Lab-scale Vibration Analysis Dataset and Baseline Methods for Machinery Fault Diagnosis with Machine Learning

TL;DR

This paper introduces a lab-scale vibration dataset for machinery fault diagnosis, evaluates machine learning classifiers on it, and provides baseline results demonstrating high classification accuracy.

Contribution

It presents a new open dataset of vibration signals for different machine conditions and benchmarks machine learning methods for fault diagnosis.

Findings

SVM achieved 99.75% weighted accuracy

The dataset includes four machine conditions

Baseline results for fault classification are established

Abstract

The monitoring of machine conditions in a plant is crucial for production in manufacturing. A sudden failure of a machine can stop production and cause a loss of revenue. The vibration signal of a machine is a good indicator of its condition. This paper presents a dataset of vibration signals from a lab-scale machine. The dataset contains four different types of machine conditions: normal, unbalance, misalignment, and bearing fault. Three machine learning methods (SVM, KNN, and GNB) evaluated the dataset, and a perfect result was obtained by one of the methods on a 1-fold test. The performance of the algorithms is evaluated using weighted accuracy (WA) since the data is balanced. The results show that the best-performing algorithm is the SVM with a WA of 99.75\% on the 5-fold cross-validations. The dataset is provided in the form of CSV files in an open and free repository at https://zenodo.org/record/7006575.