The state of charge (SOC) prediction for an electric vehicle battery pack is critical to ensure the reliability, efficiency, and life of the battery pack. Various techniques and statistical systems have been proposed in the past to improve the prediction accuracy, reduce complexity, and increase adaptability. Machine learning techniques have been vigorously introduced in recent years, to be incorporated into the existing prediction algorithms, or as a stand-alone system, with a large amount of recorded past data to interpret the battery characteristics, and further predict for the present and future. This paper presents an overview of the machine learning techniques followed by a proposed pre-processing technique employed as the input to the long short-term memory network (LSTM) algorithm. The proposed pre-processing technique is based on the time-based sliding window algorithm (SW) and the Shapley additive explanation theory (SHAP). The proposed technique showed improvement in accuracy, adaptability, and reliability of SOC prediction when compared to other conventional machine learning models. All the data employed in this investigation were extracted from the actual driving cycle of five different electric vehicles driven by different drivers throughout a year. The computed prediction error, as compared to the original SOC data extracted from the vehicle, was within the range of less than 2%. The proposed enhanced technique also demonstrated the feasibility and robustness of the prediction results through the persistent computed output from a random selection of the data sets, consisting of different driving profiles and ambient conditions.
In recent years, medium manganese steels (MMSs) have garnered increased attention and interest due to their relatively low cost and superior combination properties compared to other steels. In particular, MMSs have been recognised as ideal wear-resistant materials employed in the mining industry. However, the studies on their wear performance have a lack of systematic documentation. This review provides an extensive overview of recent advances in the wear performance of MMSs, starting from discussions on applicable wear testing methods and typical wear testing results, followed by a further discussion on the wear mechanisms of MMSs based on five wear characteristics, including abrasive wear, adhesive wear, corrosive wear, fatigue wear and impact wear. The effects of hardness and hardened layers on the wear mechanisms are also discussed. Finally, the influence of phase constitution and microstructure on the wear performance of MMSs are comprehensively elaborated in terms of transformation induced plasticity (TRIP), twinning induced plasticity (TWIP), alloy elements and heat treatment. The key factors that affect the wear performance of MMSs include the elemental composition in MMSs and the phase transformation occurred during TRIP and TWIP as well as various heat treatment processes. The current review of key factors affecting the wear performance of MMSs sheds some light on new strategies to enhance the service performance and longevity of wear resistant steels in various engineering applications.
24 July 2023 in International Journal of Mining Science and Technology