A kind of three remote test method, equipment and storage medium of substation secondary equipment

Abstract

The application discloses a kind of secondary equipment of transformer substation three remote test method, equipment and storage medium, the method comprises: three remote test signal is transmitted to secondary equipment in transformer substation;Response signal that secondary equipment is output to three remote test signal is collected;Three remote test signal is input into expected response semantic simulator and is handled, and expected response feature is obtained;Response signal is input into response signal feature extractor and is handled, and actual response feature is obtained;The distance between expected response feature and actual response feature is calculated;According to distance, the operating state of secondary equipment is detected.This embodiment compares the difference between actual response and expected response to carry out three remote test to secondary equipment in transformer substation, detects the operating state of secondary equipment in transformer substation, can effectively reduce the dependence on technical personnel, greatly improves the simplicity of test, time-consuming is short, coverage is high, can effectively improve the consistency and reliability of test.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid testing, and particularly relates to a three-remote testing method, device and storage medium for secondary equipment of a substation. BACKGROUND

[0002] As one of components of a power grid, secondary equipment in a substation is mainly responsible for monitoring, protecting and controlling primary equipment to ensure stable operation of a power system.

[0003] In order to maintain normal operation of secondary equipment, currently, technical personnel mainly rely on testing of secondary equipment, sending and receiving signals one by one according to testing requirements, and manually recording testing results.

[0004] This testing method is relatively cumbersome and time-consuming, especially in a system composed of complex secondary equipment, testing may take several hours or even several days, and in the testing process, the coverage rate of testing is low due to the experience and knowledge of technical personnel, and is easily affected by human subjective factors, resulting in poor consistency and reliability of testing. SUMMARY

[0005] Therefore, the present application provides a three-remote testing method, device and storage medium for secondary equipment of a substation, to improve consistency and reliability of testing of secondary equipment in a substation.

[0006] A first aspect of the present application provides a three-remote testing method for secondary equipment of a substation, comprising:

[0007] transmitting a three-remote testing signal to secondary equipment in a substation;

[0008] collecting a response signal output by the secondary equipment in response to the three-remote testing signal;

[0009] inputting the three-remote testing signal into an expected response semantic simulator for processing to obtain an expected response feature;

[0010] inputting the response signal into a response signal feature extractor for processing to obtain an actual response feature;

[0011] calculating a distance between the expected response feature and the actual response feature;

[0012] detecting an operating state of the secondary equipment according to the distance.

[0013] A second aspect of the present application provides a three-remote testing device for secondary equipment of a substation, comprising:

[0014] a three-remote testing signal transmission module configured to transmit a three-remote testing signal to secondary equipment in a substation;

[0015] a response signal collection module, configured to collect a response signal output by the secondary device in response to the three-remote test signal;

[0016] an expected response feature generation module, configured to input the three-remote test signal into an expected response semantic simulator for processing to obtain an expected response feature;

[0017] an actual response feature generation module, configured to input the response signal into a response signal feature extractor for processing to obtain an actual response feature;

[0018] a distance calculation module, configured to calculate a distance between the expected response feature and the actual response feature;

[0019] a running state detection module, configured to detect a running state of the secondary device according to the distance.

[0020] A third aspect of the present application provides an electronic device, comprising:

[0021] at least one processor; and

[0022] a memory connected to the at least one processor in communication; wherein,

[0023] the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the three-remote test method for a secondary device of a substation as described in the first aspect above.

[0024] A fourth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the three-remote test method for a secondary device of a substation as described in the first aspect above.

[0025] A fifth aspect of the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the three-remote test method for a secondary device of a substation as described in the first aspect above.

[0026] In the embodiment, the three-remote test signal is transmitted to the secondary equipment in the transformer substation; the response signal output by the secondary equipment to the three-remote test signal is collected; the three-remote test signal is input into the expected response semantic simulator for processing to obtain the expected response feature; the response signal is input into the response signal feature extractor for processing to obtain the actual response feature; the distance between the expected response feature and the actual response feature is calculated; and the running state of the secondary equipment is detected according to the distance. The embodiment provides an automatic test framework for three-remote test, detects the running state of the secondary equipment in the transformer substation by comparing the difference between the actual response and the expected response, can effectively reduce the dependence on technical personnel, greatly improves the convenience of test, is time-saving, has high coverage, and can effectively improve the consistency and reliability of test.

[0027] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0029] Figure 1 is a flow chart of a three-remote test method for secondary equipment in a transformer substation provided by the first embodiment of the present application.

[0030] Figure 2 is a structural schematic diagram of a three-remote test device for secondary equipment in a transformer substation provided by the second embodiment of the present application.

[0031] Figure 3 is a structural schematic diagram of an electronic device provided by the third embodiment of the present application. DETAILED DESCRIPTION

[0032] In order to make the technical personnel in the art better understand the present application scheme, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0033] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described accompanying drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can cover the order of implementation other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment one

[0035] Referring to Figure 1 , a flow chart of a method for testing a substation secondary device provided by the embodiment one of the present application is shown, the method can be executed by a three-remote testing device of a substation secondary device, the three-remote testing device of the substation secondary device can be realized in the form of hardware and / or software, and the three-remote testing device of the substation secondary device can be configured in an electronic device of a test platform. As shown in Figure 1 , the method comprises:

[0036] Step 101, transmitting a three-remote testing signal to a secondary device in a substation.

[0037] In the secondary device of the substation, the three-remote (i.e. remote signaling, remote measurement, remote control) technology is one of the technologies for realizing remote monitoring and control.

[0038] Among them, remote signaling refers to the detection of remote state signals, such as the position (open / closed) of a circuit breaker, the state of a protection device, etc., and the test platform can simulate the change of the state signal to verify whether the secondary device can accurately reflect the change of the state signal.

[0039] Remote measurement involves the transmission of remote measurement data, such as current, voltage values, etc., and the test platform can generate simulated measurement values to check whether the secondary device can correctly receive and process the measurement values.

[0040] Remote control refers to the operation of controlling the device from a distance, such as remotely controlling the opening and closing of a circuit breaker, etc., and during testing, the test platform can send control commands to confirm that the secondary device can perform the corresponding operation.

[0041] In the embodiment, the analog terminal (i.e. analog signal generator) is connected to the secondary device to be tested, and the test platform can periodically or non-periodically configure the analog terminal and the secondary device according to the type of function to be tested (remote control, remote measurement, remote signaling), simulate various three-remote test signals (such as voltage signals and current signals) that the primary device may generate in the actual operation process of the substation under the condition that the actual operation of the power grid is not disturbed, and transmit the three-remote test signals to the secondary device to test the secondary device and verify whether the secondary device can correctly respond to the three-remote test signals.

[0042] Step 102, collect the response signal output by the secondary device to the three-remote test signal.

[0043] In the embodiment, the secondary device is configured with a data collector, and the data collector is started to collect the response signal output by the secondary device to the three-remote test signal at the same time when the three-remote test signal is transmitted, so as to verify whether the secondary device can correctly respond to the simulated three-remote test signal (remote signaling, remote measurement, remote control).

[0044] In the process of collection, it is ensured that the time window of collection is sufficient to cover the entire test period, so as to completely capture the response signal.

[0045] Step 103, input the three-remote test signal into the expected response semantic simulator for processing to obtain an expected response feature.

[0046] In the embodiment, the expected response semantic simulator can be constructed and trained in advance based on deep learning, the three-remote test signal is input into the expected response semantic simulator, and the response semantic simulator can generate a feature of the response signal generated when the secondary device correctly captures and responds to the three-remote test signal, which is recorded as an expected response feature.

[0047] In one embodiment of the application, step 103 can include the following steps:

[0048] Step 1031, load the expected response semantic simulator.

[0049] In the embodiment, the expected response semantic simulator is constructed based on the seq2seq (Sequence to Sequence) architecture in deep learning.

[0050] The expected response semantic simulator includes an encoder Encoder with a structure of a one-dimensional (1D) convolutional neural network (CNN) and a decoder Decoder with a structure of a recurrent neural network (RNN).

[0051] During the test, the pre-trained expected response semantic simulator can be loaded into the memory for running.

[0052] Step 1032, inputting the three-remote test signal into an encoder for coding to obtain a sequence of local implicit correlation features.

[0053] The test platform inputs the simulated three-remote test signal into the encoder in the expected response semantic simulator for coding to obtain a sequence of local implicit correlation features.

[0054] Step 1033, performing feature optimization and aggregation processing on the sequence of local implicit correlation features based on clustering contribution analysis to obtain global semantic significant aggregation features.

[0055] Since each local implicit correlation feature in the sequence of local implicit correlation features contains local correlation feature information about the three-remote test signal, the local correlation feature information has correlation semantics and global-based aggregation representation information, but not all local implicit correlation features have equal importance to the final expected response features, and some local implicit correlation features can contain redundant information or noise.

[0056] Based on this, the sequence of local implicit correlation features can be subjected to feature optimization and aggregation processing based on clustering contribution analysis to obtain global semantic significant aggregation features.

[0057] The feature optimization and aggregation processing based on clustering contribution analysis aims to use field domain analysis theory to model the clustering contribution degree of each local implicit correlation feature based on the field domain, improve the accuracy of feature aggregation, and thus improve the performance and generalization ability of the expected response semantic simulator.

[0058] In an embodiment of the present application, step 1033 can further include the following steps:

[0059] Step 10331, performing self-supervised clustering on the sequence of local implicit correlation features to obtain category features.

[0060] In this embodiment, the sequence of local implicit correlation features can be subjected to self-supervised clustering to obtain category features. The so-called self-supervised clustering refers to clustering without relying on pre-labeled training samples, but by automatically learning the internal structure and pattern of the sequence of local implicit correlation features.

[0061] For example, the mean of each local implicit correlation feature in the sequence of local implicit correlation features can be calculated to obtain category features.

[0062] Step 10332, modulating and aggregating the sequence of local implicit correlation features based on the feature clustering contribution field distribution according to the category feature, to obtain a global semantic saliency aggregation feature.

[0063] In this embodiment, on the basis of the category feature, the sequence of local implicit correlation features can be modulated and aggregated based on the feature clustering contribution field distribution, to obtain a global semantic saliency aggregation feature.

[0064] In an embodiment of the present application, step 10332 can further include the following steps:

[0065] Step 103321, calculating an implicit clustering contribution factor of each local implicit correlation feature in the sequence of local implicit correlation features with respect to the category feature, to obtain a sequence of implicit clustering contribution factors.

[0066] In this embodiment, an implicit clustering contribution factor of each local implicit correlation feature in the sequence of local implicit correlation features with respect to the category feature is calculated, to obtain a sequence of implicit clustering contribution factors.

[0067] Illustratively, the absolute value of the ratio between the local implicit correlation feature and the category feature by position is taken, to obtain a clustering interaction correlation feature; the logarithmic function value of each position feature value in the clustering interaction correlation feature with base 2 is calculated, to obtain a clustering interaction value; each position feature value in the clustering interaction value is taken as a weighting coefficient, and each position feature value in the local implicit correlation feature is weighted and summed, to obtain a clustering contribution degree factor; the exponential function value of the clustering contribution degree factor with base of the natural constant is calculated, to obtain an implicit clustering contribution factor.

[0068] Step 103322, vectorizing and arranging the sequence of implicit clustering contribution factors, to obtain a clustering contribution field distribution vector.

[0069] In this embodiment, each implicit clustering contribution factor in the sequence of implicit clustering contribution factors is vectorized and arranged, to obtain a clustering contribution field distribution vector.

[0070] Step 103323, inputting the clustering contribution field distribution vector into a clustering contribution field explicit modeling module based on a self-attention mechanism for processing, to obtain a clustering contribution field domain modulation weight.

[0071] In this embodiment, the clustering contribution field distribution vector can be input into a clustering contribution field explicit modeling module based on a self-attention mechanism (Self-Attention) for processing, to obtain a clustering contribution field domain modulation weight.

[0072] Exemplarily, matrix multiplication between the cluster contribution field distribution vector and the query weight matrix (Q matrix), the key weight matrix (K matrix) and the value weight matrix (V matrix) in the self-attention mechanism is calculated respectively to obtain a cluster contribution field distribution query vector (Q matrix), a cluster contribution field distribution key vector (K matrix) and a cluster contribution field distribution value vector (V matrix);

[0073] The product between the cluster contribution field distribution query vector and the transposed vector of the cluster contribution field distribution key vector is divided by the square root of the length of the cluster contribution field distribution key vector to obtain a cluster contribution field semantic interaction matrix.

[0074] The cluster contribution field semantic interaction matrix is normalized by using a function such as Softmax.

[0075] If the normalization is completed, the product between the cluster contribution field distribution value vector and the cluster contribution field semantic interaction matrix is calculated to obtain a cluster contribution field domain modulation weight.

[0076] Step 103324, each feature value in the cluster contribution field domain modulation weight is used to positionally weight-sum the sequence of local implicit correlation features to obtain a global semantic saliency aggregation feature.

[0077] In the embodiment, each feature value in the cluster contribution field domain modulation weight can be used as a weight to positionally calculate the product between it and the sequence of local implicit correlation features, and the product is summed to obtain the global semantic saliency aggregation feature.

[0078] In the embodiment, the process of aggregating the sequence of local implicit correlation features into the global semantic saliency aggregation feature can be represented as follows:

[0079] X={x1,x2,...,x k ,...,x n}

[0080]

[0081] v d ={d1;d2;...;d j ;...;d n}

[0082]

[0083] v q =W q v d

[0084] v k =W k v d

[0085] v v =W b v d

[0086]

[0087] Where X is a sequence of locally implicit association features, x1, x2, x... k ,x n Let x be the 1st, 2nd, kth, and nth local implicit association features in the sequence of local implicit association features. i Let x be the i-th local implicit association feature in the sequence of local implicit association features, and N be the number of local implicit association features in the sequence of local implicit association features. c For categorical features, x j Let j be the j-th local implicit association feature in the sequence of local implicit association features. Let x be the feature value at the k-th position in the j-th local implicit association feature. ck Let be the feature value at the k-th position in the categorical features, where log represents the logarithmic function value to the base 2, exp represents the natural exponential function value, and d j v is the latent clustering contribution factor corresponding to the j-th local implicit association feature. d W is the cluster contribution field distribution vector obtained by vectorizing and arranging multiple latent cluster contribution factors. q W k and W b These are the query weight matrix, key weight matrix, and value weight matrix, respectively. q v k and v v These represent the cluster contribution field distribution query vector, cluster contribution field distribution key vector, and cluster contribution field distribution value vector, respectively, where L is the length of the cluster contribution field distribution key vector, and Softmax(·) is the Softmax function. For vector multiplication, v w To contribute field modulation weights for clustering, x f It is a globally significant aggregated semantic feature.

[0088] In this embodiment, firstly, a self-supervised learning method is used to perform cluster analysis on the sequences of local implicit correlation features to automatically discover the local correlation feature patterns and structures of the simulated remote sensing test signals in the set, so as to generate category features.

[0089] In this process, the self-supervised clustering can reveal the internal structure of the local correlation characteristics of each simulated three-remote test signal, helping the expected response semantic simulator learn meaningful feature representations without explicit labels, enhancing the expected response semantic simulator's understanding of the correlation between various local features of the simulated three-remote test signal, and helping to reveal the internal relationship of each feature vector.

[0090] Furthermore, by calculating the implicit clustering contribution factor between the local implicit correlation features and the category features, the contribution of each local implicit correlation feature to the cluster to which it belongs is reflected.

[0091] Correspondingly, the calculation of the implicit clustering contribution factor helps to identify and quantify the role of each local implicit correlation feature in the clustering process, providing a basis for subsequent feature selection and weight allocation, so that the model can pay more attention to features that make significant contributions to clustering.

[0092] Then, the sequence of calculated implicit clustering contribution factors is converted into a clustering contribution field distribution vector, that is, the sequence of implicit clustering contribution factors is integrated into a vector field to construct a clustering contribution field using data integration.

[0093] Then, the self-attention mechanism is used to explicitly model the clustering contribution field distribution vector to generate the clustering contribution field domain modulation weight. That is, the self-attention mechanism is used to perform clustering contribution degree explicit modeling based on field domain self-correlation global analysis of each implicit clustering contribution factor in the clustering contribution field, which can enhance the attention to feature vectors with high clustering contribution while suppressing unimportant features, improving the quality of feature representation and the accuracy of subsequent global semantic representation of the simulated three-remote test signal and semantic representation of the expected response signal.

[0094] Finally, the sequence of local implicit correlation features is weighted and fused using the clustering contribution field domain modulation weight to generate global semantic significant aggregation features. The global semantic significant aggregation features provide a comprehensive feature representation that not only includes the original local correlation feature information of the simulated three-remote test signal, but also integrates the knowledge learned in the clustering process, enabling the expected response semantic simulator to more accurately identify and analyze signals when processing complex tasks, thereby improving the overall performance and reliability of the expected response semantic simulator.

[0095] Step 1034, input the global semantic significant aggregation features into the decoder to obtain the expected response features.

[0096] In this embodiment, the global semantic significant aggregation features are input into the decoder of the expected response semantic simulator to decode the global semantic significant aggregation features, predict the response behavior of the secondary device to be tested in the real operating environment, and thus obtain the expected response features.

[0097] When the structure of the decoder is an RNN, the RNN can capture the global semantic long-distance correlation features and relationships about the simulated three-remote test signals in the globally semantically significant aggregated features after the feature aggregation representation, thereby generating the decoding of the expected response signal semantics simulation to obtain the expected response features.

[0098] Step 104, inputting the response signal into the response signal feature extractor for processing to obtain actual response features.

[0099] In this embodiment, the response signal is input into the response signal feature extractor to extract features from the response signal, which are denoted as actual response features.

[0100] When the structure of the encoder of the expected response semantics simulator is a one-dimensional (1D) convolutional neural network (CNN), the structure of the response signal feature extractor is a one-dimensional (1D) convolutional neural network (CNN), and the structure of the encoder of the expected response semantics simulator is the same as or similar to that of the response signal feature extractor, which helps to extract features at the same level.

[0101] Further, the convolutional neural network can identify local patterns in the response signal through convolution operations, reduce the amount of data, and thereby abstract the key features of the response signal. At the same time, constructing the response signal feature extractor based on the convolutional neural network can enhance the robustness of the response signal feature extractor to noise and changes. Even if the input response signal is disturbed or has slight changes, the extracted actual response features can still reflect the main features of the response signal, and subsequent comparison and analysis can be easily performed.

[0102] When the response signal feature extractor includes a convolutional layer, a pooling layer, and a fully connected layer, in the convolutional layer, the response signal can be subjected to convolution processing based on a one-dimensional (1D) convolution kernel to obtain convolution features, wherein the one-dimensional convolution kernel slides on the response signal to extract local implicit correlation features in the response signal, and the convolution kernel can capture patterns in the response signal, which can be specific frequency waveforms, periodic patterns, or other meaningful features. In the pooling layer, the convolution feature vector is subjected to pooling processing to obtain a pooling feature vector, wherein the pooling processing is used to reduce the spatial dimension of the data while retaining the most important feature information. The pooling operation helps the model to focus on the most significant features and reduces the risk of overfitting. The pooling feature vector is subjected to nonlinear activation to obtain an activation feature vector. In the fully connected layer, the activation feature vector is mapped to the actual response features.

[0103] Step 105, calculating the distance between the expected response features and the actual response features.

[0104] In the embodiment, a distance between the expected response feature and the actual response feature can be calculated, such as a Hamming distance, to quantify the difference between the expected response feature and the actual response feature.

[0105] The Hamming distance can be used to measure the number of differences between two binary strings of equal length, which is used to represent the difference between two semantic encoding feature vectors. By calculating the Hamming distance, subtle changes between the expected response feature and the actual response feature can be more accurately captured, thereby improving the reliability of the test results.

[0106] In step 106, the running state of the secondary device is detected according to the distance.

[0107] In the embodiment, the difference between the actual response and the expected response can be compared, thereby realizing more reliable and intelligent automatic testing of the three remote of the secondary device of the substation to verify the running state of the secondary device of the substation, that is, whether it operates in the expected manner or whether there is an abnormality.

[0108] When the secondary device can correctly respond to the three remote test signal, it can be ensured that it can work normally in actual operation.

[0109] By comparing the difference between the actual response signal and the expected response signal, it can be found in time whether the device has an abnormality, so that measures can be taken to correct or prevent it.

[0110] In a specific implementation, the distance can be compared with a preset threshold.

[0111] If the distance is greater than or equal to the preset threshold, it indicates that the difference between the expected response feature and the actual response feature is large, and it is determined that the running state of the secondary device is abnormal.

[0112] If the distance is less than the preset threshold, it indicates that the difference between the expected response feature and the actual response feature is small, and it is determined that the running state of the secondary device is normal.

[0113] In the embodiment, the three remote test signal is transmitted to the secondary device in the substation; the response signal output by the secondary device for the three remote test signal is collected; the three remote test signal is input into the expected response semantic simulator for processing to obtain an expected response feature; the response signal is input into the response signal feature extractor for processing to obtain an actual response feature; the distance between the expected response feature and the actual response feature is calculated; and the running state of the secondary device is detected according to the distance. The embodiment provides an automatic testing framework for three remote testing, which performs three remote testing on the secondary device in the substation by comparing the difference between the actual response and the expected response, detects the running state of the secondary device in the substation, can effectively reduce the dependence on technical personnel, greatly improves the simplicity of testing, is time-saving, has high coverage, and can effectively improve the consistency and reliability of testing.

[0114] Embodiment Two

[0115] Referring to Figure 2 , a structural schematic diagram of a three-remote testing device for a secondary device of a substation is shown. As Figure 2 indicated, the device includes:

[0116] a three-remote testing signal transmission module 201, configured to transmit a three-remote testing signal to a secondary device in a substation;

[0117] a response signal collection module 202, configured to collect a response signal output by the secondary device in response to the three-remote testing signal;

[0118] an expected response feature generation module 203, configured to input the three-remote testing signal into an expected response semantic simulator for processing to obtain an expected response feature;

[0119] an actual response feature generation module 204, configured to input the response signal into a response signal feature extractor for processing to obtain an actual response feature;

[0120] a distance calculation module 205, configured to calculate a distance between the expected response feature and the actual response feature;

[0121] a running state detection module 206, configured to detect a running state of the secondary device according to the distance.

[0122] In an embodiment of the present application, the expected response feature generation module 203 includes:

[0123] an expected response semantic simulator loading module, configured to load an expected response semantic simulator; wherein the expected response semantic simulator includes an encoder with a structure of a convolutional neural network and a decoder with a structure of a recurrent neural network; and the response signal feature extractor has a structure of a convolutional neural network;

[0124] an encoding module, configured to input the three-remote testing signal into the encoder for encoding to obtain a sequence of local implicit correlation features;

[0125] a feature aggregation module, configured to perform feature optimization and aggregation processing based on clustering contribution analysis on the sequence of local implicit correlation features to obtain a global semantic significant aggregation feature;

[0126] a decoding module, configured to input the global semantic significant aggregation feature into the decoder for decoding to obtain the expected response feature.

[0127] In an embodiment of the present application, the feature aggregation module includes:

[0128] The self-supervised clustering module is configured to perform self-supervised clustering on the sequence of local implicit correlation features to obtain category features.

[0129] The modulation and aggregation module is configured to perform modulation and aggregation on the sequence of local implicit correlation features based on a feature clustering contribution field distribution according to the category features to obtain global semantic saliency aggregation features.

[0130] In an embodiment of the present application, the self-supervised clustering module is further configured to:

[0131] The self-supervised clustering module is configured to calculate a mean value of the sequence of local implicit correlation features to obtain category features.

[0132] In an embodiment of the present application, the modulation and aggregation module comprises:

[0133] The implicit clustering contribution factor calculation module is configured to calculate an implicit clustering contribution factor of each local implicit correlation feature in the sequence of local implicit correlation features with respect to the category features to obtain a sequence of implicit clustering contribution factors.

[0134] The clustering contribution field distribution vector calculation module is configured to vectorize and arrange the sequence of implicit clustering contribution factors to obtain a clustering contribution field distribution vector.

[0135] The clustering contribution field domain modulation weight calculation module is configured to input the clustering contribution field distribution vector into a clustering contribution field explicit modeling module based on a self-attention mechanism to obtain clustering contribution field domain modulation weights.

[0136] The global semantic saliency aggregation feature generation module is configured to use each feature value in the clustering contribution field domain modulation weights to perform weighted summation on the sequence of local implicit correlation features according to positions to obtain global semantic saliency aggregation features.

[0137] In an embodiment of the present application, the implicit clustering contribution factor calculation module is further configured to:

[0138] The implicit clustering contribution factor calculation module is configured to take an absolute value of a ratio between the local implicit correlation features and the category features according to positions to obtain clustering interaction correlation features.

[0139] The implicit clustering contribution factor calculation module is configured to calculate a logarithmic function value of each position feature value in the clustering interaction correlation features with a base of 2 to obtain a clustering interaction value.

[0140] The implicit clustering contribution factor calculation module is configured to perform weighted summation on each position feature value in the local implicit correlation features using each position feature value in the clustering interaction value as a weighting coefficient to obtain a clustering contribution degree factor.

[0141] The implicit clustering contribution factor calculation module is configured to calculate an exponential function value of the clustering contribution degree factor with a natural constant as a base to obtain an implicit clustering contribution factor.

[0142] In one embodiment of the present application, the cluster contribution field domain modulation weight calculation module is further configured to:

[0143] respectively calculate matrix multiplication between the cluster contribution field distribution vector and the query weight matrix, the key weight matrix and the value weight matrix, to obtain a cluster contribution field distribution query vector, a cluster contribution field distribution key vector and a cluster contribution field distribution value vector;

[0144] divide the product between the cluster contribution field distribution query vector and the transposed vector of the cluster contribution field distribution key vector by the square root of the length of the cluster contribution field distribution key vector to obtain a cluster contribution field semantic interaction matrix;

[0145] perform normalization processing on the cluster contribution field semantic interaction matrix;

[0146] if the normalization processing is completed, calculate the product between the cluster contribution field distribution value vector and the cluster contribution field semantic interaction matrix to obtain a cluster contribution field domain modulation weight.

[0147] In one embodiment of the present application, the running state detection module 206 comprises:

[0148] an abnormality determination module configured to determine that the running state of the secondary equipment is abnormal if the distance is greater than or equal to a preset threshold value;

[0149] a normality determination module configured to determine that the running state of the secondary equipment is normal if the distance is less than a preset threshold value.

[0150] The substation secondary equipment three-way test device provided by the embodiment of the present application can execute the substation secondary equipment three-way test method provided by any embodiment of the present application, and has the corresponding function modules and beneficial effects of executing the substation secondary equipment three-way test method.

[0151] Embodiment three

[0152] Referring to Figure 3 , a structural schematic diagram of an electronic device provided by an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The components shown here, their connections, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0153] As Figure 3As shown, the electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., communicatively connected to the at least one processor 11, where the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded into the random access memory (RAM) 13 from the storage unit 18. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0154] Various components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc., an output unit 17, such as various types of displays, a speaker, etc., a storage unit 18, such as a magnetic disk, an optical disk, etc., and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0155] The processor 11 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the three-remote testing method of the substation secondary equipment.

[0156] In some embodiments, the three-remote testing method of the substation secondary equipment can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the three-remote testing method of the substation secondary equipment described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the three-remote testing method of the substation secondary equipment by any other appropriate means, such as by means of firmware.

[0157] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0158] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented on the computer or other programmable apparatus. The computer programs can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0159] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0160] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0161] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0162] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0163] Embodiment Four

[0164] The embodiment of the application further provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the three remote testing method of the substation secondary equipment provided in any embodiment of the application.

[0165] The computer program code can also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce the computer implemented process such that the

[0166] It should be understood that the various forms of flow shown in the figures are illustrative examples of implementing the steps of the application. Several steps have been described as being performed by a single device. It will be understood that these steps can be performed by a single device or multiple devices, and that the steps can be performed in an order different from that shown in the figures. For example, the steps described in the figures can be performed in parallel or in a different order, as long as the desired results of the application are achieved. The application is not limited in this regard.

[0167] The specific embodiments have been shown and described for the purposes of illustrating the physiological principles of the application and its practical application. It is therefore to be understood that various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the application. The scope of the application is not to be limited by specific illustrative embodiments. The application is to cover any and all modifications and the equivalents thereof within the spirit and scope of the application.

Claims

1. A method of performing three-remote testing of substation secondary equipment, the method comprising: The method comprises the following steps: transmitting a three-remote test signal to secondary equipment in a substation; collecting a response signal output by the secondary equipment in response to the three-remote test signal; loading an expected response semantic simulator, wherein the expected response semantic simulator comprises an encoder in the form of a convolutional neural network and a decoder in the form of a recurrent neural network, and the response signal feature extractor is in the form of a convolutional neural network; inputting the three-remote test signal into the encoder to obtain a sequence of local implicit correlation features; calculating the mean of the sequence of local implicit correlation features to obtain a category feature; modulating and aggregating the sequence of local implicit correlation features based on a feature clustering contribution field distribution according to the category feature to obtain a global semantic significant aggregation feature; inputting the global semantic significant aggregation feature into the decoder to obtain an expected response feature; inputting the response signal into a response signal feature extractor to obtain an actual response feature; calculating the distance between the expected response feature and the actual response feature; detecting the operating state of the secondary equipment according to the distance.

2. The method of claim 1, wherein, The modulation and aggregation of the sequence of local implicit correlation features based on the feature clustering contribution field distribution according to the category feature to obtain a global semantic significant aggregation feature comprises: calculating the implicit clustering contribution factor of each local implicit correlation feature in the sequence of local implicit correlation features with respect to the category feature to obtain a sequence of implicit clustering contribution factors; vectorizing and arranging the sequence of implicit clustering contribution factors to obtain a clustering contribution field distribution vector; inputting the clustering contribution field distribution vector into a clustering contribution field explicit modeling module based on a self-attention mechanism to obtain a clustering contribution field domain modulation weight; using each feature value in the clustering contribution field domain modulation weight to perform position-weighted summation on the sequence of local implicit correlation features to obtain a global semantic significant aggregation feature.

3. The method of claim 2, wherein, The calculation of the implicit clustering contribution factor of each local implicit correlation feature in the sequence of local implicit correlation features with respect to the category feature to obtain a sequence of implicit clustering contribution factors comprises: taking the absolute value of the ratio of the local implicit correlation feature to the category feature at each position to obtain a clustering interaction correlation feature; calculating the logarithmic function value of each position feature value in the clustering interaction correlation feature with base 2 to obtain a clustering interaction value; performing weighted summation on each position feature value in the local implicit correlation feature using each position feature value in the clustering interaction value as a weighting coefficient to obtain a clustering contribution degree factor; calculating the exponential function value of the clustering contribution degree factor with a natural constant as the base to obtain an implicit clustering contribution factor.

4. The method of claim 2, wherein, The inputting of the clustering contribution field distribution vector into the clustering contribution field explicit modeling module based on the self-attention mechanism to obtain a clustering contribution field domain modulation weight comprises: respectively calculating the matrix multiplication between the clustering contribution field distribution vector and a query weight matrix, a key weight matrix and a value weight matrix to obtain a clustering contribution field distribution query vector, a clustering contribution field distribution key vector and a clustering contribution field distribution value vector; multiply the product between the cluster contribution field distribution query vector and the transpose vector of the cluster contribution field distribution key vector by the square root of the length of the cluster contribution field distribution key vector by position to obtain a cluster contribution field semantic interaction matrix; perform normalization processing on the cluster contribution field semantic interaction matrix; if the normalization processing is completed, calculate the product between the cluster contribution field distribution value vector and the cluster contribution field semantic interaction matrix to obtain a cluster contribution field domain modulation weight.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: if the distance is greater than or equal to a preset threshold, determining that the running state of the secondary equipment is abnormal; if the distance is less than the preset threshold, determining that the running state of the secondary equipment is normal.

6. An electronic device, comprising: The electronic device includes: at least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for testing the three remote of the secondary equipment of the substation according to any one of claims 1-5.

7. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method for testing the three remote of the secondary equipment of the substation according to any one of claims 1-5.

Images