As one of the critical state parameters of the battery management system, the state of charge (SOC) of lithium batteries can provide an essential reference for battery safety management, charge/discharge control, and the energy management of electric vehicles (EVs). To analyze the application of deep learning in electric vehicles’ power battery SOC estimation, this study reviewed the technical process, common public datasets, and the neural networks used, as well as the structural characteristics and advantages and disadvantages of lithium battery SOC estimation in deep learning methods. First, the specific technical processes of the deep learning method for SOC estimation were analyzed, including data collection, data preprocessing, feature engineering, model training, and model evaluation. Second, the current commonly and publicly used lithium battery dataset was summarized. Then, the input variables, data sets, errors, and advantages and disadvantages of three types of deep learning methods were obtained using the structure of the neural network used for training as the classification criterion; further, the selection of the deep learning structure for SOC estimation was discussed. Finally, the challenges and future development directions of lithium battery SOC estimation using the deep learning method were explained. Over all, this review provides insights into deep learning for EVs’ Li-ion battery SOC estimation in the future.

As one of the critical state parameters of the battery management system, lithium battery state of charge (SOC) can provide an essential reference for battery safety management, charge/discharge control, and energy management of electric vehicles. To analyze the application of deep learning in electric vehicle power battery SOC estimation, this study reviewed the technical process, common public datasets, and the neural networks used, structural characteristics, advantages and disadvantages of lithium battery SOC estimation in deep learning method. First, the specific technical processes of the deep learning method for SOC estimation were analyzed, including data collection, data preprocessing, feature engineering, model training, and model evaluation. Secondly, the current commonly and publicly used lithium battery dataset was summarized. Then, the input variables, data sets, errors, and advantages and disadvantages of four types of deep learning methods, were concluded using the structure of neural network used for training as the classification criterion. Finally, the challenges and future development directions of lithium battery SOC estimation in deep learning method were explained.

The in-wheel-motor electric vehicle (IWM-EV) is hailed as the epitome of driving ingenuity within the realm of electric vehicles. Nonetheless, the intricate nature of its components, compounded by the intricate interplay of multiple force fields, poses a significant detriment to ride comfort. In the present study, an IWM-EV driven by a permanent magnet synchronous motor was employed as a representative case study. Initially, the calculations were conducted to determine the unbalanced magnetic force (UMF) in the presence of static eccentricity of the stator. Subsequently, the characteristics of UMF across different ratios of static eccentricity as well as different velocities in the time domains were analyzed. Furthermore, the road-electromagnetic-mechanical model was developed to investigate the influence of UMF on the vertical vibration of IWM-EV under static eccentricity, comparing it against the scenario devoid of UMF. Finally, a reinforcement learning control approach was adopted to regulate the active suspension system, comparing its efficacy with that of passive suspension and semi-active suspension (specifically, skyhook control). Through extensive simulations, the results demonstrated that the reinforcement learning control strategy derived from the road-electromagnetic-mechanical model outperforms the other two control strategies, exhibiting commendable resilience and adaptability across diverse road surfaces and velocities. This study unveiled the potential of RL methods in enhancing riding comfort through active suspension control.

Electromagnetic levitation systems are instrumental in rail transportation, manufacturing machinery, contactless bearings, and precision scientific instrumentation. These systems are inherently open-loop-unstable, require accurate motion tracking to detect the position of the levitated object, and need effective real-time control to adjust the electromagnetic force. In this paper, we propose a machine-vision-based magnetic levitation system comprising a Raspberry Pi microcomputer programmed in Python, a machine-vision camera with software triggering, and a lifting electromagnet actuated using a model-based PID controller with compensation and feedforward augmentation. Since all components are available off-the-shelf, the present magnetic levitation system is cost-effective and easy to replicate. To the best of our knowledge, the present setup seems to be the first entirely based on a Raspberry Pi microcomputer; the first in which the electromagnetic force is predicted with an empirical correlation based on dedicated measurements, making analytical/numerical predictions unnecessary; and the first where the added mass is incorporated in the equation of motion of the levitated object (it is a non-negligible phenomenon, function of the position, for levitation in liquids). The visual tracking system has an accuracy of about ±15 micrometers, and the controller operates at 100 Hz. When actuating a sphere large enough to significantly distort the electromagnetic field, this magnetic levitation setup achieves position-tracking errors (RMS errors in the range of 74 to 194 μm during quasi-static and dynamic tests) comparable to or better than those of machine-vision-based magnetic levitation systems proposed in previous investigations, at a fraction of the cost.