Novel digital intelligent monitoring system based on distribution network station area node heating
By designing a new digital and intelligent monitoring system in the distribution network station area, using high-precision sensors and machine learning-based prediction models, the problem of difficulty in real-time, continuous monitoring and in-depth analysis in traditional manual inspections is solved, and accurate prediction and multi-level early warning of node heating are achieved, which significantly improves the safety and reliability of the distribution network station area.
Patent Information
- Application Number
- CN202411840479.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-13
- Publication Date
- 2025-05-13
AI Technical Summary
Traditional distribution network station monitoring mainly relies on manual inspection, making it difficult to achieve real-time and continuous monitoring of nodes, and it is impossible to deeply explore and comprehensively analyze a large number of temperature, electrical parameters and environmental data, resulting in difficult time discovering and predicting node heating problems.
A new digital monitoring system based on heating of nodes in the distribution network station area is designed, including a collection module, a data transmission module, a data processing center and a monitoring terminal. The acquisition module collects temperature, electrical parameters and environmental data through high-precision sensors. The data transmission module uses wireless transmission to transmit data to the data processing center. The data processing center uses algorithms based on machine learning or deep learning to establish a node heating prediction model, generates early warning information, and displays and manages it through monitoring terminals.
It realizes accurate judgment of the node's heating status and advance prediction of trends, and timely issues multi-level warning information to avoid the expansion of faults caused by node heating problems, which significantly improves the safety and reliability of the distribution network station area operation.
Smart Images
Figure CN119995139A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of new digital and intelligent monitoring of node heating, and specifically to a new digital and intelligent monitoring system for node heating in a distribution network area. Background Art
[0002] With the continuous growth of electricity demand and the increasing complexity of distribution network substation architecture, node heating problem has become a major hidden danger to the safe and stable operation of distribution network. Traditional distribution network substation monitoring mainly relies on manual inspection, which has many disadvantages. On the one hand, manual inspection is difficult to achieve real-time and continuous monitoring of many nodes. The data collection interval is long and easily interfered by human factors, which makes it difficult to discover heating problems in time. On the other hand, manual inspection is extremely limited in data analysis and processing capabilities. It is impossible to conduct in-depth mining and comprehensive analysis of a large amount of temperature, electrical parameters and environmental data, making it difficult to accurately predict the node heating trend and take effective measures in advance.
[0003] In recent years, although some monitoring technologies have developed, there are still some shortcomings. Some early monitoring systems can only collect a single type of data. For example, they only focus on temperature data and ignore the synergistic effects of electrical parameters and environmental factors on node heating, resulting in the judgment of the cause of heating is not comprehensive and accurate. At the same time, the stability and security of data transmission, the accuracy and timeliness of model predictions, etc. need to be further improved. Therefore, there is an urgent need for a new type of digital intelligent monitoring system that can comprehensively, accurately and real-time monitor the heating conditions of distribution network substation nodes, and effectively ensure the safe and reliable operation of the distribution network system through intelligent analysis and processing. Summary of the invention
[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: A new digital intelligent monitoring system based on heating of distribution network nodes, including:
[0005] The acquisition modules are respectively arranged at each key heating monitoring node in the distribution network area, and are used to collect temperature data, electrical parameter data and environmental data of the corresponding nodes. The acquisition modules include temperature sensors, electrical parameter acquisition modules and environmental sensors;
[0006] A data transmission module is used to transmit the data collected by the sensor node to the data processing center. The data transmission module adopts a wireless transmission method, including but not limited to Wi-Fi, Bluetooth, ZigBee or 4G / 5G communication module;
[0007] A data processing center receives data from the data transmission module, stores, analyzes and processes the data, and the data processing center includes a data storage unit, a data analysis unit and a data processing unit, wherein the data storage unit is used to store the received data, the data analysis unit analyzes the data based on a preset algorithm to determine the heating status and trend of the node, and the data processing unit is used to generate corresponding control instructions or warning information according to the analysis results;
[0008] The monitoring terminal is connected to the data processing center and is used to receive and display the node heating status information, warning information and historical data query results sent by the data processing center. The monitoring terminal includes a display screen and an operation interface, which can realize human-computer interaction operations so that users can set system parameters, view and manage data.
[0009] Preferably, the temperature sensor is a high-precision thermistor temperature sensor or a thermocouple temperature sensor, and its measurement accuracy is within ±1°C.
[0010] Preferably, the electrical parameter acquisition module is used to acquire electrical parameters such as voltage, current, power factor, etc. at the node, and the electrical parameter acquisition module has high-precision sampling capability.
[0011] Preferably, the environmental sensor includes one or more combinations of humidity sensors, light sensors and air pressure sensors, which are used to collect environmental information around the monitoring node so as to comprehensively consider the impact of environmental factors on node temperature when analyzing the cause of node heating.
[0012] Preferably, the data analysis unit of the data processing center adopts a data analysis algorithm based on machine learning or deep learning, and establishes a node heating prediction model through learning and training of a large amount of historical data, so as to realize early prediction of node heating trends.
[0013] Preferably, the method for establishing the node heating prediction model includes data collection and organization, data preprocessing, model selection and training, model evaluation and optimization, and model deployment and updating.
[0014] Preferably, when generating warning information, the data processing unit of the data processing center sets warning signals of different levels according to the severity of node fever. The warning signals include sound warnings, light warnings, and sending text message or email warnings to designated managers. At the same time, the warning information includes node location information, fever temperature data, and fever trend analysis results.
[0015] Preferably, the method of using the digital intelligence monitoring system is as follows:
[0016] Step 1: Install sensor nodes at key nodes in the distribution network area, ensure that the sensor nodes are properly connected to the data transmission module, and complete the startup and initialization settings of various components such as the data processing center and monitoring terminal, including setting system parameters such as data collection frequency and warning threshold;
[0017] Step 2: The sensor node collects the temperature data, electrical parameter data and environmental data of the node in real time according to the set data collection frequency, and transmits the collected data to the data processing center through the data transmission module;
[0018] Step 3: After the data processing center receives the data, the data storage unit stores the data, and the data analysis unit calls the node heating prediction model to analyze the data, extracts data features, and combines historical data and preset algorithms to determine the node heating status and trend, and generates analysis results;
[0019] Step 4: Based on the analysis results, if the node has an abnormal heating state, the data processing unit generates different levels of warning information according to the severity of the heating, and issues an alarm through sound warning, light warning, and sending SMS or email warnings to designated managers;
[0020] Step 5. The monitoring terminal receives and displays the node heating status information, warning information and historical data query results sent by the data processing center in real time. Authorized users can adjust system parameters, view and manage data through the operation interface of the monitoring terminal, including viewing detailed data of specific nodes, modifying warning thresholds, remotely controlling related equipment, etc., so as to timely understand the operating status of the distribution network area and make corresponding decisions.
[0021] The present invention provides a new digital intelligent monitoring system based on heating of distribution network substation nodes. It has the following beneficial effects:
[0022] This new digital intelligent monitoring system based on node heating in the distribution network area can accurately collect temperature, electrical parameters and environmental data with the help of high-precision sensor nodes, and accurately judge the node heating status and trend with advanced data analysis algorithms and models, and issue multi-level warning information in time, effectively avoiding the expansion of faults caused by node heating problems, and significantly improving the safety and reliability of distribution network operation. The node heating prediction model built based on machine learning or deep learning algorithms can deeply mine the value of data, fully consider the correlation of multiple factors, predict the heating trend in advance, and provide forward-looking decision-making basis for operation and maintenance personnel, helping to achieve preventive Maintenance, reducing the probability of power outages, and ensuring the continuity of power supply. Through the monitoring terminal, operation and maintenance management personnel can obtain real-time information and historical data on node heating anytime and anywhere, and conveniently adjust system parameters, remotely control related equipment and other operations, which greatly improves the flexibility and efficiency of operation and maintenance management. Especially in response to emergencies, it can respond quickly and take effective measures. It integrates a variety of environmental sensors, comprehensively analyzes the impact of environmental factors such as humidity, light, and air pressure on node heating, and makes the judgment of the cause of node heating more comprehensive and accurate, which helps to formulate more targeted operation and maintenance strategies and further optimize the operation and management of distribution network substations. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 This is a logic flow chart of the new digital intelligent monitoring system based on the heating of distribution network area nodes in the present invention; DETAILED DESCRIPTION
[0024] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0025] For examples, see Figure 1 The present invention provides a technical solution: a new digital intelligent monitoring system based on heating of distribution network nodes, including:
[0026] The acquisition modules are respectively arranged at each key heating monitoring node in the distribution network area, and are used to collect temperature data, electrical parameter data and environmental data of the corresponding nodes. The acquisition modules include temperature sensors, electrical parameter acquisition modules and environmental sensors. The temperature sensors use high-precision thermistor temperature sensors or thermocouple temperature sensors with a measurement accuracy within ±1°C. The electrical parameter acquisition modules are used to collect electrical parameters such as voltage, current, power factor and the like at the nodes. The electrical parameter acquisition modules have high-precision sampling capabilities. The environmental sensors include one or more combinations of humidity sensors, light sensors and air pressure sensors, and are used to collect environmental information around the monitoring nodes, so as to comprehensively consider the impact of environmental factors on node temperature when analyzing the causes of node heating;
[0027] A data transmission module is used to transmit the data collected by the sensor node to the data processing center. The data transmission module adopts a wireless transmission method, including but not limited to Wi-Fi, Bluetooth, ZigBee or 4G / 5G communication module;
[0028] A data processing center receives data from the data transmission module, and stores, analyzes and processes the data. The data processing center includes a data storage unit, a data analysis unit and a data processing unit, wherein the data storage unit is used to store the received data, the data analysis unit analyzes the data based on a preset algorithm to determine the heating status and trend of the node, and the data processing unit is used to generate corresponding control instructions or early warning information according to the analysis results. The data analysis unit of the data processing center adopts a data analysis algorithm based on machine learning or deep learning, and establishes a node heating prediction model through learning and training of a large amount of historical data, so as to realize the early prediction of the heating trend of the node;
[0029] A monitoring terminal is connected to the data processing center and is used to receive and display the node heating status information, warning information and historical data query results sent by the data processing center. The monitoring terminal includes a display screen and an operation interface, which can realize human-computer interaction so that users can set system parameters, view and manage data;
[0030] The steps to establish the node heating prediction model are as follows:
[0031] Data collection and organization
[0032] Extensively collect historical data of each monitoring node in the distribution network under different operating conditions, including long-term temperature data, corresponding electrical parameter data, and environmental data, conduct integrity checks and preliminary screening on the collected data, and remove data records with obvious errors or serious omissions;
[0033] Data preprocessing
[0034] Data cleaning: For the filtered data, further outliers are processed. For temperature data, if the temperature value of a sampling point obviously deviates from the temperature value of its adjacent time points and exceeds the reasonable range, it is judged as an outlier and replaced or corrected using data interpolation or outlier correction methods based on statistical models.
[0035] Data normalization, in order to improve the efficiency and accuracy of model training, the feature data of different magnitudes are normalized. For example, for temperature data, it can be mapped to the [0,1] interval using the formula where x norm is the normalized temperature value, x is the original temperature value, and x m i n and x max are the minimum and maximum values in the temperature data, respectively. A similar normalization method is used for electrical parameters and environmental data to give them a unified dimension and data distribution range;
[0036] Feature engineering: extracting time series features and constructing electrical parameter correlation features, integrating environmental factor features;
[0037] Model selection and training
[0038] According to the data characteristics and prediction requirements, the deep learning algorithm is selected as the basic model. The preprocessed data is divided into training set, validation set and test set in the ratio of 70%, 15% and 15%. The decision tree model is selected, and the gradient descent method is used to iteratively optimize the model parameters to minimize the loss function. During the training process, the performance indicators of the model are evaluated on the validation set and the hyperparameters of the model are adjusted. For the deep learning model, the network structure is first determined, and then the back propagation algorithm is used in combination with the optimizer to train the network parameters. During the training process, the model performance is also monitored on the validation set, the hyperparameters are adjusted, and the early stopping method is used to prevent overfitting, that is, the training is stopped when the performance of the model on the validation set no longer improves;
[0039] Model evaluation and optimization
[0040] Use the test set to comprehensively evaluate the trained model, calculate the root mean square error (RMSE) used to measure the average deviation between the predicted temperature value and the true temperature value, the average absolute error (ABE) that reflects the average absolute value of the prediction error, as well as the accuracy and recall rate. Through these indicators, we can fully understand the prediction accuracy, stability and reliability of the model. According to the evaluation results;
[0041] If the model performance does not meet the expected requirements, the model is further optimized. The optimization strategies include increasing the amount of training data, adjusting the model structure, improving feature engineering, and adopting ensemble learning methods. Then, the model training and evaluation steps are repeated until the model performance meets the actual application requirements.
[0042] Model deployment and update
[0043] The final node heating prediction model after evaluation and optimization is integrated into the data analysis unit of the data processing center, so that it can receive new data from the data transmission module in real time and perform online prediction. As time goes by and the operating conditions of the distribution network change, new data is constantly generated, and new historical data is collected regularly. The above data collection, preprocessing, model training, evaluation and optimization steps are repeated to update the node heating prediction model.
[0044] The usage of the digital intelligence monitoring system is as follows:
[0045] Step 1: Install sensor nodes at key nodes in the distribution network area, ensure that the sensor nodes are properly connected to the data transmission module, and complete the startup and initialization settings of various components such as the data processing center and monitoring terminal, including setting system parameters such as data collection frequency and warning threshold;
[0046] Step 2: The sensor node collects the temperature data, electrical parameter data and environmental data of the node in real time according to the set data collection frequency, and transmits the collected data to the data processing center through the data transmission module;
[0047] Step 3: After the data processing center receives the data, the data storage unit stores the data, and the data analysis unit calls the node heating prediction model to analyze the data, extracts data features, and combines historical data and preset algorithms to determine the node heating status and trend, and generates analysis results;
[0048] Step 4: Based on the analysis results, if the node has an abnormal heating state, the data processing unit generates different levels of warning information according to the severity of the heating, and issues an alarm through sound warning, light warning, and sending SMS or email warnings to designated managers;
[0049] Step 5. The monitoring terminal receives and displays the node heating status information, warning information and historical data query results sent by the data processing center in real time. Authorized users can adjust system parameters, view and manage data through the operation interface of the monitoring terminal, including viewing detailed data of specific nodes, modifying warning thresholds, remotely controlling related equipment, etc., so as to timely understand the operating status of the distribution network area and make corresponding decisions.
[0050] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.
Claims
1. A new digital intelligent monitoring system based on heating of distribution network nodes, characterized in that: include: The acquisition modules are respectively arranged at each key heating monitoring node in the distribution network area, and are used to collect temperature data, electrical parameter data and environmental data of the corresponding nodes. The acquisition modules include temperature sensors, electrical parameter acquisition modules and environmental sensors; A data transmission module is used to transmit the data collected by the sensor nodes to the data processing center; A data processing center receives data from the data transmission module and stores, analyzes and processes the data. The data processing center includes a data storage unit, a data analysis unit and a data processing unit; The monitoring terminal is connected to the data processing center and is used to receive and display the node heating status information, warning information and historical data query results sent by the data processing center.
2. According to claim 1, a new digital intelligent monitoring system based on heating of distribution network area nodes is characterized by: The temperature sensor adopts a high-precision thermistor temperature sensor or a thermocouple temperature sensor, and its measurement accuracy is within ±1°C.
3. According to claim 1, a new digital intelligent monitoring system based on heating of distribution network area nodes is characterized by: The electrical parameter acquisition module is used to acquire electrical parameters such as voltage, current, power factor, etc. at the node, and the electrical parameter acquisition module has high-precision sampling capability.
4. According to claim 1, a new digital intelligent monitoring system based on heating of distribution network area nodes is characterized by: The environmental sensor includes one or more combinations of humidity sensors, light sensors and air pressure sensors, which are used to collect environmental information around the monitoring node so as to comprehensively consider the impact of environmental factors on node temperature when analyzing the cause of node heating.
5. According to claim 1, a new digital intelligence monitoring system based on heating of distribution network area nodes is characterized by: The data analysis unit of the data processing center adopts a data analysis algorithm based on machine learning or deep learning, and establishes a node heating prediction model through learning and training of a large amount of historical data, so as to realize early prediction of node heating trends.
6. According to claim 1, a new digital intelligent monitoring system based on heating of distribution network area nodes is characterized by: The method for establishing the node heating prediction model includes data collection and organization, data preprocessing, model selection and training, model evaluation and optimization, and model deployment and updating.
7. According to claim 1, a new digital intelligence monitoring system based on heating of distribution network area nodes is characterized by: When generating warning information, the data processing unit of the data processing center sets warning signals of different levels according to the severity of node fever. The warning signals include sound warnings, light warnings, and sending text messages or email warnings to designated managers. At the same time, the warning information includes node location information, fever temperature data, and fever trend analysis results.
8. According to claim 1, a new digital intelligent monitoring system based on heating of distribution network area nodes is characterized by: The method of using the digital intelligence monitoring system is as follows: Step 1: Install sensor nodes at key nodes in the distribution network area, ensure that the sensor nodes are properly connected to the data transmission module, and complete the startup and initialization settings of various components such as the data processing center and monitoring terminal, including setting system parameters such as data collection frequency and warning threshold; Step 2: The sensor node collects the temperature data, electrical parameter data and environmental data of the node in real time according to the set data collection frequency, and transmits the collected data to the data processing center through the data transmission module; Step 3: After the data processing center receives the data, the data storage unit stores the data, and the data analysis unit calls the node heating prediction model to analyze the data, extracts data features, and combines historical data and preset algorithms to determine the node heating status and trend, and generates analysis results; Step 4: Based on the analysis results, if the node has an abnormal heating state, the data processing unit generates different levels of warning information according to the severity of the heating, and issues an alarm through sound warning, light warning, and sending SMS or email warnings to designated managers; Step 5: The monitoring terminal receives and displays the node heating status information, warning information and historical data query results sent by the data processing center in real time. Authorized users can adjust system parameters, view and manage data through the operation interface of the monitoring terminal.