Textile Production Line Monitoring System Using Wavelet-Regression Neural Network

Nagaraj V Dharwadkar,Vinothkumar Veeramani,Anagha R Pakhare,Wen-Ren Yang,Rajinder Kumar Mallayya Math

doi:10.4018/jcit.20220701.oa11

Abstract

This paper presents design and experiments for a production line monitoring system. The system is designed based on an existing production line which mapping to the smart grid standards. The Discrete wavelet transform (DWT) and regression neural network (RNN) are applied to the operation modes data analysis. DWT used to preprocess the signals to remove noise from the raw signals. The output of DWT energy distribution has given as an input to the GRNN model. The neural network GRNN architecture involves multi-layer structures. Mean Absolute Percentage Error (MAPE) loss has used in the GRNN model, which is used to forecast the time-series data. Current research results can only apply to the single production line but in future, it will used for multiple production lines.

Highlights

The paper presents research based on the textile factory production line
In fig. 3(a), when the system runs in regular mode, the power factor (PF) remains constant throughout irrespective of the change in the number of points for a certain period
The red line transient cD1s tell the information about the initiation of the start and end is going to happen and fed these values as an input to the regression neural network. 3.5 Methods used for Wavelet Transformation: Two methods can be used for wavelet transformation, but this paper focuses on the regression neural network

Summary

INTRODUCTION

The production line’s power quality and motor monitoring are essential to operational stability. Since the monitoring station for the inverter can provide users with the real-time waveform, wavelet transformation is useful for analysing power quality. To improve the capability of the WT (wavelet transforms) based on power quality monitoring system, many researchers proposed a de-noising approach to detecting transient disturbances in a noisy environment. Conventional signal processing tools have some severe drawbacks for harmonics applications, so the wavelet transform is an engaging alternative method. Because it has superior time-frequency resolution property as well as for studying non-stationary power waveforms. Wavelet neural network used for this is smaller and more efficient than immense deep learning and Convolutional Neural Network (CNN)

SYSTEM DIAGRAM AND DESIGN PROCEDURES

Signal Analysis

Window Function

Energy Distribution

Good fit

CONCLUSION