Remote monitoring device and method for on-load test data of transformer substation protection device

Abstract

The invention relates to the technical field of power system monitoring and protection, and provides a remote monitoring device and method for on-load test data of a transformer substation protection device, which can ensure the timeliness and safety of data by acquiring electrical parameters such as current, voltage and phase of a transformer substation in real time and encrypting and transmitting the electrical parameters. By means of the 1D CNN model deployed in the intelligent terminal, electrical parameter data can be efficiently analyzed, and intelligent judgment of load operation states including a normal state, an overload state and a phase imbalance state is achieved. And dynamic updating and optimization of the model: by periodically updating the 1D CNN model, data changes under different load conditions can be adapted, the prediction precision and adaptability of the model are improved, and the reliability and accuracy of the system in long-term operation are ensured. Real-time acquisition, encrypted transmission, remote storage and analysis of electrical parameters of the input side of the transformer substation protection device can be realized, a basis is provided for judging actions of the protection device, dependence on skills of personnel is reduced, and test efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system monitoring, and in particular to a device and method for remotely monitoring load test data of a transformer substation protection device. Background Art

[0002] In modern power systems, substations are important nodes for power transmission and distribution, and their stable operation is crucial to the safety of the entire power network. Traditional substation protection device detection mainly relies on local measurements. With the continuous expansion of the scale of power systems, improving the monitoring capabilities of substation protection devices, especially realizing remote monitoring and data analysis, has become an important issue that the power industry needs to solve urgently.

[0003] At present, with the development of Internet of Things, cloud computing and artificial intelligence technology, the technical conditions of remote monitoring system have become more mature. It provides advanced data acquisition, communication and processing capabilities, making it possible to analyze and evaluate the operating status of the power system in real time.

[0004] Based on this, the present invention provides a remote monitoring device and method for load test data of a substation protection device, which realizes real-time collection, encrypted transmission, remote storage and analysis of electrical parameters on the input side of the substation protection device, and at the same time provides a basis for judging the action of the protection device, reduces dependence on personnel skills, and improves testing efficiency. Summary of the invention

[0005] The purpose of the present invention is to solve the deficiencies of the prior art and to provide a remote monitoring device and method for load test data of a substation protection device, so as to realize real-time collection, encrypted transmission, remote storage and analysis of electrical parameters on the input side of the substation protection device, and at the same time provide a basis for judging the action of the protection device, reduce dependence on personnel skills and improve test efficiency.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A remote monitoring device for load test data of a transformer substation protection device comprises: a data acquisition module, a communication module, a server, and an intelligent terminal, wherein the data acquisition module is electrically connected to the communication module; the communication module and the intelligent terminal are respectively connected to the server signal;

[0008] The data acquisition module is used to collect electrical parameters on the input side of the transformer substation protection device;

[0009] The communication module is used to encrypt and send the electrical parameters collected by the data collection module to the server;

[0010] The server is used to receive the encrypted electrical parameters sent by the communication module;

[0011] The intelligent terminal is used to obtain encrypted electrical parameters from the server and determine the load operation status according to the electrical parameters.

[0012] Preferably, the data acquisition module and the communication module are arranged on the host and the slave; there are multiple slaves, and wireless communication is performed between the slave and the host, and the slave transmits the detected electrical parameters to the host; the host acts as a reference clock source and summarizes the electrical parameter data detected by the slave, and uploads the summarized electrical parameter data to the server through the communication module.

[0013] Preferably, the load operation state includes: a normal state, an overload state, and a phase imbalance state.

[0014] Preferably, the load operation status judgment is based on the following steps:

[0015] Step 1: The smart terminal reads the deployed 1D CNN model;

[0016] Step 2: The intelligent terminal reads the electrical parameters and performs data preprocessing;

[0017] Step 3: The intelligent terminal inputs the preprocessed electrical parameters into the 1D CNN model, and the 1D CNN model divides the load operation status into normal state, overload state, and phase imbalance state according to the electrical parameters;

[0018] Step 4: Display the load operation status information.

[0019] Preferably, the data preprocessing comprises the following steps:

[0020] Step 2.1, normalization: normalize the data to 0-1, the normalization formula is:

[0021]

[0022] Among them, X is the original data value, Xmin is the minimum value in the data set; Xmax is the maximum value in the data set, and X' is the normalized data;

[0023] Step 2.2, feature extraction; extract the mean, variance, fluctuation range of current and voltage through time domain, frequency domain and time-frequency domain analysis; frequency domain main frequency component; feature extraction formula is:

[0024] Mean:

[0025]

[0026] variance:

[0027]

[0028] Peak-to-Peak Value:

[0029] P P =x max -x min ;

[0030] Main frequency component in frequency domain:

[0031] f main = argmax(FFT(x));

[0032] Among them, xi is the sampling data point; N is the number of sampling points; FFT(x) is the Fourier transform result of the signal; fmain is the main frequency component in the spectrum.

[0033] Preferably, the 1D CNN model is obtained by the following method:

[0034] Step a, data collection: collect electrical parameters under different load operating states, and label each section of collected data to indicate its corresponding operating state; divide the data set into a training set, a validation set, and a test set;

[0035] Step b, data preprocessing;

[0036] Step c: Model architecture selection; including several convolutional layers, pooling layers and fully connected layers, and the output layer uses the Softmax activation function to obtain the state probability distribution;

[0037] Step d, model training: input the preprocessed data into the 1D CNN model and train it on the training set using the cross entropy loss function and optimization algorithm;

[0038] Step e, model verification and optimization: verify the model on the verification set, and adjust the model parameters according to the verification results to optimize the performance;

[0039] Step f, model evaluation: Evaluate the model performance on the test set and calculate the accuracy, precision, recall and F1 score;

[0040] Step g, model deployment: deploy the trained 1D CNN model to the smart terminal, and divide the load operation status into normal state, overload state, and phase imbalance state according to the electrical parameters.

[0041] Preferably, the step e comprises the following steps:

[0042] i. Learning rate adjustment: During the training process, when the loss of the no-validation set decreases after several epochs,

[0043] Reduce the learning rate by a fixed ratio to prevent oscillation and speed up convergence;

[0044] ii. Regularization adjustment: Add L2 regularization to the model, apply an L2 penalty term to each weight, and select the best value through the performance of the validation set; at the same time, apply the Dropout technology to set a certain proportion of nodes in the fully connected layer to randomly inactivate to increase the generalization ability of the model;

[0045] iii. Hyperparameter optimization: Perform grid search or random search to select the parameter combination that minimizes the loss of the validation set;

[0046] iv. Early stopping: Monitor the cross entropy loss on the validation set. When the loss does not decrease significantly for several consecutive epochs, stop training to prevent overfitting, and select the model parameters with the smallest validation loss as the final model.

[0047] Preferably, the step f specifically comprises:

[0048] Accuracy calculation: evaluate the proportion of the overall correct classification of the test set samples by the model. The calculation formula is:

[0049]

[0050] Precision calculation: The accuracy of the model in predicting the positive class is calculated using the following formula:

[0051]

[0052] Recall calculation: The proportion of correct identification of all actual positive samples by the evaluation model is calculated as follows:

[0053]

[0054] F1 Score calculation: The harmonic mean of precision and recall is considered comprehensively. The calculation formula is:

[0055]

[0056] Among them, TP, TN, FP and FN represent the number of true positive, true negative, false positive and false negative samples respectively;

[0057] Confusion matrix analysis: Construct a confusion matrix to analyze the classification effect of the model on different state categories and identify easily confused states for model improvement.

[0058] Another object of the present invention is to provide a method for remote monitoring of load test data of a substation protection device, using the above-mentioned remote monitoring device for load test data of a substation protection device, comprising the following steps:

[0059] Step S1, installation and configuration; installing the data acquisition module on the input side of the substation protection device and connecting it to the server through the communication module;

[0060] Step S2, data acquisition: real-time acquisition of current, voltage and phase electrical parameters of the substation through the data acquisition module;

[0061] Step S3, data encryption and transmission: using the communication module to encrypt the collected electrical parameters, and securely transmit the encrypted data to the server;

[0062] Step S4, data reception and storage: the server receives the encrypted electrical parameters from the communication module and stores them;

[0063] Step S5, data processing and analysis: the intelligent terminal obtains the stored electrical parameter data from the server and performs data preprocessing;

[0064] Step S6, state determination: input the preprocessed electrical parameter data into the 1DCNN model deployed in the intelligent terminal for analysis, and determine whether the operating state of the load is a normal state, an overload state, or a phase imbalance state;

[0065] Step S7, result display; display the load operation status information and the substation current, voltage, phase and other electrical parameters collected in real time by the data acquisition module on the intelligent terminal; the staff judges whether the protection device is operating correctly according to the load operation status.

[0066] The present invention discloses a device and method for remotely monitoring load test data of a transformer substation protection device, which have the following beneficial effects.

[0067] The present invention can collect electrical parameters such as current, voltage and phase of the substation in real time and transmit them in encrypted form to ensure the timeliness and security of the data. The operator can obtain the operating status information of the substation in the first place and make quick responses and decisions. With the help of the 1D CNN model deployed in the intelligent terminal, the electrical parameter data can be efficiently analyzed to realize intelligent discrimination of the load operating status, including normal state, overload state and phase imbalance state. Dynamic update and optimization of the model: By regularly updating the 1D CNN model, it can adapt to data changes under different load conditions, improve the prediction accuracy and adaptability of the model, and ensure the reliability and accuracy of the system in long-term operation. It can realize real-time collection, encrypted transmission, remote storage and analysis of electrical parameters on the input side of the substation protection device, and at the same time provide a basis for judging the action of the protection device, reduce dependence on personnel skills, and improve testing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 The present invention is a flow chart of a method for remotely monitoring load test data of a transformer substation protection device.

[0069] Figure 2 The system block diagram of the remote monitoring device for load test data of a transformer substation protection device of the present invention.

[0070] Figure 3 It is the schematic diagram of the host and slave circuits of the present invention. DETAILED DESCRIPTION

[0071] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0072] Reference to "embodiment" herein means that the specific features, structures or characteristics described in conjunction with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various places in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or association with other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the various technical features mentioned in the embodiments can be combined in any way to form a corresponding implementable technical solution.

[0073] Unless otherwise defined, the technical terms used in this document have the same meanings as those generally understood by those skilled in the art to which this application belongs; the use of relevant terms in this document is only for describing specific embodiments and is not intended to limit this application.

[0074] In the description of this application, the term "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist, for example, A and / or B, which means: A exists, B exists, and A and B exist at the same time. In addition, the character " / " in this article generally indicates that the objects before and after are in an "or" logical relationship.

[0075] Unless otherwise expressly specified or limited, in the description of the embodiments of the present application, the terms such as "install", "connect", "connect", "fix", "set", etc. used should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integrated setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. For technicians in the technical field to which the present application belongs, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0076] Example 1

[0077] Please refer to Figure 2A remote monitoring device for load test data of a transformer substation protection device comprises: a data acquisition module, a communication module, a server, and an intelligent terminal, wherein the data acquisition module is electrically connected to the communication module; the communication module and the intelligent terminal are respectively connected to the server signal;

[0078] The data acquisition module is used to collect the electrical parameters of the input side of the substation protection device; the electrical parameters collected by the data acquisition module include: current, voltage, and phase;

[0079] The communication module is used to encrypt and send the electrical parameters collected by the data collection module to the server;

[0080] A server, used for receiving encrypted electrical parameters sent by the communication module;

[0081] The smart terminal is used to obtain encrypted electrical parameters from the server through the Internet and judge the load operation status based on the electrical parameters. Through the 1D CNN model deployed on the smart terminal, the terminal can judge the load operation status based on these electrical parameters, including normal state, overload state and phase imbalance state.

[0082] As a preference, in this embodiment, the data acquisition module and the communication module are arranged on the host and the slave; there are multiple slaves, and the slaves communicate wirelessly with the host, and the slaves transmit the detected electrical parameters to the host; the host serves as a reference clock source and summarizes the electrical parameter data detected by the slaves, and uploads the summarized electrical parameter data to the server through the communication module. Figure 3 As shown in the figure, the hardware circuit diagrams of the host and slave are basically the same. The host and slave are controlled by MCU, the data acquisition module transmits data to MCU through TTL serial port, the wireless communication module is connected to MCU through UART interface, MCU connects to encryption gateway through RS485 interface for data transmission, encryption gateway encrypts data with SSL, and supports MQTT protocol to upload to server.

[0083] Preferably, in this embodiment, the load operation state includes: a normal state, an overload state, and a phase imbalance state.

[0084] Preferably, in this embodiment, the load operation status is determined based on the following steps:

[0085] Step 1: The smart terminal reads the deployed 1D CNN model;

[0086] Step 2: The intelligent terminal reads the electrical parameters and performs data preprocessing;

[0087] Preferably, in this embodiment, data preprocessing includes the following steps:

[0088] Step 2.1, normalization: normalize the data to 0-1, the normalization formula is:

[0089]

[0090] Among them, X is the original data value, Xmin is the minimum value in the data set; Xmax is the maximum value in the data set, and X' is the normalized data;

[0091] Step 2.2, feature extraction; extract the mean, variance, fluctuation range of current and voltage through time domain, frequency domain and time-frequency domain analysis; frequency domain main frequency component; feature extraction formula is:

[0092] Mean:

[0093]

[0094] variance:

[0095]

[0096] Peak-to-Peak Value:

[0097] P p =x max -x min ;

[0098] Main frequency component in frequency domain:

[0099] f main = argmax(FFT(x));

[0100] Among them, xi is the sampling data point; N is the number of sampling points; FFT(x) is the Fourier transform result of the signal; fmain is the main frequency component in the spectrum.

[0101] Step 3: The intelligent terminal inputs the preprocessed electrical parameters into the 1D CNN model, and the 1D CNN model divides the load operation status into normal state, overload state, and phase imbalance state according to the electrical parameters;

[0102] Step 4: Display the load operation status information.

[0103] Example 2

[0104] Based on Example 1, this embodiment provides a 1D CNN model acquisition method:

[0105] Step a, data collection: collect electrical parameters under different load operating states, and label each section of collected data to indicate its corresponding operating state; divide the data set into a training set, a validation set, and a test set;

[0106] Step b, data preprocessing;

[0107] Step c: Model architecture selection; including several convolutional layers, pooling layers and fully connected layers, and the output layer uses the Softmax activation function to obtain the state probability distribution;

[0108] Step d, model training: input the preprocessed data into the 1D CNN model and train it on the training set using the cross entropy loss function and optimization algorithm;

[0109] Step e, model verification and optimization: verify the model on the verification set, and adjust the model parameters according to the verification results to optimize the performance;

[0110] Preferably, in this embodiment, step e includes the following steps:

[0111] i. Learning rate adjustment: During the training process, when the loss of the no-validation set decreases after several epochs,

[0112] Reduce the learning rate by a fixed ratio to prevent oscillation and speed up convergence;

[0113] ii. Regularization adjustment: Add L2 regularization to the model, apply an L2 penalty term to each weight, and select the best value through the performance of the validation set; at the same time, apply the Dropout technology to set a certain proportion of nodes in the fully connected layer to randomly inactivate to increase the generalization ability of the model;

[0114] iii. Hyperparameter optimization: Perform grid search or random search to select the parameter combination that minimizes the loss of the validation set;

[0115] iv. Early stopping: Monitor the cross entropy loss on the validation set. When the loss does not decrease significantly for several consecutive epochs, stop training to prevent overfitting, and select the model parameters with the smallest validation loss as the final model.

[0116] Step f, model evaluation: Evaluate the model performance on the test set and calculate the accuracy, precision, recall and F1 score;

[0117] Preferably, in this embodiment, step f specifically includes:

[0118] Accuracy calculation: evaluate the proportion of the overall correct classification of the test set samples by the model. The calculation formula is:

[0119]

[0120] Precision calculation: The accuracy of the model in predicting the positive class is calculated using the following formula:

[0121]

[0122] Recall calculation: The proportion of correct identification of all actual positive samples by the evaluation model is calculated as follows:

[0123]

[0124] F1 Score calculation: The harmonic mean of precision and recall is considered comprehensively. The calculation formula is:

[0125]

[0126] Among them, TP, TN, FP and FN represent the number of true positive, true negative, false positive and false negative samples respectively;

[0127] Confusion matrix analysis: Construct a confusion matrix to analyze the classification effect of the model on different state categories and identify easily confused states for model improvement.

[0128] Step g, model deployment: deploy the trained 1D CNN model to the smart terminal, and divide the load operation status into normal state, overload state, and phase imbalance state according to the electrical parameters.

[0129] Example 3

[0130] Based on Example 1-2, please refer to Figure 1 This embodiment provides a method for remote monitoring of load test data of a substation protection device, using the above-mentioned remote monitoring device for load test data of a substation protection device, including the following steps:

[0131] Step S1, installation and configuration; installing the data acquisition module on the input side of the substation protection device and connecting it to the server through the communication module;

[0132] Step S2, data collection; the current, voltage and phase electrical parameters of the substation are collected in real time through the data collection module; it should be noted that the data collection module is arranged on the host and the slave, and the host and the slave are basically the same, except that the host can integrate the data collected by the slave and send it to the server through the communication module;

[0133] Step S3, data encryption and transmission: using the communication module to encrypt the collected electrical parameters, and securely transmit the encrypted data to the server;

[0134] Step S4, data reception and storage: the server receives the encrypted electrical parameters from the communication module and stores them;

[0135] Step S5, data processing and analysis: the intelligent terminal obtains the stored electrical parameter data from the server and performs data preprocessing;

[0136] Step S6, state determination: input the preprocessed electrical parameter data into the 1DCNN model deployed in the intelligent terminal for analysis, and determine whether the operating state of the load is a normal state, an overload state, or a phase imbalance state;

[0137] Step S7, result display; display the load operation status information and the substation current, voltage, phase and other electrical parameters collected in real time by the data acquisition module on the intelligent terminal; the staff judges whether the protection device is operating correctly according to the load operation status.

[0138] The above are only preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The substitution may be a substitution of a part of the structure, device, method step, or a complete technical solution. The equivalent replacement or change according to the technical solution and the inventive concept of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A remote monitoring device for load test data of a transformer substation protection device, characterized in that: include: A data acquisition module, a communication module, a server, and an intelligent terminal, wherein the data acquisition module is electrically connected to the communication module; The communication module and the intelligent terminal are respectively connected with the server signal; The data acquisition module is used to collect electrical parameters on the input side of the transformer substation protection device; The communication module is used to encrypt and send the electrical parameters collected by the data collection module to the server; The server is used to receive the encrypted electrical parameters sent by the communication module; The intelligent terminal is used to obtain encrypted electrical parameters from the server and determine the load operation status according to the electrical parameters.

2. The remote monitoring device for load test data of a transformer substation protection device according to claim 1, characterized in that: The data acquisition module and the communication module are arranged on the host and the slave; there are multiple slaves, and wireless communication is performed between the slaves and the host, and the slaves transmit the detected electrical parameters to the host; the host acts as a reference clock source and summarizes the electrical parameter data detected by the slaves, and uploads the summarized electrical parameter data to the server through the communication module.

3. The remote monitoring device for load test data of a transformer substation protection device according to claim 1, characterized in that: The load operation status includes: normal state, overload state, and phase imbalance state.

4. The remote monitoring device for load test data of a transformer substation protection device according to claim 3, characterized in that: The load operation status determination is based on the following steps: Step 1: The smart terminal reads the deployed 1D CNN model; Step 2: The intelligent terminal reads the electrical parameters and performs data preprocessing; Step 3: The intelligent terminal inputs the preprocessed electrical parameters into the 1D CNN model, and the 1D CNN model divides the load operation status into normal state, overload state, and phase imbalance state according to the electrical parameters; Step 4: Display the load operation status information.

5. The remote monitoring device for load test data of a transformer substation protection device according to claim 3, characterized in that: The data preprocessing comprises the following steps: Step 2.1, normalization: normalize the data to 0-1, the normalization formula is: Among them, X is the original data value, Xmin is the minimum value in the data set; Xmax is the maximum value in the data set, and X' is the normalized data; Step 2.2, feature extraction; extract the mean, variance, fluctuation range of current and voltage through time domain, frequency domain and time-frequency domain analysis; frequency domain main frequency component; feature extraction formula is: Mean: variance: Peak-to-Peak Value: P p =x max -x min ; Main frequency component in frequency domain: f main =argmax(FFT(x)); Among them, xi is the sampling data point; N is the number of sampling points; FFT(x) is the Fourier transform result of the signal; fmain is the main frequency component in the spectrum.

6. The remote monitoring device for load test data of a transformer substation protection device according to claim 3, characterized in that: The 1D CNN model is obtained by the following method: Step a, data collection: collect electrical parameters under different load operating states, and label each section of collected data to indicate its corresponding operating state; divide the data set into a training set, a validation set, and a test set; Step b, data preprocessing; Step c: Model architecture selection; including several convolutional layers, pooling layers and fully connected layers, and the output layer uses the Softmax activation function to obtain the state probability distribution; Step d, model training: input the preprocessed data into the 1D CNN model and train it on the training set using the cross entropy loss function and optimization algorithm; Step e, model verification and optimization: verify the model on the verification set, and adjust the model parameters according to the verification results to optimize the performance; Step f, model evaluation: Evaluate the model performance on the test set and calculate the accuracy, precision, recall and F1 score; Step g, model deployment: deploy the trained 1D CNN model to the smart terminal, and divide the load operation status into normal state, overload state, and phase imbalance state according to the electrical parameters.

7. The device for remote monitoring of load test data of a transformer substation protection device according to claim 6, characterized in that: The step e comprises the following steps: i. Learning rate adjustment: During the training process, when the loss of the validation set decreases after several epochs, the learning rate is reduced by a fixed ratio to prevent oscillation and accelerate convergence; ii. Regularization adjustment: Add L2 regularization to the model, apply an L2 penalty term to each weight, and select the best value through the performance of the validation set; at the same time, apply the Dropout technology to set a certain proportion of nodes in the fully connected layer to randomly inactivate to increase the generalization ability of the model; iii. Hyperparameter optimization: Perform grid search or random search to select the parameter combination that minimizes the loss of the validation set; iv. Early stopping: Monitor the cross entropy loss on the validation set. When the loss does not decrease significantly for several consecutive epochs, stop training to prevent overfitting, and select the model parameters with the smallest validation loss as the final model.

8. The device for remote monitoring of load test data of a transformer substation protection device according to claim 6, characterized in that: The step f specifically comprises: Accuracy calculation: evaluate the proportion of the overall correct classification of the test set samples by the model. The calculation formula is: Precision calculation: The accuracy of the model in predicting the positive class is calculated using the following formula: Recall calculation: The proportion of correct identification of all actual positive samples by the evaluation model is calculated as follows: F1 Score calculation: The harmonic mean of precision and recall is considered comprehensively. The calculation formula is: Among them, TP, TN, FP and FN represent the number of true positive, true negative, false positive and false negative samples respectively; Confusion matrix analysis: Construct a confusion matrix to analyze the classification effect of the model on different state categories and identify easily confused states for model improvement.

9. A method for remote monitoring of load test data of a substation protection device, using the device for remote monitoring of load test data of a substation protection device according to any one of claims 1 to 8, characterized in that: The steps include: Step S1, installation and configuration; installing the data acquisition module on the input side of the substation protection device and connecting it to the server through the communication module; Step S2, data acquisition: real-time acquisition of current, voltage and phase electrical parameters of the substation through the data acquisition module; Step S3, data encryption and transmission: using the communication module to encrypt the collected electrical parameters, and securely transmit the encrypted data to the server; Step S4, data receiving and storage; The server receives the encrypted electrical parameters from the communication module and stores them; Step S5, data processing and analysis: the intelligent terminal obtains the stored electrical parameter data from the server and performs data preprocessing; Step S6, state determination; The pre-processed electrical parameter data is input into the 1DCNN model deployed on the smart terminal for analysis to determine whether the load operation status is normal, overloaded or phase unbalanced; Step S7, result display; The load operation status information and the substation current, voltage, phase and other electrical parameters collected in real time by the data acquisition module are displayed on the intelligent terminal; the staff judges whether the protection device is operating correctly based on the load operation status.

Images