A voltage sag duration assessment method, system, device, medium and product

Abstract

The present invention relates to the technical field of distribution network systems and discloses a voltage sag duration assessment method, system, equipment, medium and product. The method identifies real-time influencing factor data through a relay protection action coordination mode identification model, determines the current relay protection action coordination mode, and then updates the voltage sag duration in a duration rule library based on the obtained predicted melting time of the fuse. The duration rule library is used to determine the voltage sag duration based on the current relay protection action coordination mode, thereby utilizing the relay protection action coordination mode identification model and the real-time update of the duration rule library to determine the voltage sag duration, thereby improving the accuracy and real-time performance of the voltage sag duration assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network systems, and in particular to a method, system, device, medium and product for evaluating the duration of a voltage sag. Background Art

[0002] As modern industrial production and power systems rapidly evolve toward high reliability and high power quality, voltage sags (VS) have become a core concern in the power system sector due to their frequent occurrence and severe damage to sensitive equipment. Voltage sags are typically triggered by events such as grid short circuits, lightning strikes, the connection of distributed power sources, or the startup of large-capacity equipment. Essentially, voltage sags are brief drops in the effective voltage value to 10% to 90% of the rated value, typically lasting from 10 milliseconds to several minutes. Despite their brief duration, they can cause significant economic losses, including disruptions to industrial production, damage to precision equipment, and downtime in digital systems.

[0003] As a core indicator for measuring the severity of voltage sag events, accurate assessment of voltage sag duration has multiple engineering benefits. First, this parameter provides a critical action timing benchmark for dynamic voltage compensation devices, significantly reducing the risk of downtime for sensitive industrial equipment through millisecond-level response. Second, through spatiotemporal coupling analysis with fault location information, it can accurately expose potential weak points such as system impedance anomalies and improper protection configuration, providing a basis for targeted governance to enhance grid resilience. Furthermore, quantitative assessment based on the probability distribution of duration can support risk modeling for user-side power quality insurance pricing and guide differentiated grid investment strategies, prioritizing the strengthening of active defense capabilities in areas with high sag risk.

[0004] In the existing technology, the assessment of the duration of voltage sag in the distribution network relies on precise parameters, which results in a large amount of calculation and poor accuracy and real-time performance. Summary of the Invention

[0005] In view of this, the present invention provides a method, system, device, medium and product for evaluating the duration of a voltage sag, which solves the technical problems that the evaluation of the duration of a voltage sag in a distribution network depends on precise parameters, has a large amount of calculation, and has poor accuracy and real-time performance.

[0006] A first aspect of the present invention provides a method for evaluating voltage sag duration, comprising:

[0007] By using a preset relay protection action coordination mode identification model, based on pre-input real-time influencing factor data, the current relay protection action coordination mode corresponding to the real-time influencing factor data is determined; wherein the relay protection action coordination mode identification model is obtained by training a classifier using a plurality of relay protection action coordination mode historical samples and historical sample data of influencing factors corresponding to each of the relay protection action coordination mode historical samples;

[0008] The voltage sag duration in the duration rule base is updated according to the obtained predicted melting time of the fuse; wherein the duration rule base includes a mapping relationship between the relay protection action coordination mode and the voltage sag duration;

[0009] Based on the duration rule base and according to the current relay protection action coordination mode, the voltage sag duration corresponding to the current relay protection action coordination mode is determined.

[0010] Preferably, the method further comprises:

[0011] Acquire multiple relay protection action coordination mode historical samples and historical sample data of influencing factors corresponding to each of the relay protection action coordination mode historical samples to form a historical training sample set;

[0012] Preprocessing the historical training sample set;

[0013] The classifier is trained according to the pre-processed historical training sample set to obtain the relay protection action coordination mode identification model.

[0014] Preferably, the method further comprises:

[0015] Determine the voltage sag duration at multiple different fault locations based on the relay protection action coordination mode and the voltage sag impact time corresponding to the relay protection action coordination mode; wherein the voltage sag impact time includes the fault clearing time, the fuse melting time, and the main protection action time; the voltage sag duration is divided into the voltage sag duration of the branch where the fault is located, the voltage sag duration of other branches of the feeder where the fault is located, and the voltage sag duration of other feeders on the same busbar where the fault is located, according to the fault location;

[0016] The duration rule base is constructed according to the relay protection action coordination mode, the voltage sag impact time corresponding to the relay protection action coordination mode, and the voltage sag duration.

[0017] Preferably, the method further includes: predicting a predicted blowing time of the fuse; the predicting the predicted blowing time of the fuse includes:

[0018] Obtain the fuse's blowing time series data;

[0019] Performing standardization on the fuse time series data;

[0020] Based on the long short-term memory neural network, the predicted blowing time of the fuse at the current moment is obtained by predicting the standardized blowing time series data.

[0021] Preferably, the method further comprises:

[0022] Under the physical constraints of the fuse's thermodynamic equation, the accumulated thermal energy is calculated based on the current time series integral;

[0023] determining a theoretical fusing time based on the accumulated thermal energy and the thermal capacity of the fuse;

[0024] Determining a loss value using a loss function according to the predicted fusing time, the actual fusing time, and the theoretical fusing time;

[0025] Determining whether the predicted fuse time reaches the optimal prediction based on the loss value;

[0026] If it is determined that the predicted blowing time does not reach the optimal prediction, go to the step of obtaining the blowing time timing data of the fuse until it is determined that the predicted blowing time reaches the optimal prediction, and output the predicted blowing time.

[0027] Preferably, updating the voltage sag duration in the duration rule base according to the obtained predicted blowing time of the fuse includes:

[0028] The fusing time of the fuse in the duration rule base is updated according to the predicted fusing time, and the voltage sag duration is determined according to the fusing time of the fuse.

[0029] In a second aspect, the present invention further provides a voltage sag duration assessment system, comprising:

[0030] A protection action recognition module is configured to determine, using a preset relay protection action coordination mode recognition model, the current relay protection action coordination mode corresponding to the real-time influencing factor data input in advance; wherein the relay protection action coordination mode recognition model is obtained by training a classifier using a plurality of relay protection action coordination mode historical samples and historical sample data of influencing factors corresponding to each of the relay protection action coordination mode historical samples;

[0031] A rule base updating module is used to update the voltage sag duration in the duration rule base according to the obtained predicted melting time of the fuse; wherein the duration rule base contains a mapping relationship between the relay protection action coordination mode and the voltage sag duration;

[0032] The duration evaluation module is used to determine the voltage sag duration corresponding to the current relay protection action coordination mode based on the duration rule base and according to the current relay protection action coordination mode.

[0033] In a third aspect, the present invention further provides an electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the voltage sag duration assessment method as described in the first aspect.

[0034] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the steps of the voltage sag duration evaluation method as described in the first aspect.

[0035] In a fifth aspect, the present invention further provides a computer program product, comprising a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program comprises program instructions, wherein when the program instructions are executed by a computer, the computer is caused to perform the steps of the voltage sag duration assessment method as described in the first aspect.

[0036] It can be seen from the above technical solution that the present invention identifies real-time influencing factor data through the relay protection action coordination mode identification model, determines the current relay protection action coordination mode, and then updates the voltage sag duration of the duration rule library according to the obtained predicted melting time of the fuse. Through the duration rule library, according to the current relay protection action coordination mode, the duration of the voltage sag is determined. Therefore, the relay protection action coordination mode identification model and the real-time update of the duration rule library are used to determine the duration of the voltage sag, thereby improving the accuracy and real-time performance of the voltage sag duration assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1A diagram illustrating an application environment of a method for evaluating voltage sag duration provided by an embodiment of the present invention;

[0039] Figure 2 A flowchart of a method for evaluating voltage sag duration provided by an embodiment of the present invention;

[0040] Figure 3 An example logic diagram of a method for estimating voltage sag duration provided by an embodiment of the present invention;

[0041] Figure 4 A schematic structural diagram of a voltage sag duration assessment system provided by an embodiment of the present invention;

[0042] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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 making creative efforts shall fall within the scope of protection of the present invention.

[0044] The voltage sag duration evaluation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 101 communicates with the server 102 through the network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or it can be placed on the cloud or other network servers. The terminal 101 or the server 102 determines the current relay protection action coordination mode corresponding to the real-time influencing factor data according to the real-time influencing factor data input in advance through the preset relay protection action coordination mode identification model; wherein, the relay protection action coordination mode identification model is obtained by training the classifier with a plurality of relay protection action coordination mode historical samples and the influencing factor historical sample data corresponding to each relay protection action coordination mode historical sample; the voltage sag duration of the duration rule library is updated according to the obtained predicted melting time of the fuse; wherein, the duration rule library contains the mapping relationship between the relay protection action coordination mode and the voltage sag duration; based on the duration rule library, according to the current relay protection action coordination mode, the voltage sag duration corresponding to the current relay protection action coordination mode is determined.

[0045] The terminal 101 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and the like.

[0046] The server 102 may be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0047] like Figure 2 As shown, the embodiment of the present application provides a method for evaluating the duration of a voltage sag, which is applied to Figure 1 The terminal 101 or the server 102 in the embodiment is used as an example to illustrate the method, which includes the following steps S1 to S3.

[0048] Step S1. Determine the current relay protection action coordination mode corresponding to the real-time influencing factor data according to the pre-input real-time influencing factor data through a preset relay protection action coordination mode identification model; wherein, the relay protection action coordination mode identification model is obtained by training a classifier using a plurality of relay protection action coordination mode historical samples and the influencing factor historical sample data corresponding to each relay protection action coordination mode historical sample.

[0049] The relay protection coordination mode identification model is built based on a machine learning algorithm. By learning and training on a large amount of historical data, it can accurately identify the mapping relationship between real-time influencing factor data and relay protection coordination modes. This model can handle the complex and changing power system operating environment and quickly respond to and determine the current relay protection coordination mode.

[0050] The relay protection coordination mode is the sequence and coordination of the various relay protection devices in a power system during a fault, ensuring safe and stable operation of the power system. Different relay protection coordination modes have varying impacts on the duration of voltage sags. Therefore, accurately identifying the current relay protection coordination mode is a key step in assessing voltage sag duration.

[0051] At the same time, data on factors influencing the coordination mode of relay protection action refers to data on factors related to the coordination mode of relay protection action, including but not limited to fault type, fault location, grid topology, line impedance, protection device configuration, previous steady-state voltage, fault current timing sequence, fuse characteristic parameters, user access point impedance, etc. This factor data can be obtained through real-time monitoring and collection of the power system and used as input information for analysis and processing by the relay protection action coordination mode identification model.

[0052] Step S2: updating the voltage sag duration in the duration rule base according to the obtained predicted melting time of the fuse; wherein the duration rule base includes a mapping relationship between the relay protection action coordination mode and the voltage sag duration.

[0053] By accurately predicting the fuse's opening time, the duration rule base can be updated in real time, allowing for more accurate voltage sag duration assessments. This update mechanism ensures that the duration rule base can provide timely and reliable voltage sag duration assessments in various fault scenarios.

[0054] Step S3: Based on the duration rule base and according to the current relay protection action coordination mode, determine the voltage sag duration corresponding to the current relay protection action coordination mode.

[0055] It is understandable that since the duration rule base contains the mapping relationship between the relay protection action coordination mode and the voltage sag duration, it is easy to obtain the voltage sag duration corresponding to the current relay protection action coordination mode by matching the current relay protection action coordination mode.

[0056] It should be noted that the embodiment of the present application identifies real-time influencing factor data through a relay protection action coordination mode identification model, determines the current relay protection action coordination mode, and then updates the voltage sag duration of the duration rule library based on the obtained predicted melting time of the fuse. Through the duration rule library, the duration of the voltage sag is determined according to the current relay protection action coordination mode, thereby utilizing the relay protection action coordination mode identification model and the real-time update of the duration rule library to determine the duration of the voltage sag, thereby improving the accuracy and real-time performance of the voltage sag duration assessment.

[0057] In some embodiments, the process of constructing a relay protection action coordination mode identification model includes:

[0058] Step S11: Acquire multiple relay protection action coordination mode historical samples and historical sample data of influencing factors corresponding to each relay protection action coordination mode historical sample to form a historical training sample set.

[0059] Among them, the power grid's relay protection system directly affects the duration of voltage sag events. Circuit breakers (with reclosing function) and sectionalizers will have different impacts on upstream and downstream nodes when transient faults and permanent faults occur, respectively. Different protection type action characteristics also affect the duration of voltage sags.

[0060] Table 1 shows the typical protection action coordination mode of the distribution network.

[0061] Table 1

[0062]

[0063] Among them, 1) coordination mode 1 (number 1): the fault is a transient fault, the fault current does not reach the thermal melting limit of the fuse, the fault is cleared automatically, and the main protection does not operate. At this time, the users of the feeder where the fault is located will suffer a duration of the fault clearing time T Q Voltage sag: T1=T Q The users on other branches of the feeder suffer voltage sags that last for the fault clearing time: T2=T Q The users on other feeders under the same bus also suffer voltage dips T3=T that last for the fault clearing time. Q .

[0064] 2) Coordination mode 2 (No. 2): The fault is a transient fault. Before the fault is cleared, the fault current reaches the fuse thermal melting limit. The fuse is opened at T R If the fault branch is disconnected in the specified time and the main protection does not operate, the users on the feeder where the fault occurs will experience a long interruption. Users on other branches of the feeder will experience a voltage sag that lasts for the fuse disconnection time: T2=T R The users on other feeders under the same busbar also suffer voltage dips T3=T which lasts for the fuse disconnection time. R .

[0065] 3) Coordination mode 3 (No. 3): The fault is a transient fault. The main protection action time is reached before the fault is cleared. The fault current value does not reach the fuse thermal melting limit. The fault is cleared during the main protection trip period and the main protection recloses successfully. At this time, the users of the feeder where the fault occurs will suffer a duration of the main protection action time T. D A deep temporary dip, a short interruption T1=T D The users on other branches of the feeder will also suffer from the main protection action time T D A deep temporary dip, a short interruption T2=T D The voltage sag T3=T that users on other feeders under the same bus suffer from for a duration equal to the main protection action time. D .

[0066] 4) Coordination mode 4 (No. 4): The fault is a permanent fault, the fault current reaches the thermal melting limit of the fuse, and the fuse is R The faulty branch is disconnected within a certain time. At this time, users on the feeder where the fault occurs will experience a long interruption. Users on other branches of the feeder will also experience a voltage sag that lasts for the fuse disconnection time: T2=T R The users on other feeders under the same busbar also suffer voltage dips T3=T which lasts for the fuse disconnection time. R .

[0067] 5) Coordination mode 5 (No. 5): The fault is a permanent fault. Before the fault current reaches the thermal melting limit of the fuse, the main protection is activated, the main protection reclosing fails, and the feeder where the fault is located is disconnected. At this time, the users of the feeder where the fault is located will experience a duration of T in turn. D Deep temporary sag, short interruption, duration T D Deep sag and long interruption: T1=2T D The users on other branches of the feeder will also suffer from the duration of T D Deep temporary sag, short interruption, duration T D Deep dips and long interruptions: T2=2T D . The users on other feeders under the same bus suffer from 2 times of duration T D Temporary sag: T3=2T D .

[0068] Step S12: pre-process the historical training sample set.

[0069] Among them, the preprocessing is normalized continuous features (such as impedance, current value) and coded category features (such as fault type, protection device configuration, etc.).

[0070] Step S13: training the classifier based on the pre-processed historical training sample set to obtain a relay protection action coordination mode recognition model.

[0071] For example, the process of constructing the relay protection action coordination mode identification model is as follows:

[0072] 1) Data preparation and feature engineering.

[0073] Input characteristics: fault type, fault location, grid topology, line impedance, protection device configuration, previous steady-state voltage, fault current timing sequence, fuse characteristic parameters, user access point impedance, etc.

[0074] Label: 5 protection action modes (corresponding to 5 numbers).

[0075] Data preprocessing: normalizing continuous features (such as impedance and current values) and encoding categorical features (such as fault type and protection device configuration).

[0076] 2) Base learner (Level-0 model) selection and training.

[0077] Base model selection: Deep Neural Network (DNN) machine learning model is used, as shown in the following formula.

[0078]

[0079] Where, X(i) is the feature input of the i-th deep neural network layer, X (i-1) W is the feature input of the i-1th deep neural network layer. (i) is the random initialization weight, b (i) is the learnable bias matrix, is the activation function.

[0080] Training method: Use categorical cross entropy to verify the probabilities of the five protective action modes predicted by the generated base model. The loss function is:

[0081]

[0082] Where: N is the number of samples; C is the total number of categories (5 protection action modes); y n,c is the true label of the nth sample. If the nth sample belongs to the cth category, then y n,c =1, otherwise y n,c =0. p n,c is the model's predicted probability that the nth sample belongs to the cth category.

[0083] 3) Meta-learner (Level-1 model) training.

[0084] Input features: The prediction results of the base learner, that is, the probability output of each model for the five protection action modes.

[0085] Model selection: XGBoost integrates multiple weak classifiers (decision trees) through the gradient boosting framework, and its loss function is also:

[0086]

[0087] The objective function is defined as:

[0088]

[0089] in, is the regularization term of the tree. T is the number of leaf nodes, is the leaf weight.

[0090] Objective: To synthesize the output of the base model and generate the final protection action mode classification results (numbered 1 to 5).

[0091] In some embodiments, the process of building a duration rule base includes:

[0092] Step S21: Determine the voltage sag duration at multiple different fault locations based on the relay protection action coordination mode and the voltage sag impact time corresponding to the relay protection action coordination mode; wherein the voltage sag impact time includes the fault clearing time, the fuse blowing time, and the main protection action time; and the voltage sag duration is divided into the voltage sag duration of the branch where the fault is located, the voltage sag duration of other branches of the feeder where the fault is located, and the voltage sag duration of other feeders on the same busbar where the fault is located, according to the fault location.

[0093] The fault-clearing time is the time required to clear a fault, which depends on factors such as the fault type, fault location, and the power system's protection configuration. For example, in the case of a transient fault, if the fault current does not reach the thermal melting limit of the fuse, the fault may clear itself. In this case, the fault-clearing time is the time required for the fault to clear itself.

[0094] The breaking time of a fuse is the time it takes for the fuse to heat up and melt under the action of a fault current. The length of the breaking time depends on the fuse's characteristic parameters, such as the fuse's rated current, the breaking characteristic curve, and the magnitude and waveform of the fault current.

[0095] The main protection operating time is the time it takes for the main protection device to detect a fault, from issuing a trip command until the fault is cleared. The main protection operating time depends on factors such as the protection device's response speed, the time constant of the trip circuit, and the circuit breaker's operating time.

[0096] Step S22: construct a duration rule base according to the relay protection action coordination mode, the voltage sag impact time corresponding to the relay protection action coordination mode, and the voltage sag duration.

[0097] When determining the duration of a voltage sag, it is necessary to comprehensively consider factors such as fault clearing time, fuse opening time, and primary protection operation time, as well as the impact of the fault location on the duration of the voltage sag. By constructing a detailed duration rule library, the duration of the voltage sag can be accurately estimated under different fault scenarios, as shown in Table 2.

[0098] Table 2

[0099]

[0100] In some embodiments, the method further includes: predicting a predicted blowing time of the fuse; predicting the predicted blowing time of the fuse includes:

[0101] Step S31: Obtain the fuse's blowing time sequence data.

[0102] The time series data for fuse opening is a record of the actual opening time of the fuse under different fault currents, ambient temperatures, and other conditions. This data can be obtained through laboratory testing or monitoring during actual operation and is used to train the fuse opening time prediction model.

[0103] Step S32: Standardize the blown time sequence data.

[0104] The standardization process is to perform Z-Score standardization on the circuit-breaking time series data, that is:

[0105]

[0106] Where, and are the mean and standard deviation of the circuit breaker time series data, is the fuse time series data before normalization, This is the normalized fuse time series data.

[0107] Step S33: Based on the long short-term memory neural network, prediction is performed through the standardized melting time time series data to obtain the predicted melting time of the fuse at the current moment.

[0108] Among them, the Long Short-Term Memory (LSTM) neural network is a deep learning model for time series prediction that can capture long-term dependencies in time series data. In the task of predicting the time of a fuse opening, the LSTM neural network learns from standardized time series data to predict the fuse's opening time under the current fault conditions. By introducing a time prediction model, embodiments of the present application can update the predicted fuse opening time in real time, further improving the accuracy and real-time performance of voltage sag duration assessment.

[0109] LSTM controls the transmission of timing information through gating mechanisms (forget gate, input gate, output gate).

[0110] Forget Gate: determines how much historical cell state to retain:

[0111]

[0112] Input Gate: determines how much new information to update:

[0113]

[0114]

[0115] Cell status update:

[0116]

[0117] Output Gate: determines the output features:

[0118]

[0119]

[0120] Where: Input for the current moment, It is the hidden state of the previous moment and carries historical timing information. is the Sigmoid function, is the hyperbolic tangent activation function, is element-wise multiplication, are the trainable weight matrices and bias terms. Output of the forget gate, controlling the historical cell state The retention ratio. Output of the input gate, controlling the candidate state The update ratio. The updated cell state is a fusion of historical information and current input information. Is the output of the output gate, which determines the current hidden state content. It is the hidden state at the current moment, which is used to pass it to the next moment or output the prediction result.

[0121] In some embodiments, the method further comprises:

[0122] Step S34: Under the physical constraints of the thermodynamic equation of the fuse, calculate the accumulated thermal energy according to the current time series integral;

[0123] The thermodynamic equation for a fuse describes the physical process of its temperature change under the influence of a fault current. Solving this equation reveals the temperature distribution and temperature trend of the fuse during the fault. Accumulated heat energy is the total amount of heat absorbed by the fuse from the onset of the fault to the current moment. This is calculated by integrating the fault current time series data. When calculating this accumulated heat energy, factors such as the fuse's thermal capacitance and thermal resistance, as well as the magnitude and waveform of the fault current, must be considered. By introducing physical constraints into the thermodynamic equation, the accuracy of the melting time prediction can be further improved.

[0124] The thermodynamic equation of the fuse is:

[0125]

[0126] Where k is the melting time coefficient, is the thermal capacity of the fuse, t is the time, I t For current.

[0127] For each sample, the accumulated thermal energy is calculated based on the current time series integration:

[0128]

[0129] Where E is the accumulated thermal energy.

[0130] Step S35: determining the theoretical fusing time according to the accumulated heat energy and the heat capacity of the fuse;

[0131] Among them, the theoretical melting time is calculated by accumulating thermal energy:

[0132]

[0133] Where, The theoretical melting time.

[0134] Step S36: Determine the loss value through a loss function according to the predicted fusing time, the actual fusing time, and the theoretical fusing time.

[0135] The mean square error between the LSTM predicted circuit breaker time and the actual time, as well as the difference from the theoretical circuit breaker time, are added as constraints to the loss function, as shown in the following formula:

[0136]

[0137] Where L3 is the model loss function, M is the number of samples, is the predicted value of the fuse time, is the actual value of the fuse time, is the theoretical value of the melting time, is the weight coefficient, balancing data-driven and physical constraints.

[0138] Step S37: Determine whether the predicted fuse time reaches the optimal prediction based on the loss value.

[0139] Among them, by setting a fixed loss threshold, when the loss value is less than the loss threshold, it is determined that the predicted fuse time reaches the optimal prediction; when the loss value is not less than the loss threshold, it is determined that the predicted fuse time does not reach the optimal prediction.

[0140] Step S38: When it is determined that the predicted blowing time does not reach the optimal prediction, go to the step of obtaining the blowing time timing data of the fuse until it is determined that the predicted blowing time reaches the optimal prediction, and output the predicted blowing time.

[0141] In some embodiments, updating the voltage sag duration in the duration rule base according to the obtained predicted blowing time of the fuse includes:

[0142] The fusing time of the fuse in the duration rule base is updated according to the predicted fusing time, and the voltage sag duration is determined according to the fusing time of the fuse.

[0143] For example, a method for evaluating the duration of a voltage sag provided in an embodiment of the present application is as follows: Figure 3 As shown, the specific process is:

[0144] 1) Data construction: Integrate characteristic data such as grid topology, fault type, and protection device configuration, and combine historical voltage sag records to construct a training set.

[0145] 2) Model Construction: Through the Stacking integration framework, the Deep Neural Network (DNN) base learner and the XGBoost meta-learner are trained layer by layer to achieve protection action pattern classification.

[0146] 3) Duration Mapping: Based on the protection action classification results and the duration rule library, the voltage sag duration is calculated. Combined with physical rules, namely, the prediction of the fuse time, the voltage sag duration is dynamically corrected.

[0147] 4) Verification: Input the test data set, compare the predicted duration with the actual value, and quantitatively evaluate the model accuracy using indicators such as MAE (Mean Absolute Error) and RMSE (Root Mean Square Error).

[0148] Based on the same inventive concept, an embodiment of the present application further provides a voltage sag duration assessment system for implementing the above-mentioned voltage sag duration assessment method.

[0149] The implementation solution provided by the system to solve the problem is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more voltage sag duration assessment system embodiments provided below can refer to the limitations of the voltage sag duration assessment method above and will not be repeated here.

[0150] like Figure 4 As shown, an embodiment of the present application provides a voltage sag duration assessment system, comprising:

[0151] The protection action recognition module 100 is used to determine the current relay protection action coordination mode corresponding to the real-time influencing factor data based on the pre-input real-time influencing factor data using a preset relay protection action coordination mode recognition model; wherein the relay protection action coordination mode recognition model is obtained by training a classifier using multiple historical samples of relay protection action coordination modes and historical sample data of influencing factors corresponding to each historical sample of the relay protection action coordination mode;

[0152] A rule base updating module 200 is configured to update the voltage sag duration in the duration rule base according to the obtained predicted blowing time of the fuse; wherein the duration rule base includes a mapping relationship between the relay protection action coordination mode and the voltage sag duration;

[0153] The duration evaluation module 300 is used to determine the voltage sag duration corresponding to the current relay protection action coordination mode based on the duration rule base and the current relay protection action coordination mode.

[0154] In some embodiments, the system further includes: a recognition model building module for:

[0155] Acquire multiple historical samples of relay protection action coordination modes and historical sample data of influencing factors corresponding to each historical sample of relay protection action coordination mode to form a historical training sample set;

[0156] Preprocess the historical training sample set;

[0157] The classifier is trained based on the preprocessed historical training sample set to obtain a relay protection action coordination mode recognition model.

[0158] In some embodiments, the system further includes a rule base construction module for:

[0159] Determine the voltage sag duration at multiple different fault locations based on the relay protection action coordination mode and the voltage sag impact time corresponding to the relay protection action coordination mode. The voltage sag impact time includes the fault clearing time, the fuse melting time, and the main protection action time. The voltage sag duration is divided into the voltage sag duration of the branch where the fault is located, the voltage sag duration of other branches of the feeder where the fault is located, and the voltage sag duration of other feeders on the same busbar where the fault is located, based on the fault location.

[0160] A duration rule base is constructed based on the relay protection action coordination mode, the voltage sag impact time corresponding to the relay protection action coordination mode, and the voltage sag duration.

[0161] In some embodiments, the system further includes: a time prediction module, configured to: predict a predicted blowing time of the fuse; predicting the predicted blowing time of the fuse includes:

[0162] Obtain the fuse's blowing time series data;

[0163] Standardize the time series data of circuit breaking;

[0164] Based on the long short-term memory neural network, the predicted blowing time of the fuse at the current moment is obtained by predicting the standardized blowing time series data.

[0165] In some embodiments, the system further includes a time update module configured to:

[0166] Under the physical constraints of the fuse's thermodynamic equation, the accumulated thermal energy is calculated based on the current time series integral;

[0167] Determine the theoretical melting time based on the accumulated heat energy and the heat capacity of the fuse;

[0168] Determine the loss value through the loss function based on the predicted circuit breaking time, the actual circuit breaking time and the theoretical circuit breaking time;

[0169] Determine whether the predicted circuit-breaking time reaches the optimal prediction based on the loss value;

[0170] If it is determined that the predicted blowing time does not reach the optimal prediction, go to the step of obtaining the blowing time timing data of the fuse until it is determined that the predicted blowing time reaches the optimal prediction, and output the predicted blowing time.

[0171] In some embodiments, the duration assessment module 300 is configured to:

[0172] The fusing time of the fuse in the duration rule base is updated according to the predicted fusing time, and the voltage sag duration is determined according to the fusing time of the fuse.

[0173] like Figure 5 As shown, an embodiment of the present application provides an electronic device, an electronic device, the electronic device 10 includes a memory 20 and a processor 30, the memory 20 stores a computer program, and when the computer program is executed by the processor 30, the processor 30 performs the steps of the voltage sag duration assessment method in the above embodiment.

[0174] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed, the steps of the voltage sag duration evaluation method in the above embodiment are implemented.

[0175] An embodiment of the present application provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer performs the steps of the voltage sag duration assessment method described in the above embodiment.

[0176] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, electronic devices, computer storage media, and computer program products can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0177] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or apparatuses.

[0178] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0179] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, electronic devices, computer storage media, computer program products and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0180] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0181] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0182] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the method described in each embodiment of the present invention via a computer device (which can be a personal computer, server, or network device, etc.). The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0183] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for evaluating the duration of a voltage sag, characterized in that: include: By using a preset relay protection action coordination mode identification model, based on pre-input real-time influencing factor data, the current relay protection action coordination mode corresponding to the real-time influencing factor data is determined; wherein the relay protection action coordination mode identification model is obtained by training a classifier using a plurality of relay protection action coordination mode historical samples and historical sample data of influencing factors corresponding to each of the relay protection action coordination mode historical samples; The voltage sag duration in the duration rule base is updated according to the obtained predicted melting time of the fuse; wherein the duration rule base includes a mapping relationship between the relay protection action coordination mode and the voltage sag duration; Based on the duration rule base and according to the current relay protection action coordination mode, determining the voltage sag duration corresponding to the current relay protection action coordination mode; The method further comprises: Determine the voltage sag duration at multiple different fault locations based on the relay protection action coordination mode and the voltage sag impact time corresponding to the relay protection action coordination mode; wherein the voltage sag impact time includes the fault clearing time, the fuse melting time, and the main protection action time; the voltage sag duration is divided into the voltage sag duration of the branch where the fault is located, the voltage sag duration of other branches of the feeder where the fault is located, and the voltage sag duration of other feeders on the same busbar where the fault is located, according to the fault location; Constructing the duration rule base according to the relay protection action coordination mode, the voltage sag impact time corresponding to the relay protection action coordination mode, and the voltage sag duration; The method further includes: predicting a predicted blowing time of the fuse; the predicting the predicted blowing time of the fuse includes: Obtain the fuse's blowing time series data; Performing standardization on the fuse time series data; Based on the long short-term memory neural network, the predicted fuse opening time at the current moment is obtained by predicting the normalized fuse opening time series data. The method further comprises: Under the physical constraints of the fuse's thermodynamic equation, the accumulated thermal energy is calculated based on the current time series integral; determining a theoretical fusing time based on the accumulated thermal energy and the thermal capacity of the fuse; Determining a loss value using a loss function according to the predicted fusing time, the actual fusing time, and the theoretical fusing time; Determining whether the predicted fuse time reaches the optimal prediction based on the loss value; If it is determined that the predicted blowing time does not reach the optimal prediction, go to the step of obtaining the blowing time timing data of the fuse until it is determined that the predicted blowing time reaches the optimal prediction, and output the predicted blowing time.

2. The voltage sag duration evaluation method according to claim 1, characterized in that: Also includes: Acquire multiple relay protection action coordination mode historical samples and historical sample data of influencing factors corresponding to each of the relay protection action coordination mode historical samples to form a historical training sample set; Preprocessing the historical training sample set; The classifier is trained according to the pre-processed historical training sample set to obtain the relay protection action coordination mode identification model.

3. The voltage sag duration evaluation method according to claim 1, wherein: The updating of the voltage sag duration in the duration rule base according to the obtained predicted blowing time of the fuse includes: The fusing time of the fuse in the duration rule base is updated according to the predicted fusing time, and the voltage sag duration is determined according to the fusing time of the fuse.

4. A voltage sag duration assessment system, characterized in that: include: A protection action recognition module is configured to determine, using a preset relay protection action coordination mode recognition model, the current relay protection action coordination mode corresponding to the real-time influencing factor data input in advance; wherein the relay protection action coordination mode recognition model is obtained by training a classifier using a plurality of relay protection action coordination mode historical samples and historical sample data of influencing factors corresponding to each of the relay protection action coordination mode historical samples; A rule base updating module is used to update the voltage sag duration in the duration rule base according to the obtained predicted melting time of the fuse; wherein the duration rule base contains a mapping relationship between the relay protection action coordination mode and the voltage sag duration; a duration evaluation module, configured to determine, based on the duration rule base and according to the current relay protection action coordination mode, the voltage sag duration corresponding to the current relay protection action coordination mode; Rulebase building blocks for: Determine the voltage sag duration at multiple different fault locations based on the relay protection action coordination mode and the voltage sag impact time corresponding to the relay protection action coordination mode. The voltage sag impact time includes the fault clearing time, the fuse melting time, and the main protection action time. The voltage sag duration is divided into the voltage sag duration of the branch where the fault is located, the voltage sag duration of other branches of the feeder where the fault is located, and the voltage sag duration of other feeders on the same busbar where the fault is located, based on the fault location. Build a duration rule base based on the relay protection action coordination mode, the voltage sag impact time corresponding to the relay protection action coordination mode, and the voltage sag duration; The time prediction module is used to predict the predicted blowing time of the fuse; the predicted blowing time of the fuse is predicted, including: Obtain the fuse's blowing time series data; Standardize the time series data of circuit breaking; Based on the long short-term memory neural network, the predicted fuse opening time at the current moment is obtained by predicting the normalized fuse opening time series data. Time update module, used to: Under the physical constraints of the fuse's thermodynamic equation, the accumulated thermal energy is calculated based on the current time series integral; Determine the theoretical melting time based on the accumulated heat energy and the heat capacity of the fuse; Determine the loss value through the loss function based on the predicted circuit breaking time, the actual circuit breaking time and the theoretical circuit breaking time; Determine whether the predicted circuit-breaking time reaches the optimal prediction based on the loss value; If it is determined that the predicted blowing time does not reach the optimal prediction, go to the step of obtaining the blowing time timing data of the fuse until it is determined that the predicted blowing time reaches the optimal prediction, and output the predicted blowing time.

5. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the processor performs the steps of the voltage sag duration assessment method according to any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed, the steps of the voltage sag duration evaluation method according to any one of claims 1 to 3 are implemented.

7. A computer program product, characterized in that The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, wherein the computer program includes program instructions, wherein when the program instructions are executed by a computer, the computer is caused to perform the steps of the voltage sag duration estimation method according to any one of claims 1 to 3.

Images