Aerospace Knowledge and Technology Journal

Aerospace Knowledge and Technology Journal

Performance of probabilistic neural network and support vector machine for propeller fault detection using vibration analysis

Document Type : Research Paper

Author
Aliasghar Naderi
Associate Professor, Department of Engineering, Imam Ali University, Tehran, Iran.
Abstract
Fault diagnosis in propellers for aircraft and ships is of great significance. Vibration monitoring can help predict and prevent propeller failures by detecting imbalances. There are many techniques based on the vibration analysis for fault diagnosis, and this study investigates propeller defects using experimental vibration analysis. Data were collected through feature extraction methods in both the time-domain and frequency-domain. Subsequently, dimensionality-reduced features were applied as inputs to probabilistic neural networks (PNN) and support vector machines (SVM), and their classification results were analyzed and compared. The dataset was divided into training and testing subsets. The training data achieved nearly 100% classification accuracy across all propeller fault conditions, demonstrating the precision of the experimental setup and the efficacy of PNN and SVM in fault classification. To compare healthy and defective datasets, adjusting rotational speed to an optimal value combined with time- and frequency-domain features yielded the highest accuracy for test data classification. The results indicate that PNN outperforms SVM, achieving superior classification accuracy and robustness. Specifically, PNN successfully distinguished all four propeller fault conditions with high accuracy, underscoring its reliability for vibration-based fault detection.
Keywords
Fault Detection
Vibrational Analysis
Propeller
Probabilistic Neural Network
Support Vector Machin
Subjects
[1] Rajendra P Palanisamy, Chetan S. Kulkarni, Matteo Corbetta, Portia Banerjee, Fault detection and Performance Monitoring of Propellers in Electric UAV IEEE Conference Publication, pp. 05-12 2022.
[2] S. Sastry, I. Bhargavi Rachana, K. Durga Rao, Stress Analysis of Helicopter Composite Blade Using Finite Element Analysis, International Journal of Engineering Research and Technology, Vol. 2, No. 12 , pp. 1291-1299, 2018.
[3] Seyyed Mohamad M., Mostafa K., AmirMahdi S., Sensitivity Analysis of Vibration Characteristics for Localization of Imbalance Fault on the Helicopter Blade, Aerospace Knowledge and Technology Journal, Vol. 13 (1), pp. 113-128, 2024, [in persian].
[4] S.W. Doebling, C.R. Farrar, M.B. Prime, D.W. Shevitz, Damage identification and health monitoring of structural and mechanical systems from changes in their vibration characteristics: a literature review, Technical Report LA-13070-MS, Los Alamos National Laboratory, 1996.
[5] H. Sohn, C.R. Farrar, F.M. Hemez, D.D. Shunk, D.W. Stinemates, B.R. Nadler, J.J. Czarnecki, A review of structural health monitoring literature: 1996-2001, Technical Report LA-13070-MS, Los Alamos National Laboratory, 2004.
[6] Gangsar, P., & Tiwari, R., Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review, Mechanical systems and signal processing, Vol. 144:106908, 2020.
[7] Ikpe, A. E., Etuk, E. M., & Adoh, A. U., Modelling and analysis of 2-stage planetary gear train for modular horizontal wind turbine application, Journal of applied research on industrial engineering, Vol. 6(4), pp. 268-282, 2019.
[8] Bogard, F., Debray, K., Guo, Y. Q., & Pavan, A., Numerical methodology to easily detect defects in revolving machines by vibration analysis, Elsevier, Mécanique and industries, Vol. 3, pp. 79-87, 2002.
[9] Zohreh M., MirMohammad E., Morteza S., seyednacer R., Identification and damage detection of beam-like structure using vibration signals based on simulated model real healthy state and deep convolutional neural network,  Amirkabir Journal of Mechanical Engineering, Vol. 53(4), pp. 2193-2216, 2022, [in persian].
[10] Yezhong Lu, Haifeng Ma, Yuxin Sun, Qinghua Song, Zhanqiang Liu, Zhenhua Xiong, An interpretable anti-noise convolutional neural network for online chatter detection in thin-walled parts milling, Mechanical Systems and Signal Processing, Vol. 206:110885, 2024.
[11] Orhan Yaman, Ferhat Yol, Ayhan Altinors, Fault Detection Method Based on Embedded Feature Extraction and SVM Classification for UAV Motors, Microprocessors and Microsystems, Vol. 94: 104683, 2022
[12] D. F. Specht, Probabilistic neural networks, Neural Networks, Vol. 3, pp. 109-118, 1990.
[13] S. Rutkowski L., Methods and techniques of artificial intelligence, Wydawnictwo Naukowe PWN, Warsaw, 2012.
[14] S. S. Haykin, Neural networks and learning machines, Pearson Upper Saddle River, NJ, USA, 2009.
[15] G. Zheng and et.al., Neural networks and learning machines, Pearson Upper Saddle River, Underground Space,Vol. 6(2), pp. 126-133, 2021.
[16] Burdes C.J.C., A Tutorial on Support Vector Machines for Pattern Recognition Data Mining and Knowledge Discovery, Kluwer Academic Publishers, Boston, 1998.