CN-119312251-B - Abnormality detection method, abnormality detection device, electronic device, and storage medium

CN119312251BCN 119312251 BCN119312251 BCN 119312251BCN-119312251-B

Abstract

The application discloses an abnormality detection method, an abnormality detection device, electronic equipment and a storage medium, wherein the abnormality detection method comprises the steps of collecting state measurement information of a current moment of an isolation disconnecting link and obtaining disconnecting link state information of a previous moment of the isolation disconnecting link; the method comprises the steps of predicting state prediction information of an isolation knife at the current moment according to state information of the knife at the previous moment of the isolation knife, determining the state information of the knife at the current moment of the isolation knife according to state measurement information at the current moment and state prediction information at the current moment, and generating abnormal alarm information and giving an alarm when the state information of the knife at the current moment is matched with a preset knife abnormal condition. The scheme of the application ensures the accuracy of the state determination of the isolation disconnecting link, thereby accurately detecting the position of the isolation disconnecting link, avoiding distribution faults in the distribution process of the distribution network caused by judgment errors of operation and maintenance personnel, and improving the safety of the operation of the isolation disconnecting link.

Inventors

CHEN MINGHUI
WEN ZHENXING
WANG LEI
ZHOU YUTAO
SONG RONGJIAN
WANG JUN
CHEN JIEHONG
LI CHONG
ZHONG GUOCHAO

Assignees

广东电网有限责任公司
广东电网有限责任公司惠州供电局

Dates

Publication Date: 20260505
Application Date: 20241016

Claims (7)

1. An abnormality detection method, comprising: Acquiring state measurement information of the current moment of an isolation knife and acquiring knife switch state information of the previous moment of the isolation knife, wherein the previous moment is the moment when the time difference between the previous moment and the current moment is the preset duration, and the state measurement information comprises temperature data of the isolation knife, distance data of the isolation knife, point cloud data of the isolation knife and image data of the isolation knife; predicting state prediction information of the isolation disconnecting link at the current moment according to disconnecting link state information of the isolation disconnecting link at the previous moment; Determining the state information of the disconnecting link at the current moment according to the state measurement information and the state prediction information at the current moment and the weight information corresponding to the state measurement information and the state prediction information at the current moment, wherein the weight information is determined by historical experience; When the state information of the disconnecting link at the current moment is matched with a preset disconnecting link abnormal condition, abnormal alarm information is generated and an alarm is given; The step of predicting state prediction information of the isolation knife at the current moment according to the state information of the knife at the previous moment of the isolation knife comprises the following steps: Determining state transition information of the isolation disconnecting link at the current moment according to disconnecting link state information at the previous moment of the isolation disconnecting link and a preset state transition equation, wherein the preset state transition equation is a state transition equation obtained after the state transition equation is pre-applied in a disconnecting link detection system based on a Kalman filtering algorithm; Determining state prediction information of the current moment according to the state transition information and a preset measurement noise matrix; wherein, the determining the state information of the disconnecting link at the current moment according to the state measurement information at the current moment and the state prediction information at the current moment includes: Acquiring an uncertainty predicted value of a previous moment, and determining an uncertainty predicted value of a current moment according to the uncertainty predicted value of the previous moment and a preset noise covariance matrix; determining a target gain according to the uncertainty predicted value of the current moment and the preset measurement noise matrix; Determining the state information of the disconnecting link at the current moment according to the state measurement information at the current moment, the state prediction information at the current moment and the target gain; the collecting the state measurement information of the isolating switch at the current moment comprises the following steps: the method comprises the steps of collecting temperature data of an isolation knife switch sent by an infrared detection device at the current moment, distance data of the isolation knife switch sent by an ultrasonic detection device at the current moment, point cloud data of the isolation knife switch sent by a laser detection device at the current moment and image data of the isolation knife switch sent by a visible light detection device at the current moment.
2. The method of claim 1, wherein the infrared detection device, the ultrasonic detection device, the laser detection device, and the visible light detection device are all mounted directly in front of the isolation knife switch.
3. The method of claim 1, wherein the temperature data of the isolation knife comprises a surface temperature of the isolation knife, a rate of change of the surface temperature of the isolation knife, and a hot spot area of the isolation knife; The distance data of the isolation disconnecting link comprise the distance between a fixed contact and a movable contact of the isolation disconnecting link, the change rate of the distance between the fixed contact and the movable contact and the surface reflection signal intensity of the isolation disconnecting link; The point cloud data of the isolation disconnecting link comprise three-dimensional point cloud data of the isolation disconnecting link, surface characteristics of the isolation disconnecting link, distance information of the isolation disconnecting link and the laser detection device and form information of the isolation disconnecting link; the image data of the isolation knife switch comprises visual image data of the isolation knife switch, edge characteristics of the isolation knife switch and color information of the isolation knife switch.
4. The method of claim 1, wherein the knife switch status information comprises at least one of position information of the isolation knife switch, temperature information of the isolation knife switch, and morphology information of the isolation knife switch, the preset knife switch abnormal condition comprises a mismatch of the isolation knife switch position and a preset position of the isolation knife switch, a temperature of the isolation knife switch being greater than or equal to a preset alarm temperature of the isolation knife switch, and a morphology of the isolation knife switch being mismatched with a preset morphology of the isolation knife switch; When the state information of the disconnecting link at the current moment is matched with a preset disconnecting link abnormal condition, abnormal alarm information is generated and an alarm is given, and the method comprises the following steps: When the position information of the isolation disconnecting link represents that after the isolation disconnecting link is closed or the isolation disconnecting link is opened, the position of the isolation disconnecting link is not matched with the preset position of the isolation disconnecting link, abnormal alarm information is generated according to the position information of the isolation disconnecting link, and an alarm is given; When the temperature information of the isolation disconnecting link represents that the temperature of the isolation disconnecting link is greater than or equal to the preset alarm temperature of the isolation disconnecting link, abnormal alarm information is generated and an alarm is given according to the temperature information of the isolation disconnecting link; And when the form information of the isolation disconnecting link represents that the form of the isolation disconnecting link is not matched with the preset form of the isolation disconnecting link, generating abnormal alarm information according to the form information of the isolation disconnecting link and giving an alarm.
5. An abnormality detection apparatus, comprising: The device comprises an acquisition module, a detection module and a detection module, wherein the acquisition module is used for acquiring state measurement information of the current moment of an isolation knife and acquiring knife state information of the previous moment of the isolation knife, wherein the previous moment is the moment when the time difference between the previous moment and the current moment is the preset duration, and the state measurement information comprises temperature data of the isolation knife, distance data of the isolation knife, point cloud data of the isolation knife and image data of the isolation knife; the prediction module is used for predicting state prediction information of the isolation disconnecting link at the current moment according to the disconnecting link state information at the previous moment of the isolation disconnecting link; The state determining module is used for determining the state information of the disconnecting link at the current moment according to the state measurement information at the current moment, the state prediction information at the current moment and the weight information corresponding to the state measurement information and the state prediction information at the current moment, wherein the weight information is determined by historical experience; The alarming module is used for generating abnormal alarming information and alarming when the state information of the disconnecting link at the current moment is matched with the preset disconnecting link abnormal condition; The prediction module is specifically used for determining state transition information of the isolation disconnecting link at the current moment according to disconnecting link state information at the previous moment of the isolation disconnecting link and a preset state transition equation, and determining state prediction information at the current moment according to the state transition information and a preset measurement noise matrix, wherein the preset state transition equation is a state transition equation obtained after the state transition equation is pre-applied in a disconnecting link detection system based on a Kalman filtering algorithm; the state determining module is specifically configured to obtain an uncertainty predicted value at a previous time, determine an uncertainty predicted value at a current time according to the uncertainty predicted value at the previous time and a preset noise covariance matrix, determine a target gain according to the uncertainty predicted value at the current time and the preset measurement noise matrix, and determine a disconnecting link state information at the current time of the isolating disconnecting link according to state measurement information at the current time, state predicted information at the current time and the target gain; the acquisition module is specifically used for acquiring temperature data of the isolation knife switch sent by the infrared detection device at the current moment, distance data of the isolation knife switch sent by the ultrasonic detection device at the current moment, point cloud data of the isolation knife switch sent by the laser detection device at the current moment and image data of the isolation knife switch sent by the visible light detection device at the current moment.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the anomaly detection method of any one of claims 1-4 when the program is executed by the processor.
7. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when executed by a processor, implements the abnormality detection method according to any one of claims 1 to 4.

Description

Abnormality detection method, abnormality detection device, electronic device, and storage medium Technical Field The present application relates to the field of high-voltage switch cabinets, and in particular, to an abnormality detection method, an abnormality detection device, an electronic device, and a storage medium. Background The high-voltage switch cabinet is an important component in a power distribution network system, and primary equipment inside the switch cabinet mainly comprises a bus, an isolation switch (simply called a switch), a circuit breaker, a current transformer and the like. When a power grid operation and maintenance person performs power failure or power transmission operation on the high-voltage switch cabinet, the position of the isolation disconnecting link needs to be checked, and whether the opening and closing of the isolation disconnecting link are in place is judged so as to ensure the safety of power failure or power transmission. For example, if the switch is not closed in place during switching on, namely the moving contact and the fixed contact of the switch are not contacted well, the contact resistance between the isolation switch contacts is greatly increased after the switch cabinet is powered on, abnormal heating between the isolation switch contacts is caused, the health of equipment is further threatened, and unnecessary power failure times are increased. At present, after an isolation disconnecting link is operated, the position and state inspection of the disconnecting link mainly depends on visual judgment of operation and maintenance personnel to determine whether opening and closing of the isolation disconnecting link are in place. However, since the space in the high-voltage switchgear is limited, the layout of the primary equipment inside the high-voltage switchgear is compact. Therefore, when operation and maintenance personnel observe, often, the problem such as poor vision appears judging the mistake to lead to distribution trouble to appear in the distribution network distribution process, increase the manpower and materials that consume in the distribution process. Disclosure of Invention The application provides an abnormality detection method, an abnormality detection device, electronic equipment and a storage medium, which are used for solving the problems that in the prior art, due to limited space in a high-voltage switch cabinet, the layout of primary equipment in the high-voltage switch cabinet is compact, and judgment errors often occur due to poor vision and other problems when operation and maintenance personnel observe, so that distribution faults occur in the distribution process of a distribution network, and manpower and material resources consumed in the distribution process are increased. In a first aspect, the present application provides an abnormality detection method, the method comprising: Acquiring state measurement information of the current moment of an isolation disconnecting link, and acquiring disconnecting link state information of the previous moment of the isolation disconnecting link, wherein the previous moment is a moment before the current moment and the time difference between the previous moment and the current moment is a preset duration; predicting state prediction information of the isolation disconnecting link at the current moment according to disconnecting link state information of the isolation disconnecting link at the previous moment; Determining the state information of the disconnecting link at the current moment according to the state measurement information at the current moment and the state prediction information at the current moment; And when the state information of the disconnecting link at the current moment is matched with the preset disconnecting link abnormal condition, generating abnormal alarm information and giving an alarm. In a second aspect, the present application provides an abnormality detection apparatus including: The device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring state measurement information of the current moment of an isolation disconnecting link and acquiring disconnecting link state information of the previous moment of the isolation disconnecting link, wherein the previous moment is the moment before the current moment and the moment when the time difference between the previous moment and the current moment is the preset duration; the prediction module is used for predicting state prediction information of the isolation disconnecting link at the current moment according to the disconnecting link state information at the previous moment of the isolation disconnecting link; The state determining module is used for determining the state information of the disconnecting link at the current moment according to the state measurement information at the current moment and the state prediction informa