Related Experiment Video
Updated: Jan 2, 2026

Investigating the Potential of Singly Curved Thin Piezoelectric Transducers for Energy Harvesting and Structural Health Monitoring
Published on: November 14, 2025
A Classification Method for Select Defects in Power Transformers Based on the Acoustic Signals
Michał Kunicki1, Daria Wotzka2
1Institute of Electrical Power Engineering and Renewable Energy, Opole University of Technology, 45-758 Opole, Poland.
This study introduces a novel acoustic method for identifying defects in power transformers. The approach accurately classifies partial discharges and other faults, enhancing transformer condition assessment.
Area of Science:
- Electrical Engineering
- Materials Science
- Acoustics
Background:
- Effective early detection of power transformer defects remains a significant challenge.
- Non-invasive and non-destructive testing methods are crucial for maintaining operational integrity.
- Acoustic emission (AE) is a recognized technique, primarily for partial discharge (PD) detection, but capable of identifying other anomalies.
Purpose of the Study:
- To develop and validate a new classification method for identifying defects in power transformers using acoustic measurements.
- To enhance the diagnostic capabilities of acoustic emission testing beyond partial discharge detection.
- To provide a supplementary tool for power transformer condition assessment and management.
Main Methods:
- Gathering a diverse database of acoustic signals from real-life power transformers over several years.
- Implementing a two-step classification strategy: first, distinguishing between partial discharges (PD) and other signal sources, and second, classifying into eight specific defect types.
- Utilizing machine learning algorithms trained and validated on energy patterns derived from discrete wavelet transform (DWT) of the acoustic signals.
Main Results:
- The proposed method achieved high accuracy in identifying specific types of partial discharges.
- The system successfully identified other types of faults and anomalies within the power transformers.
- The two-step classification approach demonstrated robust performance in defect identification.
Conclusions:
- The developed acoustic-based classification method offers a highly accurate and effective means for power transformer defect identification.
- This technique can serve as a valuable addition to existing technical condition assessment and decision support systems.
- The study highlights the potential of advanced signal processing and machine learning in improving power transformer reliability and safety.
More Related Videos
06:17Quantifying the Relative Thickness of Conductive Ferromagnetic Materials Using Detector Coil-Based Pulsed Eddy Current Sensors
Published on: January 16, 2020
11:34Subsurface Defect Localization by Structured Heating Using Laser Projected Photothermal Thermography
Published on: May 15, 2017
Related Concept Videos
Power System Three-Phase Short Circuits
Instrument Transformers
Energy Losses in Transformers
There are four main reasons for energy losses in transformers.
The first cause can be the high resistance of the...
Three-Phase Short Circuit—Unloaded Synchronous Machine
This behavior occurs due to the magnetic flux produced by the short-circuit armature currents. Initially, these currents follow high-reluctance paths but eventually shift to...
Differential Relays
Transformers in Distribution System
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...