http://www.iaeme.com/IJMET/index.asp 31 editor@iaeme.com
International Journal of Mechanical Engineering and Technology (IJMET)
Volume 7, Issue 6, November–December 2016, pp.31–40, Article ID: IJMET_07_06_004
Available online at
http://www.iaeme.com/ijmet/issues.asp?JType=IJMET&VType=7&IType=6
Journal Impact Factor (2016): 9.2286 (Calculated by GISI) www.jifactor.com
ISSN Print: 0976-6340 and ISSN Online: 0976-6359
© IAEME Publication
DATA MINING APPROACH FOR QUALITY
PREDICTION AND IMPROVEMENT OF INJECTION
MOLDING PROCESS THROUGH SANN, GCHAID AND
ASSOCIATION RULES
Dr. E V Ramana
Professor, Department of Mechanical Engineering,
Guru Nanak Institutions Technical Campus, Hyderabad, India
S Sapthagiri
Associate Professor, Department of Mechanical Engineering,
Guru Nanak Institutions Technical Campus, Hyderabad, India
P Srinivas
Associate Professor, Department of Mechanical Engineering,
Guru Nanak Institutions Technical Campus, Hyderabad, India
ABSTRACT
Data mining technologies are slowly finding their way in determining complex relationships among
process variables in large datasets generated by different industrial processes. Extracting process
knowledge by finding trends, patterns, and anomalies in these datasets, and making use of them in real
time process control is a challenging task. Plastic injection molding process is no exception due to the
influence of large number of factors on the quality of product. In this study, a data mining approach
has been applied for the quality prediction of the plastic injection molding process by using Statistica
Automated Neural Networks (SAAN), General Chi-square Automatic Interaction Detector (GCHAID)
and Association Rules.
Key words: Injection Molding; Statistica Automated Neural Networks (SAAN); General CHAID
(GCHAID) and Association Rules.
Cite this Article: Dr. E V Ramana, S Sapthagiri and P Srinivas, Data Mining Approach for Quality
Prediction and Improvement of Injection Molding Process through SANN, GCHAID and
Association Rules. International Journal of Mechanical Engineering and Technology, 7(6), 2016,
pp. 31–40.
http://www.iaeme.com/ijmet/issues.asp?JType=IJMET&VType=7&IType=6
1. INTRODUCTION
Quality improvement of injection molding products requires collection and analysis of process data to
identify quality related problems. The main causes of defects in injection molding are generally related
with material, packing, filling, cooling etc. The improper selection of processing parameters results in
defective products in injection molding. In this paper, an investigation has been made to apply data mining