Related Experiment Video
Updated: Nov 27, 2025
07:51
Method for Recording Broadband High Resolution Emission Spectra of Laboratory Lightning Arcs
Published on: August 27, 2019
7.2K
Entropy-Based Feature Extraction for Electromagnetic Discharges Classification in High-Voltage Power Generation
Imene Mitiche1, Gordon Morison1, Alan Nesbitt1
1Department of Engineering, Glasgow Caledonian University, 70 Cowcaddens Rd, Glasgow G4 0BA, UK.
Entropy (Basel, Switzerland)
|December 3, 2020
Summary
This study uses entropy measures to analyze Electromagnetic Interference (EMI) signals for High-Voltage (HV) equipment fault diagnosis. The method accurately identifies various discharge sources, enabling online condition monitoring.
Area of Science:
- Electrical Engineering
- Signal Processing
- Condition Monitoring
Background:
- High-Voltage (HV) equipment is critical in power systems, and its reliable operation depends on effective fault diagnosis.
- Electromagnetic Interference (EMI) signals contain valuable information about discharge sources, but extracting this information efficiently is challenging.
- Existing methods for analyzing EMI signals may require significant computational resources or lack accuracy in identifying diverse discharge types.
Purpose of the Study:
- To develop an efficient method for fault diagnosis of High-Voltage (HV) equipment using Electromagnetic Interference (EMI) signals.
- To investigate the effectiveness of four entropy measures (Sample, Permutation, Weighted Permutation, and Dispersion Entropy) in characterizing EMI discharge signals.
- To enable accurate classification of various discharge sources for improved condition monitoring.
Main Methods:
- Extraction of features from time-resolved EMI discharge signals using Sample, Permutation, Weighted Permutation, and Dispersion Entropy.
- Application of multi-class classification algorithms to distinguish between different discharge sources (Partial Discharges, Exciter, Arcing, micro Sparking, Random Noise).
- Signal measurement and recording across multiple sites, with expert labeling of discharge source types.
Main Results:
- High classification accuracy was achieved for identifying discharge sources within individual sites.
- The entropy-based feature extraction method demonstrated strong performance across different sites.
- The developed system requires minimal computation, making it suitable for real-time applications.
Conclusions:
- Entropy measures are effective in extracting relevant features from EMI discharge signals for HV equipment fault diagnosis.
- The proposed method offers a computationally efficient approach for classifying diverse discharge sources.
- This technique shows significant potential for online condition monitoring of HV equipment based on EMI analysis.
More Related Videos
Related Concept Videos
01:15Van de Graaff Generator
2.1K
Van de Graaff generators (or Van de Graaffs) are devices used to demonstrate high voltage due to static electricity that can also be used for research. Robert Van de Graaff first built one in 1931 (based on original suggestions by Lord Kelvin) for use in nuclear physics research.
Van de Graaff uses both smooth and pointed surfaces, conductors, and insulators to generate large static charges and, hence, large voltages. A substantial excess charge can be deposited on the sphere because it moves...
Van de Graaff uses both smooth and pointed surfaces, conductors, and insulators to generate large static charges and, hence, large voltages. A substantial excess charge can be deposited on the sphere because it moves...
2.1K
01:20Atomic Emission Spectroscopy: Overview
3.1K
Atomic emission spectroscopy (AES) is an analytical technique used to determine the elemental composition of a sample by analyzing the light emitted from excited atoms. In AES, atoms in a sample are excited to higher energy levels by thermal energy from high-temperature sources, such as plasma, arcs, or sparks. When these excited atoms return to lower energy states, they emit light at specific wavelengths characteristic of each element. The resulting atomic emission spectrum, which consists of...
3.1K
01:20Capillary Electrophoresis: Instrumentation
631
Capillary electrophoresis instrumentation typically consists of several key components. A high-voltage power supply generates the electric field necessary for the separation by connecting to an anode (the positively charged electrode) and a cathode (the negatively charged electrode) located in buffer reservoirs at each end of the capillary tube. The system includes a sample vial, a fused silica capillary tube coated with polyimide for mechanical strength through which the sample components...
631
01:29Atomic Emission Spectroscopy: Lab
405
AES is a powerful analytical technique, especially effective when used with plasma sources, producing abundant spectra in characteristic emission lines. The Inductively Coupled Plasma (ICP), in particular, yields superior quantitative analytical data due to its high stability, low noise, low background, and minimal interferences under optimal experimental conditions. However, newer air-operated microwave sources are emerging as promising alternatives that could be more cost-effective than...
405
01:19Inductively Coupled Plasma Atomic Emission Spectroscopy: Principle
1.3K
Inductively coupled plasma (ICP) is the most widely used plasma source in atomic emission spectroscopy (AES), also known as Inductively Coupled Plasma Optical Emission Spectroscopy (ICP-OES). The ICP source, or torch, consists of three concentric quartz tubes with argon gas flowing through them. A spark from a Tesla coil initiates the ionization of argon, generating a high-temperature plasma.
The ions and electrons produced interact with the fluctuating magnetic field created by a water-cooled...
The ions and electrons produced interact with the fluctuating magnetic field created by a water-cooled...
1.3K
01:17Energy and Power Signals
910
In an electrical system with a resistor, voltage and current signals facilitate the measurement of power and energy across the resistor. For a continuous-time signal, the total energy over a time interval is defined as the integral of the square of the signal's magnitude over that interval. Mathematically, this is expressed as:
910