Tanushree Roy

Soumyoraj Mallick, Faysal Ahamed, Sanchita Ghosh et al.

A battery management system (BMS) relies on real-time estimation of battery temperature distribution in battery cells to ensure safe and optimal operation of Lithium-ion batteries. However, physical BMS often suffers from memory and computational resource limitations required by high-fidelity models. Temperature estimation of batteries for safety-critical systems using physics-based models on physical BMS can potentially become challenging due to their higher computational time. In contrast, neural network-based approaches offer faster estimation but require greater memory overhead. To address these challenges, we propose Kolmogorov-Arnold network (KAN) based thermal model, KAN-therm, to estimate the core temperature of a cylindrical battery. Unlike traditional neural network architectures, KAN uses learnable nonlinear activation functions that can effectively capture system complexity using relatively lean models. We have compared the memory overhead and estimation time of our model with state-of-the-art neural network and tree-based models to demonstrate the applicability and potential scalability of KAN-therm on a physical BMS.

Faysal Ahamed, Tanushree Roy

Sustainability-targeting attacks (STA) are a growing threat to cyber-physical system (CPS)-based infrastructure, as sustainability goals become an integral part of CPS objectives. STA can be especially disruptive if it impacts the long-term sustainability cost of CPS, while its performance goals remain within acceptable parameters. Thus, in this work, we propose a general mathematical framework for modeling such stealthy STA and derive the feasibility conditions for generating a minimum-effort maximum-impact STA on a linear CPS using a max-min formulation. A gradient ascent descent algorithm is used to construct this attack policy with an added constraint on stealthiness. An illustrative example has been simulated to demonstrate the impact of the generated attack on the sustainability cost of the CPS.

Sanchita Ghosh, Tanushree Roy

Battery health management is heavily dependent on reliable State-of-Health (SoH) estimation to ensure battery safety with maximized energy utilization. Although SoH estimation can effectively track battery degradation, it requires continuous battery data acquisition. In addition, model-based SoH estimation methods rely on accurate battery model knowledge, whereas data-driven approaches often suffer from limited interpretability. In contrast, analytical characterization of SoH will offer a direct and tractable handle on battery performance degradation, while also establishing a foundation for further analytical studies toward effective battery health management. Thus, in this work, we propose a Kolmogorov Arnold Network (KAN)-based data-driven pipeline to establish a functional relationship for SoH degradation using battery temperature data. Specifically, we learn long-term battery thermal dynamics and battery heat generation via learnable activation functions of our KAN model. We utilize the learned mapping to obtain an explicit functional relationship between SoH degradation and cycle number. The proposed pipeline was validated using real-world data, yielding a closed-form analytical formula of SoH degradation with high accuracy.

Sanchita Ghosh, Tanushree Roy

Early diagnosis of battery thermal anomalies is crucial to ensure safe and reliable battery operation by preventing catastrophic thermal failures. Battery diagnostics primarily rely on battery surface temperature measurements and/or estimation of core temperatures. However, aging-induced changes in the battery model and limited training data remain major challenges for model-based and machine-learning based battery state estimation and diagnostics. To address these issues, we propose a Kolomogorov-Arnold network (KAN) in conjunction with a Koopman-based detection algorithm that leverages the unique advantages of both methods. Firstly, the lightweight KAN provides a model-free estimation of the core temperature to ensure rapid detection of battery thermal anomalies. Secondly, the Koopman operator is learned in real time using the estimated core temperature from KAN and the measured surface temperature of the battery to provide the core and surface temperature prediction for diagnostic residual generation. This online learning approach overcomes the challenges of model changes. Furthermore, we derive analytical conditions to obtain diagnostic guarantees on our KAN-Koopman detection scheme. Our simulation results illustrate a significant reduction in detection time with the proposed algorithm compared to the baseline Koopman-only algorithm.

Sanchita Ghosh, Tanushree Roy

Optimal charging of electric vehicle (EVs) depends heavily on reliable sensor measurements from the battery pack to the cloud-controller of the smart charging station. However, an adversary could corrupt the voltage sensor data during transmission, potentially causing local to wide-scale disruptions. Therefore, it is essential to detect sensor cyberattacks in real-time to ensure secure EV charging, and the developed algorithms must be readily adaptable to variations, including pack configurations. To tackle these challenges, we propose adaptable fine-tuning of an XgBoost-based cell-level model using limited pack-level data to use for voltage prediction and residual generation. We used battery cell and pack data from high-fidelity charging experiments in PyBaMM and `liionpack' package to train and test the detection algorithm. The algorithm's performance has been evaluated for two large-format battery packs under sensor swapping and replay attacks. The simulation results also highlight the adaptability and efficacy of our proposed detection algorithm.