GIS equipment discharge fault rapid positioning method and system

Abstract

The invention discloses a GIS equipment discharge fault rapid positioning method and system, and relates to the technical field of power systems, and the method comprises the steps: collecting the historical fault data of GIS equipment, and building a historical fault mode library; collecting a vibration signal generated in the operation process of the GIS equipment in real time, and preprocessing the vibration signal; energy distribution is calculated according to the preprocessed vibration signals, a threshold value of discharge fault detection is dynamically adjusted based on an energy distribution result, and potential fault signals are marked; combining the marked potential fault signals with the three-dimensional structure characteristics of the GIS equipment to obtain a preliminary positioning result of the fault; comparing the initial positioning result of the fault with a fault mode library to generate a fault pre-judgment result; according to the fault pre-judgment result, early warning information is automatically generated; and the spatial position of the fault is accurately positioned by adopting a triangulation positioning algorithm, so that the fault detection precision is further improved.

Description

Technical Field

[0001] The invention relates to the technical field of power systems, and in particular to a method and system for quickly locating a discharge fault of a GIS device. Background Art

[0002] With the widespread application of high-voltage gas-insulated switchgear (GIS), online monitoring and fault diagnosis technology for power equipment has developed rapidly. Traditional GIS equipment fault detection methods mainly rely on partial discharge detection and insulation detection. However, these methods usually require complex on-site manual intervention and are not sensitive enough to early discharge fault detection. In recent years, vibration signal analysis technology has gradually been applied to fault detection of GIS equipment. By real-time acquisition of vibration signals during equipment operation, combined with signal processing and pattern recognition technology, online and remote fault detection and location can be achieved. However, for GIS equipment with complex structures, how to accurately and quickly locate discharge faults remains a technical challenge.

[0003] The existing GIS equipment fault detection technology has the following shortcomings: First, it is difficult for the existing method to dynamically adjust the threshold, resulting in the accuracy of fault detection being limited by the interference of environmental noise; second, the traditional fault location method lacks in-depth analysis of the internal three-dimensional structure of the equipment, making it difficult to accurately determine the spatial location of the fault. In addition, the existing technology mostly relies on fixed thresholds or simple pattern matching algorithms, which are difficult to cope with complex fault signal changes. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for quickly locating a discharge fault of a GIS device to solve the problems of difficult dynamic adjustment of thresholds, inaccurate fault location and slow predictive response speed in GIS device discharge fault detection.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for quickly locating a discharge fault of a GIS device, which comprises:

[0008] Collect historical failure data of GIS equipment and establish a historical failure mode library;

[0009] Real-time collection of vibration signals generated during the operation of GIS equipment and pre-processing;

[0010] Calculate the energy distribution according to the preprocessed vibration signal, and dynamically adjust the threshold of discharge fault detection based on the energy distribution result to mark the potential fault signal;

[0011] Combine the marked potential fault signals with the three-dimensional structural characteristics of the GIS equipment to obtain the preliminary fault location results;

[0012] Compare the preliminary fault location results with the fault mode library to generate fault prediction results;

[0013] According to the fault prediction results, early warning information is automatically generated.

[0014] As a preferred solution of the method for quickly locating the discharge fault of GIS equipment of the present invention, the historical fault data includes the equipment operation status, discharge location, fault location, vibration signal characteristics and internal structure information of the equipment;

[0015] The establishment of the historical failure mode library comprises the following steps:

[0016] Classify faults into different categories based on fault location, vibration signal characteristics and internal structure information of the equipment;

[0017] For each type of fault, the corresponding vibration signal features and the internal structure information of the equipment are combined into a pattern vector;

[0018] The pattern vectors formed by each type of fault are stored to form a fault pattern library.

[0019] As a preferred solution of the method for quickly locating a discharge fault of a GIS device according to the present invention, the preprocessing includes signal filtering and signal denoising;

[0020] The signal filtering refers to limiting the frequency range of the vibration signal by using a bandpass filter to remove high-frequency noise and low-frequency interference;

[0021] The signal denoising refers to using a wavelet denoising algorithm to perform discrete wavelet transform and layering of the signal, denoising the decomposition coefficients of each layer, and then reconstructing the signal.

[0022] As a preferred solution of the method for quickly locating the discharge fault of GIS equipment described in the present invention, the energy distribution is calculated according to the preprocessed vibration signal, and the threshold of the discharge fault detection is dynamically adjusted based on the energy distribution result, and the potential fault signal is marked, which includes the following steps:

[0023] The short-time energy algorithm is used to calculate the short-time energy distribution of the preprocessed signal in different time periods. The expression is:

[0024]

[0025] Where E(n) is the short-time energy at time point n, x(nm) is the signal amplitude at time point nm, n is the current time point index, m is the offset of the time window, and M is the length of the time window;

[0026] The short-term energy of different time periods is plotted into an energy distribution diagram, and the energy distribution diagram is updated in real time according to the new vibration signal;

[0027] In the updated energy distribution map, an initial threshold is set according to the noise level of the current environment;

[0028] Combined with the energy distribution difference between normal operation signal and fault signal in the historical fault mode library, the fault signal in the historical mode library is analyzed to dynamically adjust the current discharge fault detection threshold;

[0029] The energy distribution of the real-time vibration signal is compared with the adjusted fault detection threshold. When the energy of the real-time signal exceeds the threshold, the current signal is marked as a potential fault signal.

[0030] As a preferred solution of the method for quickly locating a discharge fault of a GIS device according to the present invention, the method of combining the marked potential fault signal with the three-dimensional structural characteristics of the GIS device to obtain a preliminary fault location result includes the following steps:

[0031] Based on the design drawings and CAD models of GIS equipment, build a complete 3D structural model and define the physical properties of each component;

[0032] Based on the three-dimensional structural model, the propagation path of the vibration signal inside the GIS equipment is simulated, and a propagation path diagram is generated, marking the propagation time and attenuation of the signal in each component;

[0033] Calculate the three-dimensional coordinates of the fault source using the triangulation positioning algorithm;

[0034] The calculated three-dimensional coordinates are mapped to the three-dimensional structural model of the GIS equipment to determine the equipment component where the fault source is located and obtain the preliminary fault location result.

[0035] As a preferred solution of the method for quickly locating the discharge fault of GIS equipment described in the present invention, the following steps are performed to compare the preliminary fault location result with the fault mode library to generate the fault prediction result:

[0036] According to the preliminary fault location result, historical fault data corresponding to the preliminary location result is retrieved from the fault mode library, and each historical fault record is represented as a mode vector;

[0037] Extracting current fault signal features from the marked potential fault signal and generating a pattern vector of the current fault signal;

[0038] The dynamic time warping algorithm is used to calculate the matching degree between the current fault signal and the historical fault signal by finding the path that minimizes the difference between the time series. The expression is:

[0039]

[0040] Among them, DTW represents the dynamic time warping algorithm, DTW(V hist ,V real ) represents the matching degree between the historical fault signal and the current fault signal, V hist Represents the pattern vector of historical faults, V real represents the mode vector of the current fault, i represents the time index of the historical fault signal, j represents the time index of the current fault signal, V hist (i) represents the mode vector of the historical fault signal at time point i, V real (j) represents the mode vector of the current fault signal at time point j, It means to find the path that minimizes the total difference between the two fault signals among all possible time-aligned paths;

[0041] According to the calculated matching results, the type of current fault and the development trend of the fault are predicted.

[0042] As a preferred solution of the method for quickly locating a discharge fault of a GIS device according to the present invention, the automatic generation of early warning information according to the fault prediction result includes the following steps:

[0043] The predicted fault types are classified into minor faults, moderately serious faults and major faults;

[0044] The predicted fault development trends are divided into slow deterioration, rapid deterioration and sharp signal deterioration;

[0045] Based on the classification results of the predicted fault types and development trends, the corresponding warning notifications are automatically generated, and the warning levels are determined as ordinary warning, emergency warning and severe warning;

[0046] Generate corresponding maintenance suggestions based on the classified warning levels.

[0047] In a second aspect, the present invention provides a GIS equipment discharge fault rapid location system, comprising:

[0048] The pattern library module collects historical fault data of GIS equipment and establishes a historical fault pattern library;

[0049] The signal acquisition module collects the vibration signals generated during the operation of GIS equipment in real time and performs pre-processing;

[0050] The energy analysis module calculates the energy distribution according to the preprocessed vibration signal, and dynamically adjusts the threshold of discharge fault detection based on the energy distribution result to mark the potential fault signal;

[0051] The positioning module combines the marked potential fault signals with the three-dimensional structural characteristics of the GIS equipment to obtain the preliminary positioning results of the fault;

[0052] The pattern matching module compares the preliminary fault location results with the fault pattern library to generate fault prediction results;

[0053] The early warning module automatically generates early warning information based on the fault prediction results.

[0054] In a third aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for quickly locating a discharge fault in a GIS device as described in the first aspect of the present invention is implemented.

[0055] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for quickly locating a discharge fault in GIS equipment as described in the first aspect of the present invention is implemented.

[0056] The beneficial effects of the present invention are as follows: by calculating the short-time energy distribution of the preprocessed vibration signal, the threshold of discharge fault detection can be dynamically adjusted according to the real-time noise level and historical fault mode, thereby effectively reducing the occurrence of false alarms and missed alarms; combining the three-dimensional structural characteristics of the GIS equipment, a triangulation positioning algorithm is used to accurately locate the spatial position of the fault, further improving the accuracy of fault detection; by comparing the preliminary fault positioning results with the historical fault mode library, the type of fault and development trend prediction can be quickly generated, and the corresponding early warning information and maintenance suggestions can be automatically generated, reducing the power grid operation risk caused by equipment failure and improving the reliability and safety of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0058] Figure 1 This is a flow chart of the method for quickly locating a discharge fault in GIS equipment in Example 1.

[0059] Figure 2 This is a schematic diagram of fault warning in Example 1. DETAILED DESCRIPTION

[0060] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0061] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0062] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0063] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for quickly locating a discharge fault of a GIS device, comprising the following steps:

[0064] S1. Collect historical failure data of GIS equipment and establish a historical failure mode library.

[0065] S1.1. Historical fault data includes equipment operating status, discharge location, fault location, vibration signal characteristics and equipment internal structure information.

[0066] Specifically, equipment operating status: record the working conditions of the GIS equipment when the fault occurs, including voltage level, load conditions, ambient temperature, humidity and other external factors; automatically extract through the equipment background database, and ensure that the timestamp of the data accurately matches the equipment operation log.

[0067] Discharge location: The spatial location of each fault must be accurately marked, and the specific location of the discharge fault must be determined using the three-dimensional structural model of the GIS equipment (including the precise coordinates of components such as circuit breakers, busbars, and lightning arresters inside the equipment).

[0068] Vibration signal characteristics: Collect signal characteristics recorded by vibration sensors, including key signal characteristics such as amplitude, frequency, and duration. Such signal data can be processed through FFT (Fast Fourier Transform) to generate frequency domain feature maps and record key frequency components.

[0069] Equipment internal structure information: The internal structure status of the equipment (such as switch status, bus connection status, electrical connection between equipment, etc.) is recorded in detail each time a fault occurs to ensure that the fault location is not only based on the vibration signal, but also combined with the internal electrical topology of the equipment.

[0070] S1.2. Establishing a historical failure mode library includes the following steps:

[0071] According to the fault location, vibration signal characteristics and internal structure information of the equipment, the faults are divided into different categories; for each type of fault, the corresponding vibration signal characteristics and the internal structure information of the equipment are combined into a pattern vector; the pattern vectors formed by each type of fault are stored to form a fault pattern library.

[0072] S2. Collect vibration signals generated during the operation of GIS equipment in real time and perform preprocessing.

[0073] S2.1. Preprocessing includes signal filtering and signal denoising.

[0074] S2.1.1 Signal filtering refers to the use of a bandpass filter to limit the frequency range of the vibration signal and remove high-frequency noise and low-frequency interference.

[0075] S2.1.2, Signal denoising refers to using the wavelet denoising algorithm to perform discrete wavelet transform and layering of the signal, denoising the decomposition coefficients of each layer, and then reconstructing the signal.

[0076] S3. Calculate the energy distribution according to the preprocessed vibration signal, and dynamically adjust the threshold of discharge fault detection based on the energy distribution result to mark the potential fault signal.

[0077] S3.1. Use the short-time energy algorithm to calculate the short-time energy distribution of the preprocessed signal in different time periods. The expression is:

[0078]

[0079] Where E(n) is the short-time energy at time point n, x(nm) is the signal amplitude at time point nm, n is the current time point index, m is the offset of the time window, and M is the length of the time window;

[0080] The short-term energy in different time periods is plotted into an energy distribution diagram, and the energy distribution diagram is updated in real time according to the new vibration signal; in the updated energy distribution diagram, the initial threshold is set according to the noise level of the current environment.

[0081] Specifically, changes in noise levels will affect the adaptive threshold. When the noise level changes significantly, the detection threshold is dynamically adjusted based on the noise changes in the energy distribution diagram:

[0082] When the noise increases: If the environmental noise suddenly increases, the overall energy value in the energy distribution diagram will increase, and the detection threshold will be increased accordingly to avoid misjudging the noise fluctuation as a fault signal, ensuring that the false alarm rate can still be kept low in a noisy environment.

[0083] When the noise decreases: When the noise level decreases, the energy baseline in the energy distribution diagram decreases, and the detection threshold is lowered to ensure that weaker discharge fault signals can be detected.

[0084] S3.2. Combined with the energy distribution differences between normal operating signals and fault signals in the historical fault mode library, analyze the fault signals in the historical mode library and dynamically adjust the current discharge fault detection threshold; compare the energy distribution of the real-time vibration signal with the adjusted fault detection threshold, and when the energy of the real-time vibration signal exceeds the threshold, mark the current signal as a potential fault signal.

[0085] Specifically, if the energy of the real-time vibration signal is significantly higher than the set initial threshold, and the energy has a high match with the historical fault mode, the detection threshold is lowered to improve the sensitivity of fault detection.

[0086] If the energy fluctuation of the real-time signal is large, but the match with the historical fault mode is low, the threshold can be appropriately increased to avoid false alarms.

[0087] S4. Combining the marked potential fault signal with the three-dimensional structural characteristics of the GIS equipment to obtain the preliminary fault location result includes the following steps:

[0088] Based on the design drawings and CAD models of the GIS equipment, a complete three-dimensional structural model is established and the physical properties of each component are defined. According to the three-dimensional structural model, the propagation path of the vibration signal inside the GIS equipment is simulated, and a propagation path diagram is generated, marking the propagation time and attenuation of the signal in each component. The three-dimensional coordinates of the fault source are calculated using the triangulation positioning algorithm. The calculated three-dimensional coordinates are mapped to the three-dimensional structural model of the GIS equipment to determine the equipment component where the fault source is located, and obtain the preliminary fault positioning result.

[0089] It should be noted that by simulating the propagation path of the vibration signal inside the equipment through a three-dimensional structural model and generating a propagation path diagram, the propagation time and attenuation of the vibration signal in each component can be clearly displayed; the triangulation positioning algorithm compares the arrival time and intensity of the vibration signal at different locations, and uses spatial geometric relationships to deduce the specific location of the fault source, which not only improves the positioning accuracy, but also significantly shortens the time for fault location.

[0090] S5. Compare the preliminary fault location results with the fault mode library to generate the fault prediction results.

[0091] According to the preliminary fault location results, the historical fault data corresponding to the preliminary location results are retrieved from the fault pattern library, and each historical fault record is represented as a pattern vector; the current fault signal features are extracted from the marked potential fault signal to generate the pattern vector of the current fault signal; the dynamic time warping algorithm is used to calculate the matching degree between the current fault signal and the historical fault signal by finding the path that minimizes the difference between the time series. The expression is:

[0092]

[0093] DTW stands for Dynamic Time Warping, which is used to calculate the similarity between two time series. In particular, when the time series are stretched or misaligned in the time dimension, DTW (V hist ,V real ) represents the matching degree between the historical fault signal and the current fault signal, V hist Represents the pattern vector of historical faults, V real represents the mode vector of the current fault, i represents the time index of the historical fault signal, j represents the time index of the current fault signal, V hist (i) represents the mode vector of the historical fault signal at time point i, V real (j) represents the mode vector of the current fault signal at time point j, It means to find the path that minimizes the total difference between the two fault signals among all possible time-aligned paths;

[0094] According to the calculated matching results, the type of current fault and the development trend of the fault are predicted.

[0095] Specifically, the size of the matching value refers to the smaller the value of the matching degree, the higher the similarity between the current signal and a certain historical pattern.

[0096] Based on the historical pattern with the highest matching degree, predict the type of current fault and its possible development trend.

[0097] Specifically, fault type prediction means that if the current signal has the highest matching degree with a historical bus discharge fault pattern, the current fault will be automatically marked as a "bus discharge fault". In addition, a brief description will be provided based on the fault type, such as the severity of the fault, possible causes, etc.

[0098] Development trend prediction: Analyze the time series data in the matched historical fault mode to determine the development trend of the fault. This step relies on the fault evolution information recorded in the historical data. For example, some types of fault signals may gradually increase over time, and the potential development trend of the current fault can be predicted based on the energy growth pattern of historical faults. The trend prediction formula is:

[0099] Epred (t+Δt)=E real (t)+β·(E hist (t+Δt)-E hist (t))|;

[0100] Among them, E pred (t+Δt) represents the energy prediction value of the fault signal at the future time t+Δt, E real (t) represents the energy value of the current fault signal at time t, β represents the adaptation coefficient, which is used to adjust the influence of historical fault modes on the current fault trend prediction, E hist (t) represents the energy value of the historical fault signal at time t, E hist (t+Δt) represents the energy value of the historical fault signal at the future time t+Δt, Δt represents the predicted time step, and t represents the current time point.

[0101] S6. Automatically generating warning information according to the fault prediction result includes the following steps:

[0102] The predicted fault types are classified into minor faults, moderately serious faults and major faults; the predicted fault development trends are classified into slow deterioration, rapid deterioration and sharp signal deterioration; based on the classification results of the predicted fault types and development trends, the corresponding early warning notifications are automatically generated to determine the early warning level; the early warning level is classified into ordinary early warning, emergency early warning and serious early warning; according to the classified early warning level, the corresponding maintenance suggestions are generated.

[0103] Specifically, ordinary warnings: indicate minor faults; the development trend is slow deterioration, and there is no major impact in the short term; maintenance recommendations are regular inspections and signal monitoring. For example, if the busbar is slightly discharged, regular monitoring and insulation inspections are recommended.

[0104] Emergency warning: indicates a moderately serious fault; the development trend is rapid deterioration, which may affect operation in the short term; the maintenance recommendation is to immediately detect, monitor the signal in real time, and shut down if necessary. For example, if the circuit breaker arcs, it is recommended to immediately shut down and check the components.

[0105] Serious warning: indicates a major fault; may cause system shutdown; maintenance recommendations include immediate shutdown, emergency treatment, and system reconstruction. For example, if the main busbar is discharged, it is recommended to immediately shut down and replace the busbar.

[0106] This embodiment also provides a GIS equipment discharge fault rapid location system, including:

[0107] The pattern library module collects historical fault data of GIS equipment and establishes a historical fault pattern library. The signal acquisition module collects vibration signals generated during the operation of GIS equipment in real time and performs preprocessing. The energy analysis module calculates the energy distribution according to the preprocessed vibration signal, and dynamically adjusts the threshold of discharge fault detection based on the energy distribution result to mark the potential fault signal. The positioning module combines the marked potential fault signal with the three-dimensional structural characteristics of the GIS equipment to obtain the preliminary positioning result of the fault. The pattern matching module compares the preliminary positioning result of the fault with the fault pattern library to generate a fault prediction result. The early warning module automatically generates early warning information according to the fault prediction result.

[0108] This embodiment also provides a computer device, which is suitable for the case of a method for quickly locating a discharge fault in a GIS device, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the method for quickly locating a discharge fault in a GIS device as proposed in the above embodiment.

[0109] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0110] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for quickly locating a discharge fault of a GIS device as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (Static Random Access Memory, referred to as SRAM), an electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), an erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), a programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), a read-only memory (Read-Only Memory, referred to as ROM), a magnetic storage device, a flash memory, a disk or an optical disk.

[0111] In summary, the present invention can dynamically adjust the threshold of discharge fault detection according to the real-time noise level and historical fault mode by calculating the short-term energy distribution of the preprocessed vibration signal, thereby effectively reducing the occurrence of false alarms and missed alarms; combined with the three-dimensional structural characteristics of the GIS equipment, the triangulation positioning algorithm is used to accurately locate the spatial position of the fault, further improving the accuracy of fault detection; by comparing the preliminary fault positioning results with the historical fault mode library, the fault type and development trend prediction can be quickly generated, and the corresponding early warning information and maintenance suggestions can be automatically generated, reducing the power grid operation risks caused by equipment failures and improving the reliability and safety of the power system.

[0112] Example 2, referring to Table 1, is the second example of the present invention. To further verify the technical solution of the present invention, experimental simulation data of a method for quickly locating a discharge fault of a GIS device are provided.

[0113] The experiment selected two types of GIS equipment as test objects, and compared the traditional fault detection method with the fault location method of the present invention. One of the test objects was a type A GIS device, which used a traditional partial discharge detection method. The detection threshold of this method is a fixed value, and it does not combine the vibration signal of the equipment with the three-dimensional structure of the equipment for in-depth analysis. The other test object was a type B GIS device, which used the fault detection and location method of the present invention, specifically including: establishing a historical fault mode library, collecting vibration signals during equipment operation and preprocessing them, dynamically adjusting the threshold based on energy distribution, combining fault location with three-dimensional structure, and pattern matching based on historical data.

[0114] The details are shown in Table 1 below:

[0115] Table 1 Experimental data record table

[0116]

[0117]

[0118] It can be seen from the table that the fault location error of type A GIS equipment is relatively large, with an average location error of 27.3 cm, while the fault location error of type B GIS equipment is significantly reduced, with an average of 5.53 cm. This shows that the technology of the present invention, which combines the three-dimensional structural model with the triangulation positioning algorithm, is significantly superior to the traditional method in terms of fault location accuracy. By simulating the propagation path of the vibration signal in the equipment and combining it with the internal structure of the equipment for positioning, the present invention can quickly and accurately determine the specific location of the fault.

[0119] The warning response time of traditional A-type GIS equipment after fault detection is relatively long, averaging 15.0 seconds, while the response time of B-type GIS equipment is shortened to 7.63 seconds, almost half of that of A-type equipment. This is mainly attributed to the dynamic threshold adjustment algorithm introduced in the present invention, which makes fault detection more sensitive, can quickly identify fault signals and issue warnings in time, thereby effectively reducing the risk of fault spread.

[0120] The fault diagnosis accuracy of type A GIS equipment is relatively low, averaging 70.3%, and is easily disturbed by external noise. However, type B GIS equipment significantly improves the accuracy of fault diagnosis to more than 95% by combining the historical fault pattern library with the dynamic time warping algorithm (DTW) to match the fault signal pattern. Combining the energy distribution of the vibration signal with the historical fault data, the present invention can more accurately determine the fault type and development trend.

[0121] In summary, the experimental results show that the method for quickly locating discharge faults of GIS equipment of the present invention is significantly superior to traditional detection methods in terms of fault detection sensitivity, fault location accuracy, warning response speed, and fault diagnosis accuracy. The present invention successfully solves the problems of fixed fault detection threshold and inaccurate fault location in the prior art by introducing technologies such as dynamic threshold adjustment, three-dimensional structure analysis, and historical pattern matching, thereby improving the efficiency and reliability of GIS equipment fault detection and location.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for quickly locating a discharge fault in a GIS device, characterized in that: include, Collect historical failure data of GIS equipment and establish a historical failure mode library; Real-time collection of vibration signals generated during the operation of GIS equipment and pre-processing; Calculate the energy distribution according to the preprocessed vibration signal, and dynamically adjust the threshold of discharge fault detection based on the energy distribution result to mark the potential fault signal; Combine the marked potential fault signals with the three-dimensional structural characteristics of the GIS equipment to obtain the preliminary fault location results; Compare the preliminary fault location results with the fault mode library to generate fault prediction results; According to the fault prediction results, early warning information is automatically generated.

2. The method for quickly locating a discharge fault in GIS equipment according to claim 1, characterized in that: The historical fault data includes equipment operating status, discharge location, fault location, vibration signal characteristics and equipment internal structure information; The establishment of the historical failure mode library comprises the following steps: Classify faults into different categories based on fault location, vibration signal characteristics and internal structure information of the equipment; For each type of fault, the corresponding vibration signal features and the internal structure information of the equipment are combined into a pattern vector; The pattern vectors formed by each type of fault are stored to form a fault pattern library.

3. The method for quickly locating a discharge fault in GIS equipment according to claim 2, characterized in that: The preprocessing includes signal filtering and signal denoising; The signal filtering refers to limiting the frequency range of the vibration signal by using a bandpass filter to remove high-frequency noise and low-frequency interference; The signal denoising refers to using a wavelet denoising algorithm to perform discrete wavelet transform and layering of the vibration signal, denoising the decomposition coefficients of each layer, and then reconstructing the vibration signal.

4. The method for quickly locating a discharge fault in GIS equipment according to claim 3, characterized in that: The energy distribution is calculated according to the preprocessed vibration signal, and the threshold of the discharge fault detection is dynamically adjusted based on the energy distribution result. The potential fault signal is marked including the following steps: The short-time energy algorithm is used to calculate the short-time energy distribution of the preprocessed vibration signal in different time periods. The expression is: Where E(n) is the short-time energy at time point n, x(nm) is the signal amplitude at time point nm, n is the current time point index, m is the offset of the time window, and M is the length of the time window; The short-term energy of different time periods is plotted into an energy distribution diagram, and the energy distribution diagram is updated in real time according to the new vibration signal; In the updated energy distribution map, an initial threshold is set according to the noise level of the current environment; Combined with the energy distribution difference between normal operation signal and fault signal in the historical fault mode library, the fault signal in the historical mode library is analyzed to dynamically adjust the current discharge fault detection threshold; The energy distribution of the real-time vibration signal is compared with the adjusted fault detection threshold, and when the energy of the real-time vibration signal exceeds the threshold, the current real-time vibration signal is marked as a potential fault signal.

5. The method for quickly locating a discharge fault in GIS equipment according to claim 4, characterized in that: The marked potential fault signal is combined with the three-dimensional structural characteristics of the GIS equipment to obtain the preliminary fault location results, including the following steps: Based on the design drawings and CAD models of GIS equipment, build a complete 3D structural model and define the physical properties of each component; Based on the three-dimensional structural model, the propagation path of the vibration signal inside the GIS equipment is simulated, and a propagation path diagram is generated, marking the propagation time and attenuation of the signal in each component; Calculate the three-dimensional coordinates of the fault source using the triangulation positioning algorithm; The calculated three-dimensional coordinates are mapped to the three-dimensional structural model of the GIS equipment to determine the equipment component where the fault source is located and obtain the preliminary fault location result.

6. The method for quickly locating a discharge fault in GIS equipment according to claim 5, characterized in that: Compare the preliminary fault location results with the fault mode library to generate the fault prediction results. According to the preliminary fault location result, historical fault data corresponding to the preliminary location result is retrieved from the fault mode library, and each historical fault record is represented as a mode vector; Extracting current fault signal features from the marked potential fault signal and generating a pattern vector of the current fault signal; The dynamic time warping algorithm is used to calculate the matching degree between the current signal and the historical fault signal by finding the path that minimizes the difference between the time series. The expression is: Among them, DTW represents the dynamic time warping algorithm, DTW(V hist ,V real ) represents the matching degree between the historical fault signal and the current fault signal, V hist Represents the pattern vector of historical faults, V real represents the mode vector of the current fault signal, i represents the time index of the historical fault signal, j represents the time index of the current fault signal, V hist (i) represents the mode vector of the historical fault signal at time point i, V real (j) represents the mode vector of the current fault signal at time point j, It means to find the path that minimizes the total difference between the two fault signals among all possible time-aligned paths; According to the calculated matching results, the type of current fault and the development trend of the fault are predicted.

7. The method for quickly locating a discharge fault in GIS equipment according to claim 6, characterized in that: According to the fault prediction results, the automatic generation of warning information includes the following steps: The predicted fault types are classified into minor faults, moderately serious faults and major faults; The predicted fault development trends are divided into slow deterioration, rapid deterioration and sharp signal deterioration; Based on the classification results of the predicted fault types and development trends, the corresponding warning notifications are automatically generated, and the warning levels are determined as ordinary warning, emergency warning and severe warning; Generate corresponding maintenance suggestions based on the classified warning levels.

8. A GIS equipment discharge fault rapid location system, based on the GIS equipment discharge fault rapid location method according to any one of claims 1 to 7, characterized in that: include, The pattern library module collects historical fault data of GIS equipment and establishes a historical fault pattern library; The signal acquisition module collects the vibration signals generated during the operation of GIS equipment in real time and performs pre-processing; The energy analysis module calculates the energy distribution according to the preprocessed vibration signal, and dynamically adjusts the threshold of discharge fault detection based on the energy distribution result to mark the potential fault signal; The positioning module combines the marked potential fault signals with the three-dimensional structural characteristics of the GIS equipment to obtain the preliminary positioning results of the fault; The pattern matching module compares the preliminary fault location results with the fault pattern library to generate fault prediction results; The early warning module automatically generates early warning information based on the fault prediction results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for quickly locating a discharge fault in a GIS device according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for quickly locating a discharge fault in a GIS device according to any one of claims 1 to 7 are implemented.

Images