Real-time classification of rotating shaft loading conditions using artificial neural networks

Abstract

Vibration analysis can give an indication of the condition of a rotating shaft highlighting potential faults such as unbalance and rubbing. Faults may however only occur intermittently and consequently to detect these requires continuous monitoring with real time analysis. This paper describes the use of artificial neural networks (ANNs) for classification of condition and compares these with other discriminant analysis methods. Moments calculated from time series are used as input features as they can be quickly computed from the measured data. Orthogonal vibrations are considered as a two-dimensional vector, the magnitude of which can be expressed as time series. Some simple signal processing operations are applied to the data to enhance the differences between signals and comparison is made with frequency domain analysis.

Fault Detection Using Support Vector Machines and Artificial Neural Networks, Augmented by Genetic Algorithms

“…Several applications have demonstrated that a neural network can successfully recognise and classify different faults in a number of different condition monitoring applications [21]. A good general introduction to neural networks is provided by Haykin [22] and also Rojas [23].…”

“…The importance of normalisation to both the speed and success of training (for example, see [20,21]) is paramount. Prior to commencing the training run for the neural network, all the data in the input data set was normalised on a feature by feature basis.…”

Artificial Neural Network Based Fault Diagnostics of Rolling Element Bearings Using Time-Domain Features

“…The use of vibration signals is quite common in the field of condition monitoring and diagnostics of rotating machinery [1][2][3][4][5][6][7]. Detection of machine faults like mass unbalance, rotor rub, shaft misalignment, gear failures and bearing defects is possible by comparing the vibration signals of a machine operating with and without faulty conditions.…”

Fault diagnosis of rolling element bearing using time-domain features and neural networks

“…Moreover, automatic fault diagnosis does not depend on subjective human judgment [5]. The application of ANNs has been gaining importance in the area of automated fault detection and diagnosis of rotating machinery [6], [7], [8]. The neural networks have the advantages of adaptive learning, nonlinear generalization, fault tolerance, resistance to noisy data, and parallel computation abilities.…”

“…Some of the previous works dealt with signals from multiple locations for fault detection [10], [14]. The number of input parameters used in the proposed algorithm is less compared to that of previous works [6], [7], [8], [9], [10], [11], [12], [13] and hence, training speed is high. Moreover, additional signal processing required for frequency domain analysis and time-frequency/scale analysis is not required for the proposed algorithm.…”