An artificial neural network application to fault detection of a rotor bearing system

Abstract

PurposeTo improve the application neural networks predictors on bearing systems and to investigate the exact neural model of the ball‐bearing system.Design/methodology/approachA feed forward neural network is designed to model‐bearing system. Two results are compared for finding the exact model of the system.FindingsThe results of the proposed neural network predictor gives superior performance for analysing the behaviour of ball bearing undergoing loading deformation.Research limitations/implicationsThe results of the proposed neural network exactly follows desired results of the system. Neural network predictor can be employed in practical applications.Practical implicationsAs theoretical and practical study is evaluated together, it is hoped that ball‐bearing designers and researchers will obtain significant results in this area.Originality/valueThis paper fulfils an identified research results need and offers practical investigation for an academic career and research. Also, It should be very helpful for industrial application of ball‐bearing systems.

Fault diagnosis and location of the aero-engine hydraulic pipeline based on Kalman filter

“…The vibration signals y(t) are measured by FBG. The Kalman filter estimate value of time step t can be calculated using equation (12), then the state error between the estimation value and the measurement result can be obtained. A safety estimate error is set first, then the new estimate error over the safety error could predict the pipeline conditions.…”

“…The value x _ t of the hydraulic pipeline vibration signals in time step t, namely, the prediction value of Kalman Filter, can be obtained from equation (11). The measurement y(t) in the same time step can be obtained by the signal acquisition, the Kalman filter estimation value of time step t can be calculated by equation (12), then state error between the estimation value and the measurement can be obtained. A safety estimate error could be set up first, then the new estimate error over the safety error could predict the pipeline conditions.…”

“…P t is the unconditional variance-covariance matrix of the estimation error. The variance-covariance matrix is given by equation (12). Kalman filter technique can be used for estimating the system status, and the prior estimates are applied to obtain a real-time estimate combining with the measurement signals.…”

“…[4][5][6] High-frequency resonance analysis methods, such as envelope, 7 bicoherence, 8 and other frequency analysis methods were proposed to analyze the vibration signals and defect localized faults. Several time-frequency methods had been applied to distinguish these vibration signals for fault location, such as wavelet analysis, [9][10][11] neural network, 12,13 and hidden Markov modeling (HMM). 14,15 The hydraulic pipeline vibration signals were nonlinear and often non-stationary duo to various working states of the aero-engine.…”

Experimental analysis on fault detection for a direct coupled rotor-bearing system

“…The system vibration and noise were analyzed with and without load. Another investigation of Taplak et al [20] has been proposed the exact neural model for fault detection of a rotor bearing system to analyze the ball-bearing behavior undergoing the loading deflection. Sawicki et al [21] have proposed a variety of approaches to identify and possibly locate crack (and other faults) in a rotor at an early stage in their development.…”