Partial Discharge Detection Using Phi-Q-N Noise Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing partial discharge determination methods struggle to accurately distinguish partial discharge signals from environmental noise, leading to incorrect determinations due to the superimposition of noise and discharge characteristics, especially when the amplitude of the discharge pulse is lower than the noise amplitude.
Innovation Solution
A partial discharge determination apparatus and method that utilizes a partial discharge measurement unit, noise processing unit, φ-q-n data generation, learning model generation, and determination unit to remove or reduce noise based on statistical information and perform machine learning on φ-q-n data to accurately determine partial discharge.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple types of sensors (UHF, HF, AE, temperature, humidity) are deployed for comprehensive PD detection, then detection coverage and reliability are improved, but device complexity and cost increase
Solution Approach 1:
The patent divides the PD detection system into multiple independent sensor modules, each responsible for detecting specific PD characteristics through different physical mechanisms (UHF for electromagnetic waves, HF for partial discharge signals, AE for acoustic emissions). This segmentation allows comprehensive detection while maintaining modular architecture that simplifies system integration and maintenance.
Solution Approach 2:
The patent creates a multi-functional sensor system where different sensor types work together to detect various aspects of partial discharge. The UHF sensor detects electromagnetic waves, the HF sensor detects partial discharge signals, the AE sensor detects acoustic emissions, and temperature/humidity sensors monitor environmental conditions. This universal approach enables a single integrated system to perform multiple detection functions simultaneously.
2Measurement precision
If complex signal processing algorithms are used to distinguish PD signals from noise, then measurement precision is improved, but processing time and computational resources increase
Solution Approach 1:
The patent applies preliminary signal processing techniques including bandpass filtering and noise thresholding before full analysis. By pre-processing signals to remove obvious noise and identify candidate PD signals early in the processing chain, the system reduces the computational burden on subsequent complex algorithms and accelerates overall processing time.
Solution Approach 2:
The patent implements feedback mechanisms where detection results from one sensor type inform the processing of other sensor data. For example, when the UHF sensor detects a potential PD signal, the system adjusts processing parameters for HF and AE sensors to focus on relevant time windows, reducing unnecessary processing and improving both precision and speed through coordinated feedback.
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
Enables highly reliable partial discharge determination by effectively removing noise components, allowing for precise identification of partial discharge events even in noisy environments.
Implementation Method 1
a first sensor that detects a radio wave generated by a partial discharge in the insulation layer of the high-voltage cable
Implementation Method 2
a second sensor that detects a high-frequency signal generated by a partial discharge in the insulation layer of the high-voltage cable
Implementation Method 3
a third sensor that detects an acoustic emission generated by a partial discharge in the insulation layer of the high-voltage cable
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A partial discharge determination method executed in a partial discharge determination apparatus that determines whether or not partial discharge has occurred in a power transmission facility includes: acquiring measurement data representing a charge amount and a phase of each partial discharge occurring in the power transmission facility; removing or reducing noise included in the measurement data based on statistical information; generating ϕ-q-n data representing a charge amount, a phase, and the number of pulses of each of the partial discharge and the noise included in the measured data from the measured data from which the noise has been removed or reduced; and determining whether or not at least the partial discharge has occurred by using a learning model generated by performing machine learning using the ϕ-q-n data of the partial discharge and the noise based on the ϕ-q-n data generated by a ϕ-q-n data generation unit.