GIS Partial Discharge Diagnosis Using Sensor Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for detecting partial discharge in Gas Insulated Switchgear (GIS) are limited by worker experience, lead to inaccurate type identification due to variations in GIS models and sensor placements, and are prone to false detection from external interference, resulting in poor model universality and lengthy training periods.
Innovation Solution
A GIS partial discharge diagnosing method using a network of sensor modules with wireless communication, where each module determines its position relative to others, and the monitoring host processes ultra-high frequency signals and position data to train a predictive model adaptive to different GIS equipment and sensor layouts, eliminating external interference.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional worker-based detection methods are used, then operational flexibility is maintained, but detection accuracy and reliability deteriorate due to limitations in worker experience
Solution Approach 1:
The system employs automated algorithms that self-adjust to different GIS models and sensor placements without requiring manual reconfiguration by workers. The diagnosing system autonomously adapts to varying conditions, eliminating dependence on worker experience while maintaining operational simplicity
Solution Approach 2:
The patent replaces the mechanical/manual detection approach with an automated electronic system using sensors, signal processing circuits, and computer algorithms. This substitution transforms the detection process from experience-based manual operation to automated electronic analysis, significantly improving accuracy
2Duration of action of stationary object
If sensors are installed for online detection, then continuous monitoring capability is improved, but model universality deteriorates due to variations in GIS models and sensor placements
Solution Approach 1:
The system dynamically adapts to different GIS models and sensor placements through automated algorithm adjustment. Rather than requiring fixed model configurations, the system continuously learns and adapts its diagnosing parameters based on the specific installation conditions, enabling both continuous monitoring and model versatility
Solution Approach 2:
The patent changes the approach from fixed parameter models to adaptive parameter adjustment. The system automatically modifies its diagnosing parameters based on detected signal characteristics, GIS model variations, and sensor placement differences, enabling universal application across different configurations
3Ease of operation
If classical spectrum comparison methods are used, then detection simplicity is maintained, but detection accuracy deteriorates due to mismatch between detected and classical discharge spectra
Solution Approach 1:
The system incorporates feedback mechanisms where the detected discharge spectra are continuously compared and used to refine the diagnosing model. The system learns from actual detections and adjusts its reference spectra accordingly, maintaining operational simplicity while improving accuracy through iterative refinement
Solution Approach 2:
The patent performs preliminary signal processing and feature extraction before comparison, preparing the detected spectra in an optimized format. This preliminary processing enhances the effectiveness of subsequent comparison operations, maintaining simplicity while improving matching accuracy
4Reliability
If external interference signals are not filtered, then signal processing simplicity is maintained, but detection reliability deteriorates due to false detection from external discharge signals
Solution Approach 1:
The system extracts and isolates the characteristic features of genuine partial discharge signals from the complex background of external interference. By focusing on specific diagnostic features rather than processing all signal components, the system achieves reliable detection without excessive processing complexity
Solution Approach 2:
The patent transforms external interference signals from harmful factors into useful diagnostic information. By analyzing the characteristics of interfering signals, the system learns to distinguish them from genuine partial discharge, converting potential false positives into opportunities for improved discrimination
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The method improves the accuracy and universality of partial discharge detection, reduces training time, and enhances the model's applicability across different GIS setups, allowing for direct application in new substations with minimal retraining.
Implementation Method 1
The ultra high frequency method detects the partial discharge signal by receiving an UHF electromagnetic wave signal in a range of 300-3000 MHz generated by the PD through an antenna
Implementation Method 2
each of the sensor modules obtains a distance from other sensor modules through a wireless communication time
Data Source
AI summary
A GIS partial discharge diagnosing method, a model training method, a device and a system are disclosed. Sensor modules are in communication with each other, so that sensor network position distribution data of each sensor module in a wireless transmission network can be determined. In a training process of a partial discharge diagnosing model, a spatial-temporal feature of the partial discharge is introduced, so that the trained partial discharge diagnosing model is adaptive to different GIS equipment and different sensors layout solutions, and has better model universality and applicability, thus greatly saving a training time of the model and expediting the deployment of the partial discharge diagnosing model. Moreover, the model trained in the present disclosure accounts for the relationship between the position where partial discharge occurs and the sensor network position distribution.