What question did this study set out to answer?

The study aims to enhance fault detection in analog circuits by ensuring reliable performance in noisy conditions.

July 16, 2026Journal of Sensor and Actuator Networks0 citationsOpen Access

Multi-Domain Feature Engineering for Noise-Tolerant Fault Classification in Analog Filter Circuits

ADArchana DhamotharanPSG INSTITUTE OF TECHNOLOGY AND APPLIED RESEARCH BMBalakumar MuniandiUniversity of Idaho VUVennila Anandaraj UmapathyPSG INSTITUTE OF TECHNOLOGY AND APPLIED RESEARCH

Key Points

The study aims to enhance fault detection in analog circuits by ensuring reliable performance in noisy conditions.
Developed a multi-stage pipeline for signal processing and noise addition at levels of 5 dB, 10 dB, and 20 dB.
Utilized Monte Carlo analysis to create a synthetic dataset with 200 runs per fault class.
Employed support vector machine, random forest, and gradient boosting as base-level classifiers in a stacking ensemble model.
Achieved solid performance in fault classification under varying noise conditions.
Demonstrated the effectiveness of combining time, frequency, and statistical-domain features for accurate detection.
Improved classification rates using a stacking ensemble model compared to individual classifiers.

Abstract

This paper proposes a method of fault detection in analog circuits which involves various steps, including selection of benchmark circuits, dataset preparation, signal decomposition, model training, and performance analysis. The main aim of this work is to provide solid performance even in noisy environments. Monte Carlo analysis is used to generate a synthetic dataset with 200 runs per fault class by introducing component tolerances and realistic faults. A multi-stage pipeline is proposed; it begins with resampling the signals and normalizing them, and then noise is added at different levels: 5 dB, 10 dB and 20 dB. Feature fusion is performed by combining time-, frequency-, and statistical-domain features. Statistical-domain features are extracted by applying Variational Mode Decomposition (VMD) to split them into four IMF levels, followed by the application of Continuous Wavelet Transform (CWT) for time–frequency-domain analysis. Support Vector Machine (SVM), Random Forest, and Gradient Boosting are used as base-level classification models. A stacking ensemble model is developed which uses Random Forest, Gradient Boosting, and Extra Trees as base learners and Logistic Regression as the meta-learner.

问 AI

Bookmark

View Full Paper