Toward Enhanced State of Charge Estimation of Lithium-ion Batteries Using Optimized Machine Learning Techniques.

State of charge (SOC) is a crucial index used in the assessment of electric vehicle (EV) battery storage systems. Thus, SOC estimation of lithium-ion batteries has been widely investigated because of their fast charging, long-life cycle, and high energy density characteristics. However, precise SOC assessment of lithium-ion batteries remains challenging because of their varying characteristics under different working environments. Machine learning techniques have been widely used to design an advanced SOC estimation method without the information of battery chemical reactions, battery models, internal properties, and additional filters. Here, the capacity of optimized machine learning techniques are presented toward enhanced SOC estimation in terms of learning capability, accuracy, generalization performance, and convergence speed. We validate the proposed method through lithium-ion battery experiments, EV drive cycles, temperature, noise, and aging effects. We show that the proposed method outperforms several state-of-the-art approaches in terms of accuracy, adaptability, and robustness under diverse operating conditions.

WS2: A New Window Layer Material for Solar Cell Application.

Radio frequency (RF) magnetron sputtering was used to deposit tungsten disulfide (WS2) thin films on top of soda lime glass substrates. The deposition power of RF magnetron sputtering varied at 50, 100, 150, 200, and 250 W to investigate the impact on film characteristics and determine the optimized conditions for suitable application in thin-film solar cells. Morphological, structural, and opto-electronic properties of as-grown films were investigated and analyzed for different deposition powers. All the WS2 films exhibited granular morphology and consisted of a rhombohedral phase with a strong preferential orientation toward the (101) crystal plane. Polycrystalline ultra-thin WS2 films with bandgap of 2.2 eV, carrier concentration of 1.01 × 1019 cm-3, and resistivity of 0.135 Ω-cm were successfully achieved at RF deposition power of 200 W. The optimized WS2 thin film was successfully incorporated as a window layer for the first time in CdTe/WS2 solar cell. Initial investigations revealed that the newly incorporated WS2 window layer in CdTe solar cell demonstrated photovoltaic conversion efficiency of 1.2% with Voc of 379 mV, Jsc of 11.5 mA/cm2, and FF of 27.1%. This study paves the way for WS2 thin film as a potential window layer to be used in thin-film solar cells.