Intelligent operation and maintenance robot real-time state monitoring system and method based on artificial intelligence

Abstract

The invention discloses an intelligent operation and maintenance robot real-time state monitoring system and method based on artificial intelligence, and belongs to the technical field of artificial intelligence. An intelligent operation and maintenance robot arrives at each equipment monitoring point of a transformer substation, a communication machine room or a data center to acquire multi-dimensional data; when arriving at a monitoring point, acquiring real-time electrical parameter data, and fusing the real-time electrical parameter data with the multi-dimensional data to obtain a data set; constructing a main analysis model by combining a convolutional neural network with a long short-term memory network, inputting the trained main analysis model, and outputting a current state evaluation result of the equipment; cooling medium parameters are measured, enthalpy difference changes in the cooling process are calculated, and the heat exchange efficiency of the cooling system is quantified; constructing a transformer cooling system performance evaluation model by using a support vector regression algorithm, and outputting a current heat dissipation capability coefficient of the cooling system; and judging whether the cooling system meets the heat dissipation requirement or not by combining the current heat dissipation capability coefficient of the cooling system with the current state evaluation result of the equipment.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a real-time status monitoring system and method for an intelligent operation and maintenance robot based on artificial intelligence. Background Art

[0002] Substations are key hubs in the power system, responsible for voltage conversion, power distribution and transmission. The safe and stable operation of their equipment is directly related to the reliability of the power grid. Any equipment failure may cause power outages, affecting industrial production, commercial activities and residents' lives. The communication room is the core facility of the communication network, carrying a large number of servers, switches, routers and other communication equipment, which ensure the transmission, exchange and storage of data. Data centers are key infrastructure in today's digital age, centrally storing and processing massive amounts of data, and providing computing resources and data services for various applications such as cloud computing, big data, and artificial intelligence.

[0003] For example, for substations, traditional manual inspections make it difficult to achieve real-time and continuous monitoring of substation equipment. Due to limited manpower, the inspection intervals are usually long, and it is impossible to capture sudden abnormalities of equipment during operation in a timely manner. Under the traditional operation and maintenance model, the recording and organization of detection data are mainly done manually, with inconsistent data formats and scattered storage, making it difficult to conduct large-scale data integration and in-depth mining. After discovering equipment abnormalities, manual inspections mainly rely on the experience and expertise of operation and maintenance personnel for fault diagnosis and decision-making, making it difficult to quickly and accurately determine the cause of the fault and formulate the best maintenance plan. Summary of the invention

[0004] The purpose of the present invention is to provide a real-time status monitoring system and method for an intelligent operation and maintenance robot based on artificial intelligence to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A real-time status monitoring method for an intelligent operation and maintenance robot based on artificial intelligence, the method comprising the following steps:

[0007] The intelligent operation and maintenance robot arrives at each equipment monitoring point according to the preset inspection path and time interval; activates the sensor array to collect multi-dimensional data;

[0008] Acquire real-time electrical parameter data from the monitoring system of the equipment, and fuse the real-time electrical parameter data with multi-dimensional data to obtain a substation data set;

[0009] The substation data set is preprocessed, and a main analysis model is built using a convolutional neural network combined with a long short-term memory network, wherein the convolutional neural network is used to automatically extract local features in image and sensor time series data, and the long short-term memory network is used to capture the time dependency in the data sequence; the main analysis model is trained and optimized, the preprocessed substation data set is input into the trained main analysis model, and the current status assessment result of the equipment is output;

[0010] Measure the parameters of the cooling medium, calculate the change in enthalpy difference during the cooling process, and quantify the heat exchange efficiency of the cooling system; based on the principles of thermodynamics and historical operating data, use the support vector regression algorithm to build a transformer cooling system performance evaluation model, input the cooling system heat exchange efficiency, ambient temperature and transformer load rate, and output the current heat dissipation capacity coefficient of the cooling system;

[0011] The current heat dissipation capacity coefficient of the cooling system is combined with the current status evaluation result of the equipment to determine whether the cooling system meets the heat dissipation requirements and issue a fault warning.

[0012] Specifically, the A* algorithm is used to grid the equipment distribution map, and each grid node is assigned a travel cost. The starting point is set as the robot charging and standby area, and the end point is the monitoring point of each device. The A* algorithm is used to calculate the route with the lowest comprehensive cost to ensure that the robot can traverse all equipment in the shortest path while avoiding the dangerous area with electricity and the equipment maintenance operation site.

[0013] The user sets the time interval. When the robot arrives at each equipment monitoring point, the lidar scans the surrounding environment contour in real time and matches it with the pre-stored map features. The visual odometer assists in correcting the displacement deviation, allowing the robot to monitor the position of the high-voltage switch cabinet door.

[0014] The robot activates the sensor array to take panoramic and detailed close-up photos of the device from different angles. It uses multispectral imaging to capture the device in infrared and ultraviolet bands. The infrared imaging is used to locate the heating parts of the device, and the ultraviolet imaging is used to detect whether the device has ultraviolet light generated by partial discharge.

[0015] The robot uses temperature and humidity sensors to obtain the temperature and humidity status of the environment in which the equipment is located in real time, uses gas sensors to obtain the concentration of gas in the environment in real time, and uses ultrasonic sensors to emit and receive ultrasonic waves to penetrate the device shell to detect the integrity of the internal structure.

[0016] The robot integrates the collected data to form multi-dimensional data.

[0017] The robot has several pre-built-in communication interface drivers for substation equipment. Through electrical signal feature matching and handshake protocol interaction, it determines the interface type, loads the corresponding driver, and establishes a physical link connection.

[0018] Specifically, the robot integrated protocol parsing engine, for IEC 61850 protocol, parses the service model from the abstract communication service interface layer, obtains the real-time data model object of the device, and actively obtains the real-time electrical parameter data according to the set period through the report service and the read service, including the instantaneous value of voltage and current, power factor and the circuit breaker opening and closing position signal; for private protocols, according to the protocol document provided by the equipment manufacturer, reversely parses the byte stream data format, locates and extracts the real-time electrical parameter data;

[0019] The network time protocol is used to keep synchronization with the clock source in the substation, and the clock accuracy is controlled at the millisecond level. The real-time electrical parameter data is merged with the multi-dimensional data according to the timestamp to obtain the substation data set.

[0020] The substation data set is preprocessed, including data cleaning and normalization. The convolutional neural network is constructed, using a multi-layer convolutional architecture to automatically extract low-level texture and edge features of images and sensor time series data curves. As the network deepens, the pooling layer is introduced to reduce the data dimension and the amount of calculation. For time series data, the one-dimensional convolution kernel of the convolutional neural network slides along the time dimension to capture the correlation features of data in different time periods.

[0021] Specifically, the convolutional neural network is connected to a long short-term memory network. In the long short-term memory network, the input gate, the forget gate and the output gate use a sigmoid activation function to control the flow of information, the memory unit state is updated based on the tanh function, and several layers of long short-term memory networks are stacked, each layer containing several hidden units, so that the model can capture the gradual trend of operating parameters in the time series.

[0022] The preprocessed substation data set is randomly divided into training set, validation set and test set in proportion. The model is trained using a small batch stochastic gradient descent algorithm, which is allocated according to the size of the data set and computing resources. During the training process, the learning rate decay strategy is used to gradually adjust the model parameters as the number of training rounds increases.

[0023] Specifically, the accuracy of the classification task is evaluated based on the cross entropy loss function. The classification task includes normal equipment and equipment failure. The mean square error loss is combined to measure the deviation of the quantitative prediction of the severity of the failure, and a composite loss function is formed to drive the model training. The early stopping method is introduced to continuously monitor the loss value of the validation set. If the loss value does not decrease for several consecutive epochs, the training is terminated in advance to prevent overfitting and lock the optimal generalization state of the model. L2 regularization is used to impose constraint penalties on the model weights. A grid search strategy is used to traverse and adjust the number of convolution kernels, size, number of long and short-term memory network layers, and number of hidden units of the convolutional neural network, and the optimal model configuration is selected based on the validation set performance indicators.

[0024] The trained and optimized main analysis model is deployed in the intelligent operation and maintenance robot. When the robot collects a new batch of substation data, it is input into the model in real time after preprocessing, and the model starts the forward propagation calculation; the model outputs the current status assessment results of the equipment, including the equipment health score, fault probability value and qualitative judgment of the fault type.

[0025] In the transformer cooling system of the substation, for the cooling oil, the inlet temperature T of the cooling oil is obtained in real time. oil，in and the outlet temperature of the cooling oil T oil,out , using Coriolis mass flowmeter to measure the mass flow rate of cooling oil m oil The measuring range depends on the scale of the transformer cooling system. For cooling air, the inlet temperature of the cooling air is measured. air,in and the outlet temperature of the cooling air T air,out ; Use a hot wire anemometer to measure the cooling air velocity, calculate the volume flow rate based on the cross-sectional area of ​​the air duct, and convert it into the mass flow rate of the cooling air m according to the standard state equation air ;

[0026] According to the principles of thermodynamics, the calculation formula for the change in enthalpy of cooling oil is:

[0027] ΔH oil =m oil *c p,oil *(T oil,out -T oil,in );

[0028] Where ΔH oil is the change in cooling oil enthalpy, c p，oil is the specific heat capacity of cooling oil at constant pressure;

[0029] The formula for the change in enthalpy of cooling air is:

[0030] ΔH air =m air *(h air,out -h air,in );

[0031] Where ΔH air is the change in cooling air enthalpy, h air，in is the specific enthalpy of the cooling air at the inlet, h air，out is the specific enthalpy of cooling air outlet, h air，in =c p，air *T air，in +d,h air,out =c p,air *T air,out +d,c p,air is the specific heat capacity of air at constant pressure, d is a constant term related to the reference enthalpy setting;

[0032] For the enthalpy difference change of the entire cooling system ΔH system Based on the law of conservation of energy, the heat released by the cooling oil should be equal to the heat absorbed by the cooling air, expressed as: ΔH system =ΔH oil =ΔH air

[0033] The heat exchange efficiency η of the cooling system is defined as the ratio of the actual heat exchange capacity to the theoretical maximum heat exchange capacity, and the calculation formula is:

[0034]

[0035] Where ΔH actual is the enthalpy difference change achieved by the cooling system in actual operation, and its value is ΔH system ; ΔH max is the theoretical limit enthalpy difference change, which is achieved when the inlet and outlet temperature difference of the cooling medium reaches the maximum possible temperature difference. For the oil-air cooling system, assuming that the cooling air temperature is constant, ΔH max It is approximately the change in enthalpy difference when the cooling oil is cooled from the initial temperature to the cooling air temperature. The formula is:

[0036] ΔH max =m oil *c p,oil *(T oil，in -T air,in ).

[0037] In the support vector regression algorithm, the radial basis function is selected as the kernel function. In the stage of model hyperparameter tuning, the grid search combined with the cross-validation strategy is used to traverse the penalty parameters and kernel functions, and the optimal combination is locked based on the minimum mean square error criterion of the validation set, so that the model simulates the dynamic performance of the cooling system; the historical data is divided into a training set and a test set in proportion, and the model training is started; during the training process, the model gradually learns the fluctuation law of the heat exchange efficiency of the cooling system under different combinations of ambient temperature and load rate, and constructs a mapping relationship from the input parameter space to the output space of the heat dissipation capacity coefficient; after the training is completed, the heat exchange efficiency of the cooling system, the ambient temperature and the transformer load rate are input into the model, and the current heat dissipation capacity coefficient of the cooling system is output.

[0038] At the same time stamp, the current heat dissipation capacity coefficient of the cooling system and the current status evaluation result of the equipment are captured; according to the substation equipment design manual and the statistical analysis of historical operation and maintenance data, the basic threshold range of the heat dissipation capacity coefficient is set for typical load conditions in different seasons and different time periods, and the threshold is dynamically corrected in combination with the oil temperature index in the current status evaluation result of the equipment.

[0039] Specifically, when the current heat dissipation capacity coefficient of the cooling system is lower than the lower limit of the threshold by less than A1, the equipment health score is between B2 and B3, the fault probability value is between C1% and C2%, and there is no key fault type prompt, a first-level warning is triggered. After receiving the warning instruction, the intelligent operation and maintenance robot automatically shortens the inspection cycle and pushes the warning information to the operation and maintenance personnel's mobile terminal;

[0040] If the current heat dissipation capacity coefficient of the cooling system is lower than the threshold A1-A2, the equipment health score drops to B1-B2, the failure probability rises to C2%-C3%, or a failure type that affects equipment operation but does not endanger power supply safety occurs, triggering a secondary warning. In addition to supervising the robot to increase the frequency of inspections, the operation and maintenance system also pops up an alarm on the large screen of the substation monitoring center and sends an emergency plan to the operation and maintenance team;

[0041] When the heat dissipation capacity coefficient is lower than the threshold value A2, the equipment health score is lower than B1, the failure probability exceeds C3%, or a high-risk failure type is identified, the third-level warning is activated. If conditions permit, the substation automatic control system will reduce the load of the equipment. If conditions do not permit, a local power outage will be carried out to avoid risks. An alarm will pop up on the large screen of the substation monitoring center, the sound and light prompts will be strengthened, and an emergency plan will be sent to the operation and maintenance team. Among them, A1, A2, B1, B2, B3, C1, C2 and C3 are all positive decimals, which are automatically set by the system.

[0042] The real-time status monitoring system of intelligent operation and maintenance robots based on artificial intelligence includes:

[0043] Inspection and data collection module: including: path planning and navigation unit and sensor array start and control unit; the path planning and navigation unit enables the intelligent operation and maintenance robot to arrive at each equipment monitoring point according to the preset inspection path and time interval; the sensor array start and control unit starts the sensor array to collect multi-dimensional data;

[0044] Data fusion and preprocessing module: including: electrical parameter acquisition and adaptation unit, data fusion unit and preprocessing unit; wherein, the electrical parameter acquisition and adaptation unit acquires real-time electrical parameter data from the monitoring system of the equipment, the data fusion unit fuses the real-time electrical parameter data with the multi-dimensional data to obtain the substation data set, and the preprocessing unit preprocesses the substation data set;

[0045] Model building and analysis module: including: model building unit, model training and optimization unit and real-time evaluation unit; wherein, the model building unit uses convolutional neural network combined with long short-term memory network to build the main analysis model, the convolutional neural network is used to automatically extract local features in image and sensor time series data, and the long short-term memory network is used to capture the time dependency in the data sequence; the model training and optimization unit trains and optimizes the main analysis model, and the real-time evaluation unit inputs the preprocessed substation data set into the trained main analysis model and outputs the current status evaluation result of the equipment;

[0046] Heat dissipation capacity coefficient calculation module: including: enthalpy difference calculation and efficiency evaluation unit and heat dissipation capacity coefficient calculation unit; wherein, the enthalpy difference calculation and efficiency evaluation unit measures the cooling medium parameters, calculates the enthalpy difference change during the cooling process, and quantifies the heat exchange efficiency of the cooling system; the heat dissipation capacity coefficient calculation unit is based on thermodynamic principles and historical operation data, and uses the support vector regression algorithm to build a transformer cooling system performance evaluation model, inputs the cooling system heat exchange efficiency, ambient temperature and transformer load rate, and outputs the current heat dissipation capacity coefficient of the cooling system;

[0047] Fault warning and decision support module: including: a comprehensive judgment unit and a warning push unit; wherein the comprehensive judgment unit combines the current heat dissipation capacity coefficient of the cooling system with the current status evaluation result of the equipment, and the warning push unit determines whether the cooling system meets the heat dissipation requirements and issues a fault warning.

[0048] Compared with the prior art, the present invention has the following beneficial effects:

[0049] 1. Based on preset inspection paths and time intervals, the intelligent operation and maintenance robot of the present invention can autonomously shuttle within the substation, accurately arrive at each equipment monitoring point at the set time interval, start the sensor array, and quickly and synchronously collect multi-dimensional data.

[0050] 2. The present invention uses a convolutional neural network combined with a long short-term memory network to build a main analysis model to conduct in-depth analysis of the collected massive substation data sets. The convolutional neural network can automatically extract local features in image and sensor time series data, while the long short-term memory network is good at capturing the time dependencies in data sequences.

[0051] 3. Based on the analysis results of the artificial intelligence algorithm, the present invention can provide intelligent decision support for substation operation and maintenance. The system automatically determines whether the equipment has a failure risk and whether the cooling system meets the heat dissipation requirements based on the current status evaluation results of the equipment and the cooling system performance evaluation results, and provides graded warnings based on the severity of the failure. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the steps of the real-time status monitoring method of the intelligent operation and maintenance robot based on artificial intelligence of the present invention;

[0053] Figure 2 It is a system structure diagram of the real-time status monitoring system of the intelligent operation and maintenance robot based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0055] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution.

[0056] According to one embodiment of the present invention, Figure 1 The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence is shown in the schematic diagram of the steps. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence comprises the following steps:

[0057] The intelligent operation and maintenance robot arrives at each equipment monitoring point according to the preset inspection path and time interval; activates the sensor array to collect multi-dimensional data;

[0058] Acquire real-time electrical parameter data from the monitoring system of the equipment, and fuse the real-time electrical parameter data with multi-dimensional data to obtain a substation data set;

[0059] The substation data set is preprocessed, and a main analysis model is built using a convolutional neural network combined with a long short-term memory network, wherein the convolutional neural network is used to automatically extract local features in image and sensor time series data, and the long short-term memory network is used to capture the time dependency in the data sequence; the main analysis model is trained and optimized, the preprocessed substation data set is input into the trained main analysis model, and the current status assessment result of the equipment is output;

[0060] Measure the parameters of the cooling medium, calculate the change in enthalpy difference during the cooling process, and quantify the heat exchange efficiency of the cooling system; based on the principles of thermodynamics and historical operating data, use the support vector regression algorithm to build a transformer cooling system performance evaluation model, input the cooling system heat exchange efficiency, ambient temperature and transformer load rate, and output the current heat dissipation capacity coefficient of the cooling system;

[0061] The current heat dissipation capacity coefficient of the cooling system is combined with the current status evaluation result of the equipment to determine whether the cooling system meets the heat dissipation requirements and issue a fault warning.

[0062] Specifically, the A* algorithm is used to grid the equipment distribution map, and each grid node is assigned a travel cost. The starting point is set as the robot charging and standby area, and the end point is the monitoring point of each device. The A* algorithm is used to calculate the route with the lowest comprehensive cost to ensure that the robot can traverse all equipment in the shortest path while avoiding the dangerous area with electricity and the equipment maintenance operation site.

[0063] The user sets the time interval. When the robot arrives at each equipment monitoring point, the lidar scans the surrounding environment contour in real time and matches it with the pre-stored map features. The visual odometer assists in correcting the displacement deviation, allowing the robot to monitor the position of the high-voltage switch cabinet door.

[0064] The robot activates the sensor array to take panoramic and detailed close-up photos of the device from different angles. It uses multispectral imaging to capture the device in infrared and ultraviolet bands. The infrared imaging is used to locate the heating parts of the device, and the ultraviolet imaging is used to detect whether the device has ultraviolet light generated by partial discharge.

[0065] The robot uses temperature and humidity sensors to obtain the temperature and humidity status of the environment in which the equipment is located in real time, uses gas sensors to obtain the concentration of gas in the environment in real time, and uses ultrasonic sensors to emit and receive ultrasonic waves to penetrate the device shell to detect the integrity of the internal structure.

[0066] The robot integrates the collected data to form multi-dimensional data.

[0067] The robot has several pre-built-in communication interface drivers for substation equipment. Through electrical signal feature matching and handshake protocol interaction, it determines the interface type, loads the corresponding driver, and establishes a physical link connection.

[0068] Specifically, the robot integrated protocol parsing engine, for IEC 61850 protocol, parses the service model from the abstract communication service interface layer, obtains the real-time data model object of the device, and actively obtains the real-time electrical parameter data according to the set period through the report service and the read service, including the instantaneous value of voltage and current, power factor and the circuit breaker opening and closing position signal; for private protocols, according to the protocol document provided by the equipment manufacturer, reversely parses the byte stream data format, locates and extracts the real-time electrical parameter data;

[0069] The network time protocol is used to keep synchronization with the clock source in the substation, and the clock accuracy is controlled at the millisecond level. The real-time electrical parameter data is merged with the multi-dimensional data according to the timestamp to obtain the substation data set.

[0070] The substation data set is preprocessed, including data cleaning and normalization. The convolutional neural network is constructed, using a multi-layer convolutional architecture to automatically extract low-level texture and edge features of images and sensor time series data curves. As the network deepens, the pooling layer is introduced to reduce the data dimension and the amount of calculation. For time series data, the one-dimensional convolution kernel of the convolutional neural network slides along the time dimension to capture the correlation features of data in different time periods.

[0071] Specifically, the convolutional neural network is connected to a long short-term memory network. In the long short-term memory network, the input gate, the forget gate and the output gate use a sigmoid activation function to control the flow of information, the memory unit state is updated based on the tanh function, and several layers of long short-term memory networks are stacked, each layer containing several hidden units, so that the model can capture the gradual trend of operating parameters in the time series.

[0072] In this embodiment, a convolutional neural network (CNN) part is constructed, the first layer convolution kernel is set to a size of 3×3, the step size is 1, the number of convolution kernels is 32, and ReLU is used as the activation function to preliminarily extract low-level texture and edge features of the image and sensor time series data curve. As the network deepens, the size of the second layer convolution kernel is adjusted to 5×5, and the number is increased to 64. The ReLU activation function is also used. After that, the maximum pooling layer is introduced, and the pooling kernel is 2×2 with a step size of 2 to reduce the data dimension and reduce the amount of calculation. For time series data, the one-dimensional convolution kernel of CNN slides along the time dimension. For example, the convolution kernel size is set to 3 and the step size is 1 to capture the data association features of different time periods.

[0073] Connect CNN to the long short-term memory network (LSTM). In LSTM, the input gate, forget gate, and output gate use sigmoid activation functions to control the flow of information, and the memory unit state update is based on the tanh function. Stack two layers of LSTM, each with 128 hidden units, so that the model can capture the gradual trend of operating parameters in the time series.

[0074] The model training adopts the small batch stochastic gradient descent algorithm, and the preprocessed substation data set is randomly divided into training set, validation set and test set at a ratio of 70%, 20% and 10%. According to the scale of the data set and computing resources, the small batch size is set to 64. The initial learning rate is set to 0.001, and the learning rate decay strategy is used during the training process. After every 5 epochs, the learning rate decays to 0.9 times the original value, and the model parameters are gradually adjusted as the number of training rounds increases.

[0075] Based on the cross entropy loss function, the accuracy of the classification task (classification of normal equipment and equipment failure) is evaluated. Combined with the mean square error loss, the deviation of the quantitative prediction of the fault severity is measured, and a composite loss function is formed to drive the model training. The early stopping method is introduced to continuously monitor the loss value of the validation set. If it does not decrease for 10 consecutive epochs, the training is terminated in advance to prevent overfitting and lock the optimal generalization state of the model. L2 regularization is used to impose constraint penalties on the model weights, and the regularization coefficient is set to 0.01. A grid search strategy is used to traverse and adjust the number of convolution kernels (range 16-64, step size 16), size (3×3, 5×5), number of LSTM layers (1-3) and number of hidden units (64-256, step size 64) of CNN, and the optimal model configuration is selected based on the validation set performance indicators (accuracy, recall rate, F1 value, root mean square error, etc.).

[0076] The model is trained using the training set. During the training process, as the number of epochs increases, the loss value of the model on the training set gradually decreases, and the performance indicators on the validation set are also constantly changing.

[0077] During the grid search process, different hyperparameter combinations were fully evaluated. When the number of CNN convolution kernels was 32, the size was 3×3, the number of LSTM layers was 2, and the number of hidden units was 128, the model had the best overall performance on the validation set, with an accuracy of 92%, a recall of 90%, an F1 value of 0.91, and a root mean square error of 0.12. These indicators show that the model can accurately classify the normal and fault states of the equipment, and also has high accuracy in quantitatively predicting the severity of the fault.

[0078] Specifically analyzing the equipment current status assessment results output by the model, the model can accurately give a score for the equipment health score based on the multi-dimensional data of the equipment. For example, a main transformer in good operating condition has a health score of 90 points; for equipment with some potential hidden dangers (such as slightly high oil temperature and slightly abnormal vibration), the health score is between 60-80 points; for equipment that has obvious signs of failure (such as partial discharge and insulation aging), the health score is less than 60 points.

[0079] In terms of numerical prediction of fault probability, the model can give corresponding probability estimates for different types of faults. For example, for a switch cabinet, the model predicts that the probability of a poor contact fault is 15%. After further inspection, it was found that the connection parts of the switch cabinet did have slight oxidation, resulting in a slight increase in contact resistance, which verified the accuracy of the model prediction.

[0080] For qualitative identification of fault types, the model can accurately identify a variety of common fault types. For example, in the monitoring of a transformer, the model determined that its fault type was "core multi-point grounding fault". After disassembling and inspecting the transformer, it was found that the core did have a multi-point grounding problem, which further proved the reliability of the model in fault diagnosis.

[0081] In the transformer cooling system of the substation, for the cooling oil, the inlet temperature T of the cooling oil is obtained in real time. oil，in and the outlet temperature of the cooling oil T oil，out , using Coriolis mass flowmeter to measure the mass flow rate of cooling oil m oil The measuring range depends on the scale of the transformer cooling system. For cooling air, the inlet temperature of the cooling air is measured. air，in and the outlet temperature of the cooling air T air，out ; Use a hot wire anemometer to measure the cooling air velocity, calculate the volume flow rate based on the cross-sectional area of ​​the air duct, and convert it into the mass flow rate of the cooling air m according to the standard state equation air ;

[0082] According to the principles of thermodynamics, the calculation formula for the change in enthalpy of cooling oil is:

[0083] ΔH oil =m oil *c p,oil *(T oil,out -T oil,in );

[0084] Where ΔH oil is the change in cooling oil enthalpy, c p，oil is the specific heat capacity of cooling oil at constant pressure;

[0085] The formula for the change in enthalpy of cooling air is:

[0086] ΔH air =m air *(h air,out -h air,in );

[0087] Where ΔH air is the change in cooling air enthalpy, h air，in is the specific enthalpy of the cooling air at the inlet, h air，out is the specific enthalpy of cooling air outlet, h air，in =c p,air *T air，in +d,h air,out =c p,air *T air,out +d,c p,air is the specific heat capacity of air at constant pressure, d is a constant term related to the reference enthalpy setting;

[0088] For the enthalpy difference change of the entire cooling system ΔH system Based on the law of conservation of energy, the heat released by the cooling oil should be equal to the heat absorbed by the cooling air, expressed as: ΔH system =ΔH oil =ΔH air ;

[0089] The heat exchange efficiency η of the cooling system is defined as the ratio of the actual heat exchange capacity to the theoretical maximum heat exchange capacity, and the calculation formula is:

[0090]

[0091] Where ΔH actual is the enthalpy difference change achieved by the cooling system in actual operation, and its value is ΔH system ; ΔH max is the theoretical limit enthalpy difference change, which is achieved when the inlet and outlet temperature difference of the cooling medium reaches the maximum possible temperature difference. For the oil-air cooling system, assuming that the cooling air temperature is constant, ΔH max It is approximately the change in enthalpy difference when the cooling oil is cooled from the initial temperature to the cooling air temperature. The formula is:

[0092] ΔH max =m oil *c p,oil *(T oil，in -T air,in ).

[0093] In the support vector regression algorithm, the radial basis function is selected as the kernel function. In the stage of model hyperparameter tuning, the grid search combined with the cross-validation strategy is used to traverse the penalty parameters and kernel functions, and the optimal combination is locked based on the minimum mean square error criterion of the validation set, so that the model simulates the dynamic performance of the cooling system; the historical data is divided into a training set and a test set in proportion, and the model training is started; during the training process, the model gradually learns the fluctuation law of the heat exchange efficiency of the cooling system under different combinations of ambient temperature and load rate, and constructs a mapping relationship from the input parameter space to the output space of the heat dissipation capacity coefficient; after the training is completed, the heat exchange efficiency of the cooling system, the ambient temperature and the transformer load rate are input into the model, and the current heat dissipation capacity coefficient of the cooling system is output.

[0094] At the same time stamp, the current heat dissipation capacity coefficient of the cooling system and the current status evaluation result of the equipment are captured; according to the substation equipment design manual and the statistical analysis of historical operation and maintenance data, the basic threshold range of the heat dissipation capacity coefficient is set for typical load conditions in different seasons and different time periods, and the threshold is dynamically corrected in combination with the oil temperature index in the current status evaluation result of the equipment.

[0095] Specifically, when the current heat dissipation capacity coefficient of the cooling system is lower than the lower limit of the threshold by less than A1, the equipment health score is between B2 and B3, the fault probability value is between C1% and C2%, and there is no key fault type prompt, a first-level warning is triggered. After receiving the warning instruction, the intelligent operation and maintenance robot automatically shortens the inspection cycle and pushes the warning information to the operation and maintenance personnel's mobile terminal;

[0096] If the current heat dissipation capacity coefficient of the cooling system is lower than the threshold A1-A2, the equipment health score drops to B1-B2, the failure probability rises to C2%-C3%, or a failure type that affects equipment operation but does not endanger power supply safety occurs, triggering a secondary warning. In addition to supervising the robot to increase the frequency of inspections, the operation and maintenance system also pops up an alarm on the large screen of the substation monitoring center and sends an emergency plan to the operation and maintenance team;

[0097] When the heat dissipation capacity coefficient is lower than the threshold value A2, the equipment health score is lower than B1, the failure probability exceeds C3%, or a high-risk failure type is identified, the third-level warning is activated. If conditions permit, the substation automatic control system will reduce the load of the equipment. If conditions do not permit, a local power outage will be carried out to avoid risks. An alarm will pop up on the large screen of the substation monitoring center, the sound and light prompts will be strengthened, and an emergency plan will be sent to the operation and maintenance team. Among them, A1, A2, B1, B2, B3, C1, C2 and C3 are all positive decimals, which are automatically set by the system.

[0098] According to another embodiment of the present invention, Figure 2 As shown in the system structure diagram of the real-time status monitoring system of the intelligent operation and maintenance robot based on artificial intelligence, the real-time status monitoring system of the intelligent operation and maintenance robot based on artificial intelligence includes:

[0099] Inspection and data collection module: including: path planning and navigation unit and sensor array start and control unit; the path planning and navigation unit enables the intelligent operation and maintenance robot to arrive at each equipment monitoring point according to the preset inspection path and time interval; the sensor array start and control unit starts the sensor array to collect multi-dimensional data;

[0100] Data fusion and preprocessing module: including: electrical parameter acquisition and adaptation unit, data fusion unit and preprocessing unit; wherein, the electrical parameter acquisition and adaptation unit acquires real-time electrical parameter data from the monitoring system of the equipment, the data fusion unit fuses the real-time electrical parameter data with the multi-dimensional data to obtain the substation data set, and the preprocessing unit preprocesses the substation data set;

[0101] Model building and analysis module: including: model building unit, model training and optimization unit and real-time evaluation unit; wherein, the model building unit uses convolutional neural network combined with long short-term memory network to build the main analysis model, the convolutional neural network is used to automatically extract local features in image and sensor time series data, and the long short-term memory network is used to capture the time dependency in the data sequence; the model training and optimization unit trains and optimizes the main analysis model, and the real-time evaluation unit inputs the preprocessed substation data set into the trained main analysis model and outputs the current status evaluation result of the equipment;

[0102] Heat dissipation capacity coefficient calculation module: including: enthalpy difference calculation and efficiency evaluation unit and heat dissipation capacity coefficient calculation unit; wherein, the enthalpy difference calculation and efficiency evaluation unit measures the cooling medium parameters, calculates the enthalpy difference change during the cooling process, and quantifies the heat exchange efficiency of the cooling system; the heat dissipation capacity coefficient calculation unit is based on thermodynamic principles and historical operation data, and uses the support vector regression algorithm to build a transformer cooling system performance evaluation model, inputs the cooling system heat exchange efficiency, ambient temperature and transformer load rate, and outputs the current heat dissipation capacity coefficient of the cooling system;

[0103] In this embodiment, the enthalpy difference change is calculated based on the collected cooling medium parameters and the heat exchange efficiency is evaluated. Taking one set of data as an example, the cooling oil inlet temperature is 60°C, the outlet temperature is 50°C, the mass flow rate is 100kg / s, the cooling air inlet temperature is 25°C, the outlet temperature is 35°C, and the mass flow rate is 500kg / s. Assuming that the constant pressure specific heat capacity of the cooling oil is 2kJ / (kg·℃) within this temperature range, according to the cooling oil enthalpy change formula, the cooling oil enthalpy change can be obtained as: 100*2*(50-60)=-2000kJ.

[0104] Assuming that the specific heat capacity of air at constant pressure is 1.005 kJ / (kg·℃), for dry air, the change in enthalpy of cooling air is: 500*1.005*(35-25)=5025 kJ. Due to the law of energy conservation, the actual heat exchange capacity should be the smaller of the two absolute values, that is, 2000 kJ.

[0105] Assuming the theoretical maximum heat exchange capacity is 2500 kJ, the heat exchange efficiency at this moment is: 2000 / 2500*100%=80%.

[0106] In the entire data set, the calculated heat exchange efficiency is distributed between 60% and 95%, with an average heat exchange efficiency of about 75%. Among them, when the ambient temperature is high (over 35°C) and the transformer load rate is greater than 80%, the heat exchange efficiency drops significantly, and even falls below 65% in some periods, indicating that the cooling system faces greater pressure under high temperature and high load conditions.

[0107] The calculated heat exchange efficiency and the corresponding ambient temperature and transformer load rate data are input into the constructed SVR model to calculate the heat dissipation capacity coefficient. After grid search and cross-validation, it is determined that the model performance is best when the penalty parameter C = 1 and the kernel function parameter γ = 0.1.

[0108] The dataset was divided into training set, validation set and test set in the ratio of 70%, 20% and 10%. After the model was trained on the training set, it was evaluated on the validation set. The mean square error (MSE) of the model on the validation set was 0.025, and the coefficient of determination (R 2 ) is 0.85. This shows that the model can fit the data well and has a high accuracy in predicting the heat dissipation capacity coefficient.

[0109] The results of the test set show that the average error between the heat dissipation capacity coefficient predicted by the model and the heat dissipation capacity coefficient actually calculated is 0.03, and the relative error is within 5%. For example, for a set of test data, the actual heat dissipation capacity coefficient is 0.78, and the model predicts a value of 0.80.

[0110] By analyzing the test data under different working conditions, it is found that when the ambient temperature is low (less than 20°C) and the load rate is less than 50%, the heat dissipation capacity coefficient predicted by the model is relatively stable and highly consistent with the actual value; when the ambient temperature and load rate change dramatically, the model can also track the change trend of the heat dissipation capacity coefficient well, but the error is relatively large, but still within an acceptable range. This shows that the constructed SVR model can effectively calculate the heat dissipation capacity coefficient based on the heat exchange efficiency of the cooling system, the ambient temperature and the transformer load rate, providing a reliable basis for judging whether the cooling system meets the heat dissipation requirements.

[0111] Fault warning and decision support module: including: a comprehensive judgment unit and a warning push unit; wherein the comprehensive judgment unit combines the current heat dissipation capacity coefficient of the cooling system with the current status evaluation result of the equipment, and the warning push unit determines whether the cooling system meets the heat dissipation requirements and issues a fault warning.

[0112] 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. A real-time status monitoring method for an intelligent operation and maintenance robot based on artificial intelligence, characterized in that: The method comprises the following steps: The intelligent operation and maintenance robot arrives at each equipment monitoring point according to the preset inspection path and time interval; activates the sensor array to collect multi-dimensional data; Acquire real-time electrical parameter data from the monitoring system of the equipment, and fuse the real-time electrical parameter data with multi-dimensional data to obtain a substation data set; The substation data set is preprocessed, and a main analysis model is built using a convolutional neural network combined with a long short-term memory network, wherein the convolutional neural network is used to automatically extract local features in image and sensor time series data, and the long short-term memory network is used to capture the time dependency in the data sequence; the main analysis model is trained and optimized, the preprocessed substation data set is input into the trained main analysis model, and the current status assessment result of the equipment is output; Measure the parameters of the cooling medium, calculate the change in enthalpy difference during the cooling process, and quantify the heat exchange efficiency of the cooling system; based on the principles of thermodynamics and historical operating data, use the support vector regression algorithm to build a transformer cooling system performance evaluation model, input the cooling system heat exchange efficiency, ambient temperature and transformer load rate, and output the current heat dissipation capacity coefficient of the cooling system; The current heat dissipation capacity coefficient of the cooling system is combined with the current status evaluation result of the equipment to determine whether the cooling system meets the heat dissipation requirements and issue a fault warning.

2. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence according to claim 1 is characterized in that: The A* algorithm is used to grid the equipment distribution map. Each grid node is assigned a travel cost. The starting point is set as the robot charging and standby area, and the end point is the monitoring point of each device. The A* algorithm is used to calculate the route with the lowest comprehensive cost to ensure that the robot can traverse all equipment in the shortest path while avoiding the dangerous areas with electricity and the equipment maintenance operation site. The user sets the time interval. When the robot arrives at each equipment monitoring point, the lidar scans the surrounding environment contour in real time and matches it with the pre-stored map features. The visual odometer assists in correcting the displacement deviation, allowing the robot to monitor the position of the high-voltage switch cabinet door.

3. The real-time status monitoring method of the intelligent operation and maintenance robot based on artificial intelligence according to claim 2 is characterized by: The robot activates the sensor array to take panoramic and detailed close-up photos of the device from different angles. It uses multispectral imaging to capture the device in infrared and ultraviolet bands. The infrared imaging is used to locate the heating parts of the device, and the ultraviolet imaging is used to detect whether the device has ultraviolet light generated by partial discharge. The robot uses temperature and humidity sensors to obtain the temperature and humidity status of the environment in which the equipment is located in real time, uses gas sensors to obtain the concentration of gas in the environment in real time, and uses ultrasonic sensors to emit and receive ultrasonic waves to penetrate the device shell to detect the integrity of the internal structure. The robot integrates the collected data to form multi-dimensional data.

4. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence according to claim 3 is characterized in that: The robot has several pre-built-in communication interface drivers for substation equipment. Through electrical signal feature matching and handshake protocol interaction, it determines the interface type, loads the corresponding driver, and establishes a physical link connection. The robot integrated protocol parsing engine, for the IEC 61850 protocol, parses the service model from the abstract communication service interface layer, obtains the real-time data model object of the device, and actively obtains the real-time electrical parameter data according to the set cycle through the report service and read service, including the instantaneous value of voltage and current, power factor and circuit breaker opening and closing position signal; For private protocols, reverse parse the byte stream data format according to the protocol document provided by the equipment manufacturer, locate and extract the real-time electrical parameter data; The network time protocol is used to keep synchronization with the clock source in the substation, and the clock accuracy is controlled at the millisecond level. The real-time electrical parameter data is merged with the multi-dimensional data according to the timestamp to obtain the substation data set.

5. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence according to claim 1 is characterized in that: The substation data set is preprocessed, including data cleaning and normalization. The convolutional neural network is constructed, using a multi-layer convolutional architecture to automatically extract low-level texture and edge features of images and sensor time series data curves. As the network deepens, the pooling layer is introduced to reduce the data dimension and the amount of calculation. For time series data, the one-dimensional convolution kernel of the convolutional neural network slides along the time dimension to capture the correlation features of data in different time periods. The convolutional neural network is connected to a long short-term memory network. In the long short-term memory network, the input gate, the forget gate and the output gate use the sigmoid activation function to control the information flow, the memory unit state is updated based on the tanh function, and several layers of long short-term memory networks are stacked, each layer containing several hidden units, so that the model can capture the gradual trend of operating parameters in the time series.

6. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence according to claim 5 is characterized in that: The preprocessed substation data set is randomly divided into training set, validation set and test set in proportion. The model is trained using a small batch stochastic gradient descent algorithm, which is allocated according to the size of the data set and computing resources. During the training process, the learning rate decay strategy is used to gradually adjust the model parameters as the number of training rounds increases. The accuracy of the classification task is evaluated based on the cross entropy loss function. The classification task includes normal equipment and equipment failure. The mean square error loss is combined to measure the deviation of the quantitative prediction of the fault severity, and a composite loss function is formed to drive the model training. The early stopping method is introduced to continuously monitor the loss value of the validation set. If the loss value does not decrease for several consecutive epochs, the training is terminated in advance to prevent overfitting and lock the optimal generalization state of the model. L2 regularization is used to impose constraint penalties on the model weights. A grid search strategy is used to traverse and adjust the number of convolution kernels, size, number of long and short-term memory network layers, and number of hidden units of the convolutional neural network, and the optimal model configuration is selected based on the validation set performance indicators. The trained and optimized main analysis model is deployed in the intelligent operation and maintenance robot. When the robot collects a new batch of substation data, it is input into the model in real time after preprocessing, and the model starts the forward propagation calculation; the model outputs the current status assessment results of the equipment, including the equipment health score, fault probability value and qualitative judgment of the fault type.

7. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence according to claim 1 is characterized in that: In the transformer cooling system of the substation, for the cooling oil, the inlet temperature T of the cooling oil is obtained in real time. oil，in and the outlet temperature of the cooling oil T oil，out , using Coriolis mass flowmeter to measure the mass flow rate of cooling oil m oil The measuring range depends on the scale of the transformer cooling system. For cooling air, the inlet temperature of the cooling air is measured. air，in and the outlet temperature of the cooling air T air，out ; Use a hot wire anemometer to measure the cooling air velocity, calculate the volume flow rate based on the cross-sectional area of ​​the air duct, and convert it into the mass flow rate of the cooling air m according to the standard state equation air ; According to the principles of thermodynamics, the calculation formula for the change in enthalpy of cooling oil is: ΔH oil =m oil *c p，oil *(T oil，out -T oil，in ); Where ΔH oil is the change in cooling oil enthalpy, c p，oil is the specific heat capacity of cooling oil at constant pressure; The formula for the change in enthalpy of cooling air is: ΔH air =m air *(h air，out -h air，in ); Where ΔH air is the change in cooling air enthalpy, h air，in is the specific enthalpy of the cooling air at the inlet, h air，out is the specific enthalpy of cooling air outlet, h air，in =c p，air *T air，in +d,h air，out =c p，air *T air，out +d,c p，air is the specific heat capacity of air at constant pressure, d is a constant term related to the reference enthalpy setting; For the enthalpy difference change of the entire cooling system ΔH system Based on the law of conservation of energy, the heat released by the cooling oil should be equal to the heat absorbed by the cooling air, expressed as: ΔH system =ΔH oil =ΔH air ; The heat exchange efficiency η of the cooling system is defined as the ratio of the actual heat exchange capacity to the theoretical maximum heat exchange capacity, and the calculation formula is: Where ΔH actual is the enthalpy difference change achieved by the cooling system in actual operation, and its value is ΔH system ; ΔH max is the theoretical limit enthalpy difference change, which is achieved when the inlet and outlet temperature difference of the cooling medium reaches the maximum possible temperature difference. For the oil-air cooling system, assuming that the cooling air temperature is constant, ΔH max It is approximately the change in enthalpy difference when the cooling oil is cooled from the initial temperature to the cooling air temperature. The formula is: ΔH max =m oil *c p,oil *(T oil,in -T air,in ).

8. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence according to claim 7 is characterized in that: In the support vector regression algorithm, the radial basis function is selected as the kernel function. In the stage of model hyperparameter tuning, the grid search combined with the cross-validation strategy is used to traverse the penalty parameters and kernel functions, and the optimal combination is locked based on the minimum mean square error criterion of the validation set, so that the model simulates the dynamic performance of the cooling system; the historical data is divided into a training set and a test set in proportion, and the model training is started; during the training process, the model gradually learns the fluctuation law of the heat exchange efficiency of the cooling system under different combinations of ambient temperature and load rate, and constructs a mapping relationship from the input parameter space to the output space of the heat dissipation capacity coefficient; after the training is completed, the heat exchange efficiency of the cooling system, the ambient temperature and the transformer load rate are input into the model, and the current heat dissipation capacity coefficient of the cooling system is output.

9. The method for real-time status monitoring of an intelligent operation and maintenance robot based on artificial intelligence according to claim 1, characterized in that: At the same time stamp, the current heat dissipation capacity coefficient of the cooling system and the current status evaluation result of the equipment are captured; according to the substation equipment design manual and the statistical analysis of historical operation and maintenance data, the basic threshold range of the heat dissipation capacity coefficient is set for typical load conditions in different seasons and different time periods, and the threshold is dynamically corrected in combination with the oil temperature index in the current status evaluation result of the equipment. When the current heat dissipation capacity coefficient of the cooling system is within A1 of the lower threshold, the equipment health score is between B2 and B3, the fault probability value is between C1% and C2%, and there is no key fault type prompt, a first-level warning is triggered. After receiving the warning instruction, the intelligent operation and maintenance robot automatically shortens the inspection cycle and pushes the warning information to the operation and maintenance personnel's mobile terminal; If the current heat dissipation capacity coefficient of the cooling system is lower than the threshold A1-A2, the equipment health score drops to B1-B2, the failure probability rises to C2%-C3%, or a failure type that affects equipment operation but does not endanger power supply safety occurs, triggering a secondary warning. In addition to supervising the robot to increase the frequency of inspections, the operation and maintenance system also pops up an alarm on the large screen of the substation monitoring center and sends an emergency plan to the operation and maintenance team; When the heat dissipation capacity coefficient is lower than the threshold value A2, the equipment health score is lower than B1, the failure probability exceeds C3%, or a high-risk failure type is identified, the third-level warning is activated. If conditions permit, the substation automatic control system will reduce the load of the equipment. If conditions do not permit, a local power outage will be carried out to avoid risks. An alarm will pop up on the large screen of the substation monitoring center, the sound and light prompts will be strengthened, and an emergency plan will be sent to the operation and maintenance team. Among them, A1, A2, B1, B2, B3, C1, C2 and C3 are all positive decimals, which are automatically set by the system.

10. A real-time status monitoring system for an intelligent operation and maintenance robot based on artificial intelligence, using the real-time status monitoring method for an intelligent operation and maintenance robot based on artificial intelligence as claimed in any one of claims 1 to 9, characterized in that: include: Inspection and data collection module: including: path planning and navigation unit and sensor array start and control unit; the path planning and navigation unit enables the intelligent operation and maintenance robot to arrive at each equipment monitoring point according to the preset inspection path and time interval; the sensor array start and control unit starts the sensor array to collect multi-dimensional data; Data fusion and preprocessing module: including: electrical parameter acquisition and adaptation unit, data fusion unit and preprocessing unit; wherein, the electrical parameter acquisition and adaptation unit acquires real-time electrical parameter data from the monitoring system of the equipment, the data fusion unit fuses the real-time electrical parameter data with the multi-dimensional data to obtain the substation data set, and the preprocessing unit preprocesses the substation data set; Model building and analysis module: including: model building unit, model training and optimization unit and real-time evaluation unit; wherein, the model building unit uses convolutional neural network combined with long short-term memory network to build the main analysis model, the convolutional neural network is used to automatically extract local features in image and sensor time series data, and the long short-term memory network is used to capture the time dependency in the data sequence; the model training and optimization unit trains and optimizes the main analysis model, and the real-time evaluation unit inputs the preprocessed substation data set into the trained main analysis model and outputs the current status evaluation result of the equipment; Heat dissipation capacity coefficient calculation module: including: enthalpy difference calculation and efficiency evaluation unit and heat dissipation capacity coefficient calculation unit; wherein, the enthalpy difference calculation and efficiency evaluation unit measures the cooling medium parameters, calculates the enthalpy difference change during the cooling process, and quantifies the heat exchange efficiency of the cooling system; the heat dissipation capacity coefficient calculation unit is based on thermodynamic principles and historical operation data, and uses the support vector regression algorithm to build a transformer cooling system performance evaluation model, inputs the cooling system heat exchange efficiency, ambient temperature and transformer load rate, and outputs the current heat dissipation capacity coefficient of the cooling system; Fault warning and decision support module: including: a comprehensive judgment unit and a warning push unit; wherein the comprehensive judgment unit combines the current heat dissipation capacity coefficient of the cooling system with the current status evaluation result of the equipment, and the warning push unit determines whether the cooling system meets the heat dissipation requirements and issues a fault warning.

Images