Fault identification method and system based on genetic algorithm optimization

Abstract

The application belongs to the technical field of power system relay protection, and proposes a band-limited transient current fault identification method and system based on genetic algorithm optimization. Three-phase current instantaneous value signals are collected and decoupled into seven current components, including three line mode components, three line mode components and one ground mode component. After band-pass filtering of each component, the absolute maximum value of the current rate of change is extracted in a short window after fault starting, and nine fault discrimination indexes are constructed accordingly. Genetic algorithm is used to perform off-line adaptive optimization on three key discrimination thresholds, taking fault identification accuracy as the fitness target to obtain the optimal threshold combination. Finally, based on the combination and the discrimination indexes, accurate differentiation of fault types such as ground / non-ground, single-phase / two-phase / three-phase, and reliable identification of fault phases are realized. The application gets rid of the dependence on manual setting and improves the adaptability and engineering applicability of transient protection.

Description

Technical Field

[0001] This invention relates to the field of power system relay protection technology, specifically to a band-limited transient current fault identification method and system based on genetic algorithm optimization. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] The safe and stable operation of power systems heavily relies on fast and reliable relay protection systems. Traditional protection schemes are mainly based on power frequency phasor calculations, but this method requires a large data window for judgment, limiting its response speed and making it difficult to meet the requirements of modern power systems for rapid fault response. Transient protection technology, by extracting high-frequency transient signals at the time of a fault, can identify faults within milliseconds, making rapid fault response possible.

[0004] In existing technologies, such as fault identification methods based on band-limited transient current signals, improvements are made... Seven current components are obtained through transformation, and nine fault discrimination indices are constructed by selecting current signals from specific frequency bands, enabling rapid identification of fault types and fault phases. However, existing technologies suffer from difficulties in threshold tuning: the key discrimination thresholds in the method require extensive data analysis for tuning, which is very time-consuming and labor-intensive to perform manually. For different network structures, line parameters, and operating modes, a fixed threshold may lead to a decrease in recognition performance. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a band-limited transient current fault identification method and system based on genetic algorithm optimization. By introducing a genetic algorithm to automatically and globally optimize the fault discrimination threshold, the method's adaptability and accuracy are significantly improved.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a band-limited transient current fault identification method based on genetic algorithm optimization.

[0007] A band-limited transient current fault identification method based on genetic algorithm optimization includes the following steps: Acquire the instantaneous three-phase current signal at one end of the protected line; The instantaneous three-phase current signals are decoupled to obtain seven current components, of which three are included in the three-phase current components. Linear module components, three A linear mode component and a ground mode component; Bandpass filtering is performed on the seven current components to obtain the corresponding seven filtered current components. Within a short time window after the fault starts, calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components. Based on the absolute maximum value of the rate of change of current, nine fault discrimination indices are constructed. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the rate of change of current of different filtered current components. The genetic algorithm is used to perform offline adaptive optimization of three preset discrimination thresholds to achieve the highest fault identification accuracy on a given fault sample set, thereby generating the optimal threshold combination. Based on the optimal threshold combination and nine fault discrimination indices, the system performs fault type determination and fault phase identification.

[0008] In one implementation of the first aspect of the present invention, the instantaneous three-phase current signals are decoupled using an improved Clarke transform. The improved Clarke transform uses a transformation matrix that linearly maps the instantaneous three-phase current signals into three... Linear module components, three The system consists of a linear mode component and a ground mode component, where the ground mode component reflects the zero-sequence characteristic. Linear component and The linear mode components correspond to the decoupling high-frequency characteristics of phases A, B, and C, respectively.

[0009] In one implementation of the first aspect of the present invention, the nine fault discrimination indices include: for each phase, a combination of the ground mode component and the phase... The first type of index is formed by the ratio of the maximum rate of change of current of the linear mode components; derived from this phase Linear component and The second type of index is formed by the ratio of the maximum rate of change of current of the linear modulus components; and the index is formed by the phase... Linear component and The third type of index is formed by the ratio of the maximum rate of change of current of the linear modulus components.

[0010] In one implementation of the first aspect of the present invention, three preset discrimination thresholds are included: a first threshold for distinguishing between ground faults and non-ground faults, a second threshold for further distinguishing between phase-to-phase faults and three-phase faults, and a third threshold for identifying specific fault phases; a genetic algorithm performs search optimization within the range of 0.05 to 0.1 for the first threshold and the range of 1 to 100 for the second and third thresholds.

[0011] As a further limitation of the first aspect of the present invention, the determination of the fault type includes: When the first type index corresponding to all three phases is greater than the first threshold, it is determined to be a ground fault; otherwise, it is determined to be a non-ground fault. For grounding faults, if the sum of the three second-type indices is greater than the second threshold, it is determined to be a single-phase grounding fault; otherwise, it is a two-phase grounding fault. For ungrounded faults, if the sum of the three third-type indices is greater than the second threshold, it is determined to be a phase-to-phase fault; otherwise, it is a three-phase fault.

[0012] As a further limitation of the first aspect of the present invention, the identification of the faulty phase includes: in the case of a single-phase ground fault, if only one phase has a second type index not less than a third threshold, then that phase is a faulty phase; in the case of a phase-to-phase fault, if only two phases have a third type index less than the third threshold, and the remaining phase has a third type index not less than the third threshold, then the two phases are faulty phases; in the case of a two-phase ground fault, the two phases with the largest second type index are taken as faulty phases.

[0013] Secondly, the present invention provides a band-limited transient current fault identification system based on genetic algorithm optimization.

[0014] A band-limited transient current fault identification system based on genetic algorithm optimization includes: The signal acquisition unit is configured to acquire the instantaneous three-phase current signal at one end of the protected line. The current decoupling unit is configured to decouple the instantaneous three-phase current signals to obtain seven current components, wherein the seven current components include three... Linear module components, three A linear mode component and a ground mode component; The bandpass filter unit is configured to perform bandpass filtering on the seven current components respectively to obtain the corresponding seven filtered current components. The rate of change extraction unit is configured to calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components within a short time window after the fault starts. The discrimination index construction unit is configured to construct nine fault discrimination indices based on the absolute maximum value of the current change rate. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the current change rates of different filtered current components. The threshold optimization unit is configured to use a genetic algorithm to perform offline adaptive optimization of three preset discrimination thresholds, with the goal of obtaining the highest fault identification accuracy on a given fault sample set, and generate the optimal threshold combination. The fault identification unit is configured to determine the fault type and identify the fault phase based on the optimal threshold combination and nine fault discrimination indices.

[0015] Thirdly, the present invention provides a computer device, comprising: a processor and a computer-readable storage medium; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by a processor, implements the band-limited transient current fault identification method based on genetic algorithm optimization according to the first aspect of the present invention.

[0016] Fourthly, the present invention provides a computer-readable storage medium storing a computer program adapted to be loaded by a processor and executed by the method for identifying band-limited transient current faults based on genetic algorithm optimization according to the first aspect of the present invention.

[0017] Fifthly, the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the band-limited transient current fault identification method based on genetic algorithm optimization according to the first aspect of the present invention.

[0018] Compared with the prior art, the beneficial effects of the present invention are: This invention deeply integrates genetic algorithms with band-limited transient current fault identification methods to construct an adaptive and highly robust fault identification system. Starting with the instantaneous values ​​of three-phase current, the method decouples seven-dimensional current characteristic components using an improved Clarke transform and focuses on the frequency band where fault transient energy is concentrated through bandpass filtering. Based on this, nine physically meaningful fault discrimination indices are constructed using the maximum value of the current change rate within a short time window. Then, a genetic algorithm is used to perform offline global optimization of key thresholds, ultimately achieving accurate determination of fault type and fault phase. The entire process forms a closed loop from front-end signal acquisition to back-end intelligent decision-making. It not only retains the advantage of fast transient protection response speed but also fundamentally solves the inherent defects of traditional methods that rely on manual experience to set thresholds and are difficult to adapt to complex power grid conditions, significantly improving the versatility and reliability of relay protection systems under different operating environments.

[0019] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0020] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0021] Figure 1 A flowchart illustrating a band-limited transient current fault identification method based on genetic algorithm optimization, provided as an exemplary embodiment of the present invention; Figure 2 A flowchart of a genetic algorithm for optimizing a threshold is provided as an exemplary embodiment of the present invention; Figure 3A fault type identification logic block diagram provided as an exemplary embodiment of the present invention; Figure 4 A fault phase identification logic block diagram provided for an exemplary embodiment of the present invention (taking a single-phase ground fault as an example); Figure 5 A schematic diagram of a band-limited transient current fault identification system based on genetic algorithm optimization, provided as an exemplary embodiment of the present invention; Figure 6 A schematic diagram of a computer device provided for an exemplary embodiment of the present invention. Detailed Implementation

[0022] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0023] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0024] This implementation proposes a band-limited transient current fault identification method based on genetic algorithm optimization. It includes an offline threshold optimization stage based on the genetic algorithm and a fault identification stage based on the optimized threshold. The threshold optimization stage is configured to automatically find a set of discrimination thresholds that maximize fault identification accuracy through iterative evolution of the genetic algorithm, and then apply these thresholds to online fault identification. Specifically, as shown... Figure 1 As shown, the process includes the following: S1: Use a current transformer to collect data at one end of the protected line. , , Three-phase current instantaneous value signal , , The sampling rate should not be lower than This is to ensure that effective transient signals can be captured.

[0025] S2: The collected three-phase current is passed through an improved... Transform the matrix to decouple and obtain seven independent current components: , , , , , , .

[0026] The transformation matrix is ​​as follows: (1); in, For the ground model component, , , , , , For line model components.

[0027] S3: The decoupled seven independent current components are passed through a fourth-order current circuit. The bandpass filter is used to filter the current, resulting in seven filtered current components: , , , , , , The preferred passband of a bandpass filter is... to This effectively suppresses power frequency components and high-frequency noise, extracting current-limiting transient signals for fault analysis. The transfer function used by the bandpass filter is: (2); in, Represents the filter transfer function; , , , and Represents the numerator coefficients of the filter; , , and Represents the denominator coefficients of the filter; , , and The delay operator represents the Z-transform.

[0028] S4: Calculate the change in current.

[0029] The time derivatives of the seven current components after filtering are calculated to obtain the rate of change of current for each component: (3); (4); (5); (6); (7); (8); (9) in, Represents phase A Rate of change of current component after filtering; Represents phase B Rate of change of current component after filtering; Represents phase C Rate of change of current component after filtering; Represents phase A Rate of change of current component after filtering; Represents phase B Rate of change of current component after filtering; Represents phase C Rate of change of current component after filtering; This represents the rate of change of the current component after ground mode filtering.

[0030] S5: Set a short window after detecting a faulty startup. Within this window, the absolute maximum values ​​of the rate of change of each component current are tracked and recorded. Using these maximum values, nine fault detection indices are constructed: (10); (11); (12); in, ; Representing the Phase I fault discrimination index; Representing the Phase II fault discrimination index; Representing the Phase III fault discrimination index.

[0031] S6: Threshold optimization based on genetic algorithm.

[0032] Optimization objective: To optimize the three key discrimination thresholds of the fault identification algorithm. , , Global optimization is performed within a set coefficient range to find the threshold combination that maximizes the accuracy of fault detection, such as... Figure 2 As shown.

[0033] S601: Population initialization.

[0034] To make the threshold , , The population is evenly distributed within its respective maximum and minimum value ranges, making it easier for the algorithm to escape local optima, maintaining population diversity, enhancing global search capabilities, and improving the efficiency of the genetic algorithm. Chaotic mapping initializes the threshold. The expression for the chaotic mapping is: (13); in, Represents the threshold number. ; For mapping parameters, take ; Represents the threshold after iterating through the chaotic mapping; This represents the threshold before the chaotic mapping iteration.

[0035] S602: Fitness calculation.

[0036] The fitness value is used to evaluate the accuracy of fault detection using a threshold function. : (14); in, To use threshold combinations The number of correctly identified faults obtained. The total number of faults searched using a genetic algorithm (a fault is considered correctly identified only if both the fault type and fault phase are correct; if either the fault type or fault phase is incorrect, it is considered an incorrect identification).

[0037] S603: Selection operation.

[0038] The selection process simulates the natural selection process. Using a roulette wheel selection algorithm, selection is performed based on accumulated probabilities, thus preserving individuals with evolutionary potential. Let a set of thresholds be... The calculated fitness The probability of selecting this set of thresholds is The cumulative probability is , The calculation method is as follows: (15); in, Represents the total number of individuals in the population; Representing the Individual fitness value.

[0039] S604: Cross operation.

[0040] Arithmetic crossover can be used for crossover operations, for example, by selecting two sets of thresholds. , Arithmetic crossover generates two new sets of thresholds. , The crossover process is as follows: (16); in, Take the intersection .

[0041] S605: Mutation operation.

[0042] The uniform mutation operation helps the algorithm escape local optima and obtain potential optimal values. Specifically, when a certain threshold is reached... When a mutation occurs, a new parameter is randomly selected within the upper and lower limits of this threshold. To replace the original parameter: (17); in, It is a random number between 0 and 1. and Coefficients The upper and lower limits of the possible values.

[0043] Through continuous iteration and population evolution, a set of optimal threshold combinations eventually converges. .

[0044] Fault type and fault identification: using optimized thresholds , , The following logical judgment process will be executed: S7: Fault type identification.

[0045] like Figure 3 As shown, the distinction between grounding faults and non-grounding faults is as follows: If If the fault is detected, it is determined to be a ground fault; otherwise, it is determined to be a non-ground fault.

[0046] Ground fault subdivision; if it is a ground fault, calculate... .like If the fault is determined to be a single-phase ground fault, it is determined to be a two-phase ground fault.

[0047] Ungrounded fault subdivision; if it is an ungrounded fault, calculate... .like If the fault is determined to be a phase-to-phase fault, it is determined to be a three-phase fault.

[0048] S8: Fault phase identification, such as Figure 4 As shown.

[0049] In a single-phase ground fault: if , The phase is the faulty phase; if , The phase is the faulty phase; if , The phase is the faulty phase.

[0050] During phase-to-phase faults: if , Harmony The phase is the faulty phase; if , Harmony The phase is the faulty phase; if , Harmony The phase is the faulty phase.

[0051] In a two-phase ground fault: if , Harmony The phase is the fault-grounded phase; if , Harmony The phase is the fault-grounded phase; if , Harmony The phase is the fault-grounded phase.

[0052] In summary, the proposed solution enhances adaptability by automatically optimizing the threshold through a genetic algorithm, enabling it to quickly adapt to different system configurations and operating conditions. This solves the problems of difficult threshold tuning and strong system dependence inherent in traditional methods. It significantly reduces engineering costs by avoiding extensive manual threshold tuning for each new application scenario, achieving "one-click" optimization of protection settings and reducing the difficulty and cost of engineering implementation. Furthermore, the genetic algorithm optimization process can be performed offline, maintaining the advantages of transient high-speed protection.

[0053] This invention employs an improved Clarke transform to generate seven decoupled current components, effectively separating the ground mode and line mode characteristics in the fault transient signal, laying the foundation for subsequent construction of multi-dimensional criteria. Compared to the traditional symmetrical component method that only extracts the sequence component, this transform can more precisely characterize the differences in high-frequency transient behavior of each phase, especially under asymmetrical faults, clearly reflecting the dynamic response differences between the faulty and non-faulty phases. Combined with bandpass filtering to focus on specific frequency bands (e.g., 2500–3000Hz), interference from power frequency steady-state components and broadband noise is further suppressed, making the extracted current change rate more accurately reflect the electromagnetic transient nature of the initial stage of the fault. This provides high-quality feature input for constructing a high-discrimination fault discrimination index, enhancing the anti-interference capability and sensitivity of fault identification.

[0054] This invention introduces a genetic algorithm for offline adaptive optimization of three core discrimination thresholds, completely eliminating the reliance on manual tuning. The optimization process is fitness-oriented, using fault identification accuracy as the fitness guide. Within a preset parameter space, it automatically searches for the optimal threshold combination through population iteration, selection, crossover, and mutation mechanisms, fully considering the impact of different line structures, power supply configurations, and grounding methods on transient characteristics. Because the optimization is based on a large number of typical fault samples, the resulting thresholds have good generalization ability and can be applied to various operating scenarios without re-tuning. This mechanism significantly lowers the engineering deployment threshold, enabling the protection algorithm to move from "fixed parameters" to "self-learning adaptation," significantly improving the intelligence level and field applicability of the relay protection system.

[0055] The nine fault discrimination indices constructed in this invention are based on the ratio relationship of the change rate of the filtered current components, exhibiting strong physical interpretability and fault sensitivity. These indices can not only effectively distinguish between grounded and ungrounded faults, but also further identify sub-types such as single-phase grounding, two-phase grounding, phase-to-phase, and three-phase faults, and accurately locate the faulty phase. Their judgment logic fully utilizes the ground mode and line mode under different fault modes. Class and The differences in transient energy distribution among the components avoid the limitations of single feature quantities being easily affected by transition resistance or load fluctuations. Combined with thresholds optimized by a genetic algorithm, the entire identification process achieves high-confidence fault classification and phase selection while maintaining millisecond-level response speed, providing a reliable basis for subsequent circuit breaker operation, fault location, and system recovery.

[0056] Figure 5 A band-limited transient current fault identification system based on genetic algorithm optimization is shown, comprising: The signal acquisition unit 501 is configured to acquire the instantaneous three-phase current signal at one end of the protected line. The current decoupling unit 502 is configured to decouple the instantaneous three-phase current signals to obtain seven current components, wherein the seven current components include three... Linear module components, three A linear mode component and a ground mode component; The bandpass filter unit 503 is configured to perform bandpass filtering on the seven current components respectively to obtain the corresponding seven filtered current components. The rate of change extraction unit 504 is configured to calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components within a short time window after the fault starts. The discrimination index construction unit 505 is configured to construct nine fault discrimination indices based on the absolute maximum value of the current change rate. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the current change rates of different filtered current components. The threshold optimization unit 506 is configured to: use a genetic algorithm to perform offline adaptive optimization of three preset discrimination thresholds, with the goal of obtaining the highest fault identification accuracy on a given fault sample set, and generate the optimal threshold combination; The fault identification unit 507 is configured to perform fault type determination and fault phase identification based on the optimal threshold combination and nine fault discrimination indices.

[0057] It is understood that the aforementioned units can be individually or entirely merged into one or more other units, or some of the units can be further divided into multiple functionally smaller units. This achieves the same operation without affecting the technical effects of the embodiments of the present invention. The aforementioned units are based on logical functional division. In practical applications, the function of one unit can be implemented by multiple units, or the function of multiple units can be implemented by one unit. In other embodiments of the present invention, the system may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented collaboratively by multiple units.

[0058] According to another embodiment of the present invention, the system of this embodiment can be constructed by running a computer program (including program code) capable of performing the steps involved in the corresponding method of the present invention on a general-purpose computing device, such as a computer, which includes processing elements and storage elements such as a central processing unit (CPU), random access memory (RAM), and read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, loaded into the aforementioned computing device through the computer-readable recording medium, and run therein.

[0059] Figure 6 A computer device is shown, which includes a processor 601, a communication interface 602, and a computer-readable storage medium 603. The processor 601, communication interface 602, and computer-readable storage medium 603 can be connected via a bus or other means.

[0060] The communication interface 602 is used to receive and send data. The computer-readable storage medium 603 can be stored in the memory of the electronic device. The computer-readable storage medium 603 is used to store computer programs, which include program instructions. The processor 601 is used to execute the program instructions stored in the computer-readable storage medium 603.

[0061] The processor 601 is the computing and control core of an electronic device. It is suitable for implementing one or more instructions, specifically for loading and executing one or more instructions to achieve the corresponding method flow or corresponding function.

[0062] Processor 601 is configured to perform the following procedure: Acquire the instantaneous three-phase current signal at one end of the protected line; The instantaneous three-phase current signals are decoupled to obtain seven current components, of which three are included in the three-phase current components. Linear module components, three A linear mode component and a ground mode component; Bandpass filtering is performed on the seven current components to obtain the corresponding seven filtered current components. Within a short time window after the fault starts, calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components. Based on the absolute maximum value of the rate of change of current, nine fault discrimination indices are constructed. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the rate of change of current of different filtered current components. The genetic algorithm is used to perform offline adaptive optimization of three preset discrimination thresholds to achieve the highest fault identification accuracy on a given fault sample set, thereby generating the optimal threshold combination. Based on the optimal threshold combination and nine fault discrimination indices, the system performs fault type determination and fault phase identification.

[0063] This invention also provides a computer-readable storage medium, which is a memory device in an electronic device for storing programs and data. It is understood that the computer-readable storage medium here may include both built-in storage media in the electronic device and extended storage media supported by the electronic device. The computer-readable storage medium provides storage space for storing the processing system of the electronic device.

[0064] Furthermore, this storage space also contains one or more instructions suitable for loading and execution by the processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory; alternatively, it can also be at least one computer-readable storage medium located remotely from the aforementioned processor.

[0065] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to perform the following process: Acquire the instantaneous three-phase current signal at one end of the protected line; The instantaneous three-phase current signals are decoupled to obtain seven current components, of which three are included in the three-phase current components. Linear module components, three A linear mode component and a ground mode component; Bandpass filtering is performed on the seven current components to obtain the corresponding seven filtered current components. Within a short time window after the fault starts, calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components. Based on the absolute maximum value of the rate of change of current, nine fault discrimination indices are constructed. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the rate of change of current of different filtered current components. The genetic algorithm is used to perform offline adaptive optimization of three preset discrimination thresholds to achieve the highest fault identification accuracy on a given fault sample set, thereby generating the optimal threshold combination. Based on the optimal threshold combination and nine fault discrimination indices, the system performs fault type determination and fault phase identification.

[0066] The present invention also provides a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the electronic device to perform the following process: Acquire the instantaneous three-phase current signal at one end of the protected line; The instantaneous three-phase current signals are decoupled to obtain seven current components, of which three are included in the three-phase current components. Linear module components, three A linear mode component and a ground mode component; Bandpass filtering is performed on the seven current components to obtain the corresponding seven filtered current components. Within a short time window after the fault starts, calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components. Based on the absolute maximum value of the rate of change of current, nine fault discrimination indices are constructed. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the rate of change of current of different filtered current components. The genetic algorithm is used to perform offline adaptive optimization of three preset discrimination thresholds to achieve the highest fault identification accuracy on a given fault sample set, thereby generating the optimal threshold combination. Based on the optimal threshold combination and nine fault discrimination indices, the system performs fault type determination and fault phase identification.

[0067] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can implement the described functions using different methods for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0068] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of the present invention is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in or transmitted through a computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic cable, digital cable) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0069] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A band-limited transient current fault identification method based on genetic algorithm optimization, characterized in that, The process includes the following: Acquire the instantaneous three-phase current signal at one end of the protected line; The instantaneous three-phase current signals are decoupled to obtain seven current components, of which three are included in the three-phase current components. Linear module components, three A linear mode component and a ground mode component; Bandpass filtering is performed on the seven current components to obtain the corresponding seven filtered current components. Within a short time window after the fault starts, calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components. Based on the absolute maximum value of the rate of change of current, nine fault discrimination indices are constructed. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the rate of change of current of different filtered current components. The genetic algorithm is used to perform offline adaptive optimization of three preset discrimination thresholds to achieve the highest fault identification accuracy on a given fault sample set, thereby generating the optimal threshold combination. Based on the optimal threshold combination and nine fault discrimination indices, the system performs fault type determination and fault phase identification.

2. The band-limited transient current fault identification method based on genetic algorithm optimization as described in claim 1, characterized in that, The instantaneous three-phase current signals are decoupled using an improved Clarke transform. The improved Clarke transform uses a transformation matrix that linearly maps the instantaneous three-phase current signals into three... Linear module components, three The system consists of a linear mode component and a ground mode component, where the ground mode component reflects the zero-sequence characteristic. Linear component and The linear mode components correspond to the decoupling high-frequency characteristics of phases A, B, and C, respectively.

3. The band-limited transient current fault identification method based on genetic algorithm optimization as described in claim 1, characterized in that, Nine fault detection indices, including: for each phase, the indices are derived from the ground mode component and the phase... The first type of index is formed by the ratio of the maximum rate of change of current of the linear mode components; derived from this phase Linear component and The second type of index is formed by the ratio of the maximum rate of change of current of the linear modulus components; and the index is formed by the phase... Linear component and The third type of index is formed by the ratio of the maximum rate of change of current of the linear modulus components.

4. The band-limited transient current fault identification method based on genetic algorithm optimization as described in claim 1, characterized in that, Three preset discrimination thresholds are included: a first threshold for distinguishing between ground faults and non-ground faults, a second threshold for further distinguishing between phase-to-phase faults and three-phase faults, and a third threshold for identifying specific fault phases; the genetic algorithm performs search optimization within the range of 0.05 to 0.1 for the first threshold and the range of 1 to 100 for the second and third thresholds.

5. The band-limited transient current fault identification method based on genetic algorithm optimization as described in claim 4, characterized in that, Fault type determination includes: When the first type index corresponding to all three phases is greater than the first threshold, it is determined to be a ground fault; otherwise, it is determined to be a non-ground fault. For grounding faults, if the sum of the three second-type indices is greater than the second threshold, it is determined to be a single-phase grounding fault; otherwise, it is a two-phase grounding fault. For ungrounded faults, if the sum of the three third-type indices is greater than the second threshold, it is determined to be a phase-to-phase fault; otherwise, it is a three-phase fault.

6. The band-limited transient current fault identification method based on genetic algorithm optimization as described in claim 4, characterized in that, The identification of faulty phases includes: in the case of a single-phase ground fault, if only one phase has a second type index that is not less than the third threshold, then that phase is the faulty phase; in the case of a phase-to-phase fault, if only two phases have a third type index that is less than the third threshold, and the remaining phase has a third type index that is not less than the third threshold, then those two phases are the faulty phases; in the case of a two-phase ground fault, the two phases with the largest second type index are taken as the faulty phases.

7. A band-limited transient current fault identification system based on genetic algorithm optimization, characterized in that, include: The signal acquisition unit is configured to acquire the instantaneous three-phase current signal at one end of the protected line. The current decoupling unit is configured to decouple the instantaneous three-phase current signals to obtain seven current components, wherein the seven current components include three... Linear module components, three A linear mode component and a ground mode component; The bandpass filter unit is configured to perform bandpass filtering on the seven current components respectively to obtain the corresponding seven filtered current components. The rate of change extraction unit is configured to calculate the absolute maximum value of the rate of change of the current for each of the seven filtered current components within a short time window after the fault starts. The discrimination index construction unit is configured to construct nine fault discrimination indices based on the absolute maximum value of the current change rate. The nine fault discrimination indices are determined by the ratio relationship between the absolute maximum values ​​of the current change rates of different filtered current components. The threshold optimization unit is configured to use a genetic algorithm to perform offline adaptive optimization of three preset discrimination thresholds, with the goal of obtaining the highest fault identification accuracy on a given fault sample set, and generate the optimal threshold combination. The fault identification unit is configured to determine the fault type and identify the fault phase based on the optimal threshold combination and nine fault discrimination indices.

8. A computer device, characterized in that, include: Processor and computer-readable storage media; A processor, adapted to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, implements the band-limited transient current fault identification method based on genetic algorithm optimization as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program adapted to be loaded by a processor and executed as described in any one of claims 1 to 6, the band-limited transient current fault identification method based on genetic algorithm optimization.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the band-limited transient current fault identification method based on genetic algorithm optimization as described in any one of claims 1 to 6.

Images