CN-121980323-A - Magnetic control type pole-mounted breaker mechanical fault diagnosis system based on coil current characteristics

CN121980323ACN 121980323 ACN121980323 ACN 121980323ACN-121980323-A

Abstract

The invention relates to the technical field of breaker fault diagnosis, and particularly discloses a magnetic control type pole-mounted breaker mechanical fault diagnosis system based on coil current characteristics, which comprises the following steps: the characteristic extraction and analysis module is used for acquiring coil current characteristic parameters of the magnetic control type pole-mounted circuit breaker, performing environment decoupling according to the association relation among the coil current characteristic parameters, the real-time voltage and the environment temperature, and extracting core characteristics. In the technical scheme of the invention, in the actual power grid operation, the coil current characteristics are firstly subjected to environmental decoupling by correlating the real-time voltage with the environmental temperature, so that the data pollution caused by the fluctuation of the external working condition is eliminated, and the core characteristics which purely reflect the mechanical physical state are obtained.

Inventors

Zheng Juyue
ZHOU QUAN
CAI JUNJIE
CHENG XIAOHUA
GONG MINGQIANG
ZHOU JIYI

Assignees

乾瑞电气有限公司

Dates

Publication Date: 20260505
Application Date: 20260407

Claims (10)

1. A magnetic control type pole-mounted breaker mechanical fault diagnosis system based on coil current characteristics, which is characterized by comprising: The characteristic extraction and analysis module is used for acquiring coil current characteristic parameters of the magnetic control type pole-mounted circuit breaker, performing environment decoupling according to the association relation among the coil current characteristic parameters, the real-time voltage and the environment temperature, and extracting core characteristics; The system comprises a core feature and equipment dynamic ageing coefficient, a fault diagnosis and trend prediction module, a verification process and a fault judgment module, wherein the core feature and equipment dynamic ageing coefficient are used for obtaining the fault occurrence probability through prediction; and the predictive maintenance decision engine module is used for generating a predictive maintenance decision scheme comprising maintenance time and a resource allocation scheme according to the comprehensive state conclusion of the equipment and preset constraint conditions.
2. The system of claim 1, further comprising a multi-source data acquisition and preprocessing module for: collecting original current, ambient temperature and real-time voltage data of a coil; sequentially performing low-pass filtering, cyclic redundancy check code checking and sliding window outlier filtering, and then performing data normalization processing to obtain preprocessed data, wherein the preprocessed data is used for the characteristic extraction and analysis module to obtain the coil current characteristic parameters; The data normalization processing process comprises the steps of subtracting the minimum value of corresponding class data from filtered single data, and dividing the difference by the difference between the maximum value and the minimum value of the corresponding class data to obtain normalized data.
3. The system of claim 1, wherein in the feature extraction and analysis module, the association relationship is a multiple linear relationship, and the process of performing environmental decoupling comprises: Summing the product of the real-time voltage and the first corresponding coefficient, the product of the ambient temperature and the second corresponding coefficient and the third corresponding coefficient, and calculating to obtain an estimated value of the coil current characteristic parameter; and subtracting the estimated value from the actually obtained coil current characteristic parameter, and extracting the core characteristic after eliminating the environmental interference.
4. The system according to claim 1, wherein the feature extraction and analysis module extracts the core features, in particular comprising: Calculating corrected instantaneous power, current change rate and temperature change rate containing total harmonic distortion, and taking the corrected instantaneous power, current change rate and temperature change rate as alternative characteristics; Calculating a pearson correlation coefficient between each candidate feature and a preset fault evaluation index; and screening out the alternative characteristics of which the absolute value of the pearson correlation coefficient is greater than or equal to a set correlation coefficient threshold value, and taking the alternative characteristics as the core characteristics.
5. The system of claim 1, wherein in the fault diagnosis and trend prediction module, the calculating process of the dynamic aging coefficient of the device includes: Acquiring a factory year correlation coefficient, an operation condition correlation coefficient, a maintenance frequency correlation coefficient and a health degree correlation coefficient of the magnetic control type pole-mounted circuit breaker; Multiplying the factory age correlation coefficient, the operation condition correlation coefficient, the maintenance frequency correlation coefficient and the health degree correlation coefficient by corresponding preset weight factors respectively, and then summing to obtain the equipment dynamic aging coefficient; and generating a correction coefficient based on the equipment dynamic aging coefficient, and adjusting the fault occurrence probability calculated preliminarily by using the correction coefficient.
6. The system of claim 1, wherein in the fault diagnosis and trend prediction module, the process of re-performing fault determination in combination with the dynamic threshold generated based on the historical fault assessment index, specifically comprises: Counting the historical fault evaluation indexes in a continuous set time window, and calculating to obtain a fault evaluation index mean value and a fault evaluation index standard deviation; adding the product of a preset adjustment coefficient and the standard deviation of the fault evaluation index to the fault evaluation index mean value, and calculating to generate the dynamic threshold; and when the value corresponding to the currently extracted core feature is larger than the dynamic threshold, judging that the diagnosis is fault-confirmed, and taking the diagnosis result as the comprehensive state conclusion of the equipment.
7. The system of claim 1, wherein the process of the predictive maintenance decision engine module generating a predictive maintenance decision scheme comprises: extracting fault risk assessment values, equipment importance level weights, operation and maintenance window periods and resource matching degrees as constraint conditions; constructing a multi-objective optimization function, wherein input variables of the multi-objective optimization function comprise fault risk reduction amount, operation and maintenance cost consumption amount and expected power failure time after scheme execution; substituting a plurality of sets of alternative maintenance schemes into the multi-objective optimization function to calculate a comprehensive score, and outputting a set of schemes with the highest comprehensive score as final predictive maintenance decision schemes.
8. The system of claim 1, wherein the system is deployed in a framework comprising an edge and cloud platform; The edge end is provided with a lightweight prediction model for executing real-time data acquisition, preprocessing and local preliminary fault occurrence probability calculation; The cloud platform is provided with a complete trend prediction model and the predictive maintenance decision engine module; And responding to the edge end to calculate that the occurrence probability of the fault is greater than or equal to the preset probability threshold, triggering the data of the edge end to be uploaded to the cloud platform in real time, and executing high-precision prediction and verification flow by the cloud platform.
9. The system of claim 5, wherein the fault diagnosis and trend prediction module is further configured with a weight reconstruction mechanism, and the specific implementation procedure of the weight reconstruction mechanism includes: Collecting the coil breaking current of the circuit breaker in real time during breaking action, and calculating to obtain a single breaking current peak value and a current square integral value in corresponding breaking time; Generating an extreme condition signal in response to the single off current peak value being greater than or equal to a set current break threshold or the increase in the current square integral value being greater than a set energy break threshold; After the extreme working condition signals are received, the calculation rule of the dynamic ageing coefficient of the equipment is adjusted, wherein the preset weight factor corresponding to the operation working condition related coefficient is set to be a first extreme value weight, the preset weight factor corresponding to the factory age related coefficient and the maintenance frequency related coefficient is set to be a second extreme value weight, and the dynamic ageing coefficient of the equipment is recalculated based on the adjusted extreme value weight; Wherein the first extremum weight value is greater than the second extremum weight value.
10. The system of claim 6, wherein the fault diagnosis and trend prediction module is further configured with a baseline migration mechanism, and wherein the specific implementation procedure of the baseline migration mechanism includes: Acquiring the real-time environmental temperature of the environment where the circuit breaker is located, and calculating the temperature change rate in unit time; Generating an environment isolation signal in response to the real-time ambient temperature being below a set phase transition critical temperature or the temperature change rate being greater than a set abrupt change rate threshold; suspending updating the dynamic threshold using the historical fault assessment index within a currently set time window during receipt of the environmental isolation signal; Retrieving a history operation interval of which the difference value between the history temperature and the real-time environment temperature is in a preset range from a full life cycle operation database module, and extracting a history mean value and a history standard deviation in the history operation interval; performing incremental compensation on the historical mean value by using the dynamic ageing coefficient of the equipment at the current moment, and calculating to generate a correction baseline; And adding the product of a preset proportional coefficient and the historical standard deviation to the correction base line, calculating to generate a phase change dynamic threshold, and replacing the original dynamic threshold by the phase change dynamic threshold to execute the fault judgment.

Description

Magnetic control type pole-mounted breaker mechanical fault diagnosis system based on coil current characteristics Technical Field The invention relates to the technical field of fault diagnosis of circuit breakers, in particular to a magnetic control type pole-mounted circuit breaker mechanical fault diagnosis system based on coil current characteristics. Background The existing mechanical fault diagnosis of the magnetic control type pole-mounted circuit breaker generally relies on collecting single coil current data, and directly inputting the original collected data into a fixed diagnosis model or simply comparing the original collected data with a preset static threshold value, so as to judge whether the equipment has fault risk and arrange a maintenance plan according to the fault risk. However, in actual outdoor operation, the coil current characteristics of the circuit breaker can generate normal physical offset due to power grid voltage fluctuation and ambient temperature rise and fall, and natural aging of equipment over time can also cause continuous change of operation references. If a single fixed judgment standard is adopted, the sensitivity of a diagnosis system is improved in order to prevent tiny mechanical hidden trouble in advance, and then parameter fluctuation caused by environment temperature and pressure interference and normal aging of equipment frequently breaks down a diagnosis threshold value, so that a large number of false early warning is caused, and operation and maintenance resources are wasted; if the judgment standard is relaxed to reduce the false alarm rate, the early actual mechanical abrasion or jamming fault is easily missed, and serious power failure accidents are caused. The lack of stripping means for environmental interference and dynamic secondary screening mechanism for suspected faults leads to the fact that the existing diagnosis mode cannot give consideration to timeliness and accuracy of early warning under actual complex working conditions. Disclosure of Invention The present invention aims to solve at least one of the technical problems in the related art to some extent. Therefore, the invention aims to provide a magnetic control type pole-mounted breaker mechanical fault diagnosis system based on coil current characteristics so as to improve the efficiency and the safety of power grid operation and maintenance. To achieve the above object, an embodiment of a first aspect of the present invention provides a magnetic control type pole-mounted circuit breaker mechanical fault diagnosis system based on coil current characteristics, including: The characteristic extraction and analysis module is used for acquiring coil current characteristic parameters of the magnetic control type pole-mounted circuit breaker, performing environment decoupling according to the association relation among the coil current characteristic parameters, the real-time voltage and the environment temperature, and extracting core characteristics; The system comprises a core feature and equipment dynamic ageing coefficient, a fault diagnosis and trend prediction module, a verification process and a fault judgment module, wherein the core feature and equipment dynamic ageing coefficient are used for obtaining the fault occurrence probability through prediction; and the predictive maintenance decision engine module is used for generating a predictive maintenance decision scheme comprising maintenance time and a resource allocation scheme according to the comprehensive state conclusion of the equipment and preset constraint conditions. To achieve the above object, a second aspect of the present invention provides a method for diagnosing mechanical faults of a magnetically controlled pole-mounted circuit breaker based on coil current characteristics, the method comprising: The method comprises the steps of obtaining coil current characteristic parameters of a magnetic control type pole-mounted circuit breaker, performing environment decoupling according to association relation among the coil current characteristic parameters, real-time voltage and environment temperature, extracting core characteristics, predicting to obtain fault occurrence probability based on the core characteristics and equipment dynamic aging coefficients, triggering a verification process in response to the fault occurrence probability being greater than or equal to a preset probability threshold, improving weight parameters of the core characteristics of corresponding fault types in a prediction model in the verification process, re-executing fault judgment by combining the dynamic threshold generated based on historical fault evaluation indexes to output equipment comprehensive state conclusions, and generating a predictive maintenance decision scheme comprising maintenance time and a resource allocation scheme according to the equipment comprehensive state conclusions and preset constraint conditions. To achieve the a