State monitoring method of high-voltage switch cabinet

Abstract

The invention discloses a state monitoring method of a high-voltage switch cabinet, which comprises a sensor setting step, a data acquisition step, a state identification step and a state analysis step, can improve the accuracy and efficiency of state monitoring of the high-voltage switch cabinet, reduces the influence of faults on the stability and safe operation of a power system, reduces the maintenance cost, and improves the reliability of the high-voltage switch cabinet. Meanwhile, the stability of an electric power system and the satisfaction degree of a user are also improved; according to the method, the key indexes and parameters are determined by analyzing the fault characteristics of the high-voltage switch cabinet, fault early warning of the high-voltage switch cabinet in the operation process can be effectively achieved, early warning information is reported to maintenance personnel in time, the maintenance cost of the high-voltage switch cabinet is reduced through application of the early warning monitoring method, and the maintenance efficiency of the high-voltage switch cabinet is improved. And meanwhile, the shutdown maintenance time caused by faults is effectively shortened.

Description

Technical Field

[0001] The invention relates to high-voltage switch cabinet technology, and in particular to a state monitoring method for a high-voltage switch cabinet. Background Art

[0002] As one of the important equipment in the power system, high-voltage switchgear plays a key role in protecting and controlling the normal operation of the power system. However, due to the influence of long-term use and environmental factors, high-voltage switchgear has various types of faults, such as mechanical faults, electrical faults and other common faults. These faults have a negative impact on the stability and safe operation of the power system, and also increase maintenance costs.

[0003] As the high-voltage switchgear is in a state of long-term operation and is affected by the increasing load of the coal preparation plant and the harsh working environment, the electrical connection parts of high-voltage equipment such as circuit breakers and disconnectors in the switchgear are very likely to age and be damaged due to excessive temperature rise, collision and extrusion, resulting in equipment leakage, short circuit, failure of circuit breakers to open and close normally, and other faults, seriously affecting the production safety and efficiency of the coal preparation plant.

[0004] At present, the existing monitoring methods for the status monitoring of high-voltage switchgear mainly rely on manual inspection and experience judgment. Manual inspection has many subjective factors and inaccurate diagnosis results, which not only wastes manpower and material resources, but also leads to missed detection and false detection. Although infrared diagnosis can determine whether a fault exists by detecting the surface temperature of the high-voltage switchgear, it can only detect the surface and cannot fully understand the internal fault situation. Summary of the invention

[0005] The present invention provides a state monitoring method for a high-voltage switch cabinet, which is used to solve the problem that the existing state monitoring of a high-voltage switch cabinet mainly relies on manual inspection and the monitoring is not comprehensive.

[0006] In order to solve the above technical problems, the present invention discloses the following technical solutions: The present invention provides a state monitoring method for a high-voltage switch cabinet, comprising a sensor setting step, a data acquisition step, a state identification step and a state analysis step.

[0007] The sensor setting step is used to obtain the parameters of the high-voltage switchgear, and according to the obtained parameters, corresponding sensors are set for the parameters that need to be monitored; the data acquisition step is used to obtain the information collected by the sensor, extract the feature points in the information, and match the feature points with the known state pattern; the state recognition step is to use machine learning to identify the operating state of the high-voltage switchgear through feature points through training models; the state analysis step is to determine whether there is any abnormality in the operation of the high-voltage switchgear based on the acquired operating state of the high-voltage switchgear, and if there is any abnormality, warn of the abnormal situation.

[0008] Furthermore, the parameters include the current and voltage of the high-voltage switch cabinet and the temperature and humidity inside the high-voltage switch cabinet.

[0009] Furthermore, the data acquisition step includes an image acquisition step, a feature extraction step and a training step.

[0010] The image acquisition step is to obtain the appearance image of the high-voltage switch cabinet by setting a camera, and save the acquired image as digital information; the feature extraction step is to use a feature extraction algorithm to extract the iconic feature information of the electrical fault in the digital information; the training step is to use a machine learning algorithm to train and classify the fault features and accurately detect different types of faults.

[0011] Furthermore, the state identification step includes a data acquisition step and a data analysis step.

[0012] The data acquisition step is used to collect historical data of the high-voltage switchgear, and the historical data includes normal operating status data and known fault data to obtain a fault threshold range; the data analysis step is used to determine whether the parameters of the high-voltage switchgear acquired in real time are within the fault threshold range. If so, it indicates that there is no abnormality in the high-voltage switchgear. If not, execute the next step.

[0013] Compared with the prior art, the present invention has at least the following technical effects: The present invention can improve the accuracy and efficiency of high-voltage switchgear status monitoring, reduce the impact of faults on the stability and safe operation of the power system, and reduce maintenance costs by designing the status monitoring method of the high-voltage switchgear, while also improving the stability of the power system and user satisfaction; the present invention can effectively realize fault early warning of the high-voltage switchgear during operation by analyzing the characteristics of the high-voltage switchgear fault and determining key indicators and parameters, and promptly report the early warning information to maintenance personnel, so that the use of the early warning monitoring method reduces the maintenance cost of the high-voltage switchgear, and also effectively reduces the downtime for maintenance caused by faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The technical solution of the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0015] Figure 1 A flow chart of a method for monitoring the status of a high-voltage switchgear according to an embodiment of the present invention; Figure 2 A flowchart of the data collection steps described in an embodiment of the present invention; Figure 3 A flowchart of the state identification steps according to an embodiment of the present invention; DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0017] The present invention provides a state monitoring method for a high-voltage switch cabinet, comprising step S1) a sensor setting step, step S2) a data acquisition step, step S3) a state identification step and step S4) a state analysis step.

[0018] Step S1) sensor setting step, obtaining parameters of the high-voltage switch cabinet, and setting corresponding sensors for parameters to be monitored according to the obtained parameters, wherein the parameters include the current and voltage of the high-voltage switch cabinet and the temperature and humidity inside the high-voltage switch cabinet.

[0019] Step S2) Data collection step, obtaining information collected by the sensor, extracting feature points in the information, and matching the feature points with known state patterns.

[0020] like Figure 2 As shown, step S2) data acquisition step includes step S21) image acquisition step, step S22) feature extraction step and step S23) training step.

[0021] Step S21) An image acquisition step is to acquire an appearance image of the high-voltage switch cabinet by setting a camera, and save the acquired image as digital information.

[0022] Step S22) A feature extraction step, using a feature extraction algorithm to extract the characteristic feature information of the electrical fault in the digital information.

[0023] Step S23) training step, using machine learning algorithm to train and classify fault features, and accurately detect different types of faults.

[0024] Step S3) is a state recognition step, which uses machine learning to train a model to recognize the operating state of the high-voltage switchgear through feature points.

[0025] like Figure 3 As shown, step S3) the state identification step includes step S31) the data acquisition step and step S32) the data analysis step.

[0026] Step S31) data acquisition step, collecting historical data of the high-voltage switch cabinet, the historical data including normal operating status data and known fault data, and obtaining a fault threshold range; Step S32) Data analysis step, determining whether the parameters of the high-voltage switch cabinet acquired in real time are within the fault threshold range, if so, indicating that the high-voltage switch cabinet has no abnormality, if not, executing the next step.

[0027] Step S4) is a state analysis step, in which, based on the acquired operating state of the high-voltage switch cabinet, it is determined whether there is any abnormality in the operation of the high-voltage switch cabinet. If there is any abnormality, an early warning is issued for the abnormal situation. When an early warning is issued, the fault information is sent to the mobile phone terminal of the maintenance personnel, and the maintenance personnel inspect the high-voltage switch cabinet according to the fault information.

[0028] The advantage of the present application is that a method for monitoring the status of a high-voltage switch cabinet is provided, which can not only improve the accuracy and efficiency of the status monitoring of the high-voltage switch cabinet, reduce the impact of faults on the stability and safe operation of the power system, and reduce maintenance costs, but also improve the stability of the power system and user satisfaction; the present invention analyzes the characteristics of the high-voltage switch cabinet faults, determines key indicators and parameters, and can effectively realize fault warning of the high-voltage switch cabinet during operation, and promptly reports the warning information to maintenance personnel, so that the use of the early warning monitoring method reduces the maintenance cost of the high-voltage switch cabinet, and also effectively reduces the downtime for maintenance caused by faults.

[0029] The above is a detailed introduction to a state monitoring method for a high-voltage switchgear provided in an embodiment of the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the technical scheme and core idea of ​​the present invention. Ordinary technicians in this field should understand that they can still modify the technical schemes recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and these modifications or replacements do not make the essence of the corresponding technical scheme deviate from the scope of the technical scheme of the embodiments of the present invention.

Claims

1. A method for monitoring the state of a high-voltage switch cabinet, characterized in that: include: The sensor setting step is to obtain the parameters of the high-voltage switch cabinet, and according to the obtained parameters, set the corresponding sensors for the parameters to be monitored; A data collection step, obtaining information collected by the sensor, extracting feature points in the information, and matching the feature points with known state patterns; In the state recognition step, machine learning is used to train the model to identify the operating state of the high-voltage switchgear through feature points; as well as The state analysis step determines whether there is any abnormality in the operation of the high-voltage switchgear according to the acquired operating state of the high-voltage switchgear. If there is any abnormality, an early warning is issued for the abnormal situation.

2. The state monitoring method of high-voltage switchgear according to claim 1, characterized in that: The parameters include the current and voltage of the high-voltage switch cabinet and the temperature and humidity inside the high-voltage switch cabinet.

3. The state monitoring method of high-voltage switchgear according to claim 1, characterized in that: The data collection step comprises: An image acquisition step is to acquire an appearance image of the high-voltage switch cabinet by setting a camera, and save the acquired image as digital information; a feature extraction step, using a feature extraction algorithm to extract characteristic feature information of the electrical fault in the digital information; and In the training step, a machine learning algorithm is used to train and classify fault features and accurately detect different types of faults.

4. The state monitoring method of high-voltage switchgear according to claim 1, characterized in that: The state identification step comprises: A data acquisition step, collecting historical data of the high-voltage switch cabinet, wherein the historical data includes normal operating status data and known fault data, and obtaining a fault threshold range; and The data analysis step determines whether the parameters of the high-voltage switch cabinet obtained in real time are within the fault threshold range. If so, it indicates that there is no abnormality in the high-voltage switch cabinet. If not, execute the next step.

Images