Power supply for a CIP position for bearings

Objective: Two possible options for power sources are considered: a controlled three-phase bridge rectifi er circuit with a step-down transformer and a pulse converter receiving power from the network through an uncontrolled three-phase bridge rectifi er to drive the wheel-motor units of electric locomotives and electric trains into rotation with the required frequency at the position of CIP bearing diagnostics. In both cases, it is assumed that the power supplies receive electricity from the 380/220 V, 50 Hz network. The power source is loaded with traction motors of the ER2R, ER2T, ET2, ET2M electric trains and the VL-10 electric locomotive. Methods: Mathematical modeling is used in the MatLab/Simulink environment for analytical calculations. Results: The currents and voltages of the load were determined, based on the calculations, the control angles and power factors of the rectifi er with a step-down transformer, the duty cycle of the pulse converter. Practical importance: A variant of an energy-effi cient power supply is proposed, including an uncontrolled rectifi er and a pulse converter.

Convolutional Neural Networks for Automated Rolling Bearing Diagnostics in Induction Motors Based on Electromagnetic Signals

Bearing faults account for over 40% of induction motor faults, and for this reason, for several decades, much attention has been paid to their condition monitoring, through vibration measurements and, more recently, through electromagnetic signal analysis. Furthermore, in the last few years, research has been focused on evaluating deep learning algorithms for the automatic diagnosis of these faults. Therefore, the purpose of this study is to propose a novel procedure to automatically diagnose different types of bearing faults and load anomalies by means of the stator current and the external stray flux measured on the induction motor in which the bearings are installed. All the data were collected by performing experimental tests in the laboratory. Then, these data were processed to obtain images (scalograms and spectrograms), which were elaborated by a pre-trained Deep Convolutional Neural Network, modified through the transfer learning technique. The results demonstrated the ability of the electromagnetic signals, and in particular of the stray flux, to detect bearing faults and mechanical anomalies, in agreement with the recent literature. Moreover, the Convolutional Neural Network has been proven to be able to automatically discriminate bearing defects and with respect to the healthy condition.

Condition Monitoring of Wind Turbines Based on the Scattering Transform of Vibration Data

As a renewable, unlimited and free resource, wind energy has been intensively deployed in the past to generate electricity. However, the maintenance of Wind Turbines (WTs) can be challengeable. On the one hand, most wind farms operate in remote areas and on the other hand, the dimension of WTs’ tip/hub/rotor are usually enormous. In order to prevent abrupt breakdowns of WTs, a number of Condition Monitoring (CM) methods have been proposed. Focusing on bearing diagnostics, Squared Envelope Spectrum is one of the most common techniques. Moreover in order to identify the optimum demodulation frequency band, fast Kurtogram, Infogram and Sparsogram are nowadays popular tools evaluating respectively the Kurtosis, the Negentropy and the Sparsity. The analysis of WTs usually requires high effort due to the complexity of the drivetrain and the varying operating conditions and therefore there is still need for research on effective and reliable CM techniques for WT monitoring. Thus the purpose of this paper is to investigate a blind and effective CM approach based on the Scattering Transform. Through the comparison with state of the art techniques, the proposed methodology is found more powerful to detect a fault on six validated WT datasets.