Affordable Access

Download Read

Damage recognition in Wood-Plastic Composites using Neural Network

Authors
Publisher
IJMCA

Abstract

Abstract: The main Aim of this work is to present a pattern recognition model by simulating five kinds of typical acoustic emission (AE) signals originating from flaw and damage in wood-plastic composite (WPC) with the aid of Simulink tool developed by the Math Works Inc. Based on Simulink software, we built a WPC AE signal pattern recognition model, consisting of AE signal pattern recognition hardware and software systems. The system can be used to collect analog signals below 400 KHz with high fidelity and recognize AE signal patterns by the software system. Acoustic emission (AE) signals are generated while a material is distorted under stress action. By using high-speed code generation technology and Real-Time Workshop to generate efficient TI C6000 code from the pattern recognition model, we build the pattern recognition system of AE signals from the flaws and damages in WPC based on Digital Signal Processing (DSP) to realize online test and automatic recognition. In order to build a online test system based on AE signals from WPC to determine the type of material’s flaws or damages quickly and exactly, first we compose an AE signal pattern recognition model using Simulink tool developed by the Math Works Inc, then design an AE signal pattern recognition hardware system based on DSP, finally build an AE signal pattern recognition software system using high-speed code generation technology. Keywords: Acoustic Emission (AE); Pattern Recognition, Simulink; DSP

There are no comments yet on this publication. Be the first to share your thoughts.