The Application of Machine Learning ICA-VMD in an Intelligent Diagnosis System in a Low SNR Environment.

Shih-Lin Lin

doi:10.3390/s21248344

Abstract

This paper proposes a new method called independent component analysis–variational mode decomposition (ICA-VMD), which combines ICA and VMD. The purpose is to study the application of ICA-VMD in low signal-to-noise ratio (SNR) signal processing and data analysis. ICA is a very important method in the field of machine learning. It is an unsupervised learning algorithm that can dig out the independent factors hidden in the observation signal. The VMD method estimates each signal component by solving the frequency domain variational optimization problem, and it is very suitable for mechanical fault diagnosis. The advantage of ICA-VMD is that it requires two sensory cues to distinguish the original source from the unwanted noise. In the three cases studied here, the original source was first contaminated by white Gaussian noise. The three cases in this study are under different SNR conditions. The SNR in the first case is –6.46 dB, the SNR in the second case is –21.3728, and the SNR in the third case is –46.8177. The simulation results show that the ICA-VMD method can effectively recover the original source from the contaminated data. It is hoped that, in the future, there will be new discoveries and advances in science and technology to solve the noise interference problem through this method.

Highlights

Sensor measurement obtains valuable data, which have been widely used in many applied sciences and engineering fields
After successfully separating the signal and noise, the variational mode decomposition (VMD) method can be used to decompose the data from these mixed sources into its component parts
The low signal-to-noise ratio data that cannot be processed by traditional methods can be analyzed using the combined independent component analysis–variational mode decomposition (ICA-VMD) method under the Independent component analysis (ICA) constraints and conditions of the two sensors

Summary

Introduction

Sensor measurement obtains valuable data, which have been widely used in many applied sciences and engineering fields. Analyzing these measurement data is indispensable and extremely challenging. Data analysis can be divided into two types. The other type is that the sensor measurement is interfered by the external environment and cannot be directly explained. It is necessary to understand the original features hidden in the data through data analysis or signal processing. This is difficult, but is an important process of scientific progress and new discoveries

Methods

Results

Conclusion