CN-121721483-B - Intelligent diagnosis method and system for drop-out high-voltage fuse

CN121721483BCN 121721483 BCN121721483 BCN 121721483BCN-121721483-B

Abstract

The invention relates to the technical field of intelligent diagnosis, in particular to an intelligent diagnosis method and system for a drop-out high-voltage fuse, comprising the steps of identifying a transformer gear based on collected electrical data to obtain the transformer gear; the method comprises the steps of verifying a transformer gear to obtain a verified transformer gear, extracting fault diagnosis characteristics of a fuse based on the verified transformer gear and electrical data, and judging the fault according to the fault diagnosis characteristics and a preset fault diagnosis model to obtain a diagnosis result of the fuse. According to the invention, through collecting the electrical data of the high-voltage side and the low-voltage side of the transformer in real time and carrying out fault feature extraction after working condition correction by combining the gear of the transformer, the precise identification of the state of the fuse is realized, and the fault discrimination accuracy is improved.

Inventors

BAI XIAOCHUN
JING YAN
LIU XINJIANG
WANG CHENXI
WU ZIHAO

Assignees

国网(西安)环保技术中心有限公司
国网陕西省电力有限公司电力科学研究院

Dates

Publication Date: 20260508
Application Date: 20260225

Claims (6)

1. The intelligent diagnosis method for the drop-out high-voltage fuse is characterized in that the drop-out high-voltage fuse is connected with a three-phase electric energy meter of a transformer, and the method comprises the following steps: based on the collected electrical data, identifying the transformer gear to obtain the transformer gear; Verifying the transformer gear to obtain a verified transformer gear; Extracting a fuse fault diagnosis feature based on the verified transformer gear and the electrical data; performing fault discrimination according to the fault diagnosis characteristics and a preset fault diagnosis model to obtain a diagnosis result of the fuse; the step of identifying the transformer gear based on the collected electrical data to obtain the transformer gear comprises the following steps: Collecting high-voltage side three-phase voltage and high-voltage side three-phase current data of a transformer, and collecting low-voltage side three-phase voltage and low-voltage side three-phase current data of a transformer three-phase electric energy meter; Filtering the high-voltage side three-phase voltage and the low-voltage side three-phase voltage, and calculating to obtain fundamental wave effective values of the high-voltage side and the low-voltage side; According to the fundamental wave effective values of the high-voltage side and the low-voltage side, calculating the actual measurement transformation ratio of the transformer; identifying the gear of the transformer according to the actually measured transformation ratio of the transformer to obtain the gear of the transformer; verifying the transformer gear to obtain a verified transformer gear, including: acquiring actual measurement transformation ratios at a plurality of moments in a preset time window; carrying out statistical analysis on the actual measured transformation ratios at the multiple moments to obtain stable values of the actual measured transformation ratios; carrying out consistency verification on the stable value of the actually measured transformation ratio and the theoretical transformation ratio corresponding to the identified transformer gear to obtain the verified transformer gear; based on the verified transformer gear and electrical data, extracting the fuse fault diagnosis feature comprises: based on the verified transformer gear, working condition correction is carried out on the electric data to obtain gear corrected electric data, and the method comprises the following steps: Converting the collected low-voltage side three-phase voltage and low-voltage side three-phase current data into high-voltage side equivalent voltage and equivalent current according to the actual measured transformation ratio; Taking the equivalent voltage and the equivalent current as electric data after gear correction; And extracting fault diagnosis characteristics of the fuse based on the electrical data before correction and the electrical data after gear correction.
2. The intelligent diagnosis method of the drop-out high voltage fuse according to claim 1, wherein the identifying the transformer gear according to the measured transformation ratio of the transformer to obtain the transformer gear comprises: generating theoretical transformation ratios corresponding to all gears according to the rated transformation ratio, the tapping range and the tapping progression of the transformer; And comparing the actual measured transformation ratio with a theoretical transformation ratio corresponding to each gear, and determining the gear corresponding to the actual measured transformation ratio as the identified transformer gear.
3. The intelligent diagnosis method of the drop-out high voltage fuse according to claim 2, wherein the step of performing consistency check on the stable value of the measured transformation ratio and the theoretical transformation ratio corresponding to the identified transformer gear to obtain a verified transformer gear comprises the steps of: When the deviation between the stable value of the actually measured transformation ratio and the corresponding theoretical transformation ratio is smaller than or equal to a preset deviation threshold value, determining that the identified transformer gear is the verified transformer gear; And when the deviation between the stable value of the actual measured transformation ratio and the corresponding theoretical transformation ratio is larger than a preset deviation threshold, carrying out gear identification again until the deviation between the stable value of the actual measured transformation ratio and the corresponding theoretical transformation ratio is smaller than or equal to the preset deviation threshold.
4. The intelligent diagnosis method of drop-out high voltage fuse according to claim 3, wherein the preset fault diagnosis model is based on LSTM/GRU network, inputs are fault diagnosis features, and outputs are health score, fault risk index and determined fuse state of the fuse.
5. The intelligent diagnosis method of a drop-out high voltage fuse according to claim 4, wherein the performing fault discrimination according to the fault diagnosis feature and a preset fault diagnosis model to obtain a diagnosis result of the fuse comprises: inputting the fault diagnosis characteristic into the preset fault diagnosis model; Performing time sequence prediction and abnormality detection on fault diagnosis features based on the preset fault diagnosis model, and calculating health scores and fault risk indexes of the fuses; Judging the current state of the fuse according to the health score and the fault risk index, wherein the state of the fuse comprises normal closing, fault falling, error falling or non-falling faults; and outputting the health score, the fault risk index and the determined current state of the fuse to obtain a diagnosis result of the fuse.
6. The utility model provides a drop-out high voltage fuse intelligent diagnosis system which characterized in that, drop-out high voltage fuse is connected with transformer three-phase electric energy meter, the system includes: The identification module is used for identifying the gear of the transformer based on the collected electrical data to obtain the gear of the transformer; the verification module is used for verifying the transformer gear to obtain a verified transformer gear; The extraction module is used for extracting the fault diagnosis characteristics of the fuse based on the validated transformer gear and the electrical data; the judging module is used for judging the faults according to the fault diagnosis characteristics and a preset fault diagnosis model to obtain the diagnosis result of the fuse; the step of identifying the transformer gear based on the collected electrical data to obtain the transformer gear comprises the following steps: Collecting high-voltage side three-phase voltage and high-voltage side three-phase current data of a transformer, and collecting low-voltage side three-phase voltage and low-voltage side three-phase current data of a transformer three-phase electric energy meter; Filtering the high-voltage side three-phase voltage and the low-voltage side three-phase voltage, and calculating to obtain fundamental wave effective values of the high-voltage side and the low-voltage side; According to the fundamental wave effective values of the high-voltage side and the low-voltage side, calculating the actual measurement transformation ratio of the transformer; identifying the gear of the transformer according to the actually measured transformation ratio of the transformer to obtain the gear of the transformer; verifying the transformer gear to obtain a verified transformer gear, including: acquiring actual measurement transformation ratios at a plurality of moments in a preset time window; carrying out statistical analysis on the actual measured transformation ratios at the multiple moments to obtain stable values of the actual measured transformation ratios; carrying out consistency verification on the stable value of the actually measured transformation ratio and the theoretical transformation ratio corresponding to the identified transformer gear to obtain the verified transformer gear; based on the verified transformer gear and electrical data, extracting the fuse fault diagnosis feature comprises: based on the verified transformer gear, working condition correction is carried out on the electric data to obtain gear corrected electric data, and the method comprises the following steps: Converting the collected low-voltage side three-phase voltage and low-voltage side three-phase current data into high-voltage side equivalent voltage and equivalent current according to the actual measured transformation ratio; Taking the equivalent voltage and the equivalent current as electric data after gear correction; And extracting fault diagnosis characteristics of the fuse based on the electrical data before correction and the electrical data after gear correction.

Description

Intelligent diagnosis method and system for drop-out high-voltage fuse Technical Field The invention relates to the technical field of intelligent diagnosis, in particular to an intelligent diagnosis method and system for a drop-out high-voltage fuse. Background In a high-voltage distribution system, a drop-out high-voltage fuse is used as an important protection element and is widely applied to line overload, short circuit and fault isolation protection. However, the existing fuse operation monitoring method mainly relies on manual inspection or simple open-close state detection, and has the problems of delayed response, inaccurate diagnosis, lack of early warning capability and the like. The traditional method is difficult to realize real-time monitoring of the state of the fuse and analysis of fault reasons. For example, tripping of fuses may be caused by various causes such as short circuits, overloads, aging, or mechanical defects, but existing systems generally can only record closing or tripping events, cannot identify specific fault types, and cannot early warn of potential risks in advance. With the development of smart grids and internet of things, fuse state monitoring and fault diagnosis using electrical data are possible. However, how to improve the fault discrimination accuracy remains a difficult problem. Disclosure of Invention Object of the invention The invention aims to provide an intelligent diagnosis method and system for a drop-out high-voltage fuse, which are used for accurately identifying the state of the fuse and improving the fault discrimination accuracy by collecting the electrical data of the high-voltage side and the low-voltage side of a transformer in real time and carrying out fault feature extraction after working condition correction by combining a transformer gear. (II) technical scheme In order to solve the problems, the invention provides an intelligent diagnosis method for a drop-out high-voltage fuse, wherein the drop-out high-voltage fuse is connected with a transformer three-phase electric energy meter, and the method comprises the following steps: based on the collected electrical data, identifying the transformer gear to obtain the transformer gear; Verifying the transformer gear to obtain a verified transformer gear; Extracting a fuse fault diagnosis feature based on the verified transformer gear and the electrical data; and carrying out fault discrimination according to the fault diagnosis characteristics and a preset fault diagnosis model to obtain a diagnosis result of the fuse. In another aspect of the present invention, preferably, the identifying the transformer gear based on the collected electrical data, to obtain the transformer gear includes: Collecting high-voltage side three-phase voltage and high-voltage side three-phase current data of a transformer, and collecting low-voltage side three-phase voltage and low-voltage side three-phase current data of a transformer three-phase electric energy meter; Filtering the high-voltage side three-phase voltage and the low-voltage side three-phase voltage, and calculating to obtain fundamental wave effective values of the high-voltage side and the low-voltage side; According to the fundamental wave effective values of the high-voltage side and the low-voltage side, calculating the actual measurement transformation ratio of the transformer; and identifying the gear of the transformer according to the actually measured transformation ratio of the transformer to obtain the gear of the transformer. In another aspect of the present invention, preferably, the identifying the transformer gear according to the measured transformation ratio of the transformer to obtain the transformer gear includes: generating theoretical transformation ratios corresponding to all gears according to the rated transformation ratio, the tapping range and the tapping progression of the transformer; And comparing the actual measured transformation ratio with a theoretical transformation ratio corresponding to each gear, and determining the gear corresponding to the actual measured transformation ratio as the identified transformer gear. In another aspect of the present invention, preferably, the verifying the transformer gear to obtain a verified transformer gear includes: acquiring actual measurement transformation ratios at a plurality of moments in a preset time window; carrying out statistical analysis on the actual measured transformation ratios at the multiple moments to obtain stable values of the actual measured transformation ratios; and carrying out consistency check on the stable value of the actually measured transformation ratio and the theoretical transformation ratio corresponding to the identified transformer gear to obtain the verified transformer gear. In another aspect of the present invention, preferably, the performing consistency verification on the stable value of the measured transformation ratio and the theoretical