Fault detection in rotor system by discrete wavelet neural network algorithm

Rao, K. Babu; Reddy, D. Mallikarjuna

doi:10.1177/10775463211030754

Cited by 15 publications

(6 citation statements)

References 36 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The eight frequency domain features are amplitudes at defect frequencies: Outer Race Defect Frequency (ORDF), Inner Race Defect Frequency (IRDF), Ball Defect Frequency (BDF), and Fundamental Train Frequency (FTF) in both the Fast Fourier Transform (FFT) and the Envelope analysis. The 14 features in the time-frequency domain are seven statistical features in each Continuous Wavelet Transform (CWT) (Rohani Bastami and Bashari, 2020) and Discrete Wavelet Transform (DWT) (Babu Rao and Mallikarjuna Reddy, 2021).…”

Section: Signal Pre-processing and Degradation Indicator Extractionmentioning

confidence: 99%

Automatic incipient fault detection and health state assessment of rolling element bearings using pruned exact linear time method

Buchaiah

Shakya

2022

Journal of Vibration and Control

View full text Add to dashboard Cite

Rolling element bearing is a crucial component in rotating machines. The existence of faults in the bearing causes sudden failures, resulting in catastrophic failure of machines. Incipient fault detection and health state assessment are the essential tasks in condition-based maintenance to avoid machine failures. This paper proposes a new method, the Pruned Exact Linear Time, for identifying the incipient faults and following damage states in the bearing. When a fault initiates in the bearing, there is an increment in the vibration response. This increment can be quantified by the degradation indicator computed from the vibration signal. The Variational Mode Decomposition technique is used to de-noise the vibration signals. Various statistical features are derived from the de-noised signal, and the best feature subset is chosen by the Recursive Feature Elimination method. Then, the significant bearing life degradation indicator is computed using the Reconstruction Independent Component Analysis method by fusing selected features. A novel index is formulated for computing the percentage of failure, which can identify whether the bearing is in a mild failure state or medium failure state. The efficiency of the proposed framework is demonstrated using experimental bearing datasets.

show abstract

Section: Signal Pre-processing and Degradation Indicator Extractionmentioning

confidence: 99%

Automatic incipient fault detection and health state assessment of rolling element bearings using pruned exact linear time method

Buchaiah

Shakya

2022

Journal of Vibration and Control

View full text Add to dashboard Cite

show abstract

“…The proposed methodology is quite signal-noise-aware. For crack detection, a discrete wavelet neural network was employed by Rao and Reddy [19]. Deng et al [20] employed informed deep learning.…”

Section: Introductionmentioning

confidence: 99%

An algorithm for localization of fatigue crack in spinning rotor based on proof by negation

Teyi,

Singh

2023

Eng. Res. Express

View full text Add to dashboard Cite

This paper presents an innovative signal-based approach for detection and localization of a fatigue crack induced in spinning rotors. For development of the algorithm and demonstration of the its capabilities, a conventional rotor supported by rigid end bearings has been considered. In this demonstration, a cracked rotor is simulated using finite elements with four degrees of freedom per node. The model accounts for the gyroscopic effects caused by the offset disc and the breathing of the fatigue crack. The gyroscopic effects are accounted for by the introduction of the gyroscopic matrix in the finite element formulation, and the crack breathing effect is considered by introduction of the crack excitation function in the equations of motion The developed algorithm can also be used to simultaneously determine the magnitude and direction of the disc unbalance relative to the crack front. Also, the algorithm is used to validate the crack location hypothesis at a single node by introducing a variable crack location flag vector. The crack location flag vector with the highest crack stiffness value accurately represents the true crack location.

show abstract

“…Based on a convolutional neural network and the transfer learning method, crack features were automatically extracted for crack diagnosis [41]. Artificial neural networks were trained for crack position and depth identification by using the discrete wavelet transforms coefficients of operating deflection shapes as inputs [42].…”

Section: Introductionmentioning

confidence: 99%

An Improved Crack Breathing Model and Its Application in Crack Identification for Rotors

Liu

Cao

2023

Machines

View full text Add to dashboard Cite

The crack breathing model and crack identification method for rotors using nonlinearity induced by cracks are studied in this work. Firstly, the finite element method is utilized to model a rotor–bearing system with a response-dependent breathing crack to obtain the numerical data for crack identification. During the modelling, an improved breathing crack model is proposed, focused on the unreasonable assumption about crack closure line in the original crack closure line position (CCLP) model. Compared with the original model, the improved breathing model can reflect the nonlinear behavior of cracks better. Secondly, based on the established model, super-harmonic features at 1/3 and 1/2 of the critical rotating speeds under different crack locations and crack depths are extracted for crack identification. Additionally, the super-harmonic features from two measurement points are used as inputs into an artificial neural network with a Levenberg–Marquardt back-propagation algorithm, corresponding crack positions and depths as outputs. The robustness of the method is tested by examining the identification results under different levels of noise. The results show that the proposed crack identification method is efficient for simultaneous identification of crack depth and position in operating rotors.

show abstract

Fault detection in rotor system by discrete wavelet neural network algorithm

Cited by 15 publications

References 36 publications

Automatic incipient fault detection and health state assessment of rolling element bearings using pruned exact linear time method

Automatic incipient fault detection and health state assessment of rolling element bearings using pruned exact linear time method

An algorithm for localization of fatigue crack in spinning rotor based on proof by negation

An Improved Crack Breathing Model and Its Application in Crack Identification for Rotors

Contact Info

Product

Resources

About