مقایسه دو روش شبکه عصبی مصنوعی عمیق و شبکه عصبی پیچشی در طبقه‌بندی عیوب جعبه‌دنده

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشگاه شهید بهشتی

چکیده

امروزه نظارت بر وضعیت ماشین‌آلات و تشخیص هوشمند عیوب برای تولیدات صنعتی نقش بسیار پراهمیتی را داراست. روش‌های هوش مصنوعی برای پایش در مقیاس‌های بزرگ (کلان‌داده‌[i]) بدون هیچ‌گونه فرض آماری در مورد داده‌ها می‌توانند به‌درستی عمل کنند. در این پژوهش مقایسه دو روش شبکه عصبی مصنوعی عمیق و شبکه عصبی پیچشی[ii] در طبقه‌بندی عیوب جعبه‌دنده انجام شده است. در روش شبکه عصبی مصنوعی عمیق ویژگی‌ها از سیگنال زمانی شتاب استخراج شده و در روش دیگر از خود سیگنال به‌عنوان ورودی استفاده شده است. به‌طور خلاصه از این روش‌ها برای طبقه‌بندی 9 حالت معیوب و یک حالت سالم در 6 ترکیب سرعت و بار متفاوت استفاده و با یکدیگر مقایسه شده است و سپس به بیان اثر چالش‌هایی از قبیل طول پنجره، ضریب یادگیری و تعیین تعداد ویژگی‌ها و چگونگی برطرف کردن آنها پرداخته شده است. در انتها با قیاس نتایج به‌دست آمده از هر دو روش این نتیجه حاصل شد که قدرت تشخیص شبکه عصبی پیچشی در این مورد بهتر از روش دیگر است.
 
[i]. Big data
[ii]. Convolutional neural network (CNN)


 


 

 
 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Comparison of two deep neural network and convolutional neural network methods in the classification of gearbox faults

نویسندگان [English]

  • Armin Fahandezh
  • Mostafa Abedi
Shahid Beheshti University
چکیده [English]

Condition monitoring and fault diagnosis of large industrial equipment has become very important role nowadays. Powerful artificial intelligent methods can be appropriately used on big data without any further statistical assumption. In this research, two compromising methods including deep neural network and convolutional neural network have been used to classify faults of a laboratory gearbox. Both networks have been used to classify nine faulty classes and one healthy class of the gearbox using vibration signal. The data have been collected at six different load and speed combinations. The measured time domain vibration signal was used as neural network input. The classification accuracy of both methods have been obtained. The effect of challenging parameters such as window size, learning rate and number of extracted features on the classification accuracy have been studied. Finally after the comparison of the results, it was concluded that the accuracy of the convolutional neural network was superior.

کلیدواژه‌ها [English]

  • Convolotional neural network
  • deep learning
  • vibration
  • gearbox
  • fault diagnosis
  • Sait, Abdulrahman S., and Yahya I. Sharaf-Eldeen, "A review of gearbox condition monitoring based on vibration analysis techniques diagnostics and prognostics." In Rotating Machinery, Structural Health Monitoring, Shock and Vibration, Volume 5: Proceedings of the 29th IMAC, A Conference on Structural Dynamics, 2011, Springer New York, 2011, pp. 307-324.
  • Goyal, Deepam, Vanraj, B. S. Pabla, and S. S. Dhami, "Condition monitoring parameters for fault diagnosis of fixed axis gearbox: a review", Archives of Computational Methods in Engineering, 2017, 24, pp.543-556.
  • Yin, Shen, Xianwei Li, Huijun Gao, and Okyay Kaynak, "Data-based techniques focused on modern industry: An overview", IEEE Transactions on industrial electronics,2014, Vol.62, no.1, 2014, pp.657-667.
  • Lei, Yaguo, Intelligent fault diagnosis and remaining useful life prediction of rotating machinery, Butterworth-Heinemann, 2016.
  • Zhang, Wan, Min-Ping Jia, Lin Zhu, and Xiao-An Yan, "Comprehensive overview on computational intelligence techniques for machinery condition monitoring and fault diagnosis", Chinese Journal of Mechanical Engineering,2017, Vol.30, pp.782-795.

[6] Mahesh, Batta, "Machine learning algorithms-a review", International Journal of Science and Research (IJSR).[Internet], 2020, Vol.9, no.1, pp.381-386.

[7] Duan, Lixiang, Mengyun Xie, Jinjiang Wang, and Tangbo Bai, "Deep learning enabled intelligent fault diagnosis: Overview and applications", Journal of Intelligent & Fuzzy Systems, 2018, Vol.35, no.5, pp.5771-5784.

[8] Liu, Ruonan, Boyuan Yang, Enrico Zio, and Xuefeng Chen, "Artificial intelligence for fault diagnosis of rotating machinery: A review", Mechanical Systems and Signal Processing, 2018, Vol.108, pp.33-47.

[9] van Dreven, Jonne, Veselka Boeva, Shahrooz Abghari, Håkan Grahn, Jad Al Koussa, and Emilia Motoasca, "Intelligent approaches to fault detection and diagnosis in district heating: Current trends, challenges, and opportunities", Electronics, 2023, Vol.12, no.6, p.1448.

[10] LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton, "Deep learning", nature, 2015, Vol.521, no.7553, pp.436-444.

[11] Lei, Yaguo, Feng Jia, Jing Lin, Saibo Xing, and Steven X. Ding, "An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data", IEEE Transactions on Industrial Electronics, 2016, Vol.63, no.5, pp.3137-3147.

[12] Praveenkumar, T., M. Saimurugan, P. Krishnakumar, and K. I. Ramachandran, "Fault diagnosis of automobile gearbox based on machine learning techniques", Procedia Engineering, 2014, Vol.97, pp.2092-2098.

[13] Gecgel, Ozhan, Stephen Ekwaro-Osire, João Paulo Dias, Abdul Serwadda, Fisseha M. Alemayehu, and Abraham Nispel, "Gearbox fault diagnostics using deep learning with simulated data", In 2019 IEEE international conference on prognostics and health management (ICPHM), 2019, IEEE, pp.1-8.

[14] Samanta, B. I. S. W. A. J. I. T., K. R. Al-Balushi, and S. A. Al-Araimi, "Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection", Engineering applications of artificial intelligence, 2003, Vol.16, no.7-8, pp.657-665.

[15] Chen, ZhiQiang, Chuan Li, and René-Vinicio Sanchez, "Gearbox fault identification and classification with convolutional neural networks", Shock and Vibration, 2015.

[16] Liang, Xihui, Ming J. Zuo, and Zhipeng Feng, "Dynamic modeling of gearbox faults: A review", Mechanical Systems and Signal Processing, 2018, Vol.98, pp.852-876.

[17] Zhao, Rui, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, and Robert X. Gao, "Deep learning and its applications to machine health monitoring", Mechanical Systems and Signal Processing, 2019, Vol.115, pp.213-237.

[18] Duan, Lixiang, Mengyun Xie, Jinjiang Wang, and Tangbo Bai, "Deep learning enabled intelligent fault diagnosis: Overview and applications", Journal of Intelligent & Fuzzy Systems, 2018, Vol.35, no.5, pp.5771-5784.

[19] Saufi, Syahril Ramadhan, Zair Asrar Bin Ahmad, Mohd Salman Leong, and Meng Hee Lim, "Challenges and opportunities of deep learning models for machinery fault detection and diagnosis: A review", Ieee Access, 2019, Vol.7, pp.122644-122662.

[20] Zhao, Xiaoli, and Minping Jia, "A new local-global deep neural network and its application in rotating machinery fault diagnosis", Neurocomputing, 2019, Vol.366, pp.215-233.

[21] Liu, Haiying, Ruizhe Ma, Daiyi Li, Li Yan, and Zongmin Ma, "Machinery fault diagnosis based on deep learning for time series analysis and knowledge graphs", Journal of Signal Processing Systems, 2021, Vol.93, pp.1433-1455.

[22] Jiang, Wanlu, Chenyang Wang, Jiayun Zou, and Shuqing Zhang, "Application of deep learning in fault diagnosis of rotating machinery", Processes, 2021, Vol.9, no.6, p.919.

[23] Li, Xiang, Wei Zhang, Qian Ding, and Jian-Qiao Sun, "Intelligent rotating machinery fault diagnosis based on deep learning using data augmentation", Journal of Intelligent Manufacturing, 2020, Vol.31, pp.433-452.

[24] Chen, Hongtian, Kai Zhong, Guangtao Ran, and Chao Cheng, "Deep Learning-Based Machinery Fault Diagnostics", Machines, 2022, Vol.10, no.8, p.690.

[25] Zhang, Cheng, Liqing Xu, Xingwang Li, and Huiyun Wang, "A method of fault diagnosis for rotary equipment based on deep learning", In 2018 Prognostics and System Health Management Conference (PHM-Chongqing), IEEE, 2018, pp.958-962.

[26] جواد حسن‌پور سنگلجی، "طراحی الگوریتم آشکارسازی عیب جعبه‌دنده توربین بادی با استفاده از شبکه‌های عصبی عمیق"، دانشگاه شهید بهشتی، 1401.