Cable fault detection method and device, electronic equipment and storage medium

Abstract

The application discloses a kind of cable fault detection method, device, electronic equipment and storage medium, it is related to power system intelligent diagnosis technical field.The method comprises: obtaining cable operation data;The cable operation data is input into pre-trained cable fault detection model, and the alternative cable fault type predicted by each cable fault detection submodel is obtained;Wherein, the cable fault detection model includes at least one cable fault detection submodel;Each of the alternative cable fault type is voted, and the target cable fault type of the cable operation data is determined.The technical scheme of the embodiment of the application improves the detection efficiency and detection accuracy of cable fault detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent diagnosis of power systems, and in particular to a cable fault detection method and device, an electronic device and a storage medium. BACKGROUND

[0002] Modern power systems are the nerve center of modern society, providing indispensable energy support for various industries through complex and delicate networks. Stable power supply is a key factor in maintaining daily life rhythm, industrial production efficiency and economic development. In this system, cables, as the blood vessels of power transmission, play a crucial role. The health of the cable is directly related to the reliability and safety of power transmission. The occurrence of cable faults not only causes local or even widespread power supply interruptions, but also can cause damage to connected equipment, trigger a chain reaction, and lead to production stagnation and economic losses. More seriously, cable faults can also pose safety hazards and threaten personnel and facility safety. Therefore, timely detection, accurate positioning and rapid repair of cable faults are of great significance to maintaining the integrity and stability of the power system.

[0003] With the advancement of technology, intelligent management has become an important direction to improve the efficiency of cable operation and maintenance. Intelligent cable systems use advanced sensors, Internet of Things technology and big data analysis to monitor the operating status of cables in real time, predict potential fault risks, and provide auxiliary decision support when faults occur. However, despite the many conveniences brought by intelligentization, existing intelligent cable systems still have limitations in automated fault diagnosis. When a fault actually occurs, the intelligent system often has difficulty in independently completing the automatic identification of fault types. This results in the need for professional personnel to conduct on-site investigation and fault diagnosis once a fault occurs, which not only increases the operation and maintenance cost, but also delays the speed of fault handling. SUMMARY

[0004] The present application provides a cable fault detection method, device, electronic device and storage medium, which improves the detection efficiency and accuracy of cable fault detection.

[0005] According to an aspect of the present application, a cable fault detection method is provided, the method comprising:

[0006] obtaining cable operation data;

[0007] inputting the cable operation data into a pre-trained cable fault detection model to obtain candidate cable fault types predicted by each cable fault detection sub-model; wherein the cable fault detection model comprises at least one cable fault detection sub-model;

[0008] voting on each of the candidate cable fault types to determine a target cable fault type of the cable operation data.

[0009] According to another aspect of the present application, there is provided a cable fault detection apparatus, the apparatus comprising:

[0010] a cable operation data acquisition module configured to acquire cable operation data;

[0011] a cable fault type prediction model configured to input the cable operation data into a pre-trained cable fault detection model to obtain candidate cable fault types predicted by each cable fault detection sub-model of the cable fault detection model; wherein the cable fault detection model comprises at least one cable fault detection sub-model;

[0012] a cable fault type voting module configured to vote on each of the candidate cable fault types to determine a target cable fault type of the cable operation data.

[0013] According to another aspect of the present application, there is provided an electronic device, the electronic device comprising:

[0014] at least one processor; and

[0015] a memory communicatively connected to the at least one processor; wherein

[0016] 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 cable fault detection method according to any one of the embodiments of the present application.

[0017] According to another aspect of the present application, there is provided a computer readable storage medium storing computer instructions for enabling a processor to perform the cable fault detection method according to any one of the embodiments of the present application when executed by the processor.

[0018] According to another aspect of the present application, there is provided a computer program product comprising a computer program for enabling a processor to perform the cable fault detection method according to any one of the embodiments of the present application when executed by the processor.

[0019] The technical solution of the embodiments of the present application realizes automatic detection of cable faults by pre-training each cable fault detection sub-model in a cable fault detection model to perform real-time detection on cable operation data, reduces operation and maintenance costs of cable fault detection, improves detection efficiency of cable fault detection, and further improves detection accuracy of cable faults by voting on each of candidate cable fault types to determine a target cable fault type.

[0020] It is to be understood that the details set forth herein do not limit the scope of the embodiments of the application to the specific embodiments described. Rather, the scope of the embodiments of the application is to be defined by the claims. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor based on these drawings.

[0022] Figure 1 is a flow chart of a cable fault detection method according to an embodiment of the present application;

[0023] Figure 2 is a flow chart of a cable fault detection method according to an embodiment of the present application;

[0024] Figure 3 is a flow chart of a cable fault detection method according to an embodiment of the present application;

[0025] Figure 4 is a structural schematic diagram of a cable fault detection model according to an embodiment of the present application;

[0026] Figure 5 is a structural schematic diagram of a cable fault detection device according to an embodiment of the present application;

[0027] Figure 6 is a structural schematic diagram of an electronic device for implementing a cable fault detection method according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to make the technical personnel in the art better understand the present application scheme, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings 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.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and in the above 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 thus used can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that 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 only 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.

[0030] Embodiment one

[0031] Figure 1 A flowchart of a cable fault detection method provided for the first embodiment of the present application. The embodiments of the present application can be applicable to the case of detecting cable faults in a power distribution network, and the method can be executed by a cable fault detection device, which can be realized in the form of hardware and / or software, and can be configured in an electronic device carrying a cable fault detection function, such as a fault analysis server.

[0032] Referring to Figure 1 The cable fault detection method shown includes:

[0033] S110, acquiring cable operation data.

[0034] The cable operation data can be used to represent the operating state of the cable in the power distribution network. For example, the cable operation data can include cable voltage, cable current, cable temperature, humidity of the environment where the cable is located, and / or cable load, etc.

[0035] In an optional embodiment of the present application, the cable operation data includes cable current, cable temperature and cable load. The cable current can be the carrying current of the cable. The cable temperature can be the surface temperature of the cable. The cable load can be the load connected to the cable. The present scheme further improves the detection efficiency of cable fault detection by selecting typical data in the cable operation data to detect the cable fault type.

[0036] Specifically, sensors provided in the power distribution network can be used to detect the cable operation data.

[0037] S120, inputting the cable operation data into a pre-trained cable fault detection model to obtain the candidate cable fault types predicted by each cable fault detection sub-model.

[0038] The cable fault detection model can be used to detect the cable fault type in the power distribution network. The cable fault detection model includes at least one cable fault detection sub-model. The single cable fault detection sub-model has high detection accuracy for a corresponding certain cable fault type. Thus, each cable fault detection sub-model can detect the cable fault type, and the detection accuracy for different cable fault types is different. For example, the cable fault detection sub-model can be a width learning model. The input data of the cable fault detection model can be cable operation data, and the output result can be each alternative cable fault type predicted by each cable fault detection sub-model. The alternative cable fault type can be the cable fault type predicted by the cable fault detection sub-model. Optionally, the number of alternative cable fault types can be single or multiple. When the number of alternative cable fault types is single, it can be understood that the alternative cable fault type is the final prediction result of the cable fault detection sub-model, for example, the alternative cable fault type is the reference cable fault type with the highest confidence in each reference cable fault type. The reference cable fault type can be all cable fault types in the power distribution network or a part of cable fault types with higher confidence and a preset output number. The preset output number can be the number of output results of the cable fault detection sub-model preset in advance. When the number of alternative cable fault types is multiple, it can be understood that the alternative cable fault type is each reference cable fault type or a further filtered result of each reference cable fault type.

[0039] Specifically, the cable operation data can be input into the pre-trained cable fault detection model, and each cable fault detection sub-model can detect the cable operation data to obtain each alternative cable fault type output by each cable fault detection sub-model.

[0040] S130, voting for each alternative cable fault type to determine the target cable fault type of the cable operation data.

[0041] The target cable fault type can be the final determined cable fault type of the cable operation data.

[0042] Specifically, each alternative cable fault type can be voted, and the alternative cable fault type with the highest occurrence frequency can be determined as the target cable fault type of the cable operation data.

[0043] For example, the number of alternative cable fault types is M; the alternative cable fault types are [y1, y2, y3,..., yM]; where ya is the prediction result of the a-th cable fault detection sub-model for the cable operation data (i.e., the alternative cable fault type of the a-th cable fault detection sub-model). M a

[0044] ​​The following formula can be used to vote for each candidate cable fault type:

[0045]

[0046] wherein Count(Y l ) is the number of votes for the cable fault type Y l , indicating the number of times the cable fault type Y l is predicted by all cable fault detection sub-models; Y l is the lth cable fault type; l is the number of the cable fault type; y a is the candidate cable fault type of the ath cable fault detection sub-model; a is the number of the cable fault detection sub-model or the candidate cable fault type; M is the number of cable fault detection sub-models; I(y a =Y l ) is an indicator function, which takes the value of 1 if (y a =Y l ) is equal to Y M , otherwise 0.

[0047] The following formula can be used to calculate the target cable fault type of the cable operation data:

[0048]

[0049] wherein Y is the target cable fault type of the cable operation data; argmax M is the maximum selection function; Count(Y l ) is the number of votes for the cable fault type Y l , indicating the number of times the cable fault type Y l is predicted by all cable fault detection sub-models. It can be understood that the cable fault type with the most votes is selected as the final prediction result, and thus the target cable fault type of the cable operation data can be obtained.

[0050] In an optional example, the candidate cable fault types of each cable fault detection sub-model and the confidence of the candidate cable fault types can be counted to determine the target cable fault type of the cable operation data. For example, the candidate cable fault type with the highest confidence can be determined as the target cable fault type. For another example, the average confidence of each candidate cable fault type can be obtained by calculating the average of the confidence of the same candidate cable fault type output by different cable fault detection sub-models, and the candidate cable fault type with the highest average confidence can be determined as the target cable fault type of the cable operation data.

[0051] The technical scheme of the embodiment of the present application realizes automatic detection of cable faults, reduces operation and maintenance costs of cable fault detection, improves detection efficiency of cable fault detection, and can further improve detection accuracy of cable faults by voting on each candidate cable fault type to determine a target cable fault type.

[0052] Embodiment Two

[0053] Figure 2 A flowchart of a cable fault detection method provided by Embodiment Two of the present application is shown. Embodiment Two of the present application further includes, before obtaining cable operation data, “obtaining cable operation samples and actual cable fault types; determining cable fault detection sub-models corresponding to each actual cable fault type and classification loss weights of each cable fault detection sub-model; for a single cable fault detection sub-model, calculating a target connection weight matrix of the cable fault detection sub-model based on the cable operation samples, the classification loss weights of the cable fault detection sub-model, and the corresponding actual cable fault type; and adjusting parameters of each cable fault detection sub-model according to the target connection weight matrix of each cable fault detection sub-model”, by pre-training cable fault detection sub-models with different classification loss weights, cable fault detection sub-models with different detection sensitivities for different actual cable fault types are obtained, and detection accuracy and detection efficiency of cable fault detection using a cable fault detection model are improved. It should be noted that parts not described in detail in Embodiment Two of the present application can be referred to the descriptions of other embodiments.

[0054] Referring to Figure 2 The cable fault detection method includes the following steps.

[0055] S210, obtaining cable operation samples and actual cable fault types.

[0056] The cable operation samples can be cable operation data collected before the current time in the power distribution network. The cable operation samples can be used to train the cable fault detection model. The actual cable fault types can be the actual cable fault types of a group of cable operation samples. Optionally, the actual cable fault types can be pre-labeled by technical personnel. The number of cable operation samples can be multiple groups. A single group of cable operation samples can correspond to a certain actual cable fault type.

[0057] Specifically, cable operation data collected by sensors in the power distribution network before the current time can be obtained as cable operation samples. The actual cable fault types corresponding to the pre-labeled cable operation samples can be obtained.

[0058] S220. Determine the cable fault detection sub-model corresponding to each actual cable fault type and the classification loss weight of each cable fault detection sub-model.

[0059] The classification loss weights can be used to adjust the detection accuracy of cable fault detection sub-models for different cable fault types. This can be understood as follows: one cable fault detection sub-model corresponds to one actual cable fault type, and the weight value of the actual cable fault type corresponding to the cable fault detection sub-model is higher in the classification loss weights. In other words, by differentially increasing the weight value of the actual cable fault type corresponding to the cable fault detection sub-model in the classification loss weights, the cable fault detection sub-model can achieve higher detection accuracy for that actual cable fault type. For example, the weight value of the actual cable fault type corresponding to the cable fault detection sub-model in the classification loss weights can be greater than 1; the weight value of other actual cable fault types can be 1. Optionally, the higher weight values ​​in the classification loss weights of different cable fault detection sub-models can be the same or different.

[0060] Specifically, a one-to-one correspondence can be established to determine the cable fault detection sub-model corresponding to each actual cable fault type. For a single cable fault detection sub-model, the weight value of the corresponding actual cable fault type can be determined to be higher than the weight values ​​of other actual cable fault types in the classification loss weight of the cable fault detection sub-model, thereby obtaining the classification loss weight of each cable fault detection sub-model.

[0061] S230. For a single cable fault detection sub-model, calculate the target connection weight matrix of the cable fault detection sub-model based on the cable operation samples, the classification loss weights of the cable fault detection sub-model, and the corresponding actual cable fault types.

[0062] The target connection weight matrix can be used to characterize the model parameters of the trained cable fault detection sub-model. It can also be used to tune the parameters of the cable fault detection sub-model to ensure its successful training.

[0063] Specifically, for a single cable fault detection sub-model, the following steps are taken: First, cable operation samples are obtained through the input layer. Second, the cable operation samples are feature-mapped through the feature layer to obtain the cable operation feature matrix. Third, the cable operation feature matrix is ​​non-linearly activated through the enhancement layer to obtain the cable operation enhancement matrix. Finally, the cable operation feature matrix and the cable operation enhancement matrix are concatenated to obtain the cable operation matrix. Finally, the target connection weight matrix of the cable fault detection sub-model is calculated using a loss function based on the cable operation matrix, the actual cable fault type, and the classification loss weights through the output layer.

[0064] For example, assume the cable fault detection sub-model is a width-learning model. The cable fault detection sub-model has n feature windows, each with C feature nodes, which can map cable operation data to n sets of random feature spaces, each containing C features. The feature windows can be used to extract features from the cable operation data.

[0065] The following formula can be used to calculate the cable operating characteristic matrix:

[0066]

[0067] In the formula, Z i Let be the feature matrix in the i-th random feature space; i is the number of the feature window; X is the feature mapping function; X is the cable running sample; and These represent the weights and biases of the randomly generated feature layers; after obtaining all Z... i ∈R N×M Then, all Z i Connect them to generate the cable operation feature matrix Z n This allows us to construct a feature space for cable operation data.

[0068] To further enhance the mapping capability of the cable fault detection sub-model and to further mine the deep feature information of cable operation data, the cable operation feature matrix Z can be... n Perform another nonlinear mapping to obtain the cable operation enhancement matrix. The cable operation enhancement matrix can be calculated using the following formula:

[0069]

[0070] In the formula, H g Z represents the enhancement matrix of the g-th group; g is the group number of the feature node in the enhancement layer; α represents the nonlinear activation function; Z n For cable operation characteristic matrix; and The weights and biases of the randomly generated enhancement layer are represented by m; m represents the total number of feature node groups in the enhancement layer; all H... g Connect them to generate the cable operation enhancement matrix H m .

[0071] The following formula can be used to connect the cable operation characteristic matrix and the cable operation enhancement matrix to calculate the cable operation matrix:

[0072]

[0073] In the formula, For cable operation matrix; Z n For cable operation characteristic matrix; H m Enhance the cable operation matrix.

[0074] Assuming the actual cable fault type corresponding to the cable fault detection sub-model D is Class I, then the classification loss weight of this cable fault detection sub-model is a. D＝ [f(β1X1:X2:X3:..:X M )]; where β is the enhancement weight with a value greater than 1; f is the reduction function set according to the greatest common divisor of different sample sizes.

[0075] The loss function of the cable fault detection sub-model D can be expressed by the following formula:

[0076]

[0077] In the formula, λ is the target connection weight matrix; λ is the penalty coefficient; f is the reduction function set according to the greatest common divisor of different sample sizes; β is the enhancement weight with a value greater than 1; For the cable operation matrix; (X1, X2, X3, ..., X...) M (Y1, Y2, Y3, ..., Y) represents the cable operation sample; M () represents the actual cable fault type corresponding to the cable operation sample.

[0078] The derivative of the loss function of the cable fault detection sub-model D can be calculated, and the derivative can be set to 0 to obtain the target connection weight matrix. Specifically, the target connection weight matrix can be calculated using the following formula:

[0079]

[0080] In the formula, λ is the target connection weight matrix; λ is the penalty coefficient; f is the reduction function set according to the greatest common divisor of different sample sizes; β is the enhancement weight with a value greater than 1; For the cable operation matrix; (X1, X2, X3, ..., X...) M (Y1, Y2, Y3, ..., Y) represents the cable operation sample; M ) represents the actual cable fault type corresponding to the cable operation sample; l represents the number of the actual cable fault type.

[0081] In an optional embodiment of the present invention, for a single cable fault detection sub-model, the target connection weight matrix of the cable fault detection sub-model is calculated based on the cable operation samples, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type. This includes: dividing the cable operation samples according to the sample ratio corresponding to each actual cable fault type in the cable operation samples and the number of cable fault detection sub-models to obtain the unit cable operation samples of each cable fault detection sub-model; and for a single cable fault detection sub-model, the target connection weight matrix of the cable fault detection sub-model is calculated based on the unit cable operation samples of the cable fault detection sub-model, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type.

[0082] The sample proportions corresponding to each actual cable fault type can be used to characterize the sample proportions of cable operation samples corresponding to different actual cable fault types. By using the sample proportions corresponding to each actual cable fault type to divide the cable operation samples, we can obtain the unit cable operation samples of each cable fault detection sub-model. This can be understood as dividing the cable operation samples in a proportional manner, which can avoid the problem of too many samples of a certain type of actual cable fault in different cable fault detection sub-models, thereby overcoming the imbalance of samples corresponding to different actual cable fault types in the cable operation samples.

[0083] Specifically, the cable operation samples can be divided proportionally into the number of cable fault detection sub-models according to the sample proportions corresponding to each actual cable fault type in the cable operation samples. Each cable operation sample is then defined as a unit cable operation sample for each cable fault detection sub-model. For a single cable fault detection sub-model, the unit cable operation sample can be obtained through the input layer of the cable fault detection sub-model. Through the feature layer of the cable fault detection sub-model, feature mapping is performed on the cable operation sample to obtain the cable operation feature matrix. Through the enhancement layer of the cable fault detection sub-model, nonlinear activation is applied to the cable operation feature matrix to obtain the cable operation enhancement matrix. The cable operation feature matrix and the cable operation enhancement matrix are then connected to obtain the cable operation matrix. Through the output layer of the cable fault detection sub-model, a loss function is used to calculate the target connection weight matrix of the cable fault detection sub-model based on the cable operation matrix, the actual cable fault type, and the classification loss weight.

[0084] For example, suppose the cable data sample is (X, Y), {(X, Y)|X∈R} N×A , Y∈R N×M}. Where N represents the total number of cable operation samples; A represents the feature dimension of the cable operation samples; M represents the number of categories of actual cable fault types; R represents a real number. The number of M is determined by the number of categories of actual cable fault types. Correspondingly, the cable fault detection model can consist of M cable fault detection sub-models. First, according to the inter-class ratio (i.e., sample ratio) of each actual cable fault type, the cable operation samples are divided into M equal parts. The resulting M unit cable operation samples are (X1, Y1), (X2, Y2), ..., (X... M Y M Each unit cable operation sample can be trained with a separate cable fault detection sub-model. Proportional division avoids the problem of an excessive number of samples in one class. Since the number of cable fault detection sub-models equals the number of actual cable fault types, each sub-model will be augmented with training on unit cable operation samples of the corresponding actual cable fault type. This augmentation training method makes the cable fault detection sub-model more sensitive to specific actual cable fault types, thus overcoming the class imbalance problem.

[0085] This scheme divides the cable operation samples proportionally according to the sample ratio of each actual cable fault type and the number of cable fault detection sub-models in the cable operation samples, obtaining unit cable operation samples for each cable fault detection sub-model. Based on the unit cable operation samples, the cable fault detection sub-model is trained. This can solve the problems of insufficient samples and imbalance of different categories of samples in the training process of cable fault detection models, improve the sample balance, and thus improve the detection accuracy of cable fault detection models.

[0086] S240. Adjust the parameters of each cable fault detection sub-model according to the target connection weight matrix of each cable fault detection sub-model.

[0087] Specifically, the connection weight matrix of each cable fault detection sub-model can be adjusted according to the target connection weight matrix of each sub-model, thereby completing the training of the cable fault detection model.

[0088] S250, Obtain cable operation data.

[0089] S260. Input the cable operation data into the pre-trained cable fault detection model to obtain the candidate cable fault types predicted by each cable fault detection sub-model.

[0090] The cable fault detection model includes at least one cable fault detection sub-model.

[0091] S270. Vote on each candidate cable fault type to determine the target cable fault type for the cable operation data.

[0092] The technical solution of this invention obtains cable operation samples and actual cable fault types, determines the cable fault detection sub-model corresponding to each actual cable fault type, and the classification loss weight of each cable fault detection sub-model. The weight value corresponding to the actual cable fault type is higher in the classification loss weight of the cable fault detection sub-model. For a single cable fault detection sub-model, based on the cable operation samples, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type, the target connection weight matrix of the cable fault detection sub-model is calculated. Based on the target connection weight matrix of each cable fault detection sub-model, the parameters of each cable fault detection sub-model are tuned. By pre-training cable fault detection sub-models with different classification loss weights, cable fault detection sub-models with different detection sensitivities to different actual cable fault types are obtained, improving the detection accuracy and efficiency of cable fault detection using cable fault detection models.

[0093] In an optional embodiment of the present invention, after voting on each candidate cable fault type to determine the target cable fault type of the cable operation data, the method further includes: periodically acquiring cable operation data and the corresponding actual cable fault type; for a single cable fault detection sub-model, performing feature mapping on the cable operation data through the newly added feature nodes of the feature layer of the cable fault detection sub-model to obtain a newly added cable operation feature matrix; for a single cable fault detection sub-model, performing nonlinear activation on the newly added cable operation feature matrix through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model to obtain a first newly added cable operation enhancement matrix; for a single cable fault detection sub-model, acquiring the original cable operation matrix through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model, and connecting the original cable operation matrix, the newly added cable operation feature matrix, and the first newly added cable operation enhancement matrix to obtain a first newly added cable operation matrix; for a single cable fault detection sub-model, updating the target connection weight matrix based on the first newly added cable operation matrix and the corresponding actual cable fault type through the output layer of the cable fault detection sub-model to obtain a first target connection weight matrix; and tuning the parameters of each cable fault detection sub-model according to each first target connection weight matrix.

[0094] Real-time cable monitoring generates a large amount of cable operation data. Regularly updating the cable fault detection model with newly added cable operation data can continuously improve the accuracy of cable fault monitoring. The update cycle of the cable fault detection model can be preset and adjusted. For example, the update cycle of the cable fault detection sub-model can be daily, weekly, monthly, or quarterly. The actual cable fault type corresponding to the cable operation data may or may not be the same as the target cable fault type corresponding to the cable operation data. It can be understood that the actual cable fault type corresponding to the cable operation data can be calibrated and corrected by technicians. New feature nodes can be used to perform feature mapping on the newly added cable operation data of the cable fault detection sub-model. New cable operation feature matrix can be used to characterize the feature extraction results of the newly added cable operation data. The first new enhancement node can be used to perform nonlinear activation on the new cable operation feature matrix of the cable fault detection sub-model. The first new cable operation enhancement matrix can be used to characterize the feature enhancement results of the newly added cable operation data based on the first new enhancement node. The first new cable operation matrix can be used to characterize the fusion result of the feature extraction results and feature enhancement results of the newly added cable operation data using the incremental method of feature nodes. The first target connection weight matrix can be the target connection weight matrix updated using the incremental method of feature nodes.

[0095] Specifically, after voting on each candidate cable fault type to determine the target cable fault type for the cable operation data, cable operation data and the pre-calibrated actual cable fault types corresponding to the cable operation data can be periodically acquired according to the pre-set update cycle of the cable fault detection sub-model. For a single cable fault detection sub-model, feature mapping of the cable operation data can be performed through the newly added feature nodes of the feature layer of the cable fault detection sub-model to obtain a new cable operation feature matrix. For a single cable fault detection sub-model, nonlinear activation is performed on the new cable operation feature matrix through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model to obtain a first new cable operation enhancement matrix. For a single cable fault detection sub-model, the original cable operation matrix is ​​obtained through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model, and the original cable operation matrix, the new cable operation feature matrix, and the first new cable operation enhancement matrix are connected to obtain a first new cable operation matrix. For a single cable fault detection sub-model, the loss function of the cable fault detection sub-model is used through the output layer of the cable fault detection sub-model to calculate the first target connection weight matrix based on the first newly added cable operation matrix and the corresponding actual cable fault type. Based on the updated first target connection weight matrices of each cable fault detection sub-model, the parameters of each cable fault detection sub-model are tuned, thereby completing the update of the cable fault detection model.

[0096] Referring to the example above, the following formula can be used to calculate the operating characteristic matrix of the newly added cable:

[0097]

[0098] In the formula, Z n+1 is the feature matrix in the (n+1)th random feature space, that is, the feature matrix in the random feature space corresponding to the newly added feature window, that is, the newly added cable operation feature matrix; n+1 is the number of the newly added feature window; X is the periodically acquired cable operation data; and These are the weights and biases generated for the newly added feature nodes, respectively.

[0099] The following formula can be used to calculate the first newly added cable operation enhancement matrix:

[0100]

[0101] In the formula, H j Z represents the enhancement matrix for the j-th group; j is the group number of the enhancement node; α represents the nonlinear activation function; Z n+1 This is the feature matrix in the (n+1)th random feature space, i.e., the newly added cable operation feature matrix; represents the weights and biases of the randomly generated enhancement layer; m represents the total number of feature nodes in the enhancement layer; where j can be multiple values.

[0102] The following formula can be used to calculate the first newly added cable operation matrix:

[0103]

[0104] In the formula, This is the first newly added cable operation matrix; For the original cable operation matrix; Z n+1 H is the feature matrix in the (n+1)th random feature space, i.e., the newly added cable operation feature matrix; j Let be the enhancement matrix of the j-th group; j is the group number of the feature node in the enhancement layer.

[0105] The updated first target connection weight matrix can be calculated using the following formula:

[0106]

[0107] In the formula, Connect the weight matrix to the updated first target; Y represents the first newly added cable operation matrix; Y represents the actual cable fault type corresponding to the first newly added cable operation matrix. The target is connected to the weight matrix; E1 is the first intermediate variable; K1 TIt is the second intermediate variable.

[0108] in,

[0109]

[0110] A n+1 =[|Z n+1 |H j ];

[0111]

[0112] In the formula, E1 is the first intermediate variable; This is the first newly added cable operation matrix; A n+1 This is a separate, newly generated cable operation matrix specifically for the newly added cable operation data; Z n+1 H is the feature matrix in the (n+1)th random feature space, that is, the feature matrix in the random feature space corresponding to the newly added feature window; j Let be the enhancement matrix of the j-th group; j is the group number of the feature node in the enhancement layer; F1 is the third intermediate variable; This is the original cable operation matrix; K1 T It is the second intermediate variable.

[0113] This solution adopts an incremental approach for feature nodes, which allows for incremental learning of each individual cable fault detection sub-model without having to train the model from scratch. Compared to traditional machine learning and deep learning models, which require retraining from scratch when remodeling, undoubtedly consuming a huge amount of hardware resources and placing a heavy burden on edge devices, this solution can significantly reduce the resource consumption of updating the cable fault detection model.

[0114] In an optional embodiment of the present invention, after voting on the cable fault types predicted by each cable fault detection sub-model to determine the target cable fault type of the cable operation data, the method further includes: periodically acquiring cable operation data and the corresponding actual cable fault types; for a single cable fault detection sub-model, performing feature mapping on the cable operation data through the feature nodes of the feature layer of the cable fault detection sub-model to obtain a cable operation feature matrix; for a single cable fault detection sub-model, performing nonlinear activation on the cable operation feature matrix through the second newly added enhancement node of the enhancement layer of the cable fault detection sub-model to obtain a second newly added cable operation enhancement matrix; for a single cable fault detection sub-model, obtaining the original cable operation matrix through the second newly added enhancement node of the enhancement layer of the cable fault detection sub-model, and connecting the original cable operation matrix and the second newly added cable operation enhancement matrix to obtain a second newly added cable operation matrix; for a single cable fault detection sub-model, updating the target connection weight matrix based on the second newly added cable operation matrix and the corresponding actual cable fault type through the output layer of the cable fault detection sub-model to obtain a second target connection weight matrix; and tuning the parameters of each cable fault detection sub-model according to each second target connection weight matrix.

[0115] The second newly added enhancement node can also be used to perform nonlinear activation on the newly added cable operation feature matrix of the cable fault detection sub-model. In comparison, both the first and second newly added enhancement nodes are new enhancement nodes for the cable fault detection sub-model. The difference lies in that the first newly added enhancement node corresponds to the incremental approach of feature nodes and is used in combination with new feature nodes; the second newly added enhancement node corresponds to the enhancement approach of enhancement nodes, requiring no additional feature nodes and can be used independently. The second newly added cable operation enhancement matrix can be used to characterize the feature enhancement result of the newly added cable operation data based on the second newly added enhancement node. The second newly added cable operation matrix can also be used to characterize the fusion result of the feature extraction and feature enhancement results of the newly added cable operation data using the incremental approach of enhancement nodes. The second target connection weight matrix can be the target connection weight matrix updated using the incremental approach of feature nodes.

[0116] Specifically, after voting on the cable fault types predicted by each cable fault detection sub-model to determine the target cable fault type for the cable operation data, cable operation data and the pre-calibrated actual cable fault types corresponding to the cable operation data can be periodically acquired according to the pre-set update cycle of the cable fault detection sub-model. For a single cable fault detection sub-model, feature mapping is performed on the cable operation data through the feature nodes of the feature layer of the cable fault detection sub-model to obtain the cable operation feature matrix. For a single cable fault detection sub-model, nonlinear activation is performed on the cable operation feature matrix through the second newly added enhancement node of the enhancement layer of the cable fault detection sub-model to obtain the second newly added cable operation enhancement matrix. For a single cable fault detection sub-model, the original cable operation matrix is ​​obtained through the second newly added enhancement node of the enhancement layer of the cable fault detection sub-model, and the original cable operation matrix and the second newly added cable operation enhancement matrix are connected to obtain the second newly added cable operation matrix. For a single cable fault detection sub-model, the updated second target connection weight matrix is ​​calculated through the output layer of the cable fault detection sub-model using the loss function of the cable fault detection sub-model, based on the second newly added cable operation matrix and the corresponding actual cable fault type. Based on the updated connection weight matrices of each second objective, the parameters of each cable fault detection sub-model are adjusted, thereby completing the update of the cable fault detection model.

[0117] Referring to the example above, the second additional cable operation enhancement matrix can be calculated using the following formula:

[0118]

[0119] In the formula, H m+1 This is the (m+1)th enhancement matrix, i.e., the second newly added cable operation enhancement matrix; m+1 is the group number of the newly added enhancement node; α represents the nonlinear activation function; Z n For cable operation characteristic matrix; and This represents the weights and biases of the enhancement layer randomly generated for the newly added enhancement nodes.

[0120] The second newly added cable operation matrix can be calculated using the following formula:

[0121]

[0122] In the formula, This is the second newly added cable operation matrix; For cable operation matrix; H n+1 This is the (m+1)th enhancement matrix, which is the second newly added cable operation enhancement matrix; m+1 is the group number of the newly added enhancement node.

[0123] The updated second-target connection weight matrix can be calculated using the following formula:

[0124]

[0125] In the formula, Connect the weight matrix to the updated second objective; Y represents the second newly added cable operation matrix; Y represents the actual cable fault type corresponding to the first newly added cable operation matrix. The target is connected to the weight matrix; E2 is the fourth intermediate variable; K2 T It is the fifth intermediate variable.

[0126] in,

[0127]

[0128]

[0129] In the formula, E2 is the fourth intermediate variable; For the original cable operation matrix; H m+1 This is the (m+1)th enhancement matrix, i.e., the second newly added cable operation enhancement matrix; m+1 is the group number of the newly added enhancement node; F2 is the sixth intermediate variable; K2 T It is the fifth intermediate variable.

[0130] This solution adopts an incremental approach to enhance nodes, which allows for incremental learning of each individual cable fault detection sub-model without having to train the model from scratch. Compared to traditional machine learning and deep learning models, which require retraining from scratch when remodeling, undoubtedly consuming a huge amount of hardware resources and placing a heavy burden on edge devices, this solution can significantly reduce the resource consumption of updating the cable fault detection model.

[0131] With the rapid development of artificial intelligence technology, cable fault identification is gradually evolving towards automatic diagnosis. By constructing cable fault detection models, automatic identification of cable faults can be achieved, effectively detecting cable faults and reducing labor costs. An intelligent cable operation monitoring system can include a data acquisition cluster, a fault analysis server, and a data storage device. Both the data acquisition cluster and the data storage device can be connected to the fault analysis server. By installing the data acquisition cluster at different locations on the intelligent cable, various normal and fault data, as well as cable fault types, are collected and stored as cable operation samples. The fault analysis server then monitors and identifies the fault results.

[0132] Figure 3 This is a flowchart of a cable fault detection method. Based on the above embodiments, Figure 3This is a preferred embodiment of the present invention. See also: Figure 3 The cable fault detection method shown includes:

[0133] Assume the cable data sample is (X, Y), {(X, Y)|X∈R} N×A , Y∈R N×M}. Where N represents the total number of cable operation samples; A represents the feature dimension of the cable operation samples; M represents the number of categories of actual cable fault types; R represents a real number. The number of M is determined by the number of categories of actual cable fault types. Correspondingly, the cable fault detection model can consist of M cable fault detection sub-models. First, according to the inter-class ratio (i.e., sample ratio) of each actual cable fault type, the cable operation samples are divided into M equal parts. The resulting M unit cable operation samples are (X1, Y1), (X2, Y2), ..., (X... M Y M Each unit cable operation sample can be trained with a separate cable fault detection sub-model. Proportional division avoids the problem of an excessive number of samples in one class. Since the number of cable fault detection sub-models equals the number of actual cable fault types, each sub-model will be augmented with training on unit cable operation samples of the corresponding actual cable fault type. This augmentation training method makes the cable fault detection sub-model more sensitive to specific actual cable fault types, thus overcoming the class imbalance problem. Figure 4 This is a schematic diagram of the structure of a cable fault detection model. Figure 4 As shown, each cable fault detection sub-model can include an input layer, a feature layer, an enhancement layer, and an output layer. The cable fault detection sub-model has n feature windows, each with C feature nodes, which can map cable operation data to n sets of random feature spaces, each containing C features. The feature windows can be used to extract features from the cable operation data.

[0134] For a single cable fault detection sub-model, feature extraction can be performed on cable operation samples through the feature layer of the cable fault detection sub-model to obtain the cable operation feature matrix:

[0135]

[0136] In the formula, Z i Let be the feature matrix in the i-th random feature space; i is the number of the feature window; X is the feature mapping function; X is the cable running sample; and These represent the weights and biases of a randomly generated feature layer; Z is obtained... n ∈R N×M Then, all Zi Connect them to generate the cable operation feature matrix Z n This allows us to construct a feature space for cable operation data.

[0137] To further enhance the mapping capability of the cable fault detection sub-model and to further mine the deep feature information of cable operation data, the cable operation feature matrix Z can be... n Perform another nonlinear mapping to obtain the cable operation enhancement matrix. The cable operation enhancement matrix can be calculated using the following formula:

[0138]

[0139] In the formula, H g Z represents the enhancement matrix of the g-th group; g is the group number of the feature node in the enhancement layer; α represents the nonlinear activation function; Z n For cable operation characteristic matrix; and The weights and biases of the randomly generated enhancement layer are represented by m; m represents the total number of feature node groups in the enhancement layer; all H... g Connect them to generate the cable operation enhancement matrix H m .

[0140] Finally, the cable of the feature layer can be run using the feature matrix Z. n and the cable running reinforcement matrix H of the reinforcement layer m Connect them in sequence to obtain the cable operation matrix.

[0141]

[0142] In the formula, For cable operation matrix; Z n For cable operation characteristic matrix; H m Enhance the cable operation matrix.

[0143] For a single cable fault detection sub-model D, the cable operation sample (X) D Y D The data is classified according to the actual cable fault type, and the resulting data matrix is ​​X. D = [X1, X2, ..., X M ] and Y D = [Y1, Y2, ..., Y] M The sample proportions corresponding to different actual cable fault types are a. D =[X1:X2:X3:..:X MThe weights of the cable fault detection sub-model D can be enhanced to improve its training ability for samples of the actual cable fault type. Assuming the actual cable fault type corresponding to the cable fault detection sub-model D is the first type, then the classification loss weight of this sub-model is a. D =[f(β1X1:X2:X3:..:X M ]; where β1 is the enhancement weight with a value greater than 1; f is the reduction function set according to the greatest common divisor of different sample sizes. Figure 3 As shown, the enhancement weights of the cable fault detection sub-model corresponding to different actual cable fault types can be [β1, β2, ..., β...]. M ].

[0144] The loss function of the cable fault detection sub-model D can be expressed by the following formula:

[0145]

[0146] In the formula, λ is the target connection weight matrix; f is the penalty coefficient; f is the reduction function set according to the greatest common divisor of different sample sizes; β1 is the enhancement weight with a value greater than 1; For the cable operation matrix; (X1, X2, X3, ..., X... M (Y1, Y2, Y3, ..., Y) represents the cable operation sample; M () represents the actual cable fault type corresponding to the cable operation sample.

[0147] The derivative of the loss function of the cable fault detection sub-model D can be calculated, and the derivative can be set to 0 to obtain the target connection weight matrix. The target connection weight matrix can be calculated using the following formula:

[0148]

[0149] In the formula, λ is the target connection weight matrix; λ is the penalty coefficient; f is the reduction function set according to the greatest common divisor of different sample sizes; β is the enhancement weight with a value greater than 1; For the cable operation matrix; (X1, X2, X3, ..., X... M (Y1, Y2, Y3, ..., Y) represents the cable operation sample; M ) represents the actual cable fault type corresponding to the cable operation sample; l represents the number of the actual cable fault type.

[0150] Real-time cable monitoring generates a large amount of cable operation data. Regularly updating the cable fault detection model with newly added cable operation data can continuously improve the accuracy of cable fault monitoring. Traditional machine learning and deep learning models require retraining from scratch when remodeling, which undoubtedly consumes a huge amount of hardware resources and places a heavy burden on edge devices. This solution can perform incremental learning for each individual subsystem, eliminating the need to retrain the model from scratch and significantly reducing training resource consumption. Optionally, two methods can be used for incremental training of the cable fault detection sub-model: incremental training of feature nodes and incremental training of enhancement nodes.

[0151] First, regarding the incremental approach for feature nodes, assuming a new (n+1)th set of feature nodes is added to the cable fault detection sub-model, the additional newly added feature node Z... n+1 An additional newly added enhanced node H will be generated separately. j This leads to the generation of the first newly added cable operation matrix. Without affecting the already trained model.

[0152] The following formula can be used to calculate the operating characteristic matrix of newly added cables:

[0153]

[0154] In the formula, Z n+1 is the feature matrix in the (n+1)th random feature space, that is, the feature matrix in the random feature space corresponding to the newly added feature window; n+1 is the number of the newly added feature window; X is the periodically acquired cable operation data; and These are the weights and biases generated for the newly added feature nodes, respectively.

[0155] The following formula can be used to calculate the first newly added cable operation enhancement matrix:

[0156]

[0157] In the formula, H j Z represents the enhancement matrix for the j-th group; j is the group number of the enhancement node; α represents the nonlinear activation function; Z n+1 It is the feature matrix in the (n+1)th random feature space, that is, the feature matrix in the random feature space corresponding to the newly added feature window; represents the weights and biases of the randomly generated enhancement layer; m represents the total number of feature nodes in the enhancement layer; where j can be multiple values.

[0158] The following formula can be used to calculate the first newly added cable operation matrix:

[0159]

[0160] In the formula, This is the first newly added cable operation matrix; For the original cable operation matrix; Z n+1 H is the feature matrix in the (n+1)th random feature space, that is, the feature matrix in the random feature space corresponding to the newly added feature window; j Let be the enhancement matrix of the j-th group; j is the group number of the feature node in the enhancement layer.

[0161] The updated first target connection weight matrix can be calculated using the following formula:

[0162]

[0163] In the formula, Connect the weight matrix to the updated first target; Y represents the first newly added cable operation matrix; Y represents the actual cable fault type corresponding to the first newly added cable operation matrix. The target is connected to the weight matrix; E1 is the first intermediate variable; K1 T It is the second intermediate variable.

[0164] in,

[0165]

[0166] A n+1 =[|Z n+1 |H j ];

[0167]

[0168] In the formula, E1 is the first intermediate variable; This is the first newly added cable operation matrix; A n+1 This is a separate, newly generated cable operation matrix specifically for the newly added cable operation data; Z n+1 H is the feature matrix in the (n+1)th random feature space, that is, the feature matrix in the random feature space corresponding to the newly added feature window; j Let be the enhancement matrix of the j-th group; j is the group number of the feature node in the enhancement layer; F1 is the third intermediate variable; This is the original cable operation matrix; K1 T It is the second intermediate variable.

[0169] Secondly, regarding the incremental approach to enhancing nodes, assuming a new (m+1)th group of enhancing nodes is added to the cable fault detection sub-model, the additional newly added enhancing node H... m+1 The second newly added cable operation matrix will be generated for the cable fault detection sub-model. Without affecting the already trained model.

[0170] The second additional cable operation enhancement matrix can be calculated using the following formula:

[0171]

[0172] In the formula, H m+1 This is the (m+1)th enhancement matrix, i.e., the second newly added cable operation enhancement matrix; m+1 is the group number of the newly added enhancement node; α represents the nonlinear activation function; Z n For cable operation characteristic matrix; and This represents the weights and biases of the enhancement layer randomly generated for the newly added enhancement nodes.

[0173] The second newly added cable operation matrix can be calculated using the following formula:

[0174]

[0175] In the formula, This is the second newly added cable operation matrix; For cable operation matrix; H m+1 This is the (m+1)th enhancement matrix, which is the second newly added cable operation enhancement matrix; m+1 is the group number of the newly added enhancement node.

[0176] The updated second-target connection weight matrix can be calculated using the following formula:

[0177]

[0178] In the formula, Connect the weight matrix to the updated second objective; Y represents the second newly added cable operation matrix; Y represents the actual cable fault type corresponding to the first newly added cable operation matrix. The target is connected to the weight matrix; E2 is the fourth intermediate variable; K2 T It is the fifth intermediate variable.

[0179] in,

[0180]

[0181] In the formula, E2 is the fourth intermediate variable; For the original cable operation matrix; H m+1 This is the (m+1)th enhancement matrix, i.e., the second newly added cable operation enhancement matrix; m+1 is the group number of the newly added enhancement node; F2 is the sixth intermediate variable; K2 T It is the fifth intermediate variable.

[0182] Currently, intelligent cable diagnosis is generally achieved by building automatic identification models. Traditional machine learning methods such as support vector machines, backpropagation neural networks, or random forests have been widely used in the field of intelligent diagnosis. With the rapid development of deep learning technology, advanced models such as convolutional neural networks, recurrent neural networks, generative adversarial networks, autoencoders, and long short-term memory networks have been gradually introduced into the field of intelligent diagnosis to further improve the accuracy and efficiency of diagnosis. However, traditional machine learning algorithms often require complex feature extraction and screening of the raw cable data. The fault identification rate largely depends on the selected features, which not only requires certain expert knowledge and increases labor costs but may also affect the diagnostic effect. In contrast, deep learning methods usually adopt an end-to-end classification model, which can achieve automatic diagnosis without feature extraction. However, deep learning algorithms have high requirements for hardware resources, long model training time, and require a lot of computing power when the model is deployed in cable edge devices. In addition, during the construction of cable intelligent diagnosis models, the number of normal data samples is usually much greater than that of abnormal samples. Overcoming the class imbalance problem has become one of the key challenges to improving diagnostic efficiency.

[0183] This solution not only effectively overcomes the data imbalance problem but also significantly reduces reliance on hardware resources while maintaining diagnostic accuracy, achieving more efficient and precise cable fault detection. The cable fault detection model in this solution can be quickly updated without retraining, reducing resource consumption and achieving higher cost-effectiveness. It enables the power grid to be more adaptive and responsive, allowing for real-time adjustments to predictions and decisions, thereby improving the reliability and efficiency of power grid operation. As the scale and complexity of the power grid continue to expand, traditional model training methods are struggling to handle the demands of processing massive amounts of data. The incremental algorithm in this solution will continue to leverage its advantages, driving the power grid towards greater intelligence and automation.

[0184] Example 3

[0185] Figure 5 This is a schematic diagram of a cable fault detection device provided in Embodiment 3 of the present invention. This embodiment of the invention is applicable to the detection of cable faults in power distribution networks. The device can execute cable fault detection methods and can be implemented in hardware and / or software. The device can be configured in electronic equipment carrying cable fault detection functions, such as a fault analysis server.

[0186] See Figure 5The cable fault detection device shown includes: a cable operation data acquisition module 510, a cable fault type prediction model 520, and a cable fault type voting module 530. The cable operation data acquisition module 510 is used to acquire cable operation data. The cable fault type prediction model 520 is used to input the cable operation data into a pre-trained cable fault detection model to obtain candidate cable fault types predicted by each cable fault detection sub-model. The cable fault detection model includes at least one cable fault detection sub-model. The cable fault type voting module 530 is used to vote on each of the candidate cable fault types to determine the target cable fault type based on the cable operation data.

[0187] The technical solution of this invention realizes automatic detection of cable faults by pre-training each cable fault detection sub-model in the cable fault detection model to detect cable operation data in real time, thereby reducing the operation and maintenance cost of cable fault detection and improving the detection efficiency of cable fault detection. By voting on each candidate cable fault type to determine the target cable fault type, the accuracy of cable fault detection can be further improved.

[0188] In an optional embodiment of the present invention, the apparatus further includes: a cable operation sample acquisition module, configured to acquire cable operation samples and actual cable fault types before acquiring cable operation data; a classification loss weight determination module, configured to determine the cable fault detection sub-model corresponding to each actual cable fault type and the classification loss weight of each cable fault detection sub-model; wherein the weight value of the actual cable fault type is higher in the classification loss weight of the cable fault detection sub-model; a target connection weight matrix calculation module, configured to calculate the target connection weight matrix of the cable fault detection sub-model for a single cable fault detection sub-model based on the cable operation samples, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type; and a cable fault detection sub-model training module, configured to tune the parameters of each cable fault detection sub-model according to the target connection weight matrix of each cable fault detection sub-model.

[0189] In an optional embodiment of the present invention, the device further includes: a first periodic data acquisition module, configured to periodically acquire cable operation data and corresponding actual cable fault types after voting on each of the candidate cable fault types to determine the target cable fault type of the cable operation data; for a single cable fault detection sub-model, perform feature mapping on the cable operation data through feature nodes of the feature layer of the cable fault detection sub-model to obtain a cable operation feature matrix; a new cable operation feature matrix generation module, configured to perform feature mapping on the cable operation data through newly added feature nodes of the feature layer of the cable fault detection sub-model to obtain a new cable operation feature matrix; and a first new cable operation enhancement matrix generation module, configured to perform feature mapping on the cable operation data through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model for a single cable fault detection sub-model. A first newly added cable operation enhancement matrix is ​​obtained by performing nonlinear activation on the cable operation feature matrix. A first newly added cable operation matrix generation module is used to obtain the original cable operation matrix for a single cable fault detection sub-model through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model, and connect the original cable operation matrix, the newly added cable operation feature matrix, and the first newly added cable operation enhancement matrix to obtain the first newly added cable operation matrix. A first target connection weight matrix update module is used to update the target connection weight matrix for a single cable fault detection sub-model based on the first newly added cable operation matrix and the corresponding actual cable fault type through the output layer of the cable fault detection sub-model to obtain the first target connection weight matrix. A first cable fault detection sub-model update module is used to tune the parameters of each cable fault detection sub-model according to each of the first target connection weight matrices.

[0190] In an optional embodiment of the present invention, the device further includes: a second periodic data acquisition module, configured to periodically acquire cable operation data and corresponding actual cable fault types after voting on the cable fault types predicted by each of the cable fault detection sub-models to determine the target cable fault type of the cable operation data; a cable operation feature matrix generation module, configured to perform feature mapping on the cable operation data through feature nodes of the feature layer of the cable fault detection sub-model for a single cable fault detection sub-model to obtain a cable operation feature matrix; and a second newly added cable operation enhancement matrix generation module, configured to perform nonlinear activation on the cable operation data through the second newly added enhancement nodes of the enhancement layer of the cable fault detection sub-model for a single cable fault detection sub-model to obtain a second newly added cable operation feature matrix. The system includes: an enhancement matrix; a second newly added cable operation matrix generation module, used for obtaining the original cable operation matrix through the second newly added enhancement node of the enhancement layer of the cable fault detection sub-model for a single cable fault detection sub-model, and connecting the original cable operation matrix and the second newly added cable operation enhancement matrix to obtain the second newly added cable operation matrix; a second target connection weight matrix update module, used for updating the target connection weight matrix based on the second newly added cable operation matrix and the corresponding actual cable fault type through the output layer of the cable fault detection sub-model for a single cable fault detection sub-model, to obtain the second target connection weight matrix; and a second cable fault detection sub-model update module, used for parameter tuning of each cable fault detection sub-model according to each of the second target connection weight matrices.

[0191] In an optional embodiment of the present invention, the target connection weight matrix calculation module includes: a cable operation sample partitioning unit, used to partition the cable operation samples according to the sample ratio corresponding to each actual cable fault type in the cable operation samples and the number of cable fault detection sub-models, to obtain unit cable operation samples of each cable fault detection sub-model; and a target connection weight matrix calculation unit, used to calculate the target connection weight matrix of a cable fault detection sub-model for a single cable fault detection sub-model based on the unit cable operation samples of the cable fault detection sub-model, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type.

[0192] In an optional embodiment of the present invention, the cable operating data includes cable current, cable temperature, and cable load.

[0193] The cable fault detection device provided in this embodiment of the invention can execute the cable fault detection method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0194] In the technical solutions of this invention, the acquisition, storage, and application of cable operation data, cable operation samples, and actual cable fault types all comply with relevant laws and regulations and do not violate public order and good morals.

[0195] Example 4

[0196] Figure 6 A schematic diagram of an electronic device 600 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0197] like Figure 6 As shown, the electronic device 600 includes at least one processor 601 and a memory, such as a read-only memory (ROM) 602 or a random access memory (RAM) 603, communicatively connected to the at least one processor 601. The memory stores computer programs executable by the at least one processor. The processor 601 can perform various appropriate actions and processes based on the computer program stored in the ROM 602 or loaded into the RAM 603 from storage unit 608. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0198] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of displays, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0199] Processor 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 601 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 suitable processor, controller, microcontroller, etc. Processor 601 performs the various methods and processes described above, such as cable fault detection methods.

[0200] In some embodiments, the cable fault detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by processor 601, one or more steps of the cable fault detection method described above may be performed. Alternatively, in other embodiments, processor 601 may be configured to perform the cable fault detection method by any other suitable means (e.g., by means of firmware).

[0201] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0202] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0203] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0204] To provide interaction with a user, the systems and techniques described herein 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 pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; 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 sound input, voice input, or tactile input).

[0205] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0206] A computing system can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system. It addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability.

[0207] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0208] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A cable fault detection method, characterized in that, The method includes: Obtain cable operation samples and actual cable fault types; Determine the cable fault detection sub-model corresponding to each actual cable fault type and the classification loss weight of each cable fault detection sub-model; wherein, the weight value of the actual cable fault type is higher in the classification loss weight of the cable fault detection sub-model. For a single cable fault detection sub-model, the target connection weight matrix of the cable fault detection sub-model is calculated based on the cable operation sample, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type. Based on the target connection weight matrix of each cable fault detection sub-model, the parameters of each cable fault detection sub-model are adjusted. Obtain cable operation data; The cable operation data is input into a pre-trained cable fault detection model to obtain the candidate cable fault types predicted by each cable fault detection sub-model; wherein, the cable fault detection model includes at least one cable fault detection sub-model. A vote is taken on each of the candidate cable fault types to determine the target cable fault type based on the cable operation data.

2. The method according to claim 1, characterized in that, After voting on each of the candidate cable fault types to determine the target cable fault type from the cable operating data, the method further includes: Periodically acquire cable operation data and corresponding actual cable fault types; For a single cable fault detection sub-model, the cable operation data is feature-mapped using the newly added feature nodes of the feature layer of the cable fault detection sub-model to obtain a new cable operation feature matrix; For a single cable fault detection sub-model, the newly added cable operation feature matrix is ​​nonlinearly activated through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model to obtain the first newly added cable operation enhancement matrix; For a single cable fault detection sub-model, the original cable operation matrix is ​​obtained through the first newly added enhancement node of the enhancement layer of the cable fault detection sub-model, and the original cable operation matrix, the newly added cable operation feature matrix, and the first newly added cable operation enhancement matrix are connected to obtain the first newly added cable operation matrix. For a single cable fault detection sub-model, the target connection weight matrix is ​​updated through the output layer of the cable fault detection sub-model based on the first newly added cable operation matrix and the corresponding actual cable fault type, to obtain the first target connection weight matrix. Based on the first target connection weight matrix, the parameters of each cable fault detection sub-model are adjusted.

3. The method according to claim 1, characterized in that, After voting on the cable fault types predicted by each of the cable fault detection sub-models to determine the target cable fault type from the cable operation data, the method further includes: Periodically acquire cable operation data and corresponding actual cable fault types; For a single cable fault detection sub-model, feature mapping is performed on the cable operation data through the feature nodes of the feature layer of the cable fault detection sub-model to obtain the cable operation feature matrix; For a single cable fault detection sub-model, the cable operation data is nonlinearly activated through the second newly added enhancement node of the enhancement layer of the cable fault detection sub-model to obtain the second newly added cable operation enhancement matrix; For a single cable fault detection sub-model, the original cable operation matrix is ​​obtained through the second newly added enhancement node of the enhancement layer of the cable fault detection sub-model, and the original cable operation matrix and the second newly added cable operation enhancement matrix are connected to obtain the second newly added cable operation matrix. For a single cable fault detection sub-model, the target connection weight matrix is ​​updated through the output layer of the cable fault detection sub-model based on the second newly added cable operation matrix and the corresponding actual cable fault type, to obtain the second target connection weight matrix; Based on the second target connection weight matrix, the parameters of each cable fault detection sub-model are adjusted.

4. The method according to claim 1, characterized in that, For a single cable fault detection sub-model, based on the cable operation samples, the classification loss weights of the cable fault detection sub-model, and the corresponding actual cable fault type, the target connection weight matrix of the cable fault detection sub-model is calculated, including: Based on the sample proportions corresponding to each actual cable fault type in the cable operation sample and the number of cable fault detection sub-models, the cable operation sample is divided to obtain unit cable operation samples of each cable fault detection sub-model. For a single cable fault detection sub-model, the target connection weight matrix of the cable fault detection sub-model is calculated based on the unit cable operation samples of the cable fault detection sub-model, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type.

5. The method according to claim 1, characterized in that, The cable operating data includes cable current, cable temperature, and cable load.

6. A cable fault detection device, characterized in that, The device includes: The cable operation sample acquisition module is used to acquire cable operation samples and actual cable fault types; The classification loss weight determination module is used to determine the cable fault detection sub-model corresponding to each actual cable fault type and the classification loss weight of each cable fault detection sub-model; wherein, the weight value of the actual cable fault type is higher in the classification loss weight of the cable fault detection sub-model. The target connection weight matrix calculation module is used to calculate the target connection weight matrix of the cable fault detection sub-model for a single cable fault detection sub-model, based on the cable operation sample, the classification loss weight of the cable fault detection sub-model, and the corresponding actual cable fault type. The cable fault detection sub-model training module is used to tune the parameters of each cable fault detection sub-model according to the target connection weight matrix of each sub-model. The cable operation data acquisition module is used to acquire cable operation data; A cable fault type prediction model is used to input the cable operation data into a pre-trained cable fault detection model to obtain the candidate cable fault types predicted by each cable fault detection sub-model; wherein, the cable fault detection model includes at least one cable fault detection sub-model. The cable fault type voting module is used to vote on each of the candidate cable fault types to determine the target cable fault type of the cable operation data.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the cable fault detection method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the cable fault detection method according to any one of claims 1-5.

9. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the cable fault detection method according to any one of claims 1-5.

Images