The concept of a digital twin is increasingly appearing in industrial applications, including the field of predictive maintenance. A digital twin is a virtual representation of a physical system containing all data available on site. This paper presents condition monitoring of ventilation systems through the digital twin approach. A literature review regarding the most popular system faults is covered. The motor current signature analysis is used in this research to detect system faults. The physical system is further described. Then, based on the free body diagram concept and Newton’s second law, the equations of motion are obtained. Matlab/Simulink software is used to build the digital twin. The Concordia method and the Fast Fourier Transform analysis are used to process the current signal, and physical and numerical system current measurements are obtained and compared. In the final step of the modeling, specific frequencies were adjusted in the twin to achieve the best simulation. In addition, a statistical approach is used to create a complete diagnostic protocol.

In this study, the authors propose a novel control strategy of torque ripple reduction in hybrid electric vehicles (HEVs). By its periodic cycle of power production, the internal combustion engine used in a hybrid vehicle provides a torque that fluctuates constantly. This is problematic for vehicle manufacturers since this torque ripple creates uncomfortable vibrations and mechanical damage. To achieve this active control, the problem is reformulated in complex notation in the frequency domain with respect to the main order of the fluctuations. A permanent magnet synchronous machine is mounted on the crankshaft in order to generate a torque sequence opposing ripple torque. The control strategy is based on a static output feedback synthesis under ℋ_∞ performance specification. A complete modelling of the hybrid propulsion from an experimental test bench is achieved. The model is performed at low speed (900 rpm). In fact, at this speed, the ripple is very restrictive. Experimental results highlight the control approach interest.

In this article, two methods for broken bar detection in induction motors are considered and tested using data collected from the LIAS laboratory at the University of Poitiers. The first approach is Motor Current Signature Analysis (MCSA) with Convolutional Neural Networks (CNN), in which measurements have to be processed in the frequency domain before training the CNN to ensure that the resulting model is physically informed. A double input CNN has been introduced to perform a 100% detection regardless of the speed and load torque value. A second approach is the Principal Components Analysis (PCA), in which the processing is undertaken in the time domain. The PCA is applied on the induction motor currents to eventually calculate the Q statistic that serves as a threshold for detecting anomalies/faults. Even if obtained results show that both approaches work very well, there are major differences that need to be pointed out, and this is the aim of the current paper.