مدل پیش‌بینی زمان کارکرد باقی‌مانده تا وضعیت بحرانی بر اساس سوابق تحلیل روغن موتور با راهکار داده‌کاوی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استاد دانشکده مهندسی صنایع و سیستم ها، دانشگاه تربیت مدرس، تهران، ایران (نویسنده مسئول) / skch@modares.ac.ir

2 کارشناسی ارشد، دانشکده مهندسی صنایع و سیستم‌ها، دانشگاه تربیت مدرس، تهران، ایران / a.nabavi124@gmail.com

3 استادیار، دانشکده مهندسی صنایع و سیستم‌ها، دانشگاه تربیت مدرس، تهران، ایران / b.teimourpour@modares.ac.ir

چکیده

یکی از جنبه‌های مهم نگهداری و تعمیرات مبتنی بر شرایط (CBM) پیش‌بینی عمر مفید باقی‌مانده (RUL) بر اساس سوابق گذشته و وضعیت کنونی دستگاه است و تحلیل روغن روانکار یکی از روش‌های CBM است که به علت تماس مستقیم با دستگاه شرایطش بیانگر وضعیت سلامتی دستگاه است. در فرآیند CBM داده‌های زیادی تولید و انباشته می‌شود اما دانش موجود در این داده‌ها به‌طور کامل قابل‌درک نیست و باعث ضایع شدن منابعی گران‌بها می‌شود. برای استخراج اطلاعات و دانش از این داده‌ها به استفاده از روش‌هایی مانند داده‌کاوی نیاز است. در این پژوهش بر اساس تعریف RUL بهترین مدل پیش‌بینی زمان کارکرد باقی‌مانده تا وضعیت بحرانی برای یک مدل بلدوزر بر اساس سوابق تحلیل روغن موتور (مجموعه داده­ای با 2700 رکورد و 129 ویژگی) با راهکار داده‌کاوی ساخته‌شده است. برای ساخت بهترین مدل، بعد از آماده‌سازی مجموعه داده مناسب با 49 رکورد و چهار ویژگی مدل­هایی با روش­های رگرسیون و شبکه عصبی ساخته‌شده است. به علت امکان انجام شدن فعالیت تعویض روغن در فواصل نمونه‌گیری‌ها، مدل‌ها با دو روش اعمال مقادیر ویژگی‌های مستقل ساخته‌شده‌اند. بر اساس ارزیابی عملکرد مدل‌ها بهترین مدل با شبکه عصبی و روش دوم اعمال مقادیر ویژگی‌های مستقل که استفاده از مقادیر جدید (تجمعی) دو ویژگی مستقل (Fe, Cu) و مقدار واقعی (غیر تجمعی) یک ویژگی مستقل (Vis40) بوده با خطای پیش بینی 23526.662 -/+ 958559.033 ساخته‌شده است

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Prediction model of remaining operating time until critical state based on engine oil analysis records with data mining solution

نویسندگان [English]

  • Seyed Kamal Chaharsooghi 1
  • Abolfazl Nabavi 2
  • Babak Teimourpour 3
1 Professor, Faculty of Industrial & Systems Engineering, Tarbiat Modares University, Tehran, Iran (skch@modares.ac.ir) (Main Author)
2 MSc, Faculty of Industrial & Systems Engineering, Tarbiat Modares University, Tehran, Iran (a.nabavi124@gmail.com)
3 Assistant Professor, Faculty of Industrial & Systems Engineering, Tarbiat Modares University, Tehran, Iran (b.teimourpour@modares.ac.ir)
چکیده [English]

One of the important aspects of Condition Based Maintenance (CBM) is the prediction of remaining useful life (RUL) based on past records and current state of the device and lubricant oil analysis is one of the methods of CBM which due to its direct contact with the device, its condition expresses the device's health. In the CBM process a large mass of data is generated and accumulated, but the knowledge included in this data cannot be fully understood and result in the loss of valuable resources. To extract information and knowledge from these data, it is necessary to use methods such as data mining. In this study, based on the definition of RUL, the best prediction model of remaining operating time for a bulldozer model until critical state has been created with data mining solution based on engine oil analysis records (dataset with 2700 records and 129 features). To create the best model, regression and neural network models have been created after preparing the proper dataset with 49 records and 4 features. Due to the feasibility of oil change at sampling intervals, the models have been created using two methods of applying independent features values. Based on the performance evaluation of the models, the best model with neural network and the second method of applying independent features values have been created with prediction error 958559.033 +/- 23526.662, which are to use new values (cumulative) of two independent features (Fe, Cu) and the actual value (non-cumulative) of an independent feature (Vis40)

کلیدواژه‌ها [English]

  • Condition based maintenance
  • Oil analysis
  • Remaining useful life
  • Data Mining
صنیعی آباده، محمد. محمودی، سینا و طاهرپور، محدثه (1391). داده‌کاوی کاربردی، تهران: انتشارات نیاز دانش
Alwyn Carstens, Wiehahn (2012). Regression Analysis of Caterpillar 793D Haul Truck Engine Failure Data and Through-Life Diagnostic  Information Using the Proportional Hazards Model. Master's thesis of Science in Industrial Engineering, Stellenbosch University, South Africa.
Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996a) From data mining to knowledge discovery: An overview, In Advances in Knowledge Discovery and Data Mining, U. Fayyad, G. Piatetsky-Shapiro, P. Smyth, & R. Uthurusamy, Eds. AAAI/MIT Press, Cambridge, Mass.
Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996b) From Data Mining to Knowledge Discovery in Databases, AI Magazine, Vol. 17, pp. 1-13
Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996c) Knowledge Discovery and Data Mining: Towards a Unifying Framework, KDD'96 Proceedings of the Second International Conference on Knowledge Discovery and Data Mining, pp. 82-88
Fayyad, U., Piatetsky-Shapiro, G., and Smyth, P. (1996d) The KDD Process for Extracting Useful Knowledge from Volumes of Data, Communications of the ACM, Vol. 39, pp. 27-34 
J. Guillén, A., González-Prida, V., Fco. Gómez, J., and Crespo, A. (2016) Standards as reference to build a PHMBased solution, 10th World Congr. Eng. Asset Manag, Springer International Publishing, pp. 207–214
Han, J., Kamber, M., & Pei, J. (2012) Data Mining Concepts and Techniques, 3th ed. Morgan Kaufmann Publishers, San Francisco
Hodkiewicz, M. & Cripps, E. (2012) Remaining Useful Life Estimation of Caterpillar Vehicle Compartments, CEED Seminar Proceedings
Jardine, A.K.S., Lin, D., & Banjevic, D. (2006) A review on machinery diagnostics and prognostics implementing condition-based maintenance, Journal of Mechanical Systems and Signal Processing, Vol. 20, pp. 1483–1510
Meng, X., Qu, Y., & Zhou, Y. (2012) Linear Regression Method-Based Data Mining in Vehicle Maintenance, International Conference on Information Engineering and Applications (IEA), pp. 625-630
Mwanza, B.G., & Mbohwa, CH. (2016) Safety in Maintenance: An Improvement Framework, 14th Global Conference on Sustainable Manufacturing
Olurotimi Akintunde, D. (2008) Spectrometric Oil Analysis–An Untapped Resource for Condition Monitoring, AU Journal of Technology, Vol. 12, pp. 107-114
 Piatetsky-Shapiro, G. (1991) Knowledge Discovery in Real Databases, AI Magazine, Vol. 11
Prajapati, A., Bechtel, J., & Ganesan, S. (2012) Condition based aintenance: a survey, Journal of Quality in Maintenance Engineering, Vol. 18, pp. 384-400
Ruschel, E., Alves Portela Santos, E., & de Freitas Rocha Loures, E. (2017) Industrial maintenance decision-making: A systematic literature review, Journal of Manufacturing Systems, Vol. 45, pp 180–194
Shin, JH., & Jun, HB. (2015) On condition based maintenance policy, Journal of Computational Design and Engineering, Vol. 2, pp. 119–127
Sikorska, J.Z., Hodkiewicz, M., & Ma, L. (2011) Prognostic modelling options for remaining useful life estimation by industry, Journal of Mechanical Systems and Signal Processing, 25 pp 1803–1836
Tianle, Feng., & Jianmin, Z. (2010) SVM-PHM:  A Novel Method for Remaining Useful Life Prediction, International Conference of Information Science and Management Engineering, , pp. 369-372
Wang, W.,  & Zhang, W. (2005) A Model To Predict the Residual Life of Aircraft Engines Based upon Oil Analysis Data, naval research logistics, Vol. 52, pp. 276-284
Wang, J., Duan, X., Li, Y., & Bai, P. (2014) Prediction of aero engine fault by relative vector machine and genetic algorithm model,Journal of Advanced Materials Research, Vols. 998-999 , pp 1033-1036
Wong, EL., Jefferis, T., & Montgomery ,N. (2010) Proportional hazards modeling of engine failures in military vehicles, Journal of Quality in Maintenance Engineering, Vol. 16, pp. 144-155
Xiongzi, C., Jinsong, Y., Diyin, T., &  Yingxun, W. (2011) Remaining Useful Life Prognostic Estimation for Aircraft Subsystems or Components: A Review, The Tenth International Conference on Electronic Measurement & Instruments
Yadav, G., Ganai, P., Tiwari, S., & Maheshwari, M. (2014) An Investigation For Prior Failure Of Engine Component Through  Spectroscopey Oil Analysis program, Applied Mechanics and Materials Vols. 592-594 , pp 1362-1365
Zhu, J., Yoon, M., He, D., Qu, Y., Bechhoefer, E. (2013) Lubrication Oil Condition Monitoring and Remaining Useful Life Prediction with Particle Filtering. International Journal of Prognostics and Health Management, ISSN 2153-2648