ResFaultyMan: An intelligent fault detection predictive model in power electronics systems using unsupervised learning isolation forest

Intelligent fault detection considered as a paramount importance in Power Electronics Systems (PELS) to ensure operational reliability along with rising complexities and critical application demands. However, most of the developed methods in real-world scenarios can have better detection, and accura...

Full description

Saved in:
Bibliographic Details
Published in:Heliyon Vol. 10; no. 15; p. e35243
Main Authors: Safari, Ashkan, Sabahi, Mehran, Oshnoei, Arman
Format: Journal Article
Language:English
Published: England Elsevier Ltd 15.08.2024
Elsevier
Subjects:
Artificial intelligence
electric potential difference
electronics
forests
Intelligent fault detection
Power electronics systems
Pyboard microcontroller
Python-to-python interface
resistors
Unsupervised isolation forest
Unsupervised isolation forest
Intelligent fault detection
Pyboard microcontroller
Python-to-python interface
Power electronics systems
Artificial intelligence
ISSN:2405-8440, 2405-8440
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Intelligent fault detection considered as a paramount importance in Power Electronics Systems (PELS) to ensure operational reliability along with rising complexities and critical application demands. However, most of the developed methods in real-world scenarios can have better detection, and accurate diagnosis. In this regard, ResFaultyMan, a novel unsupervised isolation forest-based model, is presented in this paper, for real-world fault/anomaly detection in PELS. Capitalizing on the dynamics of faults, ResFaultyMan utilizes a tree-based structure for effective anomaly isolation, demonstrating adaptability to diverse fault scenarios. The test bench, comprising a load, Triac switch, resistor, voltage source, and Pyboard microcontroller, provides a dynamic setting for performance evaluation. The integration of a Pyboard microcontroller and a Python-to-Python interface facilitates fast data transfer and sampling, enhancing the efficiency of ResFaultyMan in real-time fault detection scenarios. Comparative analysis with OneClassSVM and LocalOutlierFactor, utilizing Key Performance Indicators (KPIs) of Accuracy, Precision, and Recall, as well as F1 Score, manifest ResFaultyMan's fault detection capabilities for fault detection in PELSs, and its performance in the related applications. •A practical case study and test bench for applying the intelligent detector.•The new detector uses an unsupervised isolation tree fault detector to diagnose faults in an unlabeled dataset.•The model compared several KPIs with other models, showing significant results.•The data was sampled and generated on the electronic board, then transferred quickly using a Pyboard controller with a high data transfer rate.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2405-8440
2405-8440
DOI:10.1016/j.heliyon.2024.e35243