arXiv subjects

Wenxue Liu

Publications and source records attributed to Wenxue Liu.

8 recordsLinked to original sources

arXiv2026

Modeling and Estimation of Solid Electrolyte Interphase during Formation in Battery Manufacturing

The solid electrolyte interphase (SEI) - a critical passivation layer that governs the longevity, safety, and efficiency of lithium-ion batteries - is created during the last step in cell manufacturing called cell formation. Conventional cell formation protocols are largely empirical, resulting in long processing times and limited control over the SEI growth rate that influences SEI quality and lifetime performance. This paper develops a control-oriented, semi-empirical model to estimate SEI thickness growth from terminal voltage and cell expansion measurements acquired in-operando during manufacturing using low-cost micrometer-precision integrated-sensing fixture. Model parameters are calibrated against cell formation data, and an unscented Kalman filter is employed to estimate the SEI film growth. The results lay the foundation for future closed-loop control of SEI growth, enabling high-quality and more efficient formation processes.

eess.SY↗

arXiv2026

Driving Condition-Aware Multi-Agent Integrated Power and Thermal Management for Hybrid Electric Vehicles

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.

eess.SY↗

arXiv2026

Temperature-Aware Scheduling of LLM Inference in Large-Scale Geo-Distributed Edge Data Centers with Distributed Optimization

The environmental impact of Large Language Models (LLMs) on data centers hosting these models is becoming a significant concern. While many efforts have focused on reducing the substantial training overhead of LLMs, carbon and water consumption during the inference phase can often surpass the costs associated with their training. The cooling systems of data centers are crucial in this context, but they are frequently modeled with a location-independent efficiency term. However, their energy efficiency is highly influenced by ambient temperature, which can vary significantly across different geographical locations. Leveraging this temperature diversity can help reduce total cooling energy costs and improve the performance of edge data centers. To address these critical sustainability issues related to LLMs, this study proposes a temperature-aware approach that co-optimizes LLM energy costs, carbon emissions, time-to-first token, and water consumption. The approach employs a distributed optimization algorithm based on an alternating direction method of multipliers, aimed at enhancing the sustainability of LLM hosting across geo-distributed edge data centers in Australia. Our method demonstrates reductions in cooling energy consumption and improves overall cost efficiency for geo-distributed cloud environments.

eess.SY↗

arXiv2026

Leveraging Quantum Annealing for Large-Scale Household Energy Scheduling with Hydrogen Storage

Hydrogen integration into microgrids facilitates the absorption of intermittencies from renewable energy resources. However, significant challenges remain due to complex optimization problems, particularly in large-scale applications involving multiple fuel cells (FCs) and electrolyzers (ELs) with numerous binary decision variables. This paper presents a hierarchical quantum annealing (QA) model predictive control-based power allocation framework aimed at accelerating these optimization problems. First, in a day-ahead stage, the framework determines the startup and shutdown of the FCs and ELs. The short-term stage then refines the output power of the FCs and the hydrogen generation rate of the ELs. The feasibility is evaluated through a case study consisting of multiple households in Australia. Our findings demonstrate that while the traditional optimization approach performs satisfactorily in scenarios with a small number of households, the QA approach becomes more appropriate and effectively solves the problem within an acceptable range as the number of connected households increases.

eess.SY↗

arXiv2025

Merging Physics-Based Synthetic Data and Machine Learning for Thermal Monitoring of Lithium-ion Batteries: The Role of Data Fidelity

Since the internal temperature is less accessible than surface temperature, there is an urgent need to develop accurate and real-time estimation algorithms for better thermal management and safety. This work presents a novel framework for resource-efficient and scalable development of accurate, robust, and adaptive internal temperature estimation algorithms by blending physics-based modeling with machine learning, in order to address the key challenges in data collection, model parameterization, and estimator design that traditionally hinder both approaches. In this framework, a physics-based model is leveraged to generate simulation data that includes different operating scenarios by sweeping the model parameters and input profiles. Such a cheap simulation dataset can be used to pre-train the machine learning algorithm to capture the underlying mapping relationship. To bridge the simulation-to-reality gap resulting from imperfect modeling, transfer learning with unsupervised domain adaptation is applied to fine-tune the pre-trained machine learning model, by using limited operational data (without internal temperature values) from target batteries. The proposed framework is validated under different operating conditions and across multiple cylindrical batteries with convective air cooling, achieving a root mean square error of 0.5 °C when relying solely on prior knowledge of battery thermal properties, and less than 0.1 °C when using thermal parameters close to the ground truth. Furthermore, the role of the simulation data quality in the proposed framework has been comprehensively investigated to identify promising ways of synthetic data generation to guarantee the performance of the machine learning model.

eess.SY↗

arXiv2025

RIS-MAE: A Self-Supervised Modulation Classification Method Based on Raw IQ Signals and Masked Autoencoder

Automatic modulation classification (AMC) is a basic technology in intelligent wireless communication systems. It is important for tasks such as spectrum monitoring, cognitive radio, and secure communications. In recent years, deep learning methods have made great progress in AMC. However, mainstream methods still face two key problems. First, they often use time-frequency images instead of raw signals. This causes loss of key modulation features and reduces adaptability to different communication conditions. Second, most methods rely on supervised learning. This needs a large amount of labeled data, which is hard to get in real-world environments. To solve these problems, we propose a self-supervised learning framework called RIS-MAE. RIS-MAE uses masked autoencoders to learn signal features from unlabeled data. It takes raw IQ sequences as input. By applying random masking and reconstruction, it captures important time-domain features such as amplitude, phase, etc. This helps the model learn useful and transferable representations. RIS-MAE is tested on four datasets. The results show that it performs better than existing methods in few-shot and cross-domain tasks. Notably, it achieves high classification accuracy on previously unseen datasets with only a small number of fine-tuning samples, confirming its generalization ability and potential for real-world deployment.

eess.SP↗

arXiv2024

Comparative Analysis of Control Observer-Based Methods for State Estimation of Lithium-Ion Batteries in Practical Scenarios

The reliability, lower computational complexity, and ease of implementation of control observers make them one of the most promising methods for the state estimation of Li-ion batteries (LIBs) in commercial applications. To pave their way, this study performs a comprehensive and systematic evaluation of four main categories of control observer-based methods in different practical scenarios considering estimation accuracy, computational time convergence speed, stability, and robustness against measurement uncertainties. Observers are designed using a second-order equivalent circuit model whose observability against different scenarios is rigorously investigated to verify the feasibility of the proposed analysis. Established techniques then are validated against driving datasets and their comparative usefulness is evaluated using an experimental setup. The analysis also evaluates the adaptability of different techniques to electric vehicle field data. The results indicate better accuracy, stability, robustness, and faster convergence for the PI and PID, while the estimations of the Luenberger observers find it hard to converge against highly dynamic loadfiles. Moreover, this study also discusses the sensitivity of observer-based techniques to battery ohmic polarization and voltage-related measurement uncertainties. The most remarkable contribution of the proposed study lies in providing guidance for researchers when choosing the control observers for online state estimation of LIBs.

eess.SY↗

arXiv2018

Structure Learning of Deep Networks via DNA Computing Algorithm

Convolutional Neural Network (CNN) has gained state-of-the-art results in many pattern recognition and computer vision tasks. However, most of the CNN structures are manually designed by experienced researchers. Therefore, auto- matically building high performance networks becomes an important problem. In this paper, we introduce the idea of using DNA computing algorithm to automatically learn high-performance architectures. In DNA computing algorithm, we use short DNA strands to represent layers and long DNA strands to represent overall networks. We found that most of the learned models perform similarly, and only those performing worse during the first runs of training will perform worse finally than others. The indicates that: 1) Using DNA computing algorithm to learn deep architectures is feasible; 2) Local minima should not be a problem of deep networks; 3) We can use early stop to kill the models with the bad performance just after several runs of training. In our experiments, an accuracy 99.73% was obtained on the MNIST data set and an accuracy 95.10% was obtained on the CIFAR-10 data set.

cs.NE↗