Implementation of Decision Support System with Data Mining Methods in the Quality Control Process of the Automotive Sector

Year 2019, , 102 - 114, 31.01.2019

Hikmet Canlı Sinan Toklu

https://doi.org/10.29130/dubited.427900

Abstract

Today, the automotive sector is the "key" sector for developed and even developing countries. A strong
automotive sector is striking as one of the common features of industrialized countries. Production in this sector
consists of many processes. One of the most important of these processes is quality control. The measurement
data in this area is very large and as the volume of data increases, the rate that people understand is reduced.
Variations are the enemy of quality. There are many variations in the area of quality control. In this study, a
decision support system is applied in the quality control process with classification algorithms which are data
mining methods. C4.5, Naive Bayes, SMO and Random Forest algorithms are run on data set collected from
production. These algorithms are used to measure the quality and accuracy of the product without completing the
operations during production. Algorithms have been cost-reduced by determining that the product is faulty
before operations are completed. The algorithm C4.5 has been the best performing algorithm. In addition, these
algorithms make quality analysis very fast and easy. Thanks to this work, the cost of labor and materials has
been reduced in the production company.

Keywords

Data mining, Data visualization, Decision support, Production, Quality control

Otomotiv Sektörünün Kalite Kontrol Sürecinde Veri Madenciliği Yöntemleri ile Karar Destek Sistemi Uygulaması

Abstract

Günümüzde otomotiv sektörü, gelişmiş ve hatta gelişmekte olan ülkeler için “anahtar” sektör rolündedir. Güçlü
bir otomotiv sektörü, sanayileşmiş ülkelerin ortak özelliklerinden biri olarak gözümüze çarpmaktadır. Bu
sektörde üretim birçok süreçten oluşmaktadır. Bu süreçlerin en önemli olanlarından biri de kalite kontroldür. Bu
alanda ölçüm verileri çok fazladır ve verilerin hacmi arttıkça insanların anladığı oran azalmaktadır. Varyasyonlar
kalitenin düşmanıdır ve her şeyde varyasyon bulunmaktadır. Bu çalışmada veri madenciliği yöntemlerinden olan
sınıflandırma algoritmaları ile kalite kontrol sürecinde bir karar destek sistemi uygulaması yapılmıştır. C4.5,
Naive Bayes, SMO ve Random Forest algoritmaları, üretimden toplanan veri seti üzerinde çalıştırılmaktadır. Bu
algoritmalar, üretim sırasında işlemler tamamlanmadan ürünün kalitesini ve doğruluğunu ölçmek için kullanılır.
Algoritmalar, işlem tamamlanmadan önce ürünün arızalı olduğunu belirleyerek maliyet düşürülmektedir. Algoritma C4.5 en iyi performans gösteren algoritma olmuştur. Ek olarak, bu algoritmalar kalite analizini çok
hızlı ve kolay hale getirmektedir. Bu çalışma sayesinde, firmalarda işçilik ve malzeme maliyeti azaltılmıştır.

Keywords

Kalite Kontrol, Karar Destek, Üretim, Veri Görselleştirme, Veri Madenciliği, Veri Madenciliği

References

• [1] M. Yılmaz, “Applicability of the evolution of quality management systems and of total quality management in the banknote printing general directorate”, Expertise proficiency thesis, Department of Business Administration, Gazi University, Ankara, Turkey, 2003.
• [2] A.S. Koyuncugil, N. Özgülbaş, “Data Mining: Use and applications in medical and health services”, Journal of Information Technologies, c. 2, s. 2, pp. 22-32, 2009.
• [3] M.S. Başarslan, “Customer loss analysis in telecommunication sector”, Expertise proficiency thesis, Department of Computer Engineering, Düzce University, Düzce, Turkey, 2017.
• [4] (Anonymous). (2017, 20 September). Introduction to Data Mining and Knowledge Discovery [Online]. Access: http://www.twocrows.com/intro-dm.pdf.
• [5] W. Deng, G. Weng “A novel water quality data analysis framework based on time-series data mining,” Journal of Environmental Management, vol. 196, pp. 365–375, 2017.
• [6] A. Baykasoğlu,” Data mining and an application in the cement sector”, Akademik Bilişim, pp. 1-14, 2005.
• [7] G. Robert, “A Holistic Approach for quality oriented mainctance planning supported by data mining methods.”, Procedia CIRP, vol. 57, pp. 259-264, 2016.
• [8] J.A. Harding, M. Shahbaz, Srinivas and A. Kusiak “Data Mining in Manufacturing: A Review”, Journal of Manufacturing Science and Engineering, vol. 128, no. 4, pp. 969–976, 2005.
• [9] A.M.M. Kamal, “A Data Mining Approach for Improving Manufacturing Processes Quality Control”, Next Generation Information Technology, Gyeongju, South Korea, 2011.
• [10] A.R. Khan, H. Schiøler, T. Knudsen “Statistical data mining for efficient quality control in manufacturing”, Emerging Technologies & Factory Automation (ETFA), Luxembourg, Luxembourg, 2015.
• [11] R. S. Chen, Y.C. Chen and C.C. Chen, “Using data mining technology to deign a quality control system for manufacturing industry”, Advances in Communications, Computers, Systems, Circuits and Devices, Puerto De La Cruz, Tenerife, 2015.
• [12] S. Ferreiro, B. Sierra, I. Irigoien and E. Gorritxateg, “Data mining for quality control: Burr detection in the drilling process.”, Computers & Industrial Engineering, vol. 60, no. 4, pp. 801-810, 2011.
• [13] A. Gümüşçü, R. Taşaltın, İ. B. Aydilek, “C4.5 pruning with genetic algorithm in decision trees”, Dicle University Graduate School of Natural and Applied Sciences, ss. 77-80, 2016.
• [14] E. Uzun. (2014, 3 September). Naive bayes classifier [Online].Access:https://www.e-adys.com/makine_ogrenme si/naive-bayes-classifier/.
• [15] E. Ardıl, “Software Error Estimation with Flexible Calculation Approach”, Master thesis, Department of Computer Engineering, University of Trakya, Tekirdağ, Turkey, 2009.