This article proposes an energy-efficiency strategy based on the optimization of driving patterns for an electric vehicle (EV). The EV studied in this paper is a commercial vehicle only driven by a traction motor. The motor drives the front wheels indirectly through the differential drive. The electrical inverter model and the power-train efficiency are established by lookup tables determined by power tests in a dynamometric bank. The optimization problem is focused on maximizing energy-efficiency between the wheel power and battery pack, not only to maintain but also to improve its value by modifying the state of charge (SOC). The solution is found by means of a Particle Swarm Optimization (PSO) algorithm. The optimizer simulation results validate the increasing efficiency with the speed setpoint variations, and also show that the battery SOC is improved. The best results are obtained when the speed variation is between 5% and 6%.

The estimation of the state of charge is a critical function in the operation of electric vehicles. The battery management system must provide accurate information about the battery state, even in the presence of failures in the vehicle sensors. This article presents a new methodology for the state of charge estimation (SOC) in electric vehicles without the use of a battery current sensor, relying on a virtual sensor, based on other available vehicle measurements, such as speed, battery voltage and acceleration pedal position. The estimator was derived from experimental data, employing support vector regression (SVR), principal component analysis (PCA) and a dual polarization (DP) battery model (BM). It is shown that the obtained model is able to predict the state of charge of the battery with acceptable precision in the case of a failure of the current sensor.

This paper presents a regenerative braking analysis of efficiency in real driving conditions and different road geographies. Factors affecting or benefiting energy recovery were identified, these are: the weight of the vehicle, torque, speed, inclination of road, and braking time; however, the sport and Eco driving modes were not considered because the same driving pace was chosen for the different routes. These results are intended to collaborate with real energy regeneration data and help investigators, academics, and automotive engineering, improving this system's efficiency. In the driving process, the state of charge (SOC), speed, torques, and road geography effect the efficiency of regenerative braking, as driving a vehicle on a road with irregular geography exposes it to aggressive physical factors, which considerably reduces its energy autonomy. The main aspects of recovery and regenerative braking efficiency were determined through quantitative data analysis, resulting in experimental surfaces and curves, which present the performance of current and deceleration during vehicle braking. Thus, it is shown that the energy recovery during braking is 78% considering the low autonomy of the electric vehicle.

The accelerated migration towards electric vehicles (EV) presents several problems to solve. The main aspect is the management and prediction of the state of charge (SOC) in real long-range routes of different variations in altitude for a more efficient energy consumption and vehicle recharge plan. This paper presents the implementation of a new algorithm for SOC estimation based on continuous learning and meta-experience replay (MER) with reservoir sample. It combines the reptile meta-learning algorithm with the experience replay technique for stabilizing the reinforcement learning. The proposed algorithm considers several important factors for the prediction of the SOC in EV such as: speed, travel time, route altimetry, consumed battery capacity, regenerated battery capacity. A modified principal components analysis is used to reduce the dimensionality of the route altimetry data. The experimental results show an efficient estimation of the SOC values and a convergent increase in knowledge while the vehicle travels the routes.

Nowadays, due to different pollution factors, the electric vehicle is considered as a solution for the energy and environmental crisis, but it has not yet managed to outperform internal combustion vehicles due to limited energy density, therefore, it is necessary to study in which parts of the electric vehicle the greatest losses of powers occur to find the most optimal points of operation of the EV, which opens up possibilities to raise energy optimization issues and thus try to obtain greater efficiency and autonomy, this paper presents a methodology for the analysis of energy efficiency in electric vehicles (EV). To obtain a measurement of the real power in the wheels, a MAHA LPS 3000 dynamometer bank was used. In addition, a data acquisition system (DAS) that records different variables necessary for the analysis obtained directly from the ECU through the on-board diagnostic port (OBD), according to the analysis performed, it is concluded that the power losses are not a function of the value of the state of charge (SOC), the results of the calculated losses and the analysis in measurements are detailed in power curves for different systems (electric motor, inverter and mechanical transmission). Finally, efficiency curves are presented, showing the optimum operating points of each component analysed.

This paper presents a comparison of different machine learning techniques for classification of the unbalance and damage Niquel-Metal Hydride (Ni-MH) battery cells used in hybrid electric vehicles (HEV) and electric vehicles (EV). The implemented linear and non-linear classification algorithms used in this study are: logistic regression (LR), k-nearest neighbors (k-NN), kernel space vector machine (KSVM), Gaussian naive Bayes (GNB) and a neural network (NN); the classifiers in this work used the principal component analysis (PCA) in dual variables to reduce the high dimensional data set. To evaluate the performance of the classifiers, experimental results and a detailed analysis of the confusion matrix are used where the effectiveness of the algorithms are demonstrated.