A hybrid fault diagnosis scheme for railway point machines by motor current signal analysis

Proper analysis of point machine current signal provides pervasive information of health status of their internal components. Point machines are subjected to several failure modes during their operation. “Gearbox,” “ball bearing,” “lead screw,” and “sliding chair” faults are among common mechanical failure modes. In this article, a two-stage prediction innovative process is proposed using Fault Detection based Decision Tree strategy (FDDT) where the healthy and faulty modes are first determined, followed by classifying the types of mechanical faults based on Parallel Neural Network Architecture and Fuzzy System (PNNFS). To differentiate between faulty and healthy point machines, some relevant features are extracted from the motors’ current signals which are used as input data for the proposed FDDT_PNNFS method. Feature selection has been performed using the ReliefF to select the dominant predictors in the point machine. Firstly, the Decision Tree (DT) algorithm is used to obtain a classifier model based on the offline training method for fault detection. The performance of DT is compared with the support vector machine algorithm. In the second stage, faulty data is fed to a bank of Neural Networks, designed in Parallel Neural Network Architecture (PNNA), which is used for identifying the type of failures. Each Neural Network Algorithm (NNA) is responsible for detecting only one type of failure and assessment of the NNA outputs shows the final failure of the point machine. If there is a discrepancy between the outputs of the NNAs, fuzzy logic plays the role of modifier and judges among outputs of NNAs and determines the more probable fault type.

A Deep Autoencoder-Based Convolution Neural Network Framework for Bearing Fault Classification in Induction Motors

Fault diagnosis and classification for machines are integral to condition monitoring in the industrial sector. However, in recent times, as sensor technology and artificial intelligence have developed, data-driven fault diagnosis and classification have been more widely investigated. The data-driven approach requires good-quality features to attain good fault classification accuracy, yet domain expertise and a fair amount of labeled data are important for better features. This paper proposes a deep auto-encoder (DAE) and convolutional neural network (CNN)-based bearing fault classification model using motor current signals of an induction motor (IM). Motor current signals can be easily and non-invasively collected from the motor. However, the current signal collected from industrial sources is highly contaminated with noise; feature calculation thus becomes very challenging. The DAE is utilized for estimating the nonlinear function of the system with the normal state data, and later, the residual signal is obtained. The subsequent CNN model then successfully classified the types of faults from the residual signals. Our proposed semi-supervised approach achieved very high classification accuracy (more than 99%). The inclusion of DAE was found to not only improve the accuracy significantly but also to be potentially useful when the amount of labeled data is small. The experimental outcomes are compared with some existing works on the same dataset, and the performance of this proposed combined approach is found to be comparable with them. In terms of the classification accuracy and other evaluation parameters, the overall method can be considered as an effective approach for bearing fault classification using the motor current signal.

Research on restoration method of nuclear pulse current signal of semiconductor detector based on artificial neural networks

The charge pulse generated by semiconductor detector caused by nuclear event carries nuclide and nuclear reaction information, but the amplified charge pulse amplitude is obviously weak and the noise is so large. Aiming at the difficulty of obtaining the charge signal pulse generated by the detector, a method for recovering the nuclear pulse current signal of semiconductor detector is proposed. Pulse recovery is divided into two parts: pulse shape recovery and pulse amplitude recovery. Point at the pulse shape, a shape recognition network of nuclear pulse current signal based on deep learning is proposed. For pulse amplitude,it can be obtained by Mexican straw hat wavelet forming algorithm. This algorithm can eliminate the baseline fluctuation caused by pulse stacking. The proposed shape recognition network of nuclear pulse current signal is composed of classifier and regressor. The classifier is used to judge whether the data contains a complete rising edge. The data containing the complete rising edge is sent to the regressor for prediction, so as to obtain the parameters related to the current pulse shape. The precision, recall and F-Measure of the classifier in classifying the test set are 98.88%, 98.05% and 98.33%, respectively. The average absolute error of the regressor in predicting the parameters related to the current pulse shape is about 9 ns. The experimental results show that the proposed method can recover the shape and amplitude of the current signal.

Mathematical modeling of the eddy current testing of delamination cracks in multilayer CFRP objects

We propose an approximate mathematical model making it possible to obtain estimates of the change in the eddy current signal under the influence of delamination in multilayer carbon fiber reinforced plastic (CFRP) objects. We give the dependences of the change in the eddy current signal on delamination in the CFRP objects for a new flaw detection method based on the comparison of eddy current signals from CFRP layers grouped by angular orientation.

Comparison of Mathematical Methods for Compensating a Current Signal under Current Transformers Saturation Conditions

Current measurements from electromagnetic current transformers are essential for the construction of secondary circuit systems, including for protection systems. Magnetic core of these transformers are at risk of saturation, as a result of which maloperation of protection algorithms can possibly occur. The paper considers methods for recovering a current signal in the saturation mode of current transformers. The advantages and disadvantages of methods for detecting the occurrence of current transformers core saturation are described. A comparative analysis of mathematical methods for recovering a current signal is given, their approbation was carried out, and the most promising of them was revealed. The stability and sensitivity of recovery methods were tested by adding white noise to the measured signal and taking into account the initial flux density (remanent magnetization) in the current transformers core. Their comparison is given on the basis of angular, magnitude, and total errors at a given simulation interval.

Classification of steel balls by resonant eddy current sensor

The quality and work-life of ball bearings depending on the material properties of the steel ball, hence it is necessary to carefully classify their properties for bearings and related applications. Classification of steel balls based on the subtle difference in their electromagnetic properties is presented in this paper. The conductivity and magnetic susceptibility for the steel balls of the same kind are measured to investigate the correlation with eddy-current signals. The developed eddy-current sensor works at the resonant frequency of 117 kHz with an optimal readout resistance of 15 kΩ, which helps to boost the signal level without a high-gain preamplifier. To detect the eddy-current signal, the steel ball under test moves through the pickup coil, and the recorded data are used to build the voltage probability map for the classification of the steel ball properties. Experimental results show that the steel balls with and without the hardening process can be identified by the change in the amplitude and phase of the eddy current signal, which is consistent with the observed change in the electromagnetic properties of steel balls. The built system can be applied to the related industries to check the quality of steel balls before use.