Artificial Neural Network and Regression Modeling of SIS Process for Predicting Dynamic Mechanical Properties. (2018)

• Record Type: Journal Article
• Authors: Arunkumar, P.; Esakki, Balasubramanian; Rajamani, D.
• Is Part Of: Materials today. Volume 5:Number 5(2018)Part 2
• Page Start: 12016
• Page End: 12024
• Publication Date: 2018
• Subjects: Selective inhibition sintering -- Dynamic mechanical analysis -- Artificial neural network -- Regression modeling; Materials science -- Congresses -- Periodicals; 620.1
• DOI: 10.1016/j.matpr.2018.02.176
• Languages: English
• ISSNs: 2214-7853

Abstract

Abstract: Selective inhibition sintering (SIS) is a novel rapid prototyping technique that produces parts of high quality with low cost. The present study focuses on predicting the dynamic mechanical properties of selective inhibition sintered high density polyethylene part. Experiments are designed based on RSM-BBD design approach through considering various SIS process parameters such as layer thickness, heater energy, heater feedrate and printer feedrate. Regression and artificial neural network (ANN) modeling are formulated and employed to evaluate the relationship between input parameters and output responses of SIS process. The trained model using ANN has attained better prediction of loss and storage modulus in comparison with regression analysis. Hence, the developed ANN network can be incorporated in manufacturing systems to predict nonlinear mechanical characteristics of SIS parts.