# Real-World Airborne Sound Analysis for Health Monitoring of Bearings in Railway Vehicles

## TL;DR

This paper presents a method to detect railway bearing faults using airborne sound analysis, achieving reliable results with real-world data.

## Contribution

The novel contribution is using MFCC features with an MLP classifier for bearing fault detection in real-world railway operations.

## Key findings

- MFCCs are best suited for detecting bearing faults from airborne sound.
- The MLP classifier reliably detects bearing damages not seen during training.
- The method was validated using real-world commuter railway vehicle data.

## Abstract

In this paper, the task of detecting bearing faults in railway vehicles during regular operation by analyzing acoustic (airborne sound) data is addressed. To that end, various features are studied, among which the Mel Frequency Cepstral Coefficients (MFCCs) are best suited for detecting bearing faults by analyzing airborne sound. The MFCCs are used to train a Multi-Layer Perceptron (MLP) classifier. The proposed method is evaluated with real-world data for a state-of-the-art commuter railway vehicle in a dedicated measurement campaign. Classification results demonstrate that the chosen MFCC features allow for reliable detection of bearing damages, even for damages that were not included in training.