Veri Madenciliğinde Birliktelik Kuralları ile Bir CNC Tezgahı İçin Arıza Analizi

Yıl 2022, , 205 - 226, 09.05.2022

Sena Kumcu , Bahar Özyörük

https://doi.org/10.17134/khosbd.1101520

Öz

İşletmeler için imalatta kullanılan makinelerin uygun bakım politikalarını uygulayarak çalışır durumda tutulmaları çok önemlidir. Geçmişte ortaya çıkan arızaların analiz edilmesi ile gelecek dönemlerde ortaya çıkması muhtemel arızaların öngörülmesi için pek çok çalışma yapılmaktadır. Son zamanlarda bakım alanında veri madenciliği yöntemlerinden sıkça yararlanılmaktadır. Bu çalışmada; otomotiv sektöründe yer alan bir işletmenin önemli bir süreci olan bakım-onarım faaliyetleri ele alınmıştır. İşletmenin arıza oranı yüksek olan bir CNC tezgâhında meydana gelen, üretimin çok ciddi ölçüde durmasına neden olan arıza ve etki faktörlerinin ilişkilerini belirlemek amaçlanmıştır. Bu amaç doğrultusunda CNC tezgâhının bir yıllık arıza verisi üzerinde veri madenciliği yöntemlerinden birliktelik kuralları uygulanmıştır. Uygulama, SPSS Modeler 18.2 programı ile Apriori algoritması kullanılarak gerçekleştirilmiştir. Elde edilen kurallar analiz edilip yorumlanarak işletmeye ekonomik açıdan katkı sağlayacak bakım stratejileri ortaya konularak sonuçlar yorumlanmıştır.

Anahtar Kelimeler

veri madenciliği, birliktelik kuralları, ekipman bakımı

Fault Analysis of a CNC Machine with Association Rules in Data Mining

Öz

It is very important for businesses to keep the machines used in manufacturing in working condition by applying appropriate maintenance policies. Many studies are carried out to analyze the malfunctions that have occurred in the past and to predict the malfunctions that may occur in the future periods. Recently, data mining methods have been used frequently in the field of maintenance. In this study; maintenance and repair works, which are an important activity of an enterprise operating in the automotive sector, are discussed. It is aimed to determine the relationships between the failure and impact factors that occur in a CNC machine with a high failure rate of the enterprise and cause the production to stop very seriously. For this purpose, association rules, one of the data mining methods, were applied on the one-year failure data of the CNC machine. The application was carried out using the SPSS Modeler 18.2 program and the Apriori algorithm. By analyzing and interpreting the obtained rules, maintenance strategies that will contribute to the business economically have been put forward and the results have been interpreted.

Anahtar Kelimeler

Data Mining, Association Rules, Maintenance

Kaynakça

• Cios, K. J., Pedrycz, W., Swiniarski, R. W., ve Kurgan, L. A. (2007). Data mining: a knowledge discovery approach. Springer Science and Business Media.
• Giudici, P., Figini, S. (2009). Applied Data Mining for Business and Industry Applied Data Mining for Business and Industry, Second Edition, John Wiley & Sons.
• Köksal, M. (2015). Bakım Planlaması. Ankara: Seçkin Yayıncılık.
• Rakotomalala, R., Rokach, L., and Maimon, O. (2007). Data Mining Data Mining with Decision Trees-Theory and Applications (Vol. 61). World Scientific Publishing.
• Carvalho, T. P., Soares, F. A. A. M. N., Vita, R., Francisco, R. da P., Basto, J. P., and Alcalá, S. G. S. (2019). A systematic literature review of machine learning methods applied to predictive maintenance. Computers and Industrial Engineering, 137, 106024.
• Cooke, R., and Paulsen, J. (1997). Concepts for measuring maintenance performance and methods for analysing competing failure modes. Reliability Engineering and System Safety, 55(2), 135–141.
• Djatna, T., and Alitu, I. M. (2015). An Application of Association Rule Mining in Total Productive Maintenance Strategy: An Analysis and Modelling in Wooden Door Manufacturing Industry. Procedia Manufacturing, 4, 336–343.
• Doostan, M., Chowdhury, B. H. (2017). Power distribution system fault cause analysis by using association rule mining. Electric Power Systems Research, 152, 140–147.
• Duan, C., Makis, V., and Deng, C. (2019). Optimal Bayesian early fault detection for CNC equipment using hidden semi-Markov process. Mechanical Systems and Signal Processing, 122, 290–306.
• He, S. G., He, Z., and Wang, G. A. (2013). Online monitoring and fault identification of mean shifts in bivariate processes using decision tree learning techniques. Journal of Intelligent Manufacturing, 24(1), 25–34.
• Liang, Y. C., Li, W. D., Lou, P., and Hu, J. M. (2020). Thermal error prediction for heavy-duty CNC machines enabled by long short-term memory networks and fog-cloud architecture. Journal of Manufacturing Systems.
• Liu, G., Peng, C. (2017). Research on Reliability Modeling of CNC System Based on Association Rule Mining. Procedia Manufacturing, 11, 1162–1169.
• Liu, J., Shi, D., Li, G., Xie, Y., Li, K., Liu, B., and Ru, Z. (2020). Data-driven and association rule mining-based fault diagnosis and action mechanism analysis for building chillers. Energy and Buildings, 216, 109957.
• Marquez, A. C., Gupta, J. N. (2006). Contemporary maintenance management: process, framework and supporting pillars. Omega, 34(3), 313-326.
• Maquee, A., Shojaie, A. A., and Mosaddar, D. (2012). Clustering and association rules in analyzing the efficiency of maintenance system of an urban bus network. International Journal of Systems Assurance Engineering and Management, 3(3), 175–183.
• Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., and Beghi, A. (2015). Machine learning for predictive maintenance: A multiple classifier approach. IEEE Transactions on Industrial Informatics, 11(3), 812–820.
• Tian, Z. (2012). An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. Journal of Intelligent Manufacturing, 23(2), 227-237.
• Zhang, Z., Wang, Y., and Wang, K. (2013). Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network. Journal of Intelligent Manufacturing, 24(6), 1213–1227.
• Zheng, Q., Li, Y., and Cao, J. (2020). Application of data mining technology in alarm analysis of communication network. Computer Communications, 163, 84–90.
• Agrawal, R., and Srikant, R. (1994). Fast Algorithms for Mining Association Rules. Proc. of 20th International Conference on Very Large Data Bases, {VLDB’94}, 487–499.
• Bin, Z., and Wensheng, X. (2016). An Improved Algorithm for High Speed Train’s Maintenance Data Mining Based on MapReduce. International Conference on Cloud Computing and Big Data, CCBD 2015, 59–66.
• Young, T., Fehskens, M., Pujara, P., Burger, M., and Edwards, G. (2010). Utilizing data mining to influence maintenance actions. In 2010 IEEE AUTOTESTCON, 267–271.