Total views : 208

Quality Control Method of Engine Manufacturing Process Using Data Mining Technique


  • Graduate School of Business, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea;
  • School of Business, Sogang University, 35 Baekbeom-ro, Mapo-gu, Seoul 04107, Korea;


Objectives: This study analyzes the major defect factors that influence the defective percentage of an engine manufacturing processes and to find the processes that influence other defect factors. Methods/Statistical Analysis: This study uses the process data from actual manufacturing sites, and analyzes the major defect factors occurring in the manufacturing processes using the data mining techniques. Analysis on the process data has two steps: The first step is to preprocess to reorganize the raw data into accurate data, and the second step is to analyze for each defect factor to classify defects by factors. Findings: As a result of the analysis, it found defects of LEAK during operation of the engine, defects in components of the inlet and outlet systems of the engine and defects in components of the electronic system of the engine influence the percent defective. This study also analyzes the main defect types of product using big data from the engine manufacturing process. To solve the problem that was hard to find analytic data or useful information out of the huge data collected in real time, the data mining technique was employed. It is a practical methodology to offer beneficial information for decision making in the database marketing field. In terms of product quality management, estimating the defect types in the manufacturing process stage will shorten the time consumption in resolving the problems. By reducing the defective products in advance, it also lowers the cost accompanied with defect occurrences and raw materials. Improvements/Applications: This study suggests methods to control quality in manufacturing processes with an application of preventing defects in advance and further to control the future defects.


Data Mining Techniques, Decision Tree, Defect Factors, Manufacturing Processes, Quality Control.

Full Text:

 |  (PDF views: 159)


  • Hancock W, Yoon J, Plot R. Use of ridge regression in the improved control of casting process. Quality Engineering.1998; 8(3);395–403.
  • Montgomery D, Peck E, Vining G. Introduction to linear regression analysis, 4th ed. USA: Wiley; 2007.
  • Banks D. Pre-analysis of super large industrial data sets.Journal of Quality Technology. 1992; 24:115–92.
  • Sivakumar S, Venkataraman S, Selvaraj R. Predictive modeling of student dropout indicators in educational data mining using improved decision tree. Indian Journal of Science and Technology. 2016; 9(4):2–5.
  • Undavia J, Dolia P, Patel A. Customized prediction model to predict post-graduation course for graduating students using decision tree classifier. Indian Journal of Science and Technology. 2016; 9(12):2–7.
  • Lee K, Lee H. A study on the combined decision tree (C4.5) and neural network algorithm for classification of mobile telecommunication customer. Korea Journal of Intelligent Information Systems. 2003; 9(1):139–55.
  • Byeon S, Kang C, Sim S. Defect type prediction method in manufacturing process using data mining technique.Journal of the Society of Korea Industrial and Systems Engineering. 2004; 27(2):10–6.
  • Goodlin B, Boning D, Sawin H, Wise B. Simultaneous fault detection and classification for semiconductor manufacturing tools. Journal of the Electrochemical Society. 2002; 150(12):778–84.
  • Berry M, Linoff G. Data mining techniques: for marketing, sales, and customer support. USA: John Wiley and Sons; 1997.
  • Galit S, Nitin R, Peter C. Data mining for Business Intelligence. USA; Wiley; 2009.
  • Michael J. Data mining techniques. USA: John Wiley and Sons; 1997.
  • Ture M, Tokatli F, Omurlu I. The comparisons of prognostic indexes using data mining techniques and cox regression analysis in the breast cancer data. Expert Systems with Applications. 2009; 36(4):8347–254.
  • Montgomery D. Introduction to statistical quality control.USA: John Wiley and Sons; 1996.
  • Guh R, Hsieh YA. Neural network based model for abnormal pattern recognition of control charts. Computer and Industrial Engineering. 1993; 36:97–108.
  • Lim S, Her Y. Customer churning forecasting and strategic implication in online auto insurance using decision tree algorithms. Korea Journal of Information Systems Review.2006; 8(8):125–34.
  • Chang N. Improving the effectiveness of customer classification models: A pre-segmentation approach. Korea Journal of Information Systems Review. 2005; 7(2):23–40.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.