With the advancement of machine-learning and deep-learning technologies, the estimation of the state of charge (SOC) of lithium-ion batteries is gradually shifting from traditional methodologies to a new generation of digital and AI-driven data-centric approaches. This paper provides a comprehensive review of the three main steps involved in various machine-learning-based SOC estimation methods. It delves into the aspects of data collection and preparation, model selection and training, as well as model evaluation and optimization, offering a thorough analysis, synthesis, and summary. The aim is to lower the research barrier for professionals in the field and contribute to the advancement of intelligent SOC estimation in the battery domain.

This study presents a multi-technique, real-time analysis that quantitatively correlates the pyrolysis stages of waste lignin with the sequential evolution of its key functional groups—a level of mechanistic insight beyond the macroscopic yield correlations of prior studies. The pyrolysis behavior and group evolution of lignin derived from agricultural and forestry residues were investigated under nitrogen (10 °C min−1, 30–900 °C) using thermogravimetric analysis coupled with Fourier-transform infrared spectroscopy, nuclear magnetic resonance, and elemental analysis. The process was delineated into three distinct stages: (i) desorption of physically adsorbed water and light volatiles (500 °C), yielding ∼19 wt. % stable biochar. The functional group decomposition followed the sequence methoxy/ether > aromatic C=C > hydroxyl > aliphatic C–H, driving dominant pathways of dehydration, decarboxylation, decarbonylation, and condensation. These findings establish a quantitative functional-group-led framework for optimizing lignin conversion toward targeted products like high-quality bio-oil and high-value biochar.

As a new type of energy that can meet the requirements of carbon neutrality, biomass has received wide attention in recent years, and its rational and efficient thermal utilization can help reduce greenhouse gas emissions and establish an energy-saving, low-carbon energy system to promote sustainable development. In this paper, the current utilization and research status of plant-based biomass waste is comprehensively summarized from four aspects, namely component properties, industrial thermal utilization means, experiments and theoretical calculations. In addition, this paper summarizes the research progress in several aspects, such as microscopic experimental studies, macroscopic pyrolysis characterization, and multiscale theoretical model construction of biomass waste. However, due to the diversity and heterogeneity of biomass, there are still some challenges to extending the laboratory research results to large-scale industrial production, for which we also provide an outlook on future technological innovations and development directions in this research area.

Electric vehicles (EVs) powered by lithium-ion batteries are crucial for sustainable transportation. Accurate State of Charge (SOC) estimation, a core function of Battery Management Systems (BMS), enhances battery performance, lifespan, and safety. This paper proposes a hybrid CNN-LSTM-AKF model integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) Neural Networks with an Adaptive Kalman Filter. CNN extracts spatial features from current, voltage, and temperature data, while LSTM processes temporal dependencies. AKF reduces output fluctuations. Trained on datasets under three operating conditions, the model was tested across various temperatures and initial SOC states. Results demonstrate that the proposed model significantly outperforms standalone LSTM and LSTM-AKF model, particularly at low temperatures. Within 0 °C to 50 °C, it achieves Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) below 1.51% and 1.18%, respectively. With an initial SOC of 80%, the model achieves an RMSE of 1.09% and MAE of 0.88%, showing rapid convergence. The model exhibits high accuracy, strong adaptability, and robust performance.