High-voltage transmission line fault identification method and device based on wavelet packet energy ratio, electronic equipment, storage medium and computer program

Abstract

The invention relates to the technical field of high-voltage transmission line fault identification, in particular to a high-voltage transmission line fault identification method and device based on a wavelet packet energy ratio, electronic equipment, a storage medium and a computer program. Extracting a plurality of wavelet energy ratios to form a feature vector; and inputting the feature vector into a fault recognition model to obtain a fault recognition result. According to the method, the reverse traveling wave currents at the two ends of the to-be-recognized same-pole double-circuit line are obtained and decomposed through wavelet analysis, so that local features in the reverse traveling wave currents are captured, multiple wavelet energy ratios are extracted to form feature vectors, fault positions in multiple directions are positioned in combination with a fault recognition model, and the fault recognition accuracy is improved. Therefore, the fault identification method can be effectively suitable for the scene of the same-pole double-circuit high-voltage transmission line with complex structure and many reasons for fault occurrence.

Description

Technical Field

[0001] The present invention relates to the technical field of high-voltage transmission line fault identification, and is a high-voltage transmission line fault identification method, device, electronic equipment, storage medium and computer program based on wavelet packet energy ratio. Background Art

[0002] High-voltage transmission lines play an important role in the power system. The lines are responsible for transmitting electric energy from power stations to various power consumption areas. During the transmission process, due to various reasons such as equipment aging and human interference, the frequency of high-voltage transmission line failures is relatively high. These failures will not only affect the normal dispatching of electricity, but also affect the service life of the equipment and the personal safety of the staff.

[0003] At present, traditional fault identification methods for high-voltage transmission lines include single-item identification and series compensation identification. However, the structure of double-circuit high-voltage transmission lines on the same pole is complex and there are many reasons for the occurrence of faults. Traditional fault identification methods cannot effectively identify various types of faults in double-circuit high-voltage transmission lines on the same pole. Summary of the invention

[0004] The present invention provides a method, which overcomes the above-mentioned deficiencies of the prior art and can effectively solve the problem that the traditional fault identification method cannot effectively identify the fault of the double-circuit high-voltage transmission line on the same pole.

[0005] One of the technical solutions of the present invention is achieved by the following measures: a high-voltage transmission line fault identification method based on wavelet packet energy ratio, comprising: Obtain the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, perform wavelet decomposition on it, and extract multiple wavelet energy ratios to form a feature vector; The feature vector is input into a fault identification model to obtain a fault identification result, wherein the fault identification model is obtained by machine learning using a number of fault samples, wherein each fault sample includes a feature vector and a label of the fault type.

[0006] The following are further optimizations and / or improvements to the above technical solutions: The above-mentioned obtaining of the reverse traveling wave current at both ends of the double-circuit line to be identified on the same pole includes: Obtain the traveling wave voltage and current data at both ends of the double-circuit line on the same pole; Decoupling the traveling wave voltage and current data using phase mode transformation; The same modulus is selected to calculate the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified.

[0007] The above-mentioned reverse traveling wave current is subjected to wavelet decomposition, and multiple wavelet energy ratios are extracted to form a characteristic vector, including: Perform six-layer wavelet decomposition on the reverse traveling wave current to obtain six-layer wavelet components; Based on the six-layer wavelet components, six wavelet energy ratios are obtained, and the six wavelet energy ratios are combined into a feature vector.

[0008] The construction of the above fault identification model includes: Obtain a number of fault samples with different fault types and different fault initial angles, wherein each fault sample includes a feature vector and a label of the fault type; The fault samples are expanded using the SMOTE algorithm to obtain a fault sample set, which is then divided into a training sample set and a test sample set according to the ratio. Combined with the training stop condition, the support vector machine algorithm is trained using the training sample set to obtain a fault recognition model; The fault recognition model is tested using a test sample set. If the test requirements are met, the final fault recognition model is output; if the test requirements are not met, the support vector machine algorithm parameters are adjusted and retrained.

[0009] The second technical solution of the present invention is achieved by the following measures: a high-voltage transmission line fault identification device based on wavelet packet energy ratio, comprising: The feature extraction unit obtains the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, performs wavelet decomposition on the reverse traveling wave current, and extracts multiple wavelet energy ratios to form a feature vector; The fault identification unit inputs the feature vector into the fault identification model to obtain a fault identification result, wherein the fault identification model is obtained by machine learning using a number of fault samples, wherein each fault sample includes a feature vector and a label of the fault type.

[0010] The following are further optimizations and / or improvements to the above technical solutions: The feature extraction unit comprises: The first extraction module obtains the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, including: Obtain the traveling wave voltage and current data at both ends of the double-circuit line on the same pole; Decoupling the traveling wave voltage and current data using phase mode transformation; Select the same modulus to calculate the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified; The second extraction module performs wavelet decomposition on the reverse wave current and extracts multiple wavelet energy ratios to form a feature vector, including: Perform six-layer wavelet decomposition on the reverse traveling wave current to obtain six-layer wavelet components; Based on the six-layer wavelet components, six wavelet energy ratios are obtained, and the six wavelet energy ratios are combined into a feature vector.

[0011] The above-mentioned fault identification unit comprises: Training module, building fault identification model, including: Obtain a number of fault samples with different fault types and different fault initial angles, wherein each fault sample includes a feature vector and a label of the fault type; The fault samples are expanded using the SMOTE algorithm to obtain a fault sample set, which is then divided into a training sample set and a test sample set according to the ratio. Combined with the training stop condition, the support vector machine algorithm is trained using the training sample set to obtain a fault recognition model; The fault identification model is tested using the test sample set. If the test requirements are met, the final fault identification model is output. If not, the support vector machine algorithm parameters are adjusted and retrained. The recognition module inputs the feature vector into the fault recognition model to obtain the fault recognition result.

[0012] The third technical solution of the present invention is achieved through the following measures: an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the steps in the high-voltage transmission line fault identification method based on wavelet packet energy ratio.

[0013] The fourth technical solution of the present invention is achieved through the following measures: a storage medium, on which a computer program that can be read by a computer is stored, and the computer program is configured to execute the steps in the high-voltage transmission line fault identification method based on wavelet packet energy ratio when running.

[0014] The fifth technical solution of the present invention is achieved through the following measures: a computer program product, including a computer program or instructions, characterized in that when the computer program or instructions are executed by a processor, the steps in the high-voltage transmission line fault identification method based on wavelet packet energy ratio are implemented.

[0015] The present invention obtains the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, decomposes it using wavelet analysis, thereby capturing local features in the reverse traveling wave current, extracting multiple wavelet energy ratios to form a feature vector, and locating the fault position in multiple directions in combination with a fault identification model, thereby obtaining a more accurate fault identification result. Therefore, the present invention can be effectively applied to scenarios such as double-circuit high-voltage transmission lines on the same pole with complex structures and many causes of faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Attached Figure 1 A schematic diagram of an implementation environment provided for an embodiment of the present invention.

[0017] Attached Figure 2A schematic diagram of a fault identification method flow chart provided by an embodiment of the present invention.

[0018] Attached Figure 3 A diagram showing a double-circuit line model on the same pole provided by an embodiment of the present invention.

[0019] Attached Figure 4 A diagram showing traveling wave transmission in a fault area provided by one embodiment of the present invention.

[0020] Attached Figure 5 A diagram showing traveling wave transmission outside a fault area provided by an embodiment of the present invention.

[0021] Attached Figure 6 A schematic flow chart of a feature vector forming method provided by one embodiment of the present invention.

[0022] Attached Figure 7 A schematic diagram of a model building method flow chart provided for one embodiment of the present invention.

[0023] Attached Figure 8 A diagram showing the recognition results of training samples provided by an embodiment of the present invention.

[0024] Attached Fig. 9 A diagram showing different fault identification results provided by an embodiment of the present invention.

[0025] Attached Fig.10 A schematic diagram of the structure of a fault identification device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The present invention is not limited by the following embodiments, and specific implementation methods can be determined based on the technical solution of the present invention and actual conditions.

[0027] Those skilled in the art will understand that, unless otherwise stated, a "module" or "unit" in the embodiments of the present invention refers to a computer program or a part of a computer program with a predetermined function, and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as a processing circuit or memory) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0028] In addition, the term “plurality” in the embodiments of the present invention refers to two or more than two, and “first” and “second” are used to distinguish descriptions and should not be understood as implying relative importance.

[0029] At present, the traditional fault identification methods for high-voltage transmission lines include single-item identification and series compensation identification. However, the structure of the double-circuit high-voltage transmission line on the same pole is complex, and there are many reasons for the occurrence of faults. The traditional fault identification method cannot effectively identify the faults of the double-circuit high-voltage transmission line on the same pole. Therefore, in order to improve the accuracy of the double-circuit high-voltage transmission line on the same pole and ensure the stability and safety of power transmission, the present invention effectively identifies the faults of the double-circuit high-voltage transmission line on the same pole based on wavelet analysis to ensure the stable operation of the power system.

[0030] The embodiment of the present invention provides a high-voltage transmission line fault identification method, device, electronic device, storage medium and computer program based on wavelet packet energy ratio. A fault identification model is obtained by using a number of fault samples for machine learning, and the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified is obtained. The reverse traveling wave current is decomposed by wavelet, and a feature vector composed of multiple wavelet energy ratios is extracted. The feature vector is input into the fault identification model to obtain a fault identification result.

[0031] Among them, the method provided by the embodiment of the present invention may involve artificial intelligence (AI) technology, and can be implemented based on artificial intelligence technology, for example, using machine learning to obtain a corresponding model using sample training.

[0032] Among them, Machine Learning (ML) is a multi-disciplinary interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in studying how computers simulate or implement human learning behavior to acquire new knowledge or skills and reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent. Its applications are spread across all areas of artificial intelligence.

[0033] The above-mentioned machine learning usually includes technologies such as neural networks, belief networks, reinforcement learning, transfer learning, and inductive learning.

[0034] As attached Figure 1 As shown, it shows a schematic diagram of an implementation environment provided by an embodiment of the present invention. The implementation environment may include: training equipment and use equipment.

[0035] Both the training device and the use device are computer devices; optionally, the computer device is a terminal device, such as a mobile phone, a tablet computer, a PC (Personal Computer) and other electronic devices; or, the computer device is a server, which can be a single server, a server cluster composed of multiple servers, or a cloud computing service center, which is not limited to the embodiments of the present invention.

[0036] The training device refers to a computer device with model training and learning capabilities. Optionally, the training device has the ability to obtain the model, and train and learn it according to application requirements. For example, the training device obtains the model from other devices through the network, and then trains it through training samples according to application requirements, so that the model has the ability to obtain fault identification; Optionally, the training device has the ability to build a model, and it can build a model by itself according to application requirements, and then train and learn it. For example, in order to realize the fault identification of double-circuit high-voltage transmission lines on the same pole, the training device builds a neural network by itself, and then trains and learns it through fault samples according to application requirements.

[0037] The device used refers to a computer device that has the requirements for using the model. Optionally, the device uses the model according to the application requirements and obtains the model from other devices through the network. For example, if the device uses the requirement for fault identification, it can obtain a model that has been trained and learned to perform fault identification from other devices through the network, and use the fault identification to perform fault identification on the same pole double-circuit high-voltage transmission line.

[0038] Based on this, the present invention is further described below in conjunction with embodiments and drawings: Embodiment 1: As attached Figure 2 As shown, the embodiment of the present invention discloses a high-voltage transmission line fault identification method based on wavelet packet energy ratio, comprising: Step S110, obtaining the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, performing wavelet decomposition on the reverse traveling wave current, and extracting a plurality of wavelet energy ratios to form a feature vector; Step S120, inputting the feature vector into a fault identification model to obtain a fault identification result, wherein the fault identification model is obtained by machine learning using a number of fault samples, wherein each fault sample includes a feature vector and a label of a fault type.

[0039] This embodiment introduces the reverse traveling wave current at both ends of the double-circuit line to be identified on the same pole for fault identification. The reasons why the reverse traveling wave current can be used for fault identification are as follows: The double-circuit line model on the same pole is as shown in the attached figure. Figure 3 As shown, it contains two loops: L1 and L2, which share the same tower in the protected area. On both sides of the protected area, the line continues to extend through L3 and L4. The key components in the attached figure are: M and N represent the busbars at both ends, which are the starting point and end point of power transmission; L1 and L2 are double-loop lines on the same pole in the protected area, representing L and L respectively; L3 and L4 are lines outside the protected area; R1 to R6 are traveling wave protection units, located inside and outside the protected area, near the M or N end busbar, responsible for monitoring the line status and triggering protection actions when a fault is detected.

[0040] The positive direction of traveling wave propagation is the direction from the busbar to the line. That is to say, when the traveling wave propagates from the M or N busbar to the L1, L2, L3, and L4 lines, its direction is considered to be the positive direction. When a line fault occurs, the fault state can be decomposed into the superposition of the normal operating state and the fault additional state. The fault additional state can be regarded as an additional power source added to the fault point. This power source generates a fault traveling wave at the fault point and propagates it to both ends of the line. By monitoring the characteristics of these traveling waves, such as amplitude, arrival time, etc., the fault type can be identified and the fault point can be located.

[0041] Attached Figure 4 The figure shows the propagation process of the fault traveling wave when a single-phase line has an internal fault at K1. The traveling wave generated by the fault will propagate along the line to the busbars M and N at both ends. and represent the time it takes for the traveling wave to propagate from the fault point to the busbars M and N respectively, while T represents the time it takes for the traveling wave to propagate from the busbar M to the busbar N. When a fault occurs, the forward traveling wave propagating toward the fault point and the reverse traveling wave propagating away from the fault point will be detected at the busbar, i Mf and i Mb They represent the forward wave current and reverse wave current detected at the M-terminal bus, i Nf and i Nb This corresponds to the forward wave current and reverse wave current detected at the N-terminal bus.

[0042] When a fault occurs in the area, the traveling wave generated by the fault point will propagate to both ends of the line at the same time. The traveling wave protection units at both ends will first detect the reverse traveling wave current, i.e. Mb and i Nb This is because the reverse traveling wave current propagates away from the fault point, and it will reach the bus end earlier than the forward traveling wave current. If one end of the line detects the reverse traveling wave current first at time t, then since the propagation time of the traveling wave between the two ends of the bus is t, the other end will definitely detect the reverse traveling wave current within the time interval t, t+. This feature provides an important basis for the determination of traveling wave protection. By comparing the time difference between the detection of the reverse traveling wave current at the two ends of the bus, combined with the known traveling wave propagation speed, it is possible to accurately determine whether the fault occurs in the protection zone.

[0043] Attached Figure 5 The figure shows the propagation process of the fault traveling wave in the single-phase line when an out-of-zone fault occurs in the K2 section. In this case, the fault occurs outside the line, but it will affect the line, so the propagation characteristics of the traveling wave are different from those of the in-zone fault. After the fault occurs, the traveling wave protection unit at the N end first detects the traveling wave current i before the fault. Nf， This is because the traveling wave generated by the fault will propagate to both sides along the line. Since the line remains intact, i Nf It will continue to be transmitted along the line to the M end, and after reaching the M end, it will be converted into a reverse wave current iMb when i Mb When it reaches the physical boundary of the M end, it will reflect due to the impedance discontinuity point. Mb Generate forward wave current i Mf , return to the N end along the original path, at the N end, i Mf Converted into reverse wave current i again Nf .

[0044] When an out-of-zone fault occurs in section K2, the N terminal detects the traveling wave i before the fault at time Mf Since the traveling wave needs to propagate the entire length of the line back and forth, the N end will not be able to detect the reverse traveling wave i in the time interval t and t+2. Nf This is because i Mb is i Mf After reflection, i Mf The propagation and reflection of the M terminal take time. Mb The reverse wave current i is detected immediately after it arrives Mb This is because i Mb It is directly transmitted from the N end to the M end without going through the reflection process.

[0045] As described above, the present invention discloses a method for identifying high-voltage transmission line faults based on wavelet packet energy ratios, which obtains the reverse-traveling wave currents at both ends of the double-circuit lines on the same pole to be identified, decomposes them using wavelet analysis, thereby capturing local features in the reverse-traveling wave currents, extracting a plurality of wavelet energy ratios to form a feature vector, and locating the fault position in multiple directions in combination with a fault identification model, thereby obtaining a more accurate fault identification result. Therefore, the present invention can be effectively applied to scenarios such as double-circuit high-voltage transmission lines on the same pole, which have complex structures and many causes for faults.

[0046] Embodiment 2: As attached Figure 6 As shown, the embodiment of the present invention is a further optimization of the above embodiment, wherein the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified is obtained, and wavelet decomposition is performed on it, and multiple wavelet energy ratios are extracted to form a feature vector, including: Step S210, obtaining traveling wave voltage and current data at both ends of the double-circuit line on the same pole.

[0047] Step S220, decoupling the traveling wave voltage and current data by using phase mode transformation; This step decouples the traveling wave voltage and current data through the phase mode transformation matrix for subsequent analysis and identification.

[0048] Step S230, selecting the same modulus to calculate the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified; In this step, the same modulus is selected to calculate the reverse traveling wave current at both ends of the double-circuit line to be identified on the same pole, which helps to eliminate the influence of line parameters on traveling wave propagation and improve the accuracy of analysis.

[0049] Step S240, performing six-layer wavelet decomposition on the reverse traveling wave current to obtain six-layer wavelet components; This step performs six-layer wavelet decomposition on the extracted reverse traveling wave current to decompose it into components of different scales. Wavelet decomposition helps capture local features in the signal.

[0050] Step S250, based on the six layers of wavelet components, six wavelet energy ratios P1, P2, P3, P4, P5, and P6 are obtained, and the six wavelet energy ratios are combined into a feature vector.

[0051] It should be noted that the six wavelet energy ratios P1, P2, P3, P4, P5, and P6 are ratios of the wavelet components of each layer to the total energy.

[0052] Therefore, wavelet analysis is used to decompose and reconstruct the fault signal of the double-circuit high-voltage transmission line on the same pole, and feature vectors are extracted that are beneficial to identifying faults in multiple directions, thereby improving the accuracy of fault identification.

[0053] Embodiment 3: As attached Figure 7 As shown, the embodiment of the present invention is a further optimization of the above embodiment, wherein the construction of the fault identification model includes: Step S310 , obtaining a number of fault samples with different fault types and different fault initial angles, wherein each fault sample includes a feature vector and a label of the fault type.

[0054] Step S320, using the SMOTE algorithm to expand the fault samples, obtain a fault sample set, and divide it into a training sample set and a test sample set according to the ratio; the SMOTE algorithm is an algorithm for dealing with the problem of data category imbalance, which synthesizes new minority class samples to increase the number of minority class samples, thereby balancing the data set and improving the performance of the classifier. This embodiment effectively expands the fault samples through the SMOTE algorithm to provide a data basis for subsequent model training.

[0055] Step S330 , training the support vector machine algorithm using the training sample set in combination with the training stop condition to obtain a fault recognition model.

[0056] The support vector machine (SVM) algorithm used above is a quadratic classification model, and its learning strategy is to find a point (that is, a support vector) on both the positive and negative sides of the classification hyperplane that is closest to the classification hyperplane, so that the sum of the distances between these two points and the classification hyperplane is maximized. The purpose of this classification strategy is to set as much redundant space as possible for noise on the basis of ensuring the correct classification of the training data, so as to improve the robustness of the classifier.

[0057] The above training stop condition can be set according to needs, and can be but not limited to the number of iterations.

[0058] Step S340, using the test sample set to test the fault identification model, if the test requirements are met, the final fault identification model is output, if not, the support vector machine algorithm parameters are adjusted and retrained.

[0059] The above test requirements can be set by introducing evaluation indicators or loss functions, which can be set according to actual conditions.

[0060] Embodiment 4: An example is introduced to verify the high-voltage transmission line fault identification method based on wavelet packet energy ratio disclosed in the present invention. The specific process includes: Will attach Figure 3 The length of line MN is set to 3km, while the length of line NO is 15km. In order to ensure the accuracy of simulation and data analysis, the sampling frequency is set to 20kHz, the voltage level is set to 500kV, the operating frequency is 50Hz, and fault samples under different fault types and different fault initial angles are collected. In view of the complexity of double-circuit lines on the same pole, the number of out-of-area fault samples is less than that of in-area fault samples. In order to balance the data set and improve the generalization ability of the model, the SLOTE algorithm is used to expand the out-of-area fault samples. The expanded out-of-area fault samples are combined with the original in-area fault samples to construct a training set. During the training process, the parameters of the SVM algorithm are continuously optimized to ensure that it can accurately distinguish between in-area and out-of-area faults. After the training is completed, a fault recognition model with superior performance is obtained. The recognition results of the model for the training samples are shown in the attached figure. Figure 8 As shown in the figure, it can be seen that the model can identify the faults inside and outside the zone very accurately.

[0061] In order to comprehensively evaluate the performance of the trained fault recognition model in actual scenarios, 8 groups of in-region fault samples and 10 groups of out-of-region fault test samples were sorted out. The fault test samples were input into the trained fault recognition model and the recognition results of the model were recorded. The recognition results are shown in the attached figure. Fig. 9 As shown, it can be seen that the model has a high recognition accuracy for in-zone faults and out-of-zone faults, showing good classification performance.

[0062] In order to verify the recognition effect of the model for different fault types, Table 1 lists the recognition results of the model under various fault conditions. In the table, "1" and "2" represent L1 and L2 lines respectively, and the letter "G" is used to represent ground faults. For example, "1A2BCG" means that a cross-line short-circuit ground fault occurs between phase A of L1 line and phases B and C of L2 line.

[0063] From Table 1, it can be found that the fault identification model shows good performance under various fault types and conditions.

[0064] In the power system, the different fault locations may affect the accuracy of fault identification. Since the attenuation of the traveling wave energy is directly related to the location of the fault point, it is very important to explore the impact of the fault location on the identification algorithm. In order to comprehensively evaluate the identification effect of the present invention, the same single-phase short-circuit grounding fault at different locations on the line is simulated, and the corresponding data is collected. The corresponding identification results are shown in Table 2.

[0065] It can be seen from the table that no matter the fault occurs at the beginning, middle or end of the line, the fault can be accurately identified, and the identification accuracy is not affected by the fault location.

[0066] Embodiment 5: As attached Fig.10 As shown, the embodiment of the present invention discloses a high-voltage transmission line fault identification device based on wavelet packet energy ratio, comprising: The feature extraction unit obtains the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, performs wavelet decomposition on the reverse traveling wave current, and extracts multiple wavelet energy ratios to form a feature vector; The fault identification unit inputs the feature vector into the fault identification model to obtain a fault identification result, wherein the fault identification model is obtained by machine learning using a number of fault samples, wherein each fault sample includes a feature vector and a label of the fault type.

[0067] The feature extraction unit includes: The first extraction module obtains the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, including: Obtain the traveling wave voltage and current data at both ends of the double-circuit line on the same pole; Decoupling the traveling wave voltage and current data using phase mode transformation; Select the same modulus to calculate the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified; The second extraction module performs wavelet decomposition on the reverse wave current and extracts multiple wavelet energy ratios to form a feature vector, including: Perform six-layer wavelet decomposition on the reverse traveling wave current to obtain six-layer wavelet components; Based on the six-layer wavelet components, six wavelet energy ratios are obtained, and the six wavelet energy ratios are combined into a feature vector.

[0068] Wherein, the fault identification unit includes: Training module, building fault identification model, including: Obtain a number of fault samples with different fault types and different fault initial angles, wherein each fault sample includes a feature vector and a label of the fault type; The fault samples are expanded using the SMOTE algorithm to obtain a fault sample set, which is then divided into a training sample set and a test sample set according to the ratio. Combined with the training stop condition, the support vector machine algorithm is trained using the training sample set to obtain a fault recognition model; The fault identification model is tested using the test sample set. If the test requirements are met, the final fault identification model is output. If not, the support vector machine algorithm parameters are adjusted and retrained. The recognition module inputs the feature vector into the fault recognition model to obtain the fault recognition result.

[0069] Embodiment 6: The embodiment of the present invention discloses a storage medium, on which a computer program readable by a computer is stored, and the computer program is configured to execute a high-voltage transmission line fault identification method based on wavelet packet energy ratio when running.

[0070] The above storage medium may include, but is not limited to: a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0071] Embodiment 7: The embodiment of the present invention discloses an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement a high-voltage transmission line fault identification method based on wavelet packet energy ratio.

[0072] The processor may be a central processing unit (CPU), a general purpose processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the present invention. It may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The memory may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory, a mobile hard disk, a magnetic disk or an optical disk.

[0073] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The solutions in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and interpreted scripting language JavaScript, etc.

[0074] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0075] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0076] Embodiment 8: The embodiment of the present invention discloses a computer program product, including a computer program or instructions, which, when executed by a processor, implements the steps in a high-voltage transmission line fault identification method based on wavelet packet energy ratio.

[0077] The above content is only a specific implementation mode of the present invention, which has strong adaptability and implementation effect, but the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered within the protection scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope covered by the present invention.

Claims

1. A method for identifying high-voltage transmission line faults based on wavelet packet energy ratio, characterized in that: include: Obtain the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, perform wavelet decomposition on it, and extract multiple wavelet energy ratios to form a feature vector; The feature vector is input into a fault identification model to obtain a fault identification result, wherein the fault identification model is obtained by machine learning using a number of fault samples, wherein each fault sample includes a feature vector and a label of the fault type.

2. The high-voltage transmission line fault identification method based on wavelet packet energy ratio according to claim 1 is characterized in that: The step of obtaining the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified includes: Obtain the traveling wave voltage and current data at both ends of the double-circuit line on the same pole; Decoupling the traveling wave voltage and current data using phase mode transformation; The same modulus is selected to calculate the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified.

3. The high-voltage transmission line fault identification method based on wavelet packet energy ratio according to claim 1 or 2 is characterized in that: The reverse traveling wave current is subjected to wavelet decomposition, and a plurality of wavelet energy ratios are extracted to form a characteristic vector, including: Perform six-layer wavelet decomposition on the reverse traveling wave current to obtain six-layer wavelet components; Based on the six-layer wavelet components, six wavelet energy ratios are obtained, and the six wavelet energy ratios are combined into a feature vector.

4. The high-voltage transmission line fault identification method based on wavelet packet energy ratio according to any one of claims 1 to 3, characterized in that: The construction of the fault identification model includes: Obtain a number of fault samples with different fault types and different fault initial angles, wherein each fault sample includes a feature vector and a label of the fault type; The fault samples are expanded using the SMOTE algorithm to obtain a fault sample set, which is then divided into a training sample set and a test sample set according to the ratio. Combined with the training stop condition, the support vector machine algorithm is trained using the training sample set to obtain a fault recognition model; The fault recognition model is tested using a test sample set. If the test requirements are met, the final fault recognition model is output; if the test requirements are not met, the support vector machine algorithm parameters are adjusted and retrained.

5. A high-voltage transmission line fault identification device based on wavelet packet energy ratio using the method according to any one of claims 1 to 4, characterized in that: include: The feature extraction unit obtains the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, performs wavelet decomposition on the reverse traveling wave current, and extracts multiple wavelet energy ratios to form a feature vector; The fault identification unit inputs the feature vector into the fault identification model to obtain a fault identification result, wherein the fault identification model is obtained by machine learning using a number of fault samples, wherein each fault sample includes a feature vector and a label of the fault type.

6. The high-voltage transmission line fault identification device based on wavelet packet energy ratio according to claim 5 is characterized in that: The feature extraction unit comprises: The first extraction module obtains the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified, including: Obtain the traveling wave voltage and current data at both ends of the double-circuit line on the same pole; Decoupling the traveling wave voltage and current data using phase mode transformation; Select the same modulus to calculate the reverse traveling wave current at both ends of the double-circuit line on the same pole to be identified; The second extraction module performs wavelet decomposition on the reverse wave current and extracts multiple wavelet energy ratios to form a feature vector, including: Perform six-layer wavelet decomposition on the reverse traveling wave current to obtain six-layer wavelet components; Based on the six-layer wavelet components, six wavelet energy ratios are obtained, and the six wavelet energy ratios are combined into a feature vector.

7. The high-voltage transmission line fault identification device based on wavelet packet energy ratio according to claim 5 or 6, characterized in that: The fault identification unit comprises: Training module, building fault identification model, including: Obtain a number of fault samples with different fault types and different fault initial angles, wherein each fault sample includes a feature vector and a label of the fault type; The fault samples are expanded using the SMOTE algorithm to obtain a fault sample set, which is then divided into a training sample set and a test sample set according to the ratio. Combined with the training stop condition, the support vector machine algorithm is trained using the training sample set to obtain a fault recognition model; The fault identification model is tested using the test sample set. If the test requirements are met, the final fault identification model is output. If not, the support vector machine algorithm parameters are adjusted and retrained. The recognition module inputs the feature vector into the fault recognition model to obtain the fault recognition result.

8. An electronic device, characterized in that: It comprises a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the steps in the high-voltage transmission line fault identification method based on wavelet packet energy ratio as described in any one of claims 1 to 4.

9. A storage medium, characterized in that: The storage medium stores a computer program that can be read by a computer, and the computer program is configured to execute the steps of the high-voltage transmission line fault identification method based on wavelet packet energy ratio as claimed in any one of claims 1 to 4 when running.

10. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the steps of the high-voltage transmission line fault identification method based on wavelet packet energy ratio as described in any one of claims 1 to 4 are implemented.

Images