Transformer-Based Denoising of Mechanical Vibration Signals

TL;DR

This paper presents a transformer-based deep learning model designed to effectively denoise mechanical vibration signals, improving industrial system monitoring and failure prediction capabilities.

Contribution

It introduces a novel transformer architecture tailored for mechanical vibration denoising, with specific design choices enhancing feature extraction and noise filtering.

Findings

Effective noise reduction while preserving critical vibration features

Robust performance demonstrated on complex mechanical signals

Potential for improved industrial diagnostics

Abstract

Mechanical vibration signal denoising is a pivotal task in various industrial applications, including system health monitoring and failure prediction. This paper introduces a novel deep learning transformer-based architecture specifically tailored for denoising mechanical vibration signals. The model leverages a Multi-Head Attention layer with 8 heads, processing input sequences of length 128, embedded into a 64-dimensional space. The architecture also incorporates Feed-Forward Neural Networks, Layer Normalization, and Residual Connections, resulting in enhanced recognition and extraction of essential features. Through a training process guided by the Mean Squared Error loss function and optimized using the Adam optimizer, the model demonstrates remarkable effectiveness in filtering out noise while preserving critical information related to mechanical vibrations. The specific design and choice of parameters offer a robust method adaptable to the complex nature of mechanical systems, with promising applications in industrial monitoring and maintenance. This work lays the groundwork for future exploration and optimization in the field of mechanical signal analysis and presents a significant step towards advanced and intelligent mechanical system diagnostics.