Model-based state-of-charge (SOC) and state-of- health (SOH) estimation for lithium-ion batteries has been widely applied in electrified vehicles, while the SOC and SOH estimators are highly coupled and nonlinear in conventional techniques. This leads to a bulky design of observer network and complicates the stability analyses. In this paper, a new reduced-decoupling SOC and SOH co-estimation algorithm based on convex optimization is proposed. This scheme estimates the battery SOC from the battery model and does not require the classic coulomb-counting method. Therefore, it can decouple the capacity estimation from the SOC estimator and reduce the strong interaction existing in conventional co-estimation methods. Besides, all state variables can be solved together by one estimator, which is straightforward and avoids the complicated observer network. Owing to the decoupling design, the stability of the proposed method becomes more intuitive and can be always guaranteed according to the convexity analysis without using other stabilizing approaches. In consequence, a weak-interaction and robust co-estimation algorithm of SOC and SOH can be realized by the proposed technique. The experiments on a 5.4 Ah lithium polymer battery are implemented to validate the feasibility of the algorithm.

Electric Vehicles (EVs) are crucial in reducing greenhouse gas emissions and combating climate change. However, their adoption is hindered by range anxiety, high costs, and inadequate charging infrastructure. Battery Management Systems (BMS) are essential for EV efficiency, but current systems face limitations such as restricted computational resources and non-updatable software. Cloud computing offers a promising solution by providing enhanced computational power and storage. This paper reviews recent research on cloud-based BMS frameworks and applications, in addition to available industry solutions. The review is coupled with a review of the recent cloud developments, combining both reviews to reach a list of research gaps and suggested future work. The findings emphasize the need for improved online learning applications, connectivity, and security. Future work should focus on integrating recent cloud developments to enhance BMS functionality and reliability.

The global transportation system’s need for electrification is driving research efforts to overcome the drawbacks of battery electric vehicles (BEVs). The accurate and reliable estimation of the states of charge (SOC) and health (SOH) of Li-Ion batteries (LIBs) is crucial for the widespread adoption of BEVs. Transformers, cutting-edge deep learning (DL) models, are demonstrating promising capabilities in addressing various sequence-processing problems. This manuscript presents a thorough survey study of previous research papers that introduced modifications in the development of Transformer-based architectures for the SOC and SOH estimation of LIBs. This study also highlights approximately 15 different real-world datasets that have been utilized for training and testing these models. A comparison is made between the architectures, addressing each state using the root mean square error (RMSE) and mean absolute error (MAE) metrics.

Sensor fusion is vital for many critical applications, including robotics, autonomous driving, aerospace, and beyond. Integrating data streams from different sensors enables us to overcome the intrinsic limitations of each sensor, providing more reliable measurements and reducing uncertainty. Moreover, deep learning-based sensor fusion unlocked the possibility of multimodal learning, which utilizes different sensor modalities to boost object detection. Yet, adverse weather conditions remain a significant challenge to the reliability of sensor fusion. However, introducing the Transformer deep learning model in sensor fusion presents a promising avenue for advancing its sensing capabilities, potentially overcoming that challenge. Transformer models proved powerful in modeling vision, language, and numerous other domains. However, these models suffer from high latency and heavy computation requirements. This paper aims to provide: (1) an extensive overview of sensor fusion and transformer models; (2) an in-depth survey of the state-of-the-art (SoTA) methods for Transformer-based sensor fusion, focusing on camera-LiDAR and camera-radar methods; and (3) a quantitative analysis of the SoTA methods, uncovering research gaps and stimulating future work.

The increasing adoption of Battery Electric Vehicles (BEVs) is driving advancements in battery management systems (BMS) to address challenges like cost and range anxiety, both tied to battery performance. This paper investigates various state of charge (SOC) and state of health (SOH) estimation methods, presenting a novel hybrid neural network that combines Gate Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) models. Our proposed method demonstrates significant improvements in SOH and SOC estimation accuracy, with minimal training data required. Key contributions include (1) a hybrid GRU-LSTM model improving SOC/SOH accuracy, (2) self-optimization capabilities, (3) effective handling of temperature variations without OCV-SOC lookup tables, and (4) its application to various lithium battery types. Experimental results show the method achieves an RMSE of 2% and MAE of 1.7% for SOC, and an RMSE of 0.65% and MAE of 0.85% for SOH across a temperature range of -10°C to 40°C. These results indicate a reliable and cost-effective approach for BEV battery management, contributing to the wider adoption of sustainable transportation.