Detection of Blade Crack in a Rotor System Using MLP-Based Automatic Feature Selector

پذیرفته شده برای ارائه شفاهی ، صفحه 1-11 (11) اصل مقاله (992.22 K)

کد مقاله : 1076-ISAV2022 (R2)

نویسندگان

Abdolreza Ohadi ؛ Emadaldin Sh. Khoram-Nejad

آزمایشگاه تحقیقاتی آکوستیک، دانشکده مهندسی مکانیک، دانشگاه صنعتی امیرکبیر (پلی تکنیک تهران)

چکیده

This paper aimed to detect the crack location in a shaft-disk-cracked blade (SDCB) system. An open crack with three different depths and three distances from the blade root is considered. A finite element (FE) simulation of the SDCB system rotating at 3000 rpm was done in the MSC Adams as commercial software, simulating the systems' dynamics. The results are compared with those of another FE software and the assumed mode method (AMM) to validate the modeling procedure. Feature extraction and selection always have crucial roles in classification problems. Therefore, this paper tries to show the benefit of automatic feature selection compared to manual feature selection to detect the crack location. For this purpose, the performance of an ensemble classifier using manual feature selection is compared to a deep multi-layer perceptron (MLP)-based classifier, which selects the best features automatically and determines the crack location. The ensemble classifier includes the support vector machine (SVM), k-nearest neighbor (k-NN), and decision tree classifiers. Then, the sensitivity of the proposed crack detection models to different measuring points, one at the bearing location and another near the cracked blade tip, is studied. The best location for sensors to detect cracks more accurately is determined during this comparison. The results indicate that the best accuracy of crack detection is achieved when using the MLP-based classifier and the signals of the displacement of the cracked blade tip. This accuracy is 97.14%, and the existence of a crack is detected without an error (100% accuracy).

کلیدواژه ها

Crack Detection؛ feature selection؛ Assumed mode method؛ multi-layer perceptron؛ Ensemble classifier

موضوعات

Monitoring and diagnostics of rotating machinery

Title

Detection of Blade Crack in a Rotor System Using MLP-Based Automatic Feature Selector

Authors

Abdolreza Ohadi, Emadaldin Sh. Khoram-Nejad

Abstract

Keywords

Crack Detection, feature selection, Assumed mode method, multi-layer perceptron, Ensemble classifier

مراجع

<div class="page" title="Page 11"> <div class="layoutArea"> <div class="column"><ol dir="ltr"> <li> T. Zhang, J. Chen, F. Li, K. Zhang, H. Lv, S. He, and E. Xu, “Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions,” ISA Trans. 119, 152–171 (2022). </li> <li> H. Alavi, A. Ohadi, and S. T. Niaki, “A novel targeted method of informative frequency band selection based on lagged information for diagnosis of gearbox single and compound faults,” Mech. Syst. Signal Process. 170, 108828 (2022). </li> <li> B. Li, B. Tang, L. Deng, and J. Wei, “Joint attention feature transfer network for gearbox fault diagnosis with imbalanced data,” Mech. Syst. Signal Process. 176, 109146 (2022). </li> <li> M. Gohari and A. M. Eydi, “Modelling of shaft unbalance: Modelling a multi discs rotor using K-Nearest Neighbor and Decision Tree Algorithms,” Measurement 151, 107253 (2020). </li> <li> P. Shinde and R. G. Desavale, “Application of dimension analysis and soft competitive tool to predict compound faults present in rotor-bearing systems,” Measurement, 110984 (2022). </li> <li> Y. Liu, J. T. Li, K. P. Feng, Y. L. Zhao, X. X. Yan, and H. Ma, “A novel fault diagnosis method for rotor rub-impact based on nonlinear output frequency response functions and stochastic resonance,” J. Sound Vib. 481, 115421 (2020). </li> <li> Q. Wang, W. Wu, F. Zhang, and X. Wang, “Early rub-impact fault detection of rotor systems via deterministic learning,” Control Eng. Pract. 124, 105190 (2022). </li> <li> S. Fatima, A. R. Mohanty, and V. A. Naikan, “A misalignment detection methodology by measuring rate of temperature rise of shaft coupling using thermal imaging,” Proc. Inst. Mech. Eng. Part O J. Risk Reliab. 229, 209–219 (2015). </li> <li> T. Zhang, F. Xu, and M. Jia, “A centrifugal fan blade damage identification method based on the multi-level fusion of vibro-acoustic signals and CNN,” Measurement 199, 111475 (2022). </li> <li> T. Ma, F. Xu, J. Hu, D. Song, and S. Cao, “Double Gaussian potential stochastic resonance method and its application in centrifugal fan blade crack detection,” Chin. J. Phys. 74, 279– 295 (2021). </li> <li> F. Mevissen and M. Meo, “Ultrasonically stimulated thermography for crack detection of tur- bine blades,” Infrared Phys. Technol. 122, 104061 (2022). </li> <li> Y. Zhang, F. Avallone, and S. Watson, “Wind turbine blade trailing edge crack detection base on airfoil aerodynamic noise: An experimental study,” Appl. Acoust. 191, 108668 (2022). </li> <li> S. Chen, Y. Yang, H. Hu, F. Guan, G. Shen, Z. Bian, and H. Guo, “Interpolation method for wideband signal reconstruction based on blade tip timing measurement,” Measurement 176, 109168 (2021). </li> <li> P. Beauseroy and R. Lengellé, “Nonintrusive turbomachine blade vibration measurement sys- tem,” Mech. Syst. Signal Process. 21, 1717–1738 (2007). </li> </ol></div> </div> </div>