An intelligent monitoring platform for substations

Abstract

The present invention relates to an intelligent monitoring platform for substations, which uses sensors to monitor environmental data of substations; monitors equipment operation status data of substations; obtains layout data of various links of substations, wherein the layout data includes equipment location and line distribution; uses GIS software to generate a layout image of the layout data, and uses a convolutional neural network to extract the main features of the layout image; when a substation fails, the cause of the failure is investigated based on environmental data, equipment operation status data and main features of the layout image. The present invention solves the problem that the prior art is difficult to monitor various links of a substation in real time and comprehensively, and cannot realize centralized integration and comprehensive analysis of information, resulting in poor monitoring accuracy and effect. Through historical big data, environmental data, equipment operation status data and main features of layout images are used as explanatory variables, and fault types are used as response variables, a CART model is constructed to improve the efficiency of monitoring fault investigation.

Description

Technical Field

[0001] The invention belongs to the technical field of substation monitoring, and relates to an intelligent substation monitoring platform. Background Art

[0002] In today's society, the demand for electricity continues to grow. As a key node in the power system, the safe and stable operation of substations is of vital importance. However, the traditional substation monitoring method mainly relies on manual inspections and decentralized monitoring systems, which has many disadvantages. On the one hand, with the continuous expansion of the scale of the power grid and the increasing complexity of power equipment, the workload of manual inspections is huge, and it is difficult to monitor all aspects of the substation in real time and comprehensively. Inspection personnel may miss some potential problems due to fatigue, negligence, etc., resulting in safety hazards that cannot be discovered and handled in time. On the other hand, decentralized monitoring systems cannot achieve centralized integration and comprehensive analysis of information. Different types of monitoring equipment operate independently, and data is difficult to share, making it difficult for managers to make accurate judgments and decisions when faced with complex situations.

[0003] Therefore, in order to improve the safety, reliability and management efficiency of substations and meet the high requirements of modern power systems for substation operation and management, it is necessary to conduct centralized, real-time and intelligent monitoring of substations and change the traditional substation monitoring method. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides an intelligent monitoring platform for substations, which aims to realize centralized, real-time and intelligent monitoring of substations by integrating various advanced technologies such as video monitoring, sensor technology and GIS technology, combined with big data analysis models, so as to solve the problems of low monitoring accuracy and efficiency of the prior art.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The present application provides an intelligent monitoring platform for a substation, including an environment monitoring module, an equipment monitoring module, a GIS module and a fault troubleshooting module, wherein the environment monitoring module, the equipment monitoring module, the GIS module and the fault troubleshooting module are communicatively connected, wherein:

[0007] The environmental monitoring module uses sensors to monitor environmental data of the substation; the environmental data includes temperature and humidity;

[0008] The equipment monitoring module is used to monitor the equipment operation status data of the substation, and the equipment operation status data includes electrical parameters, physical parameters and start and stop status;

[0009] The GIS module is used to obtain layout data of each link of the substation, wherein the layout data includes equipment location and line distribution; a layout image of the layout data is generated using GIS software, and a convolutional neural network is used to extract the main features of the layout image;

[0010] The fault troubleshooting module is used to troubleshoot the fault type according to the environment data, equipment operation status data and main features of the layout image when a fault occurs in the substation.

[0011] Furthermore, in the equipment monitoring module, the electrical parameters include voltage, current, power and frequency; the physical parameters include vibration, equipment temperature and noise; and the start-stop state indicates that the equipment is in the start or stop state.

[0012] Furthermore, the GIS module also interpolates the environmental data and the equipment operation status data to the corresponding equipment location and presents them visually, including the following steps:

[0013] By installing RFID tags on each device in the substation, the location coordinates of the equipment are determined;

[0014] According to the location of the device and the collected data, an interpolation method is used to interpolate the environmental data and the device operating status data to the corresponding device location; the interpolation method is configured as an inverse distance weighted method or a Kriging interpolation method;

[0015] The interpolated environmental data and equipment operating status data are presented on the GIS map in a visual way;

[0016] Update environmental data and equipment operating status data regularly, and update interpolation results and visualization presentations.

[0017] Furthermore, in the GIS module, the links include the incoming link, the transformer link, the bus link, the outgoing link and the relay protection link, wherein:

[0018] The incoming line link introduces high voltage electricity from the power plant or the upper-level substation into the substation through overhead lines or cables;

[0019] The transformer is responsible for converting high voltage electric energy into voltage levels suitable for different user needs;

[0020] The bus link is divided into high-voltage bus, medium-voltage bus and low-voltage bus according to different voltage levels to control the flow and distribution of electric energy;

[0021] The outgoing link transmits the electric energy transformed by the substation to the lower-level substation or user;

[0022] The relay protection link cuts off the faulty equipment when a fault occurs in the power system to protect the safety of the power grid and equipment.

[0023] Furthermore, in the fault troubleshooting module, the fault types include short circuit, open circuit, overvoltage and undervoltage.

[0024] Furthermore, in the fault troubleshooting module, the troubleshooting of the fault type includes the following steps:

[0025] S1. Prepare a substation fault data set monitored in a historical period, wherein the substation fault data set includes environmental data, equipment operation status data, main features of layout images, and corresponding fault types;

[0026] S2, using environmental data, equipment operation status data and main features of layout images as explanatory variables and fault type as response variable, construct a CART model to obtain a fault troubleshooting decision tree;

[0027] S3. Obtain the current environmental data, equipment operating status data and main features of the layout image, substitute them into the fault troubleshooting decision tree, and determine the fault type of the substation.

[0028] Furthermore, the construction of the CART model to obtain a troubleshooting decision tree includes the following steps:

[0029] S11, select a certain explanatory variable as a feature, determine the split point of the feature to split the response variable data set into two data subsets, wherein the selected feature and split point make the purity of the split data subset the highest;

[0030] S12, repeating the segmentation step for each data subset selection feature until it cannot be segmented any further, and generating a preliminary decision tree;

[0031] S13, pruning the preliminary decision tree according to the order of data set segmentation to obtain a final decision tree as a troubleshooting decision tree;

[0032] S14. Use the test set data to evaluate and verify the troubleshooting decision tree.

[0033] Furthermore, the fault detection module also includes a video monitoring module for real-time monitoring of the operating conditions of various equipment in the substation, checking the appearance of the equipment, supervising personnel operations, assisting in fault location and cause analysis, and ensuring the safety of the substation.

[0034] Furthermore, the fault troubleshooting module also includes a fault reporting module for reporting the current fault type and marking the location of the fault in the GIS module.

[0035] Beneficial effects of the present invention:

[0036] (1) Use sensors to monitor the environmental data of the substation; monitor the equipment operation status data of the substation; obtain the layout data of each link of the substation, the layout data includes the equipment location and line distribution; when a substation fails, investigate the cause of the failure based on the environmental data, equipment operation status data and layout data. The present invention solves the problem that the existing technology is difficult to monitor each link of the substation in real time and comprehensively, and cannot realize the centralized integration and comprehensive analysis of information, resulting in poor monitoring accuracy and effect.

[0037] (2) By using big data from historical periods, a CART model was constructed with environmental data, equipment operating status data, and layout data as explanatory variables and fault type as the response variable, which improved the efficiency of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0039] Figure 1 The figure is a structural diagram of an intelligent monitoring platform for a substation in the present invention.

[0040] Figure 2 The figure is a flow chart of a fault troubleshooting module in one embodiment of the present invention.

[0041] Figure 3 The figure is a schematic diagram of the structure of a fault troubleshooting decision tree in one embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0043] See also Figure 1-Figure 3 The present application provides a substation intelligent monitoring platform, including an environment monitoring module, an equipment monitoring module, a GIS module, a fault troubleshooting module and a fault warning, wherein the environment monitoring module, the equipment monitoring module, the GIS module, the fault troubleshooting module and the fault warning are connected in communication, wherein:

[0044] The environmental monitoring module uses sensors to monitor environmental data of the substation; the environmental data includes temperature and humidity;

[0045] In this embodiment, the environmental monitoring module mainly uses sensors to monitor the environmental data of the substation, among which temperature and humidity are key monitoring indicators. For core equipment such as transformers, temperature can reflect their load conditions and health status. When the transformer is overloaded, the temperature rises. By monitoring its oil temperature and winding temperature in real time through the temperature sensor, overload problems can be discovered in time to avoid failures or even fires caused by overheating and damage to insulation. At the same time, the temperature changes indoors and outdoors of the substation also affect the operation of the equipment. Indoor high temperature will reduce the operating efficiency and life of the equipment, and outdoor extreme temperature may cause equipment heat dissipation difficulties or affect the starting performance. According to the temperature monitoring data, ventilation, air conditioning and other equipment can be started in time for environmental control. High humidity environment will reduce the insulation performance of electrical equipment, and moisture condensation on the surface of the equipment may form a conductive path, increasing the risk of leakage and short circuit. For equipment using special insulating materials, the humidity effect is more obvious. In addition, long-term high humidity can also cause corrosion of metal parts. Humidity sensors are installed indoors and near sensitive equipment to monitor relative humidity in real time.

[0046] Sensors have different types and characteristics. Temperature sensors such as thermocouples, thermal resistors and infrared sensors can be installed in key locations according to different needs to achieve comprehensive monitoring. Humidity sensors include capacitive, resistive and humidity-sensitive elements, which have the advantages of fast response speed and good stability. The environmental monitoring module receives the sensor signal and performs real-time processing and display, and automatically alarms when it exceeds the safety range. Analyzing long-term monitoring data can understand the trend of environmental changes, predict future temperature and humidity changes, provide reference for equipment maintenance and operation management, and formulate reasonable environmental control strategies to ensure the safe and stable operation of substations.

[0047] The equipment monitoring module is used to monitor the equipment operation status data of the substation, and the equipment operation status data includes electrical parameters, physical parameters and start / stop status.

[0048] Furthermore, in the equipment monitoring module, the electrical parameters include voltage, current, power and frequency; the physical parameters include vibration, equipment temperature and noise; and the start-stop state indicates that the equipment is in the start or stop state.

[0049] In this embodiment, the electrical parameters include monitoring of voltage, current, power and frequency. Voltage stability is crucial to equipment operation, and abnormal fluctuations may affect the normal operation of the equipment or even damage it. Current reflects the load of the equipment, and excessive or insufficient current may indicate problems. Power monitoring can understand the energy consumption and power factor of the equipment, and provide a basis for optimizing the operating efficiency of the power system. Frequency stability is also critical, and abnormalities may affect the speed and synchronization performance of the equipment. Through real-time monitoring of these electrical parameters, problems can be discovered in a timely manner and adjustment measures can be taken, such as adjusting transformer taps, switching on and off reactive compensation equipment, etc.

[0050] Among the physical parameters, vibration monitoring can reflect the mechanical status of the equipment through vibration amplitude and frequency. Abnormal vibration may be caused by loose or worn internal parts, which helps to promptly detect hidden mechanical failures. Equipment temperature monitoring is particularly important for equipment with high heat generation, such as transformers. Excessive temperature may damage the equipment. When the temperature exceeds the limit, cooling measures can be taken in time. Noise monitoring can determine the operating status of the equipment based on the noise level and frequency. Abnormal noise may indicate internal failure or loose parts.

[0051] Start-stop status monitoring can monitor whether the equipment is in the start or stop state in real time. Start status monitoring can record parameters such as start time and start current to determine whether the start is normal. It can also remotely monitor the operation of important equipment. Stop status monitoring can record the stop time and reason to understand whether the stop is normal, providing a basis for equipment maintenance and overhaul.

[0052] The GIS module is used to obtain layout data of each link of the substation, wherein the layout data includes equipment location and line distribution; a layout image of the layout data is generated using GIS software, and a convolutional neural network is used to extract the main features of the layout image;

[0053] In this embodiment, the GIS module is mainly responsible for obtaining the equipment location and line layout information of each link of the substation. First of all, for the determination of the equipment location, the GIS module can accurately mark the specific coordinates of various key equipment in the substation. Whether it is a large transformer, a complex circuit breaker, or various types of mutual inductors, disconnectors and other equipment, the GIS module can clearly display their exact location on the virtual map. This enables staff to quickly and accurately locate the target equipment when conducting equipment inspections, maintenance and troubleshooting, greatly improving work efficiency. For example, when a certain device has a fault alarm, the staff can immediately determine the location of the device through the GIS module and quickly go to the site for processing, reducing the fault handling time and reducing the impact on the operation of the power system.

[0054] Secondly, in terms of line distribution, the GIS module can present in detail the direction and connection relationship of various lines in the substation, including high-voltage incoming lines, busbars, outgoing lines, and internal connection lines. Through the clear line layout display, the staff can intuitively understand the transmission path of electricity in the substation, which is convenient for line planning, transformation and fault analysis. For example, when carrying out substation expansion or transformation projects, the GIS module can help engineers accurately understand the existing line layout, reasonably plan the installation location of new equipment and lines, and avoid conflicts with existing lines. At the same time, when a line fault occurs, the GIS module can assist the staff to quickly determine the location and impact range of the faulty line and formulate an effective maintenance plan. In addition, the GIS module can also interact with other modules for data and work together. For example, combined with the video monitoring module, when the staff is viewing the real-time video of a certain device, the GIS module can simultaneously display the location information of the device, which is convenient for the staff to better understand the on-site situation. Combined with the environmental monitoring module, sensors can be reasonably arranged according to the equipment location and line layout to achieve comprehensive monitoring of the substation environment.

[0055] In addition, after obtaining the equipment location and line distribution, it is necessary to obtain the main features of the layout data, which is an important basis for judging the fault type. By extracting the main features of the layout image, problems with substation equipment and line layout can be better discovered. Among them, the steps of extracting the main features of the layout image using convolutional neural network (CNN) are as follows:

[0056] (1) Data preparation

[0057] Data collection: First, there must be enough substation layout image data. These images should cover various layout situations of different substations, including different equipment location arrangements, line distribution differences, etc., to ensure that the network can learn rich feature patterns.

[0058] (2) Data preprocessing:

[0059] Normalization: Normalize the pixel values ​​of the image, such as mapping the pixel values ​​to the interval [0, 1] or [-1,1], which helps speed up network training and improve stability.

[0060] Cropping and scaling: Make sure all images are the same size. You can crop images to focus on key layout areas, or scale them to reach the target size, such as the common 224×224, 256×256 and other pixel specifications.

[0061] (3) Constructing a convolutional neural network

[0062] Convolutional Layers:

[0063] This is the core layer of CNN, which performs convolution operations by sliding the convolution kernel (also called filter) on the image. For example, a 3×3 or 5×5 convolution kernel slides pixel by pixel on the image, multiplies and sums the pixels at the corresponding position, and obtains a pixel value in the new feature map.

[0064] The convolution kernel will automatically learn to extract local features in the image, such as edges, textures, etc. For substation layout images, features such as the outline edges of equipment and the direction and texture of the lines may be learned.

[0065] Usually multiple convolutional layers are set up. As the number of layers increases, the network can learn more abstract and advanced features. The number of convolution kernels in each layer can be gradually increased to extract more types of features.

[0066] Activation Functions: After each convolutional layer, an activation function is generally applied to introduce nonlinear factors. Common activation functions include ReLU (Rectified Linear Unit). For example, the ReLU function sets values ​​less than 0 to 0 and keeps values ​​greater than 0 unchanged, so that the network can learn nonlinear feature relationships rather than simple linear combinations, which can better fit complex image features.

[0067] Pooling Layers:

[0068] The function of the pooling layer is to downsample the feature map, reduce the amount of data, and retain the main features. Common pooling methods include Max Pooling and Average Pooling.

[0069] For example, the maximum pooling method selects the maximum value in a small area (such as a 2×2 window) as a pixel value in the new feature map, which helps to highlight the most significant features in the image and remove some unimportant local change information. For substation layout images, key features of equipment or lines may be highlighted.

[0070] The pooling layer can prevent overfitting to a certain extent and improve the generalization ability of the network.

[0071] Fully Connected Layers:

[0072] After passing through multiple convolutional and pooling layers, the feature map is flattened into a one-dimensional vector and then input into the fully connected layer.

[0073] The neurons in the fully connected layer are connected to all the neurons in the previous layer. It can comprehensively process the various features extracted previously and map them to a specific output space, such as determining the category to which the image belongs (in classification tasks) or generating specific feature representations (in feature extraction tasks).

[0074] (4) Training the network

[0075] Define the loss function: Choose an appropriate loss function based on the task requirements. If it is a simple feature extraction task, a common approach is to minimize the reconstruction error, that is, to make the features extracted by the network as close to the original image as possible after some reconstruction operation; if there are subsequent tasks such as classification, the cross entropy loss function (for classification tasks) can be used.

[0076] Select an optimizer: Commonly used optimizers include stochastic gradient descent (SGD) and its variants such as Adagrad, Adadelta, Adam, etc. The function of the optimizer is to update the weight parameters of the network according to the gradient calculated by the loss function, so that the loss function continues to decrease, allowing the network to learn better feature representation.

[0077] Training process:

[0078] The pre-processed substation layout image data is divided into a training set, a validation set, and a test set. The training set is used to train the network, the validation set is used to monitor the performance of the network during the training process and adjust the training parameters (such as learning rate, etc.), and the test set is used to finally evaluate the performance of the network after training.

[0079] The training set images are input into the constructed convolutional neural network in sequence, and the output (such as feature representation or classification prediction, etc.) is obtained through forward propagation calculation. Then, the value of the loss function is calculated based on the output and the true value (labeled features or classification labels).

[0080] The optimizer then back-propagates the gradient of the loss function to update the network’s weight parameters, and repeats this process over and over again until the network performance reaches a satisfactory level (such as the loss on the validation set no longer decreases or the expected accuracy is achieved).

[0081] (5) Feature extraction

[0082] Freeze network weights: After training the network, if you are only performing feature extraction, you will usually freeze all the network weight parameters, that is, no longer update them. This ensures that the extracted features are based on the feature patterns learned by the trained network model.

[0083] Input image for feature extraction: Input the new substation layout image into the trained and weight-frozen convolutional neural network. After the network's forward propagation process, the main feature representation of the image can be obtained in a specific layer of the network (usually the last convolutional layer or pooling layer before the fully connected layer, etc., the features extracted by these layers are relatively more abstract and representative). These feature vectors contain the main feature information about the equipment location, line distribution, etc. in the substation layout image, which can be used for subsequent analysis, classification, retrieval and other tasks.

[0084] Furthermore, the GIS module also interpolates the environmental data and the equipment operation status data to the location of the corresponding equipment and presents them visually, including the following steps:

[0085] By installing RFID tags on each device in the substation, the device location coordinates are determined;

[0086] According to the location of the equipment and the collected data, the environmental data and equipment operating status data are interpolated to the corresponding equipment location using interpolation methods; common interpolation methods include inverse distance weighted method, Kriging interpolation method, etc. These methods can estimate the data value of unknown location points based on the location and value of known data points.

[0087] For example, for a temperature measurement point around a device, the estimated temperature value at the device location is calculated based on the distance between the measurement point and the device and the temperature value of the measurement point by using the inverse distance weighted method.

[0088] The interpolated environmental data and equipment operating status data are presented in a visual way on the GIS map. Different icons, colors, charts, etc. can be used to represent different data types and value ranges.

[0089] For temperature data, it can be represented by a color gradient icon. The higher the temperature, the redder the icon color. For equipment operating status data, such as voltage and current, numbers can be marked next to the equipment icon, or different colored lines can be used to represent different numerical ranges.

[0090] At the same time, different display levels and interactive functions can be set to facilitate users to view and analyze data. For example, users can click on the device icon to view the detailed data information of the device; they can switch between different data layers to view environmental data or device operating status data separately.

[0091] In order to ensure the accuracy and real-time performance of visualization, it is necessary to regularly update environmental data and equipment operating status data, and update interpolation results and visualization. The frequency of data collection and update can be set, and dynamic display can be performed according to actual needs, so that users can understand the environment and equipment operation status in the substation at any time.

[0092] In the intelligent monitoring platform of substations, the role of GIS module is further expanded and deepened. In addition to obtaining the equipment location and line layout of each link of the substation, it also interpolates the environmental data and equipment operation status data to the location of the corresponding equipment and presents them visually. For the interpolation and visualization of environmental data, the GIS module can accurately associate environmental parameters such as temperature and humidity with the location of specific equipment. In this way, when viewing the GIS map of the substation, the staff can not only see the specific location and line layout of the equipment, but also intuitively understand the environmental conditions around each device. For example, when the temperature in a certain area is too high, it may mean that there is a problem with the heat dissipation of the equipment in the area, and cooling measures need to be taken in time. Or when the humidity exceeds a certain limit, it may affect the insulation performance of nearby electrical equipment, reminding the staff to carry out moisture-proof treatment. Through this visual method, the potential impact of environmental factors on equipment operation can be discovered more timely and accurately, so as to take targeted measures for prevention and treatment.

[0093] In terms of equipment operation status data, the GIS module interpolates electrical parameters such as voltage, current, power, and physical parameters such as vibration, equipment temperature, and noise to the location of the corresponding equipment. This allows staff to grasp the specific operating status of each device at a glance. For example, by visually presenting the current size of the equipment, it is possible to quickly determine whether the equipment is in an overloaded state; if the vibration amplitude of a certain equipment is abnormal, the location of the equipment can be clearly seen on the map and timely inspection and maintenance can be carried out. At the same time, the start and stop status of the equipment can also be intuitively displayed on the GIS map, making it convenient for staff to understand the operating dynamics of the equipment.

[0094] This function of interpolating and visualizing environmental data and equipment operating status data provides great convenience for the management and maintenance of substations. It allows complex monitoring data to be presented to staff in an intuitive and clear form, greatly improving the readability and operability of the data. Staff can more efficiently monitor equipment, diagnose faults and make decisions, thereby effectively improving the operational safety and reliability of substations.

[0095] Furthermore, in the GIS module, the links include an incoming line link, a transformer link, a bus link, an outgoing line link and a relay protection link.

[0096] In this embodiment, the incoming line link is the starting point for the substation to receive external power. It usually includes overhead lines or cables to introduce high-voltage power from power plants or upper-level substations into the substation. The key equipment includes incoming line switchgear, such as circuit breakers and disconnectors, which are used to control the on and off of the incoming line to ensure the safe access to power in the substation.

[0097] The transformer link is the core part of the substation. The main transformer is responsible for converting high-voltage electric energy into a voltage level suitable for different user needs. Its operating status directly affects the power supply reliability of the entire substation. In this link, auxiliary equipment such as the cooling system is also included to ensure that the transformer operates within the normal temperature range.

[0098] The busbar plays an important role in collecting and distributing electric energy. It is divided into high-voltage busbar, medium-voltage busbar and low-voltage busbar according to different voltage levels. Busbar connection equipment such as disconnectors, circuit breakers, and transformers control the flow and distribution of electric energy to ensure the stable operation of the power system.

[0099] The outgoing link is to transmit the electric energy after transformation in the substation to the lower substation or user. The outgoing switchgear controls the output of electric energy, and the overhead line or cable is responsible for transmitting the electric energy to the destination.

[0100] Relay protection is an important guarantee for substation safety. When a fault occurs in the power system, the relay protection device can quickly and accurately cut off the faulty equipment to protect the safety of the power grid and equipment. It is closely connected with the equipment in each link and realizes real-time protection of the power system through complex line layout.

[0101] The fault troubleshooting module is used to troubleshoot the fault type according to the environmental data, equipment operation status data and main features of the layout image when a fault occurs in the substation;

[0102] In this embodiment, when a substation fails, the troubleshooting module can make full use of environmental data, equipment operating status data and layout data to quickly and accurately troubleshoot the fault. Environmental data provides important clues for troubleshooting: for example, when the temperature is too high or the humidity is too high, it may affect the insulation performance of the equipment, thereby causing a fault. By analyzing the temperature, humidity and other data obtained by the environmental monitoring module, the troubleshooting module can determine whether environmental factors have played a role in promoting the occurrence of the fault. If the environmental data is found to be abnormal, targeted measures can be taken, such as starting ventilation equipment to lower the temperature, performing dehumidification treatment, etc., to eliminate the adverse effects of environmental factors on the equipment.

[0103] The equipment operation status data is the core basis for troubleshooting: electrical parameters such as voltage, current, power, frequency, and physical parameters such as vibration, equipment temperature, and noise can directly reflect the equipment's operating status. The troubleshooting module can find out the anomaly by comparing the data under normal operating conditions with the data when the fault occurred. For example, if the current suddenly increases, it may mean that the equipment has a short circuit fault; if the temperature of the equipment rises abnormally, it may be due to poor heat dissipation caused by overload or internal fault. Through in-depth analysis of these data, the troubleshooting module can preliminarily determine the type and location of the fault.

[0104] Layout data also plays an important role in troubleshooting: device location and line distribution information can help the troubleshooting module quickly locate the area where the faulty device is located, as well as identify other devices and lines related to the faulty device. This helps narrow the scope of troubleshooting and improve troubleshooting efficiency. For example, if equipment in a certain area frequently fails, layout data can be used to analyze whether there is a problem with the line connection in that area, or whether there are common environmental factors affecting it.

[0105] Furthermore, in the fault troubleshooting module, the fault types include short circuit, open circuit, overvoltage and undervoltage.

[0106] In this embodiment, during the operation of the substation, environmental data, equipment operation status data and layout data may all cause different types of faults.

[0107] From the perspective of environmental data, high temperature environments may cause equipment to overheat, such as transformer heat dissipation difficulties and reduced cable current carrying capacity, which will affect the insulation performance and service life of the equipment and even cause faults such as winding insulation aging, contact overheating and cable short circuit. High humidity environments will reduce the insulation performance of equipment, making leakage and short circuit faults more likely to occur, while accelerating the corrosion of metal parts. In a dirty environment, dust and other dirt deposited on the surface of the insulator may cause flashover and lead to short circuits. It will also accumulate dirt on the surface of the equipment, affecting heat dissipation and ventilation, and increasing the risk of failure.

[0108] Faults caused by equipment operating status data should not be ignored. When electrical parameters are abnormal, voltage that is too high or too low can damage the equipment or cause it to fail to operate normally. Overcurrent can burn the equipment and cause a fire. Undercurrent can indicate equipment failure or insufficient load. Low power factor can increase grid losses. In terms of physical parameter abnormalities, excessive vibration may be caused by loose internal components, which can cause equipment damage and loose connections. Excessive temperature may damage equipment insulation or even cause a fire due to overload and other reasons. Excessive noise may indicate a potential equipment failure.

[0109] Layout data can also cause faults. Improper line layout may cause short circuit faults due to the close distance between wires, and poor grounding may increase the risk of grounding faults. Improper equipment location may lead to poor heat dissipation, affect equipment operation, make maintenance and repair difficult, increase maintenance costs and time, and affect equipment reliability.

[0110] Furthermore, in the fault troubleshooting module, the troubleshooting of the fault type includes the following steps:

[0111] S1. Prepare a substation fault data set monitored in a historical period, wherein the substation fault data set includes environmental data, equipment operation status data, main features of layout images, and corresponding fault types;

[0112] S2, using environmental data, equipment operation status data and main features of layout images as explanatory variables and fault type as response variable, construct a CART model to obtain a fault troubleshooting decision tree;

[0113] S3. Obtain the current environmental data, equipment operating status data and main features of the layout image, substitute them into the fault troubleshooting decision tree, and determine the fault type of the substation.

[0114] In this embodiment, CART (Classification and Regression Tree) is a binary tree that divides the data into different sub-nodes by segmenting the features. In the process of building a decision tree, the Gini index or square error is used to select the best segmentation features and segmentation points.

[0115] Furthermore, the construction of the CART model to obtain a troubleshooting decision tree includes the following steps:

[0116] S11, select a certain explanatory variable as a feature, determine the split point of the feature to split the response variable data set into two data subsets, wherein the selected feature and split point make the purity of the split data subset the highest;

[0117] S12, repeat the segmentation step for each data subset by selecting features until it cannot be segmented any further (i.e., each data subset contains only one fault type), and generate a preliminary decision tree;

[0118] S13, pruning the preliminary decision tree according to the order of data set segmentation to obtain a final decision tree as a troubleshooting decision tree;

[0119] In this embodiment, the constructed decision tree may have an overfitting problem, that is, it fits the training data well, but has poor prediction performance for the test data. In order to solve this problem, it is necessary to perform pruning optimization on the decision tree.

[0120] S14. Use the test set data to evaluate and verify the troubleshooting decision tree. Evaluation indicators may include accuracy, precision, recall, F1 value, etc.

[0121] In this embodiment, accuracy is the ratio of the number of samples correctly predicted by the model to the total number of samples, and is one of the most commonly used evaluation indicators; precision measures how many of the positive examples predicted by the model are truly positive examples, and is an important indicator for evaluating the accuracy of model predictions; recall measures the ratio of the number of positive examples that the model can correctly predict to the actual number of positive examples, also known as recall; F1 value is the harmonic mean of precision and recall, which comprehensively considers the accuracy and recall of the model. The higher the F1 value, the better the balance between precision and recall.

[0122] Furthermore, in step S5, the accuracy rate is calculated as follows:

[0123] ,

[0124] In the formula, ACC represents accuracy; TP represents true positive examples; TN represents true negative examples; FP represents false positive examples; and FN represents false negative examples.

[0125] Furthermore, in step S5, the accuracy is calculated as follows:

[0126] ,

[0127] Where PPV represents precision, TP represents true positives, and FP represents false positives.

[0128] Furthermore, in step S5, the recall rate is calculated as follows:

[0129] ,

[0130] Where TRP represents the recall rate; TP represents the true positive examples; and FN represents the false negative examples.

[0131] Further, in step S5, the F1 value is calculated by the formula:

[0132] ,

[0133] Where, F1 represents the F1 value; PPV represents the precision; TRP represents the recall rate.

[0134] The optimization control module is used to control the power supply mode of the distribution cabinet according to the current power generation situation of the distribution cabinet.

[0135] Furthermore, the fault detection module also includes a video monitoring module for real-time monitoring of the operating conditions of various equipment in the substation, checking the appearance of the equipment, supervising personnel operations, assisting in fault location and cause analysis, and ensuring the safety of the substation.

[0136] In this embodiment, the video monitoring module in the troubleshooting module is used in the following aspects:

[0137] The first is to monitor the operating conditions of various equipment in the substation in real time. Through the cameras installed in key positions, the transformers, circuit breakers, disconnectors, busbars and other equipment are continuously photographed. The operating posture of the equipment can be observed, such as whether the transformer has abnormal vibrations and whether the opening and closing actions of the circuit breaker are normal. For the instruments on the equipment, the reading information can be obtained intuitively, and the abnormal performance of parameters such as voltage and current on the appearance of the equipment can be discovered in time, such as abnormal swing of the instrument pointer and smoke from the equipment, providing an intuitive basis for fault judgment.

[0138] The second is to check the appearance of the equipment. Carefully check whether the surface of the equipment is damaged, deformed, leaked, etc. For example, whether the cable sheath is damaged, whether the connection parts of the equipment are loose and deformed, whether the oil-immersed equipment has oil leakage, etc. At the same time, it can also monitor whether there are foreign objects on the equipment, such as bird nests, branches, etc., which may cause short circuits or other faults.

[0139] The third is to monitor the operation of personnel. When the staff operates the equipment, the video monitoring module can record the operation process to ensure that the operation complies with the regulations. If there is an operation error, such as the wrong opening and closing of the knife switch, it can be discovered and corrected in time to avoid failures caused by human error. And when a failure occurs, the operation process can be traced back to analyze whether it is caused by the operation.

[0140] Fourth, it assists in fault location and cause analysis. When a fault alarm occurs in a substation, the staff can quickly determine the specific location and scene of the fault by viewing the video surveillance records, and combine other data to more accurately determine the cause of the fault. At the same time, in daily inspections, the image information recorded by the video surveillance module can also be used as a supplement to the inspection, reducing the frequency and intensity of manual on-site inspections and improving inspection efficiency.

[0141] Fifth, it ensures the safety of the substation. In addition to monitoring equipment and personnel, the video surveillance module can also monitor the environment around the substation to prevent illegal intrusion, theft and other security incidents, ensuring the overall safe and stable operation of the substation.

[0142] Furthermore, the fault troubleshooting module also includes a fault reporting module for reporting the current fault type and marking the location of the fault in the GIS module.

[0143] In this embodiment, the fault broadcast module in the fault troubleshooting module plays a key role when a fault occurs. When a fault is detected, it will quickly identify the current fault type, such as electrical faults such as short circuit, open circuit, overvoltage, undervoltage, or equipment faults such as transformer fault and circuit breaker fault, and then clearly broadcast it to the staff through voice or other means. At the same time, it can be linked with the GIS module to accurately mark the location of the fault in the substation space layout diagram constructed by the GIS module, whether it is the transformer, busbar, incoming line, outgoing line and other equipment, or the specific fault point on the line, it can be presented intuitively, helping the staff to quickly locate the fault, improve the efficiency of fault handling, and ensure the safe and stable operation of the substation.

[0144] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. An intelligent monitoring platform for substations, characterized by: It includes an environment monitoring module, an equipment monitoring module, a GIS module and a troubleshooting module, wherein the environment monitoring module, the equipment monitoring module, the GIS module and the troubleshooting module are communicatively connected, wherein: The environmental monitoring module uses sensors to monitor environmental data of the substation; the environmental data includes temperature and humidity; The equipment monitoring module is used to monitor the equipment operation status data of the substation, and the equipment operation status data includes electrical parameters, physical parameters and start and stop status; The GIS module is used to obtain layout data of each link of the substation, and the layout data includes equipment location and line distribution; The fault troubleshooting module is used to troubleshoot the fault type according to the environmental data, equipment operation status data and layout data when a fault occurs in the substation, and includes the following steps: S1. Prepare a substation fault data set monitored in a historical period, wherein the substation fault data set includes environmental data, equipment operation status data and layout data, and corresponding fault types; S2, using environmental data, equipment operation status data and layout data as explanatory variables and fault type as response variable, construct a CART model to obtain a fault troubleshooting decision tree; S3. Obtain current environmental data, equipment operation status data and layout data, substitute them into the fault troubleshooting decision tree, and determine the fault type of the substation; The construction of the CART model and the acquisition of the fault troubleshooting decision tree include the following steps: S11, select a certain explanatory variable as a feature, determine the split point of the feature to split the response variable data set into two data subsets, wherein the selected feature and split point make the purity of the split data subset the highest; S12, repeating the segmentation step for each data subset selection feature until it cannot be segmented any further, and generating a preliminary decision tree; S13, pruning the preliminary decision tree according to the order of data set segmentation to obtain a final decision tree as a troubleshooting decision tree; S14. Use the test set data to evaluate and verify the troubleshooting decision tree.

2. The intelligent monitoring platform for substations according to claim 1 is characterized by: In the equipment monitoring module, the electrical parameters include voltage, current, power and frequency; the physical parameters include vibration, equipment temperature and noise; the start-stop state indicates whether the equipment is in the start-up or stop state.

3. The intelligent monitoring platform for substations according to claim 1 is characterized in that: The GIS module also interpolates the environmental data and the equipment operation status data to the corresponding equipment location and presents them visually, including the following steps: By installing RFID tags on each device in the substation, the device location coordinates are determined; According to the location of the device and the collected data, an interpolation method is used to interpolate the environmental data and the device operating status data to the corresponding device location; the interpolation method is configured as an inverse distance weighted method or a Kriging interpolation method; The interpolated environmental data and equipment operating status data are presented on the GIS map in a visual way; Update environmental data and equipment operating status data regularly, and update interpolation results and visualization presentations.

4. The intelligent monitoring platform for substations according to claim 1 is characterized in that: In the GIS module, the links include the incoming link, transformer link, bus link, outgoing link and relay protection link, among which: The incoming line link introduces high voltage electricity from the power plant or the upper-level substation into the substation through overhead lines or cables; The transformer is responsible for converting high voltage electric energy into voltage levels suitable for different user needs; The bus link is divided into high-voltage bus, medium-voltage bus and low-voltage bus according to different voltage levels to control the flow and distribution of electric energy; The outgoing link transmits the electric energy transformed by the substation to the lower-level substation or user; The relay protection link cuts off the faulty equipment to protect the safety of the power grid and equipment when a fault occurs in the power system.

5. The intelligent monitoring platform for substations according to claim 1 is characterized by: In the fault troubleshooting module, the fault types include short circuit, open circuit, overvoltage and undervoltage.

6. The intelligent monitoring platform for substations according to claim 1 is characterized by: The fault detection module also includes a video monitoring module, which is used to monitor the operating conditions of various equipment in the substation in real time, check the appearance of the equipment, supervise the operation of personnel, assist in fault location and cause analysis, and ensure the safety of the substation.

7. The intelligent monitoring platform for substations according to claim 1 is characterized by: The fault troubleshooting module also includes a fault reporting module, which is used to report the current fault type and mark the location of the fault in the GIS module.

Images