انتخاب توابع ویژگی مناسب برای ایجاد شاخص سلامت در ماشین‌آلات دوار با بهره‌گیری از فلسفه نوین مدیریت سلامت پیش‌بینانه

نوع مقاله: مقاله پژوهشی

نویسندگان

دانشکده مهندسی مکانیک، دانشگاه علم و صنعت ایران، تهران، ایران

چکیده

مدیریت سلامت پیش‌بینانه (PHM) یک فلسفه نوین در علم نگهداری و تعمیرات (نت) است که به تشخیص و پیش‌آگاهی نارسایی و عیوب در دستگاه‌ها می‌پردازد. PHM در ماشین‌آلات دوار عموما با تجزیه و تحلیل سیگنال‌های ارتعاش، انتشار صوت، دما یا آنالیز روغن انجام می‌شود. با در دست داشتن شاخص سلامت مناسب بدست آمده از تجزیه و تحلیل سیگنال، می‌توان نقص سیستم را به موقع تشخیص داد و دستگاه را برای عملیات نت آماده کرد. در این مقاله، از سیگنال‌های انتشار صوتی اسپیندل یک دستگاه فرز برای تشخیص ساییدگی و یا شکستگی ابزار استفاده شده است. ابتدا با تجزیه و تحلیل موجک، نویز سیگنال کاهش داده شد تا بتوان با تجزیه و تحلیل سیگنال به شاخص سلامت مناسب دست یافت. در اینجا از سه تابع موجک مادر db4 و sym5 و haar و سه روش آستانه گذاری استفاده شده است. تحقیقات نشان داد که توابع مادر sym5 و haar با روش آستانه‌گذاری penalize low، با 3 سطح تجزیه، کمترین MSE به ترتیب 0.0018 و 0.0019 را دارد. در مرحله بعد، چهارده تابع ویژگی سیگنال، استخراج و با یکدیگر مقایسه شدند. از بین توابع مورد بررسی برای شاخص سلامت، نتیجه نشان داد که میزان تغییرات از حالت سالم به ناسالم ابزار علاوه بر تابع میانگین مجذور مربعات (RMS) با 10% تغییر، مربع ریشه سیگنال با 10%، آنتروپی 15%، انرژی 28%، فاکتور ضربه 33%، شاخص بیشینه سیگنال 48% نیز می‌توانند معیارهای مناسبی برای شاخص سلامت باشند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Appropriate Feature Selection for Creating Health Index in Rotary Machines Utilizing the Prognostic Health Management System

نویسندگان [English]

  • Amid Maghsoudi
  • mohammad riahi
mechanical school, Iran University of Science and Technology, Tehran, Iran
چکیده [English]

Prognostic Health Management (PHM) is a new philosophy in maintenance that deals with the diagnosis and prognosis of failures and defects in devices PHM in rotary machines is usually utilizing the analysis of vibration signals, acoustic emission, temperature or oil analysis. By having a proper health index obtained from signal analysis, it is possible to detect system defects and prepare the device for maintenance operation. In this paper, the acoustic emission signals of a milling machine are used to detect tool wear or breakage. First, with wavelet analysis, the signal noise was reduced in order to achieve a suitable analysis to select the health index. Here, three mother wavelet functions db4, sym5 and haar and three thresholding methods are used. Research has shown that the parent functions sym5 and haar with low penalize threshold method, with 3 levels of analysis, have the lowest MSE of 0.0018 and 0.0019, respectively. In the next step, fourteen signal feature functions were extracted and compared with each other. Among the functions studied for the health index, the result showed that from healthy to unhealthy instrument in addition to the root mean square (RMS) function with 10% change, signal root square with 10%, entropy 15%, energy 28%, impact factor 33%, the maximum signal index of 48% can also be suitable criteria for the health index.

کلیدواژه‌ها [English]

  • Rotating machines
  • Health Index
  • Feature selection
  • wavelet analysis
  • Noise Reduction
A. Soualhi, Y. Hawwari, K. Medjaher, G. Clerc, R. Hubert, and F. Guillet, "PHM survey: implementation of signal processing methods for monitoring bearings and gearboxes," International Journal of Prognostics and Health Management, vol. 9, p. 0, 2018.
T. Xia, Y. Dong, L. Xiao, S. Du, E. Pan, and L. Xi, "Recent advances in prognostics and health management for advanced manufacturing paradigms," Reliability Engineering & System Safety, vol. 178, pp. 255-268, 2018.
M. C. O. Keizer, S. D. P. Flapper, and R. H. Teunter, "Condition-based maintenance policies for systems with multiple dependent components: A review," European Journal of Operational Research, vol. 261, pp. 405-420, 2017.
S. Alaswad and Y. Xiang, "A review on condition-based maintenance optimization models for stochastically deteriorating system," Reliability Engineering & System Safety, vol. 157, pp. 54-63, 2017.
Y. Zheng, "Predicting Remaining Useful Life Based on Hilbert–Huang Entropy with Degradation Model," Journal of Electrical and Computer Engineering, vol. 2019, 2019.
Y. Lei, N. Li, L. Guo, N. Li, T. Yan, and J. Lin, "Machinery health prognostics: A systematic review from data acquisition to RUL prediction," Mechanical Systems and Signal Processing, vol. 104, pp. 799-,2018
A. Agogino and K. Goebel, "BEST lab," UC Berkeley, Milling data set. NASA Ames Prognostics Data Repository. http://ti. arc. nasa. gov/project/prognostic-data-repository, NASA Ames Research Center, Moffett Field, CA, 2007.
V. Vakharia, S. Pandya, and P. Patel, "Tool wear rate prediction using discrete wavelet transform and K-Star algorithm," Life Cycle Reliability and Safety Engineering, vol. 7, pp. 115-125, 2018.
M. Riahi and A. Maghsoudi, "Identification of the Optimum Level of Wavelet Decomposition for Acoustic Emission Signal Denoising of a Milling Machine," presented at the "Biennial International Conference on Experimental Solid Mechanics", iran university of science and technology, Tehran, Iran, 2020.
T. Benkedjouh, N. Zerhouni, and S. Rechak, "Tool wear condition monitoring based on continuous wavelet transform and blind source separation," The International Journal of Advanced Manufacturing Technology, vol. 97, pp. 3311-3323, 2018.
M. Riahi and A. Maghsoudi, “Feature Selection in Milling Process Utilizing Wavelet Analysis," presented "Biennial International Conference on Experimental Solid Mechanics", iran university of science and technology, Tehran, Iran, 2020.
M. Srivastava, C. L. Anderson, and J. H. Freed, "A new wavelet denoising method for selecting decomposition levels and noise thresholds," IEEE Access, vol. 4, pp. 3862-3877, 2016.
C. Drouillet, J. Karandikar, C. Nath, A.-C. Journeaux, M. El Mansori, and T. Kurfess, "Tool life predictions in milling using spindle power with the neural network technique," Journal of Manufacturing Processes, vol. 22, pp. 161-168, 2016.
S. Ramezani, A. Moini, and M. Riahi, "A Model to Determining the State of Degradation and Remaining Useful Life of Rotating Equipment, With a New Approach to Combination and Predicting Health Index," Modares Mechanical Engineering, vol. 19, pp. 2351-2365, 2019.
J. Lee, F. Wu, W. Zhao, M. Ghaffari, L. Liao, and D. Siegel, "Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications," Mechanical systems and signal processing, vol. 42, pp. 314-334, 2014.
A. Qin, Q. Zhang, Q. Hu, G. Sun, J. He, and S. Lin, "Remaining useful life prediction for rotating machinery based on optimal degradation indicator," Shock and Vibration, vol. 2017, 2017.
R. Liu, B. Yang, E. Zio, and X. Chen, "Artificial intelligence for fault diagnosis of rotating machinery: A review," Mechanical Systems and Signal Processing, vol. 108, pp. 33-47, 2018.
B. Huang, Y. Di, C. Jin, and J. Lee, "Review of data-driven prognostics and health management techniques: lessions learned from PHM data challenge competitions," in Conference: Machine Failure Prevention Technology, 2017.