Pritesh Shah

Bio: Pritesh Shah is an academic researcher from Symbiosis International University. The author has contributed to research in topics: PID controller & Control theory. The author has an hindex of 8, co-authored 25 publications receiving 430 citations.

Soft Sensors for State of Charge, State of Energy, and Power Loss in Formula Student Electric Vehicle

Abstract: The proliferation of electric vehicle (EV) technology is an important step towards a more sustainable future. In the current work, two-layer feed-forward artificial neural-network-based machine learning is applied to design soft sensors to estimate the state of charge (SOC), state of energy (SOE), and power loss (PL) of a formula student electric vehicle (FSEV) battery-pack system. The proposed soft sensors were designed to predict the SOC, SOE, and PL of the EV battery pack on the basis of the input current profile. The input current profile was derived on the basis of the designed vehicle parameters, and formula Bharat track features and guidelines. All developed soft sensors were tested for mean squared error (MSE) and R-squared metrics of the dataset partitions; equations relating the derived and predicted outputs; error histograms of the training, validation, and testing datasets; training state indicators such as gradient, mu, and validation fails; validation performance over successive epochs; and predicted versus derived plots over one lap time. Moreover, the prediction accuracy of the proposed soft sensors was compared against linear or nonlinear regression models and parametric structure models used for system identification such as autoregressive with exogenous variables (ARX), autoregressive moving average with exogenous variables (ARMAX), output error (OE) and Box Jenkins (BJ). The testing dataset accuracy of the proposed FSEV SOC, SOE, PL soft sensors was 99.96%, 99.96%, and 99.99%, respectively. The proposed soft sensors attained higher prediction accuracy than that of the modelling structures mentioned above. FSEV results also indicated that the SOC and SOE dropped from 97% to 93.5% and 93.8%, respectively, during the running time of 118 s (one lap time). Thus, two-layer feed-forward neural-network-based soft sensors can be applied for the effective monitoring and prediction of SOC, SOE, and PL during the operation of EVs.

Distance to empty soft sensor for ford escape electric vehicle

Abstract: Electric vehicle (EV) drivers require reliable distance to empty (DTE) indication to plan their trips. In the current study, feed forward neural networks based soft sensors were designed to accurately predict DTE in a Ford Escape EV. The proposed DTE soft sensors were trained on actual drive cycle data and rated DTE using Levenberg Marquardt, Bayesian Regularization and Scaled Conjugate Gradient algorithms. Regression models were also developed for comparisons. Primary results show that the Bayesian Regularization trained soft sensor network with eleven hidden layer neurons achieved the highest testing accuracy (99.64%) among the two layered networks, followed by the Levenberg Marquardt (two layered, eleven hidden layer neurons, testing accuracy 99.62%) and Scaled Conjugate Gradient trained networks (two layered, seven hidden layer neurons, testing accuracy 99.49%). The linear and non linear regression models attained 96.19% and 97.53% accuracies respectively. Deeper soft sensor networks yielded better prediction accuracies at higher computation times. The five layered Bayesian Regularization trained network (with ten neurons in each hidden layer) maximized DTE prediction accuracy to 99.89%, but at the cost of 1175% more training time as compared to the best performing two layered network soft sensor. An optimal choice of prediction accuracy considering reasonable computation timescales can help reduce range anxiety of EV users significantly.

Fractional Order Control of Power Electronic Converters in Industrial Drives and Renewable Energy Systems: A Review

Abstract: The power electronics industry is undergoing a revolution driven by an industry 4.0 perspective, with smart and green/hybrid energy management systems being the requirement of the future. There is a need to highlight the potential of fractional order control in power electronics for the highly efficient systems of tomorrow. This paper reviews the developments in fractional order control in power electronics ranging from stand-alone power converters, industrial drives and electric vehicles to renewable energy systems and management in smart grids and microgrids. Various controllers used in power electronics such as the fractional order PI/PID (FOPI/FOPID) and fractional-order sliding mode controllers have been discussed in detail. This review indicates that the plug-and-play type of intelligent fractional order systems needs to be developed for our sustainable future. The review also points out that there is tremendous scope for the design of modular fractional-order intelligent controllers. Such controllers can be embedded into power converters, resulting in smart power electronic systems that contribute to the faster and greener implementation of industry 4.0 standards.

Design of a fractional PI λ D μ controller using the cohort intelligence method

Abstract: The cohort intelligence (CI) method has recently evolved as an optimization method based on artificial intelligence. We use the CI method for the first time to optimize the parameters of the fractional proportionalintegral- derivative (PID) controller. The performance of the CI method in designing the fractional PID controller was validated and compared with those of some other popular algorithms such as particle swarm optimization, the genetic algorithm, and the improved electromagnetic algorithm. The CI method yielded improved solutions in terms of the cost function, computing time, and function evaluations in comparison with the other three algorithms. In addition, the standard deviations of the CI method demonstrated the robustness of the proposed algorithm in solving control problems.

Practical Tracking Control of Linear Motor With Adaptive Fractional Order Terminal Sliding Mode Control

Abstract: This paper proposes a practical adaptive fractional order (FO) terminal sliding mode control (SMC) strategy for tracking control of the linear motor. Compared with conventional fast nonsingular SMC, the proposed approach, with a FO integral sliding surface and the adaptive switching input, can obtain higher convergence precision, even though the motion control system suffers from system uncertainties. The adaptive term is designed to guarantee finite-time high-precision convergence of the sliding mode variable, and meanwhile to degenerate the effect of uncertainties by selecting the proper adaptive gain. Moreover, continuous input due to cancelling the sign term ensures that the motion control system is chattering-free. Finally, to further improve precision, we introduce the super-twisting sliding mode disturbance observer for reducing unknown bounded disturbance, i.e., the quantization noise caused by velocity estimation. Experimental results indicate that the control system with the proposed controller is easily implemented, and has higher tracking precision and considerable robustness to uncertainties compared with the existing controllers.