Intelligent height limit control system of transformer substation for laser technology
By combining high-precision three-dimensional laser scanning technology and deep learning algorithms, adaptive recognition and accurate measurement of the substation's intelligent height limit control system are solved, and the problem of insufficient identification and stability of the height limit system in the existing technology is improved. The accuracy and intelligence level of height limit control are achieved.
Patent Information
- Application Number
- CN202411048107.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing substation height limit system cannot adapt to complex environments and variable needs. Mechanical systems are susceptible to external environments. Infrared induction systems are susceptible to light and temperature interference, resulting in false alarms or missed reports, and cannot achieve three-dimensional high-precision measurement and Adaptively identify objects of different shapes and sizes.
High-precision three-dimensional laser scanning technology combined with deep learning algorithms is used to adaptively identify objects through convolutional neural network models, determine whether they exceed the set height, and remote monitoring and height-limiting operations are performed through wireless communication.
It significantly improves the accuracy and intelligence level of height limit control, can accurately identify objects in complex environments, reduce false alarms and missed reports, and the system is stable and reliable, adapting to the specific needs of different substations.
Smart Images

Figure CN119027870A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of transformer substation safety, and in particular to an intelligent height-limiting control system for transformer substations using laser technology. Background Art
[0002] With the rapid development of the power industry and the advancement of smart grid construction, substations, as the core components of the power system, have increasingly higher requirements for safety and reliability. Safety monitoring of the internal space of substations has become particularly critical. Among them, height limit control is one of the important measures to ensure the internal safety of substations. It can effectively prevent over-height vehicles or equipment from entering the substation and avoid collisions with high-voltage equipment in the substation, thereby preventing possible safety accidents.
[0003] However, traditional height limit systems mostly use mechanical or infrared sensing methods. The mechanical height limit system limits the height of vehicles or equipment by setting a physical device at a fixed height. Although this method is simple and direct, it cannot adapt to the complex environment and changing needs of different substations. At the same time, the mechanical device is easily affected by external environmental factors, such as wind, rain and corrosion, resulting in failure of height limit control. The infrared sensing height limit system detects the height of vehicles or equipment through infrared rays, but this method is easily affected by light and temperature environmental factors, resulting in false alarms or missed alarms.
[0004] Therefore, how to build an intelligent height limit control system for substations that can combine high-precision three-dimensional laser scanning technology with deep learning algorithms has become an important direction for the current development of substation safety technology. However, most of the intelligent height limit control systems for substations using laser technology on the market can only meet some of the requirements of the above-mentioned characteristics, and cannot achieve three-dimensional high-precision measurement of the internal space of the substation, and adaptively identify objects of different shapes and sizes through powerful feature learning and recognition capabilities. Therefore, the development of an intelligent height limit control system for substations using laser technology that can comprehensively realize the above-mentioned characteristics has important practical significance and broad market prospects for improving the accuracy and intelligence level of height limit control. Summary of the invention
[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and provide an intelligent height limit control system for substations using laser technology. It can use a convolutional neural network model through a deep learning algorithm module to adaptively identify objects of different shapes and sizes, and use a deep learning model to identify the processed data to determine whether there are objects exceeding the set height entering the substation, so that it can handle complex spatial scenes and improve the accuracy of height limit control.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a substation intelligent height limit control system, characterized in that the system includes the following components:
[0007] Laser scanning module: uses high-precision 3D laser scanning technology to scan the internal space of the substation in real time and obtain the 3D coordinate data of objects in the space;
[0008] Data processing module: responsible for receiving the three-dimensional coordinate data obtained by the laser scanning module, and performing preprocessing and feature extraction for subsequent deep learning algorithm recognition;
[0009] Deep learning algorithm module: uses a pre-trained deep learning model to identify the processed data and determine whether there are objects exceeding the set height entering the substation. At the same time, it can be adaptively updated based on historical data and real-time data to improve the accuracy of recognition;
[0010] Control module: Based on the recognition results of the deep learning algorithm module, control the corresponding actuator to perform height-limiting operations, such as starting the alarm light, automatically shutting down related equipment, or starting emergency braking;
[0011] Remote monitoring module: The system's real-time status, identification results and height limit operation information are transmitted to the remote monitoring center through wireless communication technology, so that management personnel can conduct real-time monitoring and operation.
[0012] Furthermore, the laser scanning module has the following specific steps:
[0013] (1) Startup and calibration: Start the laser scanning device and perform necessary calibration to ensure the accuracy of the scanned data;
[0014] (2) Scanning operation: according to the preset scanning frequency and scanning range, the laser beam is emitted into the internal space of the substation, and the laser signal reflected by the target object is received;
[0015] (3) Data collection: Collect the three-dimensional coordinate data obtained by laser scanning, including the location, shape and height information of the target object.
[0016] Furthermore, the data processing module uses a Gaussian filtering algorithm to pre-process the three-dimensional coordinate data acquired by the laser scanning module. The expression of the Gaussian filtering algorithm is: Among them, G(x,y) represents the value of the Gaussian filter function at the coordinate (x,y), σ is the standard deviation of the Gaussian function, which determines the width of the filter. The algorithm smoothes the original data by suppressing high-frequency noise and retaining low-frequency signals to improve the recognition accuracy of the subsequent deep learning algorithm module.
[0017] Furthermore, the deep learning algorithm module specifically includes the following steps:
[0018] (1) Model loading: Load a pre-trained deep learning model that can recognize objects of different shapes and sizes and determine whether their height exceeds a set threshold;
[0019] (2) Model reasoning: The feature data transmitted by the data processing module is input into the deep learning model, and the deep learning model is used to reason about the input feature data to obtain the height information of the target object and the judgment result of whether it exceeds the threshold;
[0020] (3) Control signal generation: Generate corresponding control signals based on the results of model reasoning.
[0021] Furthermore, the deep learning algorithm module adopts a convolutional neural network (CNN) model to extract features from the preprocessed three-dimensional coordinate data through convolution operations, and transforms and selects features through activation functions and pooling layer components to achieve recognition of objects in the internal space of the substation, wherein the mathematical expression of the convolution operation is: w(m,n), where s(i,j) is the pixel value at position (i,j) in the output feature map, X is the feature map obtained after preprocessing the input 3D coordinate data, W is the convolution kernel, which contains learnable weights, m and n are the size parameters of the convolution kernel, X(i+m,j+n) represents the pixel value corresponding to the current position of the convolution kernel in the feature map, and w(m,n) represents the weight value of the convolution kernel at position (m,n). Through this model, the deep learning algorithm module can adaptively identify objects of different shapes and sizes, and control the corresponding actuator to perform height limit operations according to the recognition results.
[0022] Furthermore, the deep learning algorithm module uses mean square error (MSE) as a loss function to optimize the prediction performance of the model. The deep learning algorithm module calculates the mean square error loss function by the following mathematical formula: Where: MSE is the mean square error, N is the number of samples, y i is the true label value of the i-th sample, is the predicted value of the deep learning model for the i-th sample. By minimizing the loss function, the deep learning algorithm module can adaptively adjust its internal parameters to improve the recognition accuracy of objects in the internal space of the substation.
[0023] Furthermore, the deep learning algorithm module adopts an anomaly detection algorithm to identify and respond to abnormal conditions in the internal space of the substation in real time. For the anomaly detection algorithm, the standard deviation and mean of the observed values are calculated, and the formula is: Among them, x i is the ith observation, N is the total number of observations, μ is the mean of these observations, Where σ is the standard deviation of these observations. For the threshold, it is usually set based on the standard deviation, such as τ = k·σ, where k is a preset constant. For a new observation x new , if it satisfies |x new -μ|>τ, it is judged as abnormal. During the operation of the substation, the deep learning algorithm module will perform real-time analysis through the above-mentioned anomaly detection algorithm. Once an abnormal situation is detected, the control module will automatically trigger the preset response measures based on the recognition results of the deep learning algorithm module, including but not limited to starting the alarm, adjusting system parameters, and shutting down related equipment to ensure the safe operation of the substation.
[0024] Furthermore, the remote monitoring module receives the operation information transmitted by the control module, and transmits the system's real-time status, identification results, and height limit operation information to the remote monitoring center through wireless communication technology. The management personnel of the remote monitoring center can view the height limit control status of the substation in real time through the monitoring center computer or mobile terminal, and perform necessary operations and management.
[0025] Furthermore, the system also includes a user interaction interface, which allows managers to view the system's operating status, identification results, and height limit operation information in real time through a graphical interface, and provides interactive functions for parameter setting and function configuration, so that managers can adjust the system's operating parameters and configuration according to actual needs.
[0026] Furthermore, the system also includes an automatic calibration module, which is used to automatically calibrate the laser scanning module regularly or according to preset conditions to ensure its scanning precision and accuracy.
[0027] Compared with the existing technology, the intelligent height limit control system for substations using laser technology has the following advantages:
[0028] Beneficial effects:
[0029] 1. The present invention adopts a convolutional neural network model through a deep learning algorithm module to identify and analyze the three-dimensional coordinate data obtained by the laser scanning module, so that it can adaptively learn and identify objects of different shapes and sizes, and more accurately identify different objects in the internal space of the substation, thereby significantly improving the accuracy of height limit control. At the same time, the deep learning model has a strong self-learning ability and can be adaptively updated according to historical data and real-time data, so that the system can be continuously optimized and improved to adapt to the specific environment and needs of different substations.
[0030] 2. The present invention adopts high-precision three-dimensional laser scanning technology through a laser scanning module. The high-precision three-dimensional laser scanning technology can obtain the three-dimensional coordinate data of objects in the internal space of the substation in real time and accurately, providing a reliable data basis for subsequent object recognition and height limit control. At the same time, the laser scanning module has a fast scanning speed and can complete the scanning of the entire internal space of the substation in a short time, ensuring that the system can monitor and respond to changes in the substation in real time. Moreover, the laser scanning module is not easily affected by environmental factors, such as light and temperature, making the system more stable and reliable.
[0031] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0033] Figure 1 This is the process operation diagram of the intelligent height limit control system for substations using laser technology. DETAILED DESCRIPTION
[0034] 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 them. 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.
[0035] Example 1
[0036] This embodiment describes in detail the operation process of the intelligent height limit control system for substations using laser technology in actual applications. First, the laser scanning device is activated and accurately calibrated. The calibration process includes accurately aligning the laser transmitter and the receiver to ensure the accuracy of the scanning data. According to the preset scanning frequency and range, the laser scanning module emits a laser beam into the internal space of the substation. After encountering an object, the laser beam will be reflected back and captured by the receiver. The receiver converts the captured laser signal into three-dimensional coordinate data of the object, including position, shape and height information. These data are transmitted to the data processing module in real time. After the data processing module receives the three-dimensional coordinate data transmitted by the laser scanning module, it uses the Gaussian filtering algorithm for preprocessing. The Gaussian filtering algorithm is expressed as follows:
[0037]
[0038] The original data is smoothed by this algorithm, where G(x, y) represents the value of the Gaussian filter function at the coordinate (x, y), and σ is the standard deviation of the Gaussian function, which determines the width of the filter. By suppressing high-frequency noise and retaining low-frequency signals, the recognition accuracy of the subsequent deep learning algorithm module is improved. The deep learning algorithm module loads a pre-trained convolutional neural network (CNN) model, which can recognize objects of different shapes and sizes and determine whether their height exceeds the set threshold. The pre-processed three-dimensional coordinate data is input into the CNN model, and the model extracts features from the data through convolution operations. The calculation formula is:
[0039]
[0040] Among them, s(i, j) is the pixel value at position (i, j) in the output feature map, X is the input feature map, W is the convolution kernel, M and N are the size parameters of the convolution kernel. After being processed by the activation function and pooling layer components, the model outputs the height information of the target object and the judgment result of whether it exceeds the threshold. In the recognition process, the deep learning algorithm module uses the mean square error (MSE) as the loss function
[0041]
[0042] By minimizing the loss function, the internal parameters of the model are adaptively adjusted to improve the recognition accuracy of objects in the internal space of the substation. The system adaptively updates according to historical data and real-time data to continuously optimize the performance of the model. According to the results of model reasoning, the deep learning algorithm module generates a corresponding control signal and transmits it to the control module. After the control module receives the control signal transmitted by the deep learning algorithm module, it triggers the corresponding height limit operation according to the indication of the signal. If it is recognized that an object exceeds the set height, the control module will start the alarm light, automatically shut down related equipment or start emergency braking operation. At the same time, the control module transmits the height limit operation information to the remote monitoring module. The remote monitoring module receives the real-time status, recognition results and height limit operation information of the system through wireless communication technology, and displays it on the screen of the monitoring center. Managers can monitor and operate the system in real time through the monitoring center to ensure the safe operation of the substation.
[0043] In summary, the intelligent height limit control system can effectively limit the height of objects within the substation space through real-time scanning, data processing, deep learning algorithm recognition and execution of control modules, preventing potential safety risks. At the same time, the remote monitoring module enables managers to understand the system's operating status and height limit operation in real time, thereby improving the management efficiency and safety of the substation.
[0044] Example 2
[0045] On the basis of Example 1, an anomaly detection function is added to further improve the safety and stability of the substation through real-time monitoring and data analysis. The newly added anomaly detection function is integrated in the deep learning algorithm module. Through continuous monitoring and analysis of key parameters and recognition results within the system, timely discovery and processing of potential abnormal situations are achieved. The deep learning algorithm module continuously collects recognition results (such as the height and shape of the object) and other key system parameters (such as scanning frequency and data processing time). These data are first pre-processed as necessary, such as data cleaning and format conversion, to ensure their accuracy and availability. The pre-processed data is statistically analyzed to calculate the standard deviation σ and mean μ of the observed values. The calculation formula is:
[0046]
[0047] The standard deviation reflects the degree of dispersion of the data, while the mean represents the central trend of the data. These two statistics will serve as the basis for subsequent anomaly detection. Based on the results of statistical analysis, a threshold based on the standard deviation is set, namely:
[0048] τ=k·σ
[0049] Among them, k is a preset constant. This threshold will be used to determine whether the new observation value is an abnormal situation. For the new observation value xnew The deep learning algorithm module compares it with the previously calculated mean Compare, if |x new -μ|>τ, the observed value is determined to be an abnormal situation. Once an abnormal situation is detected, the control module will immediately trigger the preset response measures, which include but are not limited to: starting the alarm system, issuing sound or visual alarms to alert staff, automatically adjusting system parameters, such as reducing scanning frequency and increasing data processing capacity to deal with abnormal situations, shutting down related equipment or initiating emergency braking to prevent abnormal situations from causing further damage to the substation. The remote monitoring module receives the real-time status, identification results, abnormal detection information and the execution of response measures of the system through wireless communication technology. Managers can monitor and operate the system in real time through the monitoring center to understand the operating status and safety of the substation. When abnormal situations are found, managers can take quick measures through the remote monitoring module to ensure the safe and stable operation of the substation.
[0050] To sum up, by implementing an intelligent height limit control system with an abnormality detection function, it is possible to respond quickly when an abnormal situation occurs in the internal space of the substation, effectively preventing potential safety risks. The addition of this function not only improves the safety and stability of the substation, but also reduces the workload of managers and improves work efficiency.
[0051] Example 3
[0052] The steps of the system based on Example 1 and Example 2 are as follows:
[0053] (1) System startup and initialization: Turn on the power and start the system. The system performs a self-check to ensure that the laser scanning module, data processing module, deep learning algorithm module, control module, and remote monitoring module are in normal working condition. The laser scanning module performs necessary calibration to ensure the accuracy of the scanning data and sets the scanning frequency, scanning range, and height limit threshold parameters.
[0054] (2) Laser scanning and data collection: The laser scanning module emits a laser beam into the internal space of the substation according to the preset scanning frequency and range, and receives the laser signal reflected by the target object. The system collects the three-dimensional coordinate data obtained by the laser scanning, including the location, shape and height information of the target object;
[0055] (3) Data preprocessing and feature extraction: The data processing module receives the three-dimensional coordinate data obtained by the laser scanning module, uses the Gaussian filtering algorithm to smooth the original data, suppresses high-frequency noise and retains low-frequency signals, improves data quality, and performs feature extraction on the processed data to extract key information for recognition by the deep learning algorithm;
[0056] (4) Deep learning algorithm recognition: The deep learning algorithm module loads a pre-trained deep learning model and inputs the pre-processed and feature-extracted 3D coordinate data into the deep learning model. The deep learning model infers the input data to determine whether an object exceeding the set height has entered the substation. Based on the inference results, the deep learning model generates a corresponding control signal.
[0057] (5) Height limit operation and monitoring: The control module receives the control signal generated by the deep learning algorithm module and controls the corresponding actuator to perform height limit operation according to the content of the control signal, such as starting the alarm light, automatically shutting down related equipment, or starting emergency braking. The remote monitoring module transmits the system's real-time status, recognition results, and height limit operation information to the remote monitoring center through wireless communication technology. The management personnel can understand the situation inside the substation in real time through the remote monitoring center and make corresponding decisions.
[0058] (6) System maintenance and update: Regularly maintain and inspect the system to ensure the normal operation of each module. Update and optimize the deep learning model according to actual needs to improve the accuracy and robustness of recognition. Managers can remotely configure and manage the system through the remote monitoring center.
[0059] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. An intelligent height limit control system for a substation using laser technology, characterized in that: The system consists of the following components: Laser scanning module: uses high-precision 3D laser scanning technology to scan the internal space of the substation in real time and obtain the 3D coordinate data of objects in the space; Data processing module: responsible for receiving the three-dimensional coordinate data obtained by the laser scanning module, and performing preprocessing and feature extraction for subsequent deep learning algorithm recognition; Deep learning algorithm module: uses a pre-trained deep learning model to identify the processed data and determine whether there are objects exceeding the set height entering the substation. At the same time, it can be adaptively updated based on historical data and real-time data to improve the accuracy of recognition; Control module: Based on the recognition results of the deep learning algorithm module, control the corresponding actuator to perform height-limiting operations, such as starting the alarm light, automatically shutting down related equipment, or starting emergency braking; Remote monitoring module: The system's real-time status, identification results and height limit operation information are transmitted to the remote monitoring center through wireless communication technology, so that management personnel can conduct real-time monitoring and operation.
2. The intelligent height limit control system for substations using laser technology according to claim 1 is characterized in that: The specific steps of the laser scanning module are: (1) Startup and calibration: Start the laser scanning device and perform necessary calibration to ensure the accuracy of the scanned data; (2) Scanning operation: according to the preset scanning frequency and scanning range, the laser beam is emitted into the internal space of the substation, and the laser signal reflected by the target object is received; (3) Data collection: Collect the three-dimensional coordinate data obtained by laser scanning, including the location, shape and height information of the target object.
3. The intelligent height limit control system for substations using laser technology according to claim 1 is characterized in that: The data processing module uses a Gaussian filtering algorithm to pre-process the three-dimensional coordinate data obtained by the laser scanning module. The expression of the Gaussian filtering algorithm is: Among them, G(x,y) represents the value of the Gaussian filter function at the coordinate (x,y), σ is the standard deviation of the Gaussian function, which determines the width of the filter. The algorithm smoothes the original data by suppressing high-frequency noise and retaining low-frequency signals to improve the recognition accuracy of the subsequent deep learning algorithm module.
4. The intelligent height limit control system for substations using laser technology according to claim 1 is characterized in that: The specific steps of the deep learning algorithm module are as follows: (1) Model loading: Load a pre-trained deep learning model that can recognize objects of different shapes and sizes and determine whether their height exceeds a set threshold; (2) Model reasoning: The feature data transmitted by the data processing module is input into the deep learning model, and the deep learning model is used to reason about the input feature data to obtain the height information of the target object and the judgment result of whether it exceeds the threshold; (3) Control signal generation: Generate corresponding control signals based on the results of model reasoning.
5. The intelligent height limit control system for substations using laser technology according to claim 4 is characterized in that: The deep learning algorithm module adopts a convolutional neural network (CNN) model to extract features from the preprocessed three-dimensional coordinate data through convolution operations, and transforms and selects features through activation functions and pooling layer components to achieve recognition of objects in the internal space of the substation. The mathematical expression of the convolution operation is: Among them, s(i,j) is the pixel value at position (i,j) in the output feature map, X is the feature map obtained after preprocessing the input three-dimensional coordinate data, W is the convolution kernel, which contains learnable weights, m and n are the size parameters of the convolution kernel, X(i+m,j+n) represents the pixel value corresponding to the current position of the convolution kernel in the feature map, and w(m,n) represents the weight value of the convolution kernel at position (m,n). Through this model, the deep learning algorithm module can adaptively identify objects of different shapes and sizes, and control the corresponding actuator to perform height limit operations according to the recognition results.
6. The intelligent height limit control system for substations using laser technology according to claim 3 is characterized in that: The deep learning algorithm module uses mean square error (MSE) as the loss function to optimize the prediction performance of the model. The deep learning algorithm module calculates the mean square error loss function through the following mathematical formula: Where: MSE is the mean square error, N is the number of samples, y i is the true label value of the i-th sample, is the predicted value of the deep learning model for the i-th sample. By minimizing the loss function, the deep learning algorithm module can adaptively adjust its internal parameters to improve the recognition accuracy of objects in the internal space of the substation.
7. The intelligent height limit control system for substations using laser technology according to claim 4 is characterized in that: The deep learning algorithm module adopts an anomaly detection algorithm to identify and respond to abnormal conditions in the internal space of the substation in real time. For the anomaly detection algorithm, the standard deviation and mean of the observed values are calculated, and the formula is: Among them, x i is the ith observation, N is the total number of observations, μ is the mean of these observations, Where σ is the standard deviation of these observations. For the threshold, it is usually set based on the standard deviation, such as τ = k·σ, where k is a preset constant. For a new observation x new , if it satisfies |x new -μ|>τ, it is judged as abnormal. During the operation of the substation, the deep learning algorithm module will perform real-time analysis through the above-mentioned anomaly detection algorithm. Once an abnormal situation is detected, the control module will automatically trigger the preset response measures based on the recognition results of the deep learning algorithm module, including but not limited to starting the alarm, adjusting system parameters, and shutting down related equipment to ensure the safe operation of the substation.
8. The intelligent height limit control system for substations using laser technology according to claim 1 is characterized in that: The remote monitoring module receives the operation information transmitted by the control module, and transmits the system's real-time status, identification results, and height limit operation information to the remote monitoring center through wireless communication technology. The management personnel of the remote monitoring center can view the height limit control status of the substation in real time through the monitoring center computer or mobile terminal, and perform necessary operations and management.
9. The intelligent height limit control system for substations using laser technology according to claim 1 is characterized in that: The system also includes a user interaction interface, which allows managers to view the system's operating status, recognition results, and height limit operation information in real time through a graphical interface, and provides interactive functions for parameter setting and function configuration, so that managers can adjust the system's operating parameters and configuration according to actual needs.
10. The intelligent height limit control system for substations using laser technology according to claim 1, characterized in that: The system also includes an automatic calibration module, which is used to automatically calibrate the laser scanning module regularly or according to preset conditions to ensure its scanning precision and accuracy.
Citation Information
Patent Citations
Fault identification and positioning method, device and apparatus for substation power equipment
CN111144325A
Substation equipment detection method based on 3D point cloud and deep learning
CN112365455A
Risk identification method and system applied to substation field operation
CN117115728A
Intelligent substation illegal operation early warning system
CN117372723A
Substation communication network equipment monitoring and fault early warning method and system
CN118200118A
