Anomaly Detection for Gear Manufacturing Downtime in The Automotive Sector Using Rare Itemset Mining

Year 2022, Volume: 6 Issue: 2, 199 - 204, 30.12.2022

Devrim Naz Akdaş , Derya Bırant , Pelin Yıldırım Taşer

https://doi.org/10.46460/ijiea.1067365

Abstract

Downtimes in manufacturing significantly influence productivity, and their analysis is necessary for successful and flexible production. Although some classification and regression studies have been performed on the machine downtime in the manufacturing area, the rare itemset mining (RIM) technique has never been implemented in the existing downtime studies until now. Besides, anomaly detection for gear manufacturing downtime in the automotive sector using RIM is yet to be explored. To bridge this gap, this study proposes the application of the RIM method for detecting anomalies in gear manufacturing downtime of earth moving machinery for the first time. In this study, the Rare Pattern Growth (RP-Growth) algorithm was executed on a real-world dataset consisting of downtimes in gear manufacturing of earth moving machinery to discover rare itemsets that indicate anomalies in downtimes. In the experiments, the rare itemsets (anomalies) in the downtime data were detected using different minimum support (minsup) and minimum rare support (minraresup) threshold values. The obtained results were also evaluated in terms of the number of itemsets, execution time, and maximum memory usage. The experimental results show that the proposed approach, called Anomaly Detection with Rare Itemset Mining (ADRIM), is an effective method for detecting anomalies in machine downtimes and can be successfully used in the manufacturing area, especially in the automotive sector.

Keywords

Anomaly detection, data mining, gear manufacturing, rare itemset mining

Thanks

The authors are deeply grateful to Çelikiş Spare Parts of Industry and Trade Company Limited, and Projesis Software Consulting Informatics Information Systems for providing the experimental dataset used in the study.

Seyrek Öğe Seti Madenciliği Kullanılarak Otomotiv Sektöründe Dişli Üretimi Duruşlarında Anomali Tespiti

Abstract

Üretimdeki duruşlar üretkenliği önemli ölçüde etkiler ve duruşların analizi başarılı ve esnek üretim için gereklidir. Üretim alanında makine duruşları ile ilgili bazı sınıflandırma ve regresyon çalışmaları yapılmış olsa da, şimdiye kadar mevcut duruş çalışmalarında seyrek öğe kümesi madenciliği (RIM) tekniği hiç uygulanmamıştır. Ayrıca, RIM kullanılarak otomotiv sektöründe dişli üretimi duruşlarında anomali tespiti henüz keşfedilmemiştir. Bu boşluğu doldurmak için, bu çalışma, iş makinelerinin dişli imalatı duruşlarındaki anomalileri tespit etmek için ilk kez RIM yönteminin uygulanmasını önermektedir. Bu çalışmada, duruşlardaki anomalileri gösteren seyrek öğe kümelerini keşfetmek için iş makinelerinin dişli imalatındaki duruşlarından oluşan gerçek dünya veri seti üzerinde Rare Pattern Growth (RP-Growth) algoritması yürütülmüştür. Deneylerde, farklı minimum destek (minsup) ve minimum seyrek destek (minraresup) eşik değerleri kullanılarak duruş verilerindeki seyrek öğe kümeleri (anomaliler) tespit edilmiştir. Elde edilen sonuçlar ayrıca öğe kümesi sayısı, yürütme süresi ve maksimum bellek kullanımı açısından da değerlendirilmiştir. Deneysel sonuçlar, Seyrek Öğe Seti Madenciliği ile Anomali Tespiti (ADRIM) isimli önerilen yaklaşımın, makine duruşlarındaki anomalieri tespit etmek için etkili bir yöntem olduğunu ve özellikle otomotiv sektöründe üretim alanında başarıyla kullanılabileceğini göstermektedir.

Keywords

Anomali tespiti, veri madenciliği, dişli üretimi, seyrek öğe seti madenciliği

References

• Patale, G., Turukmane, R., Gulhane, S., Kolte, P., & Gupta, K. K. (2021). Causes of machine down time and its impact on nylon manufacturing process. Man-Made Textiles in India, 49(5), 158-160.
• Böhmer, K., & Rinderle-Ma, S. (2020). Mining association rules for anomaly detection in dynamic process runtime behavior and explaining the root cause to users. Information Systems, 90, 101438.
• Taşer, P. Y., Birant, K. U., & Birant, D. (2020). Multitask-based association rule mining. Turkish Journal of Electrical Engineering & Computer Sciences, 28(2), 933-955.
• Mucchielli, P., Bhowmik, B., Ghosh, B., & Pakrashi, V. (2021). Real-time accurate detection of wind turbine downtime-An Irish perspective. Renewable Energy, 179, 1969-1989.
• Wang, D. J., Liu, F., & Jin, Y. (2019). A proactive scheduling approach to steel rolling process with stochastic machine breakdown. Natural Computing, 18(4), 679-694.
• Shafieezadeh, A., DesRoches, R., Rix, G. J., & Werner, S. D. (2014). A probabilistic framework for correlated seismic downtime and repair cost estimation of geo‐structures. Earthquake engineering & structural dynamics, 43(5), 739-757.
• Garcés, D. A., & Castrillón, O. D. (2017). Design of intelligent technology to identify and reduce downtime in a production system. Información Tecnológica, 28, 157-70.
• Nwanya, S. C., Udofia, J. I., & Ajayi, O. O. (2017). Optimization of machine downtime in the plastic manufacturing. Cogent Engineering, 4(1), 1335444.
• Mohan, T. R., Roselyn, J. P., Uthra, R. A., Devaraj, D., & Umachandran, K. (2021). Intelligent machine learning based total productive maintenance approach for achieving zero downtime in industrial machinery. Computers & Industrial Engineering, 157, 107267.
• Hemalatha, C. S., Vaidehi, V. & Lakshmi, R. (2015). Minimal infrequent pattern based approach for mining outliers in data streams. Expert Systems with Applications, 42(4), 1998–2012.
• Chandran, C. R., & Padmanabhan, A. (2016). An efficient algorithm for detecting outliers in a distributed environment using minimal infrequent item set pattern mining. IIOAB Journal, 7(9), 22-25.
• Sun, C., Wang, X., & Zheng, Y. (2019). Data-driven approach for spatiotemporal distribution prediction of fault events in power transmission systems. International Journal of Electrical Power & Energy Systems, 113, 726-738.
• Jin, H., Chen, J., He, H., Williams, G. J., Kelman, C., & O'Keefe, C. M. (2008). Mining unexpected temporal associations: applications in detecting adverse drug reactions. IEEE Transactions on Information Technology in Biomedicine, 12(4), 488-500.
• Shrivastava, K., & Jotwani, V. (2020). Study to Determine Adverse Diseases Pattern using Rare Association Rule Mining. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 6(3), 519-526.
• Reps, J. M., Aickelin, U., & Hubbard, R. B. (2016). Refining adverse drug reaction signals by incorporating interaction variables identified using emergent pattern mining. Computers in biology and medicine, 69, 61-70.
• Selvarani, S., & Jeya Karthic, M. (2019). Rare Itemsets with high utility for Revenue Analysis. Journal of Computational and Theoretical Nanoscience, 16(4), 1402-1407.
• Jeyakarthic, M., & Selvarani, S. (2019). An efficient approach using FM-weight for revenue prediction on rare itemsets. International Journal of Recent Technology and Engineering, 7, 226-232.
• Rahman, A., Ezeife, C. I., & Aggarwal, A. K. (2010). Wifi miner: An online apriori-infrequent based wireless intrusion detection system. Knowledge Discovery from Sensor Data (Sensor-KDD 2008), 5840, 76-84.
• Adda, M., Wu, L., White, S., & Feng, Y. (2012). Pattern detection with rare item-set mining. International Journal on Soft Computing, Artificial Intelligence and Applications, 1(1), 1-17.
• Bakariya, B., & Thakur, G. S. (2016). Mining rare itemsets from weblog data. National Academy Science Letters, 39(5), 359-363.
• Yildirim, P., Birant, D., & Alpyildiz, T. (2017). Discovering the relationships between yarn and fabric properties using association rule mining. Turkish Journal of Electrical Engineering & Computer Sciences, 25(6), 4788-4804.
• Tsang, S., Koh, Y. S., & Dobbie, G. (2011, August). Rp-tree: rare pattern tree mining. In International Conference on Data Warehousing and Knowledge Discovery (pp. 277-288). Springer, Berlin, Heidelberg.
• Fournier-Viger, P., Lin, J. C. W., Gomariz, A., Gueniche, T., Soltani, A., Deng, Z., & Lam, H. T. (2016, September). The SPMF open-source data mining library version 2. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases (pp. 36-40). Springer, Cham.