Apply VGGNet-based deep learning model of vibration data for prediction model of gravity acceleration equipment

TL;DR

This paper introduces a deep learning-based prediction model using VGGNet architecture on vibration spectrograms to accurately detect faults in hypergravity accelerators, enhancing safety and maintenance efficiency.

Contribution

The study presents a novel approach combining spectrogram conversion of vibration data with VGGNet deep learning for fault prediction in large machinery.

Findings

Achieved 99.5% F1-Score in fault classification

Outperformed existing feature-based models by up to 23%

Validated effectiveness on real hypergravity equipment data

Abstract

Hypergravity accelerators are a type of large machinery used for gravity training or medical research. A failure of such large equipment can be a serious problem in terms of safety or costs. This paper proposes a prediction model that can proactively prevent failures that may occur in a hypergravity accelerator. The method proposed in this paper was to convert vibration signals to spectograms and perform classification training using a deep learning model. An experiment was conducted to evaluate the performance of the method proposed in this paper. A 4-channel accelerometer was attached to the bearing housing, which is a rotor, and time-amplitude data were obtained from the measured values by sampling. The data were converted to a two-dimensional spectrogram, and classification training was performed using a deep learning model for four conditions of the equipment: Unbalance, Misalignment, Shaft Rubbing, and Normal. The experimental results showed that the proposed method had a 99.5% F1-Score, which was up to 23% higher than the 76.25% for existing feature-based learning models.