Efficient battery thermal runaway prognosis is of great importance for ensuring safe operation of electric vehicles (EVs). This presents formidable challenges under widely varied and ever-changing driving conditions in real-world vehicular operations. In this article, an enabling thermal runaway prognosis model based on abnormal heat generation (AHG) is proposed by combining the long short-term memory neural network (LSTM) and the convolutional neural network (CNN). The memory cell of the LSTM is modified and the resultant modified LSTM-CNN serves to provide accurate battery temperature prediction. The principal component analysis is used to optimize the model input factors to improve prediction accuracy and to reduce computing time. A random adjacent optimization method is employed to automatically optimize the hyperparameters. Finally, a model-based scheme is presented to achieve AHG-based thermal runaway prognosis. Real-world EV operating data are used to verify the effectiveness and robustness of the proposed scheme. The verification results indicate that the presented scheme exhibits accurate 48-time-step battery temperature prediction with a mean-relative-error of 0.28% and can realize 27-min-ahead thermal runaway prognosis.

This paper presents a hierarchical three-layer trajectory planning framework to realize real-time collision avoidance under complex driving conditions. This is mainly ascribed to the generation of a collision-free trajectory cluster based on the speed and the path re-planning. The upper-layer controller is to generate a reference quintic polynomial trajectory based on the Sequential Quadratic Programming by assuming mild speed and acceleration variations of the surrounding vehicles. The waypoints and time stamps can be obtained via the reference trajectory. When the assumption is invalid under complex driving conditions, the middle-layer controller would generate a Quadratic Programming-based trajectory cluster to assign different time stamps to each waypoint through time-based sampling methods. The lower-layer controller would be triggered to create a new feasible trajectory based on the path sampling if the collision avoidance requirements are not satisfied. The host vehicle will return to its original lane if no feasible time window is available to perform a lane change maneuver under the vehicle kinematics and lane change time/displacement constraints. The effectiveness of the proposed scheme is verified under various scenarios through comprehensive simulations.

The characteristics of inductive power-transfer (IPT) systems are sensitive to the variation of the coupling coefficient caused by misalignment conditions or different gaps. This results in a reduction in transferred power and efficiency. The output characteristics considering frequency modulation applied in series–series (SS), inductor–capacitor–capacitor (LCC)-S and LCC–LCC compensated IPT systems have been explored, revealing that high-order compensation topologies hold limited power regulation ability if coupling varies significantly. The parameter sensitivity of LCC–LCC-compensated topology is investigated through the singular values (SVs) analysis. It is found that the variation of the parallel-compensated capacitors has the greatest impact on the output power. Aiming at alleviating the power drop caused by the coupling variation, a parameter offline tuning method realized by switching the parallel-compensated capacitance for a detuned LCC–LCC resonant converter is proposed for electric vehicle (EV) wireless charging. Analytical expressions have been derived in aiding the design of modified value of capacitance ensuring primary zero voltage switching (ZVS) operation. Thus, the detuned parameter combinations, which deliver rated power even with the worst coupling, are obtained. Finally, a 6.6-kw prototype has been built to verify the validity of the proposed topology, which can deliver 6.1 kW with an efficiency of 94% even when the coupling drops from 0.3 to 0.15.

In this article, an efficiency-oriented control strategy is proposed for LCC–LCC-compensated wireless power transfer (WPT) system to achieve zero-voltage-switching (ZVS) operation over a wide current regulation range, in which full-bridge (FB) and half-bridge (HB) modes are combined and switchable based on requirements from load. The harmonic-considered time-domain models for FB and HB modes are first built to calculate current through the switches at the turn- off moment accurately. Then, focused on the constant voltage charge stage with variable output current, the ZVS boundaries are identified in HB and FB modes as the preferable control trajectories, which determines the desired current output with joint considerations of frequency, phase-shift angle, and duty ratio. Next, a least squares optimization method is introduced to fit the theoretical control trajectories into a smooth curve that is practical for implementation on microcontrollers. Finally, a 4.4-kW WPT prototype is built to verify the feasibility and validity of the proposed control strategy. Results show that a high system efficiency can be achieved over a wide output current range, with an efficiency of 94.68% even at 20% rated power.

In this article, a triple-phase-shift (TPS) control strategy combining a switch-controlled capacitor (SCC) is proposed for LCC – LCC compensated wireless power transfer (WPT) system to improve the overall efficiency at wide output voltages. The basic mathematical model of the system is first established, and the conditions for zero-voltage switching (ZVS) and load matching are described under TPS. Then, the mechanism of TPS reducing system efficiency at wide output voltages is revealed based on the established model. An SCC is employed to adjust the compensation capacitance to achieve a minimum circulating reactive power on both sides and reduce the rectifier input current. Finally, the impact of the compensation capacitance variations on the current, output power, and impedance are analyzed, based on which the optimal value of adjustable capacitance for maximum efficiency is derived by further considering the established time domain model. A comparative experiment is performed with traditional TPS and the proposed control technique, which shows that the system with the proposed control technique achieves a higher efficiency over the TPS within the entire power range.