Predictive Modelling for Quality Prediction and Assurance of Extrusion Blow Molding
Vongur Ramulu1, E. V. Ramana2, N. Kiran Kumar3
1Vongur Ramulu, PG student in Advanced Manufacturing Systems (AMS) from VNR VJIET, Hyderabad, India.
2E. V. Ramana is working as a Professor, Department of Mechanical Engineering, VNR Vignana Jyothi Institute of Engineering and Technology, Hyderabad, India.
3Kiran Kumar Namala has done doctoral program from IIT Delhi, post-graduation in production engineering, India.
Manuscript received on 24 August 2019. | Revised Manuscript received on 18 September 2019. | Manuscript published on 30 September 2019. | PP: 1364-1368 | Volume-8 Issue-11, September 2019. | Retrieval Number: J96760881019/2019©BEIESP | DOI: 10.35940/ijitee.J9676.0981119
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Extrusion Blow Molding process plays an important role in manufacturing of hollow products with wide variety of materials like polyethylene (PE), polypropylene (PP), polyvinylchloride (PVC). Extrusion blow molded products are rejected due to the occurrence of defects such as die lines, blowouts, shrinkage, over weight of part. The complex relationships that exist between the process variables, and causes of defects are investigated for 1 litre container made of high-density polyethylene (HDPE) using data mining techniques in order to reduce scrap. In this paper Data Mining approach is implemented by applying Decision Tree, k-Nearest Neighbors, Rule Induction and Vote techniques in RapidMiner for quality assurance and prediction of the quality of the extrusion blow molded product.
Keywords: Rule Induction, k-Nearest Neighbors, Decision Tree, Vote, Extrusion Blow Molding.
Scope of the Article: