Xiaosong Hu

Huilong Yu, Francesco Castelli-Dezza, Federico Cheli et al.

Hybrid energy storage systems that combine lithium-ion batteries and supercapacitors are considered as an attractive solution to overcome the drawbacks of battery-only energy storage systems, such as high cost, low power density, and short cycle life, which hinder the popularity of electric vehicles. A properly sized hybrid energy storage system and an implementable real-time power management system are of great importance to achieve satisfactory driving mileage and battery cycle life. However, dimensioning and power management problems are quite complicated and challenging in practice. To address these challenges, this work proposes a Bi-level multi-objective design and control framework with the non-dominated sorting genetic algorithm-II and fuzzy logic control as key components, to obtain an optimal sized hybrid energy storage system and the corresponding optimal real-time power management system based on fuzzy logic control simultaneously. In particular, a vectorized fuzzy inference system is devised, which allows large-scale fuzzy logic controllers to run in parallel, thereby improving optimization efficiency. Pareto optimal solutions of different hybrid energy storage systems incorporating both optimal design and control parameters are obtained and compared to show the achieved enhancements of the proposed approach.

Hanghang Cui, Arash Khalatbarisoltani, Jie Han et al.

Effective co-optimization of energy management strategy (EMS) and thermal management (TM) is crucial for optimizing fuel efficiency in hybrid electric vehicles (HEVs). Driving conditions significantly influence the performance of both EMS and TM in HEVs. This study presents a novel driving condition-aware integrated thermal and energy management (ITEM) framework. In this context, after analyzing and segmenting driving data into micro-trips, two primary features (average speed and maximum acceleration) are measured. Using the K-means approach, the micro-trips are clustered into three main groups. Finally, a deep neural network is employed to develop a real-time driving recognition model. An ITEM is then developed based on multi-agent deep reinforcement learning (DRL), leveraging the proposed real-time driving recognition model. The primary objectives are to improve the fuel economy and reduce TM power consumption while maintaining a pleasant cabin temperature for passengers. Our simulation results illustrate the effectiveness of the suggested framework and the positive impact of recognizing driving conditions on ITEM, improving fuel economy by 16.14% and reducing TM power consumption by 8.22% compared to the benchmark strategy.

Kailong Liu, Xiaosong Hu, Huiyu Zhou et al.

Lithium-ion battery manufacturing is a highly complicated process with strongly coupled feature interdependencies, a feasible solution that can analyse feature variables within manufacturing chain and achieve reliable classification is thus urgently needed. This article proposes a random forest (RF)-based classification framework, through using the out of bag (OOB) predictions, Gini changes as well as predictive measure of association (PMOA), for effectively quantifying the importance and correlations of battery manufacturing features and their effects on the classification of electrode properties. Battery manufacturing data containing three intermediate product features from the mixing stage and one product parameter from the coating stage are analysed by the designed RF framework to investigate their effects on both the battery electrode active material mass load and porosity. Illustrative results demonstrate that the proposed RF framework not only achieves the reliable classification of electrode properties but also leads to the effective quantification of both manufacturing feature importance and correlations. This is the first time to design a systematic RF framework for simultaneously quantifying battery production feature importance and correlations by three various quantitative indicators including the unbiased feature importance (FI), gain improvement FI and PMOA, paving a promising solution to reduce model dimension and conduct efficient sensitivity analysis of battery manufacturing.

Kailong Liu, Xiaosong Hu, Zhongbao Wei et al.

This paper presents the development of machine learning-enabled data-driven models for effective capacity predictions for lithium-ion batteries under different cyclic conditions. To achieve this, a model structure is first proposed with the considerations of battery ageing tendency and the corresponding operational temperature and depth-of-discharge. Then based on a systematic understanding of covariance functions within the Gaussian process regression, two related data-driven models are developed. Specifically, by modifying the isotropic squared exponential kernel with an automatic relevance determination structure, 'Model A' could extract the highly relevant input features for capacity predictions. Through coupling the Arrhenius law and a polynomial equation into a compositional kernel, 'Model B' is capable of considering the electrochemical and empirical knowledge of battery degradation. The developed models are validated and compared on the Nickel Manganese Cobalt Oxide (NMC) lithium-ion batteries with various cycling patterns. Experimental results demonstrate that the modified Gaussian process regression model considering the battery electrochemical and empirical ageing signature outperforms other counterparts and is able to achieve satisfactory results for both one-step and multi-step predictions. The proposed technique is promising for battery capacity predictions under various cycling cases.

Xiaosong Hu, Wen Zhu, Qing Li

Nowadays, online clothes-selling business has become popular and extremely attractive because of its convenience and cheap-and-fine price. Good examples of these successful Web sites include Yintai.com, Vancl.com and Shop.vipshop.com which provide thousands of clothes for online shoppers. The challenge for online shoppers lies on how to find a good product from lots of options. In this article, we propose a collaborative clothes recommender for easy shopping. One of the unique features of this system is the ability to recommend clothes in terms of both user ratings and clothing attributes. Experiments in our simulation environment show that the proposed recommender can better satisfy the needs of users.