input into the fully connected layer, and the judgment results are output through the activation function.

6. The remote maintenance system of an intelligent power distribution cabinet according to claim 5, characterized in that: The determination results include whether the power distribution cabinet is normal, whether the power distribution cabinet is abnormal, and whether the component is abnormal.

7. The remote maintenance system of an intelligent power distribution cabinet according to claim 6, characterized in that: The calculation formula of the residual neural network model is as follows: ； in, is the prediction result of the distribution cabinet at time t; is the input feature at time t, including the operating parameter matrix and the distribution cabinet environmental parameters; For the The convolution kernel parameters of the layer; is the bias term; is the convolution kernel weight matrix of the output layer; is the bias term of the output layer; is the activation function; is the residual neural network The output of the layer at the previous moment; is the number of network layers.

8. The remote maintenance system of an intelligent power distribution cabinet according to claim 7, characterized in that: The loss function of the residual neural network model is as follows: ; in, is the total loss function; is the real judgment result of the distribution cabinet at time t; is the prediction result of the distribution cabinet at time t; is the mean square error between the predicted value and the true value; For the The convolution kernel parameters of the layer; is the regularization coefficient; is the number of samples in the training data set; is the number of network layers.

9. The remote maintenance system of an intelligent power distribution cabinet according to claim 1, characterized in that: The remote maintenance module includes a cloud end and a maintenance personnel end; The remote maintenance module is used to receive a plurality of three-dimensional models of power distribution cabinets and send the three-dimensional models of the power distribution cabinets to the maintenance personnel according to the abnormality determination results, and is also used to receive the maintenance record information uploaded by the personnel and synchronously update it to the component management module; The maintenance personnel end is used to receive the three-dimensional model of the distribution cabinet and perform AR visualization, and is also used to receive maintenance record information and upload it to the remote maintenance module in a standardized manner.

Images