A low-voltage multi-channel wireless temperature measurement method and device based on artificial intelligence

Abstract

The present invention proposes a low-voltage multi-channel wireless temperature measurement method and device based on artificial intelligence, wherein the method includes: collecting multi-point temperatures of low-voltage electrical equipment, transmitting the collected multi-point temperature data to a central data processing unit via a wireless protocol, and preprocessing the data; extracting features based on the preprocessed multi-point temperature data; using the sensor positions in the low-voltage electrical equipment as nodes of the graph, and the features extracted from the preprocessed temperature data as the features of the nodes of the graph, and the connection relationships between sensors as edges, to obtain the graph structure and train a graph neural network model; inputting real-time data into the trained graph neural network model, obtaining a predicted value, and comparing the difference between the predicted value and the detected value. If the difference exceeds a preset threshold, the model is retrained. Through this method and the corresponding device, manual intervention can be reduced, the efficiency of data processing and analysis can be improved, and a rapid response to changes in equipment temperature can be achieved.

Description

Technical Field

[0001] The present invention proposes a low-voltage multi-channel wireless temperature measurement method and device based on artificial intelligence, which relates to the technical field of temperature measurement circuits. Background Art

[0002] Traditional methods for temperature monitoring low-voltage electrical equipment in modern industrial and power systems face numerous challenges. Traditional contact temperature measurement methods are difficult to install, susceptible to interference, and difficult to maintain. These methods require complex wiring, hindering equipment operation and maintenance. Long-distance wire transmission is susceptible to electromagnetic interference and environmental impact, increasing costs. Traditional wireless single-point temperature measurement methods suffer from limited monitoring range, lack of systematic analysis, and unstable performance. They are unable to comprehensively monitor large, complex systems and assess the overall thermal state, and communication issues can hinder data transmission. Existing data analysis methods also have limitations, primarily due to a lack of predictive power and insufficient information processing capabilities. Using simple statistics and thresholds, they struggle to predict temperature trends and provide early warnings, and they fail to fully tap into the potential data. However, the development of artificial intelligence (AI) technology, with its powerful data processing and analysis capabilities, offers the potential to address these issues. Consequently, an AI-based low-voltage multi-channel wireless temperature measurement method has emerged. It aims to leverage techniques such as graph neural networks and deep learning to achieve efficient, accurate, and comprehensive temperature monitoring and analysis, unlocking more information for early prediction and proactive maintenance, ensuring equipment reliability and safety. Summary of the Invention

[0003] The present invention provides a low-voltage multi-channel wireless temperature measurement method and device based on artificial intelligence to solve the above-mentioned problems:

[0004] The present invention proposes a low-voltage multi-channel wireless temperature measurement method based on artificial intelligence, the method comprising:

[0005] Collect multi-point temperatures of low-voltage electrical equipment, transmit the collected multi-point temperature data to the central data processing unit via wireless protocol, and pre-process the transmitted multi-point temperature data;

[0006] Extract features based on preprocessed multi-point temperature data;

[0007] The sensor locations in the low-voltage electrical equipment are used as nodes of the graph, the features extracted from the preprocessed temperature data are used as features of the nodes of the graph, and the connection relationships between the sensors are used as edges to obtain a graph structure, and a graph neural network model is trained based on the graph structure;

[0008] The data monitored in real time by the sensor is input into the trained graph neural network model to obtain the predicted value. The difference between the predicted value and the detected value is compared at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained. Otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted.

[0009] Furthermore, the multi-point temperature of the low-voltage electrical equipment is collected, the collected multi-point temperature data is transmitted to the central data processing unit through a wireless protocol, and the transmitted multi-point temperature data is pre-processed, including:

[0010] Wireless temperature sensors installed at the switch contacts, busbar connection points, and cable connectors of low-voltage electrical equipment collect temperature data in real time at a preset collection frequency.

[0011] Transmitting temperature data collected by the wireless temperature sensor to a central data processing unit via a wireless protocol, wherein the wireless protocol includes LoRa, ZigBee, and Wi-Fi;

[0012] For the transmitted temperature dataset , first calculate the first quartile and the third quartile , , will be lower than or higher The data are regarded as outliers and are corrected using interpolation.

[0013] Furthermore, features are extracted based on the preprocessed multi-point temperature data, including:

[0014] Extracting time features from the preprocessed multi-point temperature data, the time features including: the average, maximum, minimum, and standard deviation of the temperature within each preset time window;

[0015] Extract the spatial features from the pre-processed multi-point temperature data, which include temperature gradient, temperature difference and relative temperature between different sensors. ,in, represents the temperature gradient, Indicates the low-voltage circuit temperature measured by sensor i, represents the low voltage circuit temperature measured by sensor j, represents the distance between sensors i and j, and the relative temperature is ,in, Indicates relative temperature;

[0016] According to the heat transfer principle, the formula

[0017]

[0018] extracting thermodynamic characteristics from the multi-point temperature data, wherein m represents the mass of the circuit measured by the sensor, c represents the specific heat capacity of the constituent material of the circuit measured by the sensor, represents the temperature measured by the sensor at time t, represents the temperature measured by the sensor at time t-1, It represents the amount of heat transfer in the circuit measured by the sensor during the time period from t to t-1.

[0019] Furthermore, the sensor locations in the low-voltage electrical equipment are used as nodes of a graph, the features extracted from the preprocessed temperature data are used as features of the nodes of the graph, and the connection relationships between the sensors are used as edges to obtain a graph structure. A graph neural network model is trained based on the graph structure, including:

[0020] Each wireless temperature sensor in the low-voltage electrical equipment is regarded as a node in the graph and marked with a unique identifier, i.e., a node number. The extracted time feature, the spatial feature, and the thermodynamic feature are combined as a node feature vector. The edges of the graph are constructed based on the connection relationship of the graph, and the node feature vector and edge information are encapsulated into a graph structure.

[0021] Construct a graph neural network model, which uses a graph convolutional network in the GNN architecture. The graph neural network defines a class inherited from torch.nn.Module. The graph convolutional network contains three GCNConv graph convolution layers for extracting features from the graph structure. The first graph convolution layer converts the input node features into features of the feature dimension of the hidden layer through a graph convolution operation. The second graph convolution layer receives the output features of the feature dimension of the hidden layer of the first graph convolution layer and outputs features of the same dimension. The third graph convolution layer receives the output features of the feature dimension of the hidden layer of the second graph convolution layer and converts them into a one-dimensional predicted temperature value.

[0022] Input the graph structure data into the constructed graph neural network model for training to obtain the trained graph neural network model.

[0023] Furthermore, the real-time monitoring data of the sensor is input into the trained graph neural network model to obtain the predicted value. The difference between the predicted value and the detected value is compared at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained. Otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted, including:

[0024] Input the real-time monitoring data of the sensor into the trained graph neural network model to obtain a first prediction value, and continue to input the first prediction value into the trained graph neural network model to obtain a second prediction value;

[0025] The second predicted value is compared with the value actually detected by the sensor. If the difference between the second predicted value and the value actually detected by the sensor exceeds the preset threshold, the value actually detected by the sensor is used as incremental data to retrain the model. If it does not exceed the preset threshold, the prediction result is stored and added to the historical data set. The temperature of the low-voltage electrical equipment in the next time window is continued to be predicted based on the historical data set.

[0026] The present invention proposes a low-voltage multi-channel wireless temperature measurement device based on artificial intelligence, the device comprising:

[0027] The acquisition module is used to collect the multi-point temperature of low-voltage electrical equipment, transmit the collected multi-point temperature data to the central data processing unit through a wireless protocol, and pre-process the transmitted multi-point temperature data;

[0028] A feature extraction module is used to extract features based on preprocessed multi-point temperature data;

[0029] A graph neural network model training module is used to use the sensor locations in the low-voltage electrical equipment as nodes of the graph, the features extracted from the preprocessed temperature data as the features of the nodes of the graph, and the connection relationships between the sensors as edges to obtain a graph structure, and train a graph neural network model based on the graph structure;

[0030] The prediction module is used to input the data monitored in real time by the sensor into the trained graph neural network model to obtain the predicted value, and compare the difference between the predicted value and the detected value at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained; otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted.

[0031] Furthermore, the acquisition module includes:

[0032] The temperature data collection module is used to collect temperature data in real time according to a preset collection frequency through wireless temperature sensors installed at switch contacts, busbar connection points and cable connectors of low-voltage electrical equipment;

[0033] A transmission module, used to transmit the temperature data collected by the wireless temperature sensor to the central data processing unit through a wireless protocol, wherein the wireless protocol includes LoRa, ZigBee and Wi-Fi;

[0034] Correction module for the transmitted temperature data set , first calculate the first quartile and the third quartile , , will be lower than or higher The data are regarded as outliers and are corrected using interpolation.

[0035] Furthermore, the feature extraction module includes:

[0036] A time feature extraction module is used to extract time features from the preprocessed multi-point temperature data, wherein the time features include the average, maximum, minimum and standard deviation of the temperature in each preset time window;

[0037] The spatial feature extraction module is used to extract the spatial features of the pre-processed multi-point temperature data. The spatial features include: temperature gradient, temperature difference and relative temperature between different sensors. The temperature gradient is ,in, represents the temperature gradient, Indicates the low-voltage circuit temperature measured by sensor i, represents the low voltage circuit temperature measured by sensor j, represents the distance between sensors i and j, and the relative temperature is ,in, Indicates relative temperature;

[0038] Extract thermodynamic characteristics module, used to extract the heat transfer principle through the formula

[0039]

[0040] extracting thermodynamic characteristics from the multi-point temperature data, wherein m represents the mass of the circuit measured by the sensor, c represents the specific heat capacity of the constituent material of the circuit measured by the sensor, represents the temperature measured by the sensor at time t, represents the temperature measured by the sensor at time t-1, It represents the amount of heat transfer in the circuit measured by the sensor during the time period from t to t-1.

[0041] Furthermore, the training graph neural network model module includes:

[0042] A graph construction module is configured to treat each wireless temperature sensor in the low-voltage electrical equipment as a node in a graph, mark it with a unique identifier, i.e., a node number, combine the extracted time features, the extracted spatial features, and the extracted thermodynamic features as a node feature vector, construct graph edges based on the connection relationships of the graph, and encapsulate the node feature vectors and edge information into a graph structure;

[0043] Construct a graph neural network model module for constructing a graph neural network model. The graph neural network model adopts the graph convolution network in the GNN architecture. The graph neural network defines a class inherited from torch.nn.Module. The graph convolution network contains three layers of GCNConv graph convolution layers for extracting features from the graph structure. The first graph convolution layer converts the input node features into features of the feature dimension of the hidden layer through a graph convolution operation. The second graph convolution layer receives the output features of the feature dimension of the hidden layer of the first graph convolution layer and outputs features of the same dimension. The third graph convolution layer receives the output features of the feature dimension of the hidden layer of the second graph convolution layer and converts them into one-dimensional predicted temperature values.

[0044] The training module is used to input graph structure data into the constructed graph neural network model for training and obtain the trained graph neural network model.

[0045] Furthermore, the prediction module includes:

[0046] A second prediction value acquisition module is used to input the data monitored in real time by the sensor into the trained graph neural network model to obtain the first prediction value, and further input the first prediction value into the trained graph neural network model to obtain the second prediction value;

[0047] The correction prediction module is used to compare the second predicted value with the value actually detected by the sensor. If the difference between the second predicted value and the value actually detected by the sensor exceeds a preset threshold, the value actually detected by the sensor is used as incremental data to retrain the model. If it does not exceed the preset threshold, the prediction result is stored and added to the historical data set, and the temperature of the low-voltage electrical equipment in the next time window is continued to be predicted based on the historical data set.

[0048] The present invention has the following beneficial effects: precise temperature monitoring and prediction, through multi-point temperature acquisition and graph neural network model training based on graph structure, fully considers the mutual relationship and change trend of the temperature of various parts of low-voltage electrical equipment. Compared with the traditional monitoring method of single sensor or simple model, it can more accurately predict the equipment temperature, timely detect potential overheating risks, and provide strong guarantee for the stable operation of the equipment; adaptive and self-optimizing, with adaptive capabilities, when the difference between the predicted value and the detected value exceeds the preset range, it can automatically trigger model retraining. This enables the model to continuously optimize its own performance as the equipment operating status and environmental factors change, continuously maintain high prediction accuracy, and ensure long-term stable and reliable temperature monitoring; early fault warning, accurate temperature prediction helps to detect abnormal temperature changes in time before the equipment fails, and issue early warning signals. Operation and maintenance personnel can take targeted measures based on the warning information, such as adjusting equipment operating parameters and arranging maintenance, to avoid equipment failure, reduce maintenance costs and downtime, and improve equipment reliability and availability; efficient data processing and analysis, from data acquisition and transmission to preprocessing, feature extraction, and model training and prediction, the entire process is automated and efficient. It reduces manual intervention, improves the efficiency of data processing and analysis, can quickly respond to equipment temperature changes, and adapt to the requirements of modern industrial production for real-time and efficient equipment monitoring; the constructed graph structure is not only used for temperature prediction, but also can intuitively display the relationship between various parts of low-voltage electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a schematic diagram of a low-voltage multi-channel wireless temperature measurement method based on artificial intelligence described in the present invention. DETAILED DESCRIPTION

[0050] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein may be combined with each other.

[0051] The following description sets forth numerous specific details to facilitate a thorough understanding of the present invention. The embodiments described are merely a portion of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0053] One embodiment of the present invention provides a low-voltage multi-channel wireless temperature measurement method based on artificial intelligence, the method comprising:

[0054] Collect multi-point temperatures of low-voltage electrical equipment, transmit the collected multi-point temperature data to the central data processing unit via wireless protocol, and pre-process the transmitted multi-point temperature data;

[0055] Extract features based on preprocessed multi-point temperature data;

[0056] The sensor locations in the low-voltage electrical equipment are used as nodes of the graph, the features extracted from the preprocessed temperature data are used as features of the nodes of the graph, and the connection relationships between the sensors are used as edges to obtain a graph structure, and a graph neural network model is trained based on the graph structure;

[0057] The data monitored in real time by the sensor is input into the trained graph neural network model to obtain the predicted value. The difference between the predicted value and the detected value is compared at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained. Otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted.

[0058] The working principle and effect of the above technical solution are: data collection and transmission, temperature sensors are deployed at multiple key locations of low-voltage electrical equipment to collect multi-point temperature data. These sensors are like "scouts" distributed throughout the equipment, sensing temperature changes in real time; then, the large amount of collected temperature data is sent to the central data processing unit through a wireless protocol to ensure that the data is quickly and accurately aggregated; the original temperature data received by the central data processing unit may have problems such as noise and missing values. The preprocessing phase aims to clean and optimize the data through filtering, denoising, and filling missing values, providing a high-quality data foundation for subsequent analysis and processing. From the preprocessed multi-point temperature data, features that reflect temperature variation patterns, trends, and equipment operating status are extracted. A graph structure is constructed: the locations of sensors within the low-voltage electrical equipment are used as graph nodes, and the extracted features are assigned to these nodes. The edges of the graph are determined based on the actual connections between the sensors. In this way, the originally scattered temperature data and sensor information are transformed into a structured graph representation, comprehensively and intuitively displaying the temperatures and connections of various equipment components. Model training and prediction: The constructed graph structure is used to train the graph neural network model. During training, the model continuously learns the patterns and regularities inherent in the node features and edge relationships within the graph, understanding the inherent connection between temperature data and equipment operating status. After training is complete, the real-time sensor monitoring data is input into the trained model, which then outputs a predicted value for the low-voltage electrical equipment temperature. At the end of a preset time window, the predicted value is compared with the actual measured value. If the difference between the two exceeds the preset threshold, it means that the current model's prediction of the equipment temperature change has a large deviation, and the model needs to be retrained to optimize its performance; if the difference is within an acceptable range, the model will continue to be used to predict the temperature of the next time window. Accurate temperature monitoring and prediction, through multi-point temperature acquisition and graph neural network model training based on graph structure, fully considers the relationship and change trend of the temperature of various parts of low-voltage electrical equipment. Compared with traditional single sensor or simple model monitoring methods, it can more accurately predict equipment temperature, timely detect potential overheating risks, and provide strong guarantees for the stable operation of the equipment; adaptive and self-optimizing, with adaptive capabilities, when the difference between the predicted value and the detected value exceeds the preset range, it can automatically trigger model retraining.This enables the model to continuously optimize its performance as the equipment's operating status and environmental factors change, maintaining a high level of prediction accuracy and ensuring long-term stable and reliable temperature monitoring. Early fault warning: Accurate temperature prediction helps detect abnormal temperature changes before equipment failure occurs, issuing early warning signals. Operation and maintenance personnel can take targeted measures based on the warning information, such as adjusting equipment operating parameters and arranging maintenance, to avoid equipment failures, reduce maintenance costs and downtime, and improve equipment reliability and availability. Efficient data processing and analysis: From data acquisition and transmission to preprocessing, feature extraction, and model training and prediction, the entire process is automated and efficient. This reduces manual intervention, improves the efficiency of data processing and analysis, and can quickly respond to equipment temperature changes, meeting the requirements of modern industrial production for real-time and efficient equipment monitoring.

[0059] The constructed graph structure not only predicts temperature but also visually displays the relationships between various parts of low-voltage electrical equipment. Operations and maintenance personnel can use the graph to understand the overall operating status of the equipment, identify potential weak links or abnormal connections, and provide comprehensive data support and decision-making basis for optimizing equipment design and formulating maintenance strategies.

[0060] In one embodiment of the present invention, the temperature of multiple points of a low-voltage electrical device is collected, the collected temperature data is transmitted to a central data processing unit via a wireless protocol, and the transmitted temperature data is pre-processed, including:

[0061] Wireless temperature sensors installed at the switch contacts, busbar connection points, and cable connectors of low-voltage electrical equipment collect temperature data in real time at a preset collection frequency.

[0062] Transmitting temperature data collected by the wireless temperature sensor to a central data processing unit via a wireless protocol, wherein the wireless protocol includes LoRa, ZigBee, and Wi-Fi;

[0063] For the transmitted temperature dataset , first calculate the first quartile and the third quartile , , will be lower than or higher The data are regarded as outliers and are corrected using interpolation.

[0064] The working principle and effect of the above technical solution are as follows: Wireless temperature sensors are installed at key locations on low-voltage electrical equipment, namely switch contacts, busbar connection points, and cable connectors. These locations are prone to heat accumulation and temperature anomalies. These sensors can collect temperature data in a targeted manner. The sensors periodically measure the temperature in real time at a preset collection frequency, acquiring a series of temperature data points. For example, if the preset collection frequency is every 5 minutes, the sensors will record the temperature information at each 5-minute interval, forming a raw temperature data set. The collected temperature data is then transmitted to a central data processing unit using a wireless protocol. Wireless protocols can include LoRa, ZigBee, or Wi-Fi, each of which has different characteristics and application scenarios. LoRa has the advantages of long-range transmission and low power consumption, making it suitable for large or widely distributed electrical equipment areas. ZigBee is suitable for short-range, low-speed data transmission, and is more effective for small equipment or relatively concentrated equipment areas. Wi-Fi has the advantages of high-speed transmission, facilitating rapid data processing and sharing. The sensor transmits the collected temperature data in the form of data packets via a selected wireless protocol across spatial distances to the central data processing unit for subsequent processing, thus realizing remote centralized management of the data. Data preprocessing: For the temperature data set transmitted to the central data processing unit, the first quartile and the third quartile are first calculated to obtain the interquartile range. According to the principle of quartiles, data below or above the value are considered outliers; these outliers may be inaccurate measurements caused by sensor failure, electromagnetic interference, or other accidental factors. Interpolation is used to correct outliers. The interpolation method can estimate the reasonable range of outliers based on the information of adjacent normal data points and replace them with values that are more in line with the actual situation, making the entire data set smoother and more accurate for subsequent analysis.

[0065] By deploying temperature sensors at key locations and collecting data in real time, the temperature information of low-voltage electrical equipment can be accurately captured, providing a rich and targeted data source for equipment temperature monitoring. The processing of outliers can eliminate erroneous data caused by accidental factors, avoid the interference of these abnormal data on subsequent analysis and judgment, ensure the accuracy and reliability of the data, and provide a more scientific data basis for subsequent equipment status assessment and fault diagnosis. By utilizing a variety of wireless transmission protocols, flexible selection can be made according to different electrical equipment installation environments and requirements to ensure that data can be transmitted stably and efficiently to the central data processing unit without being restricted by space and wiring, thereby improving the adaptability and scalability of the system. Whether it is a large factory, a complex electrical system or a relatively small electrical equipment group, a suitable wireless transmission method can be found to facilitate system deployment and maintenance. Through reasonable temperature data collection, flexible transmission methods and effective data preprocessing, strong support is provided for the stable operation and fault prevention of low-voltage electrical equipment, and the reliability and safety of equipment management are improved.

[0066] One embodiment of the present invention extracts features based on preprocessed multi-point temperature data, including:

[0067] Extracting time features from the preprocessed multi-point temperature data, the time features including: the average, maximum, minimum, and standard deviation of the temperature within each preset time window;

[0068] Extract the spatial features from the pre-processed multi-point temperature data, which include temperature gradient, temperature difference and relative temperature between different sensors. ,in, represents the temperature gradient, Indicates the low-voltage circuit temperature measured by sensor i, represents the low voltage circuit temperature measured by sensor j, represents the distance between sensors i and j, and the relative temperature is ,in, Indicates relative temperature;

[0069] According to the heat transfer principle, the formula

[0070]

[0071] extracting thermodynamic characteristics from the multi-point temperature data, wherein m represents the mass of the circuit measured by the sensor, c represents the specific heat capacity of the constituent material of the circuit measured by the sensor, represents the temperature measured by the sensor at time t, represents the temperature measured by the sensor at time t-1, It represents the amount of heat transfer in the circuit measured by the sensor during the time period from t to t-1.

[0072] The working principle and effect of the above technical solution are as follows: time feature extraction, for the preprocessed multi-point temperature data, it is divided into different preset time windows, and in each time window, the average, maximum, minimum and standard deviation of the temperature are calculated. Through these statistics, the overall situation, fluctuation range and degree of dispersion of the temperature in different time windows can be clearly understood. For example, in a one-hour time window, the average temperature in the time period can be known by calculating the average value, the maximum and minimum values can show the fluctuation range of the temperature, and the standard deviation reflects the degree of dispersion of the temperature, which helps to judge the stability of the temperature. These time features describe the temperature data from the time dimension, which provides a basis for the subsequent analysis of the time change law of temperature, and can be used to observe the trend of temperature change over time, such as whether there is periodic temperature increase or decrease, whether there are abnormal temperature fluctuations in a certain time period, etc.; spatial feature extraction, spatial features mainly focus on the temperature relationship between different sensors. By calculating the temperature gradient between different sensors, the spatial rate of temperature change, that is, the temperature change trend between different locations, can be reflected. Based on this gradient, the direction and speed of heat transfer in the equipment can be understood. At the same time, calculating the relative temperature can reflect the relative size relationship of the temperatures at different locations, which helps to find the hot and cold spots, as well as the temperature distribution in different areas. The extraction of spatial features is based on the positional relationship of multiple sensors and the measured temperature data. By analyzing these features, we can gain an in-depth understanding of whether the temperature distribution inside or on the surface of low-voltage electrical equipment is uniform, whether there are local overheating or overcooling areas, and thus evaluate the operating status and potential problems of the equipment; thermodynamic feature extraction, based on the principle of heat transfer, uses a formula to extract thermodynamic features. Through this formula, the amount of heat transfer occurring in the circuit measured by the sensor over a period of time can be calculated. This feature reflects the heat transfer in the circuit. Combined with time information, the rate of heat transfer can be understood, which helps to determine whether the energy conversion and transfer of the equipment is normal, whether there is abnormal energy loss or excessive local heat accumulation.Comprehensive feature information, extracting time, space and thermodynamic features, can comprehensively characterize the temperature information of low-voltage electrical equipment from multiple dimensions. It can not only grasp the dynamic changes of temperature from time, but also grasp the temperature distribution and transfer trend from space. At the same time, it can grasp the heat transfer from a thermodynamic perspective, providing all-round information for the evaluation of the equipment's operating status. Together, they constitute a comprehensive description of the equipment's temperature, which helps to more accurately judge the health status of the equipment, rather than simply judging from a single-dimensional temperature data. For fault diagnosis and prevention, time features can help detect abnormal temperature fluctuations and periodic anomalies, spatial features can find areas with uneven temperature in the equipment, and thermodynamic features can determine whether the heat transfer is abnormal. By combining these features, it is possible to detect temperature anomalies that may lead to equipment failures in advance, such as local overheating, heat transfer obstruction and other problems, providing a basis for equipment fault diagnosis and prevention; by observing abnormal changes in temperature gradients, it is possible to detect whether there are poor contact or heat dissipation problems; through abnormal heat transfer, it is possible to determine whether the circuit has short circuits or overloads, and then take measures in advance to avoid equipment failures or damage and improve the safety and reliability of the equipment; through multi-dimensional feature extraction, it provides rich information for temperature monitoring and management of low-voltage electrical equipment, improves the safety and reliability of the equipment, and also provides a basis for equipment performance optimization and fault diagnosis, which helps to improve the operating efficiency and stability of the entire system.

[0073] In one embodiment of the present invention, the sensor locations in the low-voltage electrical equipment are used as nodes of a graph, the features extracted from the preprocessed temperature data are used as features of the graph nodes, and the connection relationships between the sensors are used as edges to obtain a graph structure. A graph neural network model is trained based on the graph structure, including:

[0074] Each wireless temperature sensor in the low-voltage electrical equipment is regarded as a node in the graph and marked with a unique identifier, i.e., a node number. The extracted time feature, the spatial feature, and the thermodynamic feature are combined as a node feature vector. The edges of the graph are constructed based on the connection relationship of the graph, and the node feature vector and edge information are encapsulated into a graph structure.

[0075] Construct a graph neural network model, which uses a graph convolutional network in the GNN architecture. The graph neural network defines a class inherited from torch.nn.Module. The graph convolutional network contains three GCNConv graph convolution layers for extracting features from the graph structure. The first graph convolution layer converts the input node features into features of the feature dimension of the hidden layer through a graph convolution operation. The second graph convolution layer receives the output features of the feature dimension of the hidden layer of the first graph convolution layer and outputs features of the same dimension. The third graph convolution layer receives the output features of the feature dimension of the hidden layer of the second graph convolution layer and converts them into a one-dimensional predicted temperature value.

[0076] Input the graph structure data into the constructed graph neural network model for training to obtain the trained graph neural network model.

[0077] The working principle and effect of the above technical solution are as follows: graph structure construction, node definition: each wireless temperature sensor in the low-voltage electrical equipment is regarded as a node in the graph and marked with a unique identifier (node number) to ensure the uniqueness of each node; feature vector combination: the previously extracted time features (such as the average temperature, maximum temperature, minimum temperature and standard deviation in each time window), spatial features (temperature gradient, temperature difference and relative temperature between different sensors) and thermodynamic features (heat transfer amount calculated based on the heat transfer formula, etc.) are combined as the feature vector of each node. These feature vectors comprehensively describe the temperature characteristics of each sensor location, covering multiple aspects of information such as time, space, and energy transfer; Edge construction: Graph edges are constructed based on the connection relationships of the graph. These connection relationships may reflect the physical or logical connections of the sensors in the equipment, thereby connecting the nodes and their feature vectors with edges to form a complete graph structure. This graph structure can effectively represent the temperature sensor network of low-voltage electrical equipment and their mutual relationships; Graph neural network model construction: Architecture selection: Use the graph convolutional network (GCN) architecture in the graph neural network (GNN) and define a class inherited from torch.nn.Module; Convolutional layer setting: The constructed graph convolutional network contains three layers of GCNConv Graph convolution layer; the first graph convolution layer receives the input node feature vector and converts it into features with hidden layer feature dimensions through graph convolution operation. The graph convolution operation takes into account the information of the node and its neighboring nodes, fuses the local information between nodes, and mines the relationship between nodes; the second graph convolution layer receives the output of the first graph convolution layer, outputs features of the same dimension, and further deepens the extraction of node features and information fusion; the third graph convolution layer receives the output of the second graph convolution layer and converts it into a one-dimensional predicted temperature value, and finally converts the high-dimensional feature information into a predicted result of temperature; the constructed graph structure data is input into the graph neural network model for training. During the training process, the model continuously adjusts its own parameters by learning the node features and edge connection information in the graph structure to minimize the error between the predicted temperature value and the actual temperature value, thereby optimizing the performance of the model and finally obtaining a trained graph neural network model.Efficient feature fusion and representation: By combining multi-dimensional features (temporal, spatial, and thermodynamic) into node feature vectors and constructing a graph structure, scattered temperature sensor information can be presented in a structured and associative manner, effectively integrating temperature information from different locations and times of low-voltage electrical equipment, enabling the model to better utilize the inherent connections between different features. The graph structure can better represent the topological relationships between sensors, helping to explore potential relationships between sensors rather than viewing the information of each sensor in isolation, thereby improving the representation ability and depth of understanding of temperature data. Powerful feature extraction capabilities: Graph neural networks, based on a graph convolutional network architecture, perform feature extraction and information fusion on the graph structure through multiple graph convolution layers. Each graph convolution layer fully utilizes the local information of the node, gradually propagating and fusing the local information of the node through convolution operations, extracting deep feature information from the graph structure and more accurately capturing the complex patterns and regularities of low-voltage electrical equipment temperature data. Compared with traditional machine learning methods, graph neural networks can better process graph-structured data and explore nonlinear relationships between nodes, providing stronger feature extraction capabilities for tasks such as temperature prediction. Accurate temperature prediction and equipment monitoring: A trained graph neural network model can accurately predict temperature based on the input graph structure data. Since the spatial layout, temporal changes and thermodynamic characteristics of the sensors are fully considered, the prediction results will be more accurate and can better adapt to the complex environment and diverse operating conditions of low-voltage electrical equipment; it helps to realize real-time monitoring of low-voltage electrical equipment and detect temperature anomalies in advance, such as local overheating and uneven temperature distribution, providing a more reliable basis for equipment failure prevention and maintenance, and reducing equipment damage risks and maintenance costs; based on graph structure and graph neural network, when adding or adjusting sensor nodes, only the graph structure needs to be updated, and the model can adapt to the new structure through retraining or fine-tuning, with good scalability; at the same time, due to the characteristics of graph structure and graph neural network, the solution can adapt to low-voltage electrical equipment of different scales and layouts, and has certain adaptability to different equipment structures and complex temperature distribution conditions, and can be widely used in temperature monitoring scenarios of various low-voltage electrical equipment.

[0078] In one embodiment of the present invention, real-time sensor monitoring data is input into a trained graph neural network model to obtain a predicted value. The difference between the predicted value and the detected value is compared at the end of a preset time window. If the difference exceeds a preset threshold, the model is retrained. Otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted, including:

[0079] Input the real-time monitoring data of the sensor into the trained graph neural network model to obtain a first prediction value, and continue to input the first prediction value into the trained graph neural network model to obtain a second prediction value;

[0080] The second predicted value is compared with the value actually detected by the sensor. If the difference between the second predicted value and the value actually detected by the sensor exceeds the preset threshold, the value actually detected by the sensor is used as incremental data to retrain the model. If it does not exceed the preset threshold, the prediction result is stored and added to the historical data set. The temperature of the low-voltage electrical equipment in the next time window is continued to be predicted based on the historical data set.

[0081] The working principle and effect of the above technical solution are as follows: data input and prediction: First, the real-time sensor monitoring data is input into a trained graph neural network model. Because the graph neural network model has been previously trained, it can process and extract features from the input data and output a first prediction value based on its learned knowledge and patterns. Then, the first prediction value is re-input into the trained graph neural network model to obtain a second prediction value. This process leverages the characteristics of graph neural networks, namely, the ability to iterate input multiple times, further mining features and reprocessing information in the hope of obtaining more accurate and in-depth prediction results. For example, the first prediction may be a preliminary prediction based on the raw sensor data at the current moment, while the second prediction is based on the first prediction result and takes into account the model's further understanding and analysis of the data, potentially considering more feature associations and potential patterns, thereby improving the accuracy and reliability of the prediction. Result comparison and decision-making: After obtaining the second predicted value, it is compared with the actual value detected by the sensor. A preset threshold is set to measure whether the deviation between the predicted value and the actual value is within an acceptable range. If the difference between the two exceeds the preset threshold, it indicates that there is a problem with the current prediction performance of the model, which may be due to a change in the operating status of the device or the previous training data no longer well reflects the current situation. At this time, the actual value detected by the sensor is used as incremental data and added to the dataset for retraining the model. Through retraining, the model parameters and learned patterns are adjusted to better adapt to the new situation. If the difference does not exceed the preset threshold, the model's prediction is accurate, and the prediction result is stored and added to the historical dataset. These historical data sets contain data from previous successful predictions, which accumulate over time and provide more reference information for subsequent predictions, so that the temperature of low-voltage electrical equipment in the next time window can be predicted based on richer data. Continuously optimize prediction accuracy. By iteratively inputting the predicted values multiple times and comparing them with the actual detection values, the solution can promptly detect deviations in model predictions. Once the deviation exceeds the threshold, retraining is performed to enable the model to continuously adapt to changes in the operating status of low-voltage electrical equipment and new data patterns, thereby ensuring the accuracy and reliability of the prediction results. This self-adjustment mechanism ensures that the model will not fail due to changes in equipment status or long-term changes in data, and always maintains a good ability to predict equipment temperature, providing accurate temperature prediction information for the stable operation of the equipment. Effectively utilize historical data. For accurate predictions, the results are stored in historical data sets, enriching the historical data resources of the model.Based on a richer historical data set, the model can better grasp the temperature change trends and patterns when predicting the temperature in the next time window, because it can learn more patterns and information from past successful predictions, avoiding starting from scratch for each prediction, and improving the stability and consistency of the prediction; when the operating status of the equipment changes, such as load increase, component aging, etc., resulting in new patterns in the temperature data, the technical solution can adjust the prediction ability by retraining the model, flexibly adapting to these changes, and will not become invalid due to equipment upgrades or changes in the use environment; this flexibility makes the solution more adaptable in long-term equipment monitoring and maintenance, and can provide reliable temperature prediction services for low-voltage electrical equipment in different working conditions and different usage stages, improve the operating safety and life of the equipment, and reduce the risk of failure caused by temperature anomalies.

[0082] One embodiment of the present invention provides a low-voltage multi-channel wireless temperature measurement device based on artificial intelligence, the device comprising:

[0083] The acquisition module is used to collect the multi-point temperature of low-voltage electrical equipment, transmit the collected multi-point temperature data to the central data processing unit through a wireless protocol, and pre-process the transmitted multi-point temperature data;

[0084] A feature extraction module is used to extract features based on preprocessed multi-point temperature data;

[0085] A graph neural network model training module is used to use the sensor locations in the low-voltage electrical equipment as nodes of the graph, the features extracted from the preprocessed temperature data as the features of the nodes of the graph, and the connection relationships between the sensors as edges to obtain a graph structure, and train a graph neural network model based on the graph structure;

[0086] The prediction module is used to input the data monitored in real time by the sensor into the trained graph neural network model to obtain the predicted value, and compare the difference between the predicted value and the detected value at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained; otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted.

[0087] In one embodiment of the present invention, the acquisition module includes:

[0088] The temperature data collection module is used to collect temperature data in real time according to a preset collection frequency through wireless temperature sensors installed at switch contacts, busbar connection points and cable connectors of low-voltage electrical equipment;

[0089] A transmission module, used to transmit the temperature data collected by the wireless temperature sensor to the central data processing unit through a wireless protocol, wherein the wireless protocol includes LoRa, ZigBee and Wi-Fi;

[0090] Correction module for the transmitted temperature data set , first calculate the first quartile and the third quartile , , will be lower than or higher The data are regarded as outliers and are corrected using interpolation.

[0091] In one embodiment of the present invention, the feature extraction module includes:

[0092] A time feature extraction module is used to extract time features from the preprocessed multi-point temperature data, wherein the time features include the average, maximum, minimum and standard deviation of the temperature in each preset time window;

[0093] The spatial feature extraction module is used to extract the spatial features of the pre-processed multi-point temperature data. The spatial features include: temperature gradient, temperature difference and relative temperature between different sensors. The temperature gradient is ,in, represents the temperature gradient, Indicates the low-voltage circuit temperature measured by sensor i, represents the low voltage circuit temperature measured by sensor j, represents the distance between sensors i and j, and the relative temperature is ,in, Indicates relative temperature;

[0094] Extract thermodynamic characteristics module, used to extract the heat transfer principle through the formula

[0095]

[0096] extracting thermodynamic characteristics from the multi-point temperature data, wherein m represents the mass of the circuit measured by the sensor, c represents the specific heat capacity of the constituent material of the circuit measured by the sensor, represents the temperature measured by the sensor at time t, represents the temperature measured by the sensor at time t-1, It represents the amount of heat transfer in the circuit measured by the sensor during the time period from t to t-1.

[0097] In one embodiment of the present invention, the training graph neural network model module includes:

[0098] A graph construction module is configured to treat each wireless temperature sensor in the low-voltage electrical equipment as a node in a graph, mark it with a unique identifier, i.e., a node number, combine the extracted time features, the extracted spatial features, and the extracted thermodynamic features as a node feature vector, construct graph edges based on the connection relationships of the graph, and encapsulate the node feature vectors and edge information into a graph structure;

[0099] Construct a graph neural network model module for constructing a graph neural network model. The graph neural network model adopts the graph convolution network in the GNN architecture. The graph neural network defines a class inherited from torch.nn.Module. The graph convolution network contains three layers of GCNConv graph convolution layers for extracting features from the graph structure. The first graph convolution layer converts the input node features into features of the feature dimension of the hidden layer through a graph convolution operation. The second graph convolution layer receives the output features of the feature dimension of the hidden layer of the first graph convolution layer and outputs features of the same dimension. The third graph convolution layer receives the output features of the feature dimension of the hidden layer of the second graph convolution layer and converts them into one-dimensional predicted temperature values.

[0100] The training module is used to input graph structure data into the constructed graph neural network model for training and obtain the trained graph neural network model.

[0101] In one embodiment of the present invention, the prediction module includes:

[0102] A second prediction value acquisition module is used to input the data monitored in real time by the sensor into the trained graph neural network model to obtain the first prediction value, and further input the first prediction value into the trained graph neural network model to obtain the second prediction value;

[0103] The correction prediction module is used to compare the second predicted value with the value actually detected by the sensor. If the difference between the second predicted value and the value actually detected by the sensor exceeds a preset threshold, the value actually detected by the sensor is used as incremental data to retrain the model. If it does not exceed the preset threshold, the prediction result is stored and added to the historical data set, and the temperature of the low-voltage electrical equipment in the next time window is continued to be predicted based on the historical data set.

[0104] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A low-voltage multi-channel wireless temperature measurement method based on artificial intelligence, characterized in that: The method comprises: Collect multi-point temperatures of low-voltage electrical equipment, transmit the collected multi-point temperature data to the central data processing unit via wireless protocol, and pre-process the transmitted multi-point temperature data; Extract features based on preprocessed multi-point temperature data, including: Extracting time features from the preprocessed multi-point temperature data, the time features including: the average, maximum, minimum, and standard deviation of the temperature within each preset time window; Extract the spatial features from the pre-processed multi-point temperature data, which include temperature gradient, temperature difference and relative temperature between different sensors. ,in, represents the temperature gradient, Indicates the low-voltage circuit temperature measured by sensor i, represents the low voltage circuit temperature measured by sensor j, represents the distance between sensors i and j, and the relative temperature is ,in, Indicates relative temperature; According to the heat transfer principle, the formula extracting thermodynamic characteristics from the multi-point temperature data, wherein m represents the mass of the circuit measured by the sensor, c represents the specific heat capacity of the constituent material of the circuit measured by the sensor, represents the temperature measured by the sensor at time t, represents the temperature measured by the sensor at time t-1, It represents the amount of heat transfer in the circuit measured by the sensor during the time period from t to t-1; The sensor locations in the low-voltage electrical equipment are used as nodes of the graph, the features extracted from the preprocessed temperature data are used as features of the nodes of the graph, and the connection relationships between the sensors are used as edges to obtain a graph structure, and a graph neural network model is trained based on the graph structure; The data monitored in real time by the sensor is input into the trained graph neural network model to obtain the predicted value. The difference between the predicted value and the detected value is compared at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained. Otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted.

2. The low-voltage multi-channel wireless temperature measurement method based on artificial intelligence according to claim 1 is characterized in that: Collect multi-point temperatures of low-voltage electrical equipment, transmit the collected multi-point temperature data to the central data processing unit through wireless protocol, and pre-process the transmitted multi-point temperature data, including: Wireless temperature sensors installed at the switch contacts, busbar connection points, and cable connectors of low-voltage electrical equipment collect temperature data in real time at a preset collection frequency. Transmitting temperature data collected by the wireless temperature sensor to a central data processing unit via a wireless protocol, wherein the wireless protocol includes LoRa, ZigBee, and Wi-Fi; For the transmitted temperature dataset , first calculate the first quartile and the third quartile , , will be lower than or higher The data are regarded as outliers and are corrected using interpolation.

3. The low-voltage multi-channel wireless temperature measurement method based on artificial intelligence according to claim 1 is characterized in that: The sensor positions in the low-voltage electrical equipment are used as nodes of a graph, the features extracted from the preprocessed temperature data are used as features of the nodes of the graph, and the connection relationships between the sensors are used as edges to obtain a graph structure, and a graph neural network model is trained based on the graph structure, including: Each wireless temperature sensor in the low-voltage electrical equipment is regarded as a node in the graph and marked with a unique identifier, i.e., a node number. The extracted time feature, the spatial feature, and the thermodynamic feature are combined as a node feature vector. The edges of the graph are constructed based on the connection relationship of the graph, and the node feature vector and edge information are encapsulated into a graph structure. Construct a graph neural network model, which uses a graph convolutional network in the GNN architecture. The graph neural network defines a class inherited from torch.nn.Module. The graph convolutional network contains three GCNConv graph convolution layers for extracting features from the graph structure. The first graph convolution layer converts the input node features into features of the feature dimension of the hidden layer through a graph convolution operation. The second graph convolution layer receives the output features of the feature dimension of the hidden layer of the first graph convolution layer and outputs features of the same dimension. The third graph convolution layer receives the output features of the feature dimension of the hidden layer of the second graph convolution layer and converts them into a one-dimensional predicted temperature value. Input the graph structure data into the constructed graph neural network model for training to obtain the trained graph neural network model.

4. The low-voltage multi-channel wireless temperature measurement method based on artificial intelligence according to claim 1, characterized in that: The real-time monitoring data of the sensor is input into the trained graph neural network model to obtain the predicted value. The difference between the predicted value and the detected value is compared at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained. Otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted, including: Input the real-time monitoring data of the sensor into the trained graph neural network model to obtain a first prediction value, and continue to input the first prediction value into the trained graph neural network model to obtain a second prediction value; The second predicted value is compared with the value actually detected by the sensor. If the difference between the second predicted value and the value actually detected by the sensor exceeds the preset threshold, the value actually detected by the sensor is used as incremental data to retrain the model. If it does not exceed the preset threshold, the prediction result is stored and added to the historical data set. The temperature of the low-voltage electrical equipment in the next time window is continued to be predicted based on the historical data set.

5. A low-voltage multi-channel wireless temperature measurement device based on artificial intelligence, characterized in that: The device comprises: The acquisition module is used to collect the multi-point temperature of low-voltage electrical equipment, transmit the collected multi-point temperature data to the central data processing unit through a wireless protocol, and pre-process the transmitted multi-point temperature data; The feature extraction module is used to extract features based on preprocessed multi-point temperature data, including: A time feature extraction module is used to extract time features from the preprocessed multi-point temperature data, wherein the time features include the average, maximum, minimum and standard deviation of the temperature in each preset time window; The spatial feature extraction module is used to extract the spatial features of the pre-processed multi-point temperature data. The spatial features include: temperature gradient, temperature difference and relative temperature between different sensors. The temperature gradient is ,in, represents the temperature gradient, Indicates the low-voltage circuit temperature measured by sensor i, represents the low voltage circuit temperature measured by sensor j, represents the distance between sensors i and j, and the relative temperature is ,in, Indicates relative temperature; Extract thermodynamic characteristics module, used to extract the heat transfer principle through the formula extracting thermodynamic characteristics from the multi-point temperature data, wherein m represents the mass of the circuit measured by the sensor, c represents the specific heat capacity of the constituent material of the circuit measured by the sensor, represents the temperature measured by the sensor at time t, represents the temperature measured by the sensor at time t-1, It represents the heat transfer of the circuit measured in the sensor during the time period from t to t-1; A graph neural network model training module is used to use the sensor locations in the low-voltage electrical equipment as nodes of the graph, the features extracted from the preprocessed temperature data as the features of the nodes of the graph, and the connection relationships between the sensors as edges to obtain a graph structure, and train a graph neural network model based on the graph structure; The prediction module is used to input the data monitored in real time by the sensor into the trained graph neural network model to obtain the predicted value, and compare the difference between the predicted value and the detected value at the end of the preset time window. If the difference exceeds the preset threshold, the model is retrained; otherwise, the temperature of the low-voltage electrical equipment in the next time window is predicted.

6. The low-voltage multi-channel wireless temperature measurement device based on artificial intelligence according to claim 5, characterized in that: The acquisition module includes: The temperature data collection module is used to collect temperature data in real time according to a preset collection frequency through wireless temperature sensors installed at switch contacts, busbar connection points and cable connectors of low-voltage electrical equipment; A transmission module, used to transmit the temperature data collected by the wireless temperature sensor to the central data processing unit through a wireless protocol, wherein the wireless protocol includes LoRa, ZigBee and Wi-Fi; Correction module for the transmitted temperature data set , first calculate the first quartile and the third quartile , , will be lower than or higher The data are regarded as outliers and are corrected using interpolation.

7. The low-voltage multi-channel wireless temperature measurement device based on artificial intelligence according to claim 5, characterized in that: The training graph neural network model module includes: A graph construction module is configured to treat each wireless temperature sensor in the low-voltage electrical equipment as a node in a graph, mark it with a unique identifier, i.e., a node number, combine the extracted time features, the extracted spatial features, and the extracted thermodynamic features as a node feature vector, construct graph edges based on the connection relationships of the graph, and encapsulate the node feature vectors and edge information into a graph structure; Construct a graph neural network model module for constructing a graph neural network model. The graph neural network model adopts the graph convolution network in the GNN architecture. The graph neural network defines a class inherited from torch.nn.Module. The graph convolution network contains three layers of GCNConv graph convolution layers for extracting features from the graph structure. The first graph convolution layer converts the input node features into features of the feature dimension of the hidden layer through a graph convolution operation. The second graph convolution layer receives the output features of the feature dimension of the hidden layer of the first graph convolution layer and outputs features of the same dimension. The third graph convolution layer receives the output features of the feature dimension of the hidden layer of the second graph convolution layer and converts them into one-dimensional predicted temperature values. The training module is used to input graph structure data into the constructed graph neural network model for training and obtain the trained graph neural network model.

8. The low-voltage multi-channel wireless temperature measurement device based on artificial intelligence according to claim 5, characterized in that: The prediction module includes: A second prediction value acquisition module is used to input the data monitored in real time by the sensor into the trained graph neural network model to obtain the first prediction value, and further input the first prediction value into the trained graph neural network model to obtain the second prediction value; The correction prediction module is used to compare the second predicted value with the value actually detected by the sensor. If the difference between the second predicted value and the value actually detected by the sensor exceeds a preset threshold, the value actually detected by the sensor is used as incremental data to retrain the model. If it does not exceed the preset threshold, the prediction result is stored and added to the historical data set, and the temperature of the low-voltage electrical equipment in the next time window is continued to be predicted based on the historical data set.

Images