Diagnosing faults in electric vehicles (EVs) is a great challenge. The purpose of this paper is to demonstrate the detection of faults in an electromechanical conversion chain for conventional or autonomous EVs. The information and data coming from different sensors make it possible for EVs to recover a series of information including currents, voltages, speeds, and so on. This information is processed to detect any faults in the electromechanical conversion chain. The novelty of this study is to develop an architecture for a fault diagnosis model by means of the feature extraction technique. In this regard, the long short-term memory (LSTM) approach for the fault diagnosis is proposed. This approach has been tested for an EV prototype in practice, is superior in accuracy over other fault diagnosis techniques, and is based on machine learning. An EV in an urban context is modeled, and then the fault diagnosis approach is applied based on deep learning architectures. The EV and the fault diagnosis model is simulated in Matlab software. It is also revealed how deep learning contributes to the fault diagnosis of EVs. The simulation and practical results confirm that higher accuracy in the fault diagnosis is obtained by applying the LSTM.

A predictive direct torque controller (PDTC) for induction motors (IM) is proposed. It combines the direct torque control (DTC) and the predictive control (PC), and uses a predictive switching table to enhance the overall performance of the motor. A new type of PC is adopted for speed regulation with the use of a load torque observer, the torque being considered an unknown perturbation. A Kalman filter (KF) is used for reliable flux estimation. The validity of the proposed controller was experimentally confirmed on a rapid control prototyping station. The obtained results have proven superiority of the proposed control with respect to the speed trajectory tracking, torque and flux dynamic responses, and disturbance rejection. Also, a lower current distortion was observed with PDTC, in comparison with the regular DTC, due to increased mean inverter switching frequency.

This paper proposes the theory and application of a new designing method of the Fractional Order PID (FOPID) controller for boost converters. FOPID is a PID where the derivation and integration orders are of fractional order rather than integer. A FOPID is an extension to classic integer order PID controllers, that potentially promises better results. The method is based on the use of a Multi-Objective optimization evolutionary algorithm called Strength Pareto Evolutionary Algorithm (SPEA). Other controller methods cannot guarantee a good start-up response but the proposed method can provide an excellent start-up response besides desired dynamic response. The optimum fractional order PID coefficients for the desired control objectives are included and designers can implement each of them based on objective functions priority. A comparison between the optimum integer order PID controller and optimum fractional order PID controller is presented in the paper. The simulation and some experimental results prove the superiority of the fractional controllers over the integer controllers.

There are many important trade-offs and constraints on cost, volume, weight, conduction losses, switching losses, microcontrollers, isolation, voltage and current levels, voltage and current ripples, battery specifications, charging–discharging algorithms, control system, switch gate drivers, and efficiency of battery chargers in electric vehicles. In this paper, a well-known power electronic topology commonly used in recent relevant studies is considered, and some important technical considerations with regard to the mentioned trade-offs and constraints are discussed in detail for the first time. The discussion concerns the practical and theoretical experiences in implementation of battery chargers and charging stations of electric vehicles exclusively, and it can be extended to various other power electronic topologies.

Common-mode voltage (Vcm) generated by voltage inverters is observed on motor windings. This voltage may induce bearing currents, which can eventually damage AC motors and cause larger common-mode currents. Many methods are proposed to eliminate or reduce the common-mode voltage. Most of these methods reduce the DC-bus voltage utilization and increase the output voltage harmonics. This paper introduces a new Active Common-Mode Elimination (ACME) modulation for three-Level Neutral Point Clamped (3L-NPC) inverters. This method is based on a Modified Space Vector Modulation (MSVM) method and a power circuit system located between the inverter and the induction motor. MSVM eliminates the redundant switching states that produce high Vcm levels. Then, the power circuit system eliminates entirely the Vcm. Simulation results show the effectiveness of the proposed method. This method can increase the utilization rate of the DC bus voltage and to reduce voltage harmonics.