Intelligent Fault Diagnosis of Type and Severity in Low-Frequency, Low Bit-Depth Signals

TL;DR

This paper presents a data-driven approach for diagnosing fault types and severities in rotating machinery using sound data, achieving high accuracy with minimal resource consumption through feature analysis and classifier tuning.

Contribution

It introduces a novel methodology combining sound feature extraction, data augmentation, and classifier optimization for efficient fault diagnosis in low-resource settings.

Findings

Achieved 99.54% accuracy with time, frequency, and statistical features.

Using only MFCCs, achieved 97.83% accuracy.

Selected features with a greedy wrapper yielded 96.82% accuracy.

Abstract

This study focuses on Intelligent Fault Diagnosis (IFD) in rotating machinery utilizing a single microphone and a data-driven methodology, effectively diagnosing 42 classes of fault types and severities. The research leverages sound data from the imbalanced MaFaulDa dataset, aiming to strike a balance between high performance and low resource consumption. The testing phase encompassed a variety of configurations, including sampling, quantization, signal normalization, silence removal, Wiener filtering, data scaling, windowing, augmentation, and classifier tuning using XGBoost. Through the analysis of time, frequency, mel-frequency, and statistical features, we achieved an impressive accuracy of 99.54% and an F-Beta score of 99.52% with just 6 boosting trees at an 8 kHz, 8-bit configuration. Moreover, when utilizing only MFCCs along with their first- and second-order deltas, we recorded an accuracy of 97.83% and an F-Beta score of 97.67%. Lastly, by implementing a greedy wrapper approach, we obtained a remarkable accuracy of 96.82% and an F-Beta score of 98.86% using 50 selected features, nearly all of which were first- and second-order deltas of the MFCCs.