Automotive Science and Engineering

Experimental Investigation of Mechanical Vibration Effects on Lithium-Ion Battery State-of-Charge Estimation Using Ensemble Machine Learning Models

Saeeda Ghulami

Accurate state-of-charge (SoC) estimation is a critical requirement for reliable battery management systems in electric vehicles. While data-driven and machine learning approaches have demonstrated high estimation accuracy, most existing studies assume ideal operating conditions and neglect the influence of mechanical disturbances. In practical automotive environments, lithium-ion batteries are continuously exposed to mechanical vibration, which may affect electrical signals and estimation reliability.
In this study, the impact of mechanical vibration on SoC estimation accuracy is experimentally investigated using standardized vibration tests conducted in accordance with IEC 62660-2. A cylindrical 18650 lithium-ion cell is subjected to random vibration along three orthogonal axes during charge–discharge cycles. Four ensemble-based machine learning models—Random Forest, Extra Trees, Gradient Boosting, and LightGBM—are developed and evaluated under vibration-free and vibration-exposed conditions.
Quantitative results based on RMSE and MAE metrics demonstrate that mechanical vibration leads to a noticeable degradation in SoC estimation accuracy for all models. However, the degree of sensitivity varies among algorithms. Extra Trees and LightGBM exhibit superior robustness to vibration-induced disturbances compared to Random Forest and Gradient Boosting. The findings highlight the importance of considering mechanical operating conditions when designing data-driven SoC estimation algorithms for real-world applications.

Coordinated Control of Torque Vectoring & Active Rear Camber for Autonomous Vehicle Path-Tracking under Limit Conditions

Behrooz Mashadi

Path-tracking for autonomous vehicles at physical handling limits is severely challenged by nonlinear tire saturation, which degrades conventional Active Front Steering (AFS) systems. This study proposes a hierarchical control architecture coordinating AFS, Torque Vectoring Control (TVC), and Active Rear Camber (ARC) to enhance path-tracking accuracy under limit driving conditions. An upper-level Linear Model Predictive Control (LMPC) algorithm is designed to calculate the virtual corrective yaw moment and the optimal rear camber angle. Simultaneously, a lower-level three-mode Quadratic Programming (QP) framework dynamically allocates torques based on instantaneous tire friction capacities. MATLAB/CarSim co-simulations of severe Double Lane Change (DLC) maneuvers validate the system's efficacy. Quantitatively, during a 140 km/h maneuver on dry asphalt, the proposed fully integrated system expands the maximum achievable lateral acceleration to 0.8g. Compared to the baseline AFS configuration, it significantly reduces the root-mean-square (RMS) and peak lateral tracking errors by 32% (to 0.239 m) and 27% (to 0.687 m), respectively, while concurrently decreasing the peak steering demand by 27%. Furthermore, under low-friction critical conditions (60 km/h, μ=0.5), the controller effectively limits sideslip oscillations and prevents vehicle spin-out. Ultimately, the formulated hierarchical framework manages the over-actuation dynamically, yielding a peak execution time that consumes only 74% of the real-time step limit, providing a highly viable and computationally efficient strategy for automotive Electronic Control Unit (ECU) implementation.

Integrated Optimization of Ride Comfort and Battery Degradation in Pure Electric Vehicles with Active Suspension

Mohammad Salehpour

Pure electric vehicles are increasingly important for reducing transportation emissions, improving energy efficiency, and supporting sustainable mobility. However, their performance depends strongly on battery health, energy consumption, and vehicle dynamic behavior. This study proposes a genetic-algorithm-optimized fuzzy active suspension controller for a pure electric vehicle by simultaneously considering ride comfort, suspension travel, battery state of charge, and battery degradation. An integrated EV–active suspension simulation framework is developed by combining the electric powertrain, battery aging model, and full-car active suspension model. The fuzzy controller membership functions are optimized using a genetic algorithm and evaluated under UDDS, NEDC, and WLTP Class 3 driving cycles. The objective function combines weighted ride comfort, front and rear suspension travel, final SOC, and battery capacity loss. The results show that the optimized controller improves ride comfort by 15.32% in NEDC, 2.18% in UDDS, and 2.36% in WLTP Class 3. Battery aging is also reduced by 3.51%, 5.17%, and 4.58% under the same cycles, respectively. Overall, the proposed GA-based fuzzy controller provides an effective compromise between passenger comfort, suspension performance, actuator energy demand, and battery health preservation.

Comprehensive Review on Hygrothermal Degradation of Adhesively Bonded Composite Joints: Nanoparticle Reinforcement Strategies and Cohesive Zone Modeling Approaches

Hamed Saeidi Googarchin

Adhesively bonded joints, particularly those featuring Carbon Fiber Reinforced Polymer (CFRP) adherends, have become indispensable in aerospace and automotive industries due to their superior strength-to-weight ratios. However, the long-term structural integrity of these joints is severely challenged by hygrothermal environments (the synergistic effect of moisture and temperature) which induces degradation in both the polymer matrix and the adhesive interface. This review provides a systematic discourse on the fundamental principles of composites, nanotechnology, and the mechanisms of environmental aging. It critically analyzes various joint configurations and failure modes, such as cohesive and adhesive failures, under adverse conditions. A significant portion of this study is dedicated to the efficacy of incorporating zero-, one-, and two-dimensional nanoparticles to enhance the environmental resilience of epoxy adhesives. Furthermore, this review evaluates the recent advancements in Cohesive Zone Modeling (CZM) for predicting the residual strength and fracture energy of aged joints through environment-dependent traction-separation laws. This work identifies critical gaps in accelerated aging methodologies and highlights the necessity for high-fidelity predictive models to ensure the safety of hybrid structures in high-stakes engineering applications.

Stress Prediction in Notched Single-Lap Adhesive Joints Using Machine Learning Approach

Farzad Ghafoorian

Adhesively bonded joints, particularly the Single-Lap Joint (SLJ), are widely used in structural applications. However, stress concentrations at the overlap edges significantly limit their load-bearing capacity. Modifying the adherend geometry by introducing notches is an effective technique for stress redistribution and strength improvement. In this study, a Machine Learning (ML) approach is proposed to predict the peak peel and shear stresses in notched SLJs based on geometric parameters, namely the notch depth, notch angle, notch width, and the notch distance from the end of the overlap. First, a comprehensive dataset comprising 1183 Finite Element Analysis (FEA) simulations was generated. Subsequently, four ML models—Artificial Neural Networks (ANN), Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Machines (SVM)—were developed to map the geometric features to the maximum stress values. To ensure robust performance and prevent overfitting, a Randomized Search Cross-Validation technique was employed for hyperparameter tuning across all models prior to final evaluation. The evaluation results demonstrated highly accurate predictions across all algorithms. Specifically, the ANN model achieved the most precise results, yielding the lowest Mean Absolute Percentage Error (MAPE) for both peel (0.28%) and shear (0.16%) stresses. The SVM, XGBoost, and RF models also exhibited excellent predictive capabilities, with all MAPE values remaining well below 1%. Feature importance analysis from XGBoost and SHapley Additive exPlanations (SHAP) applied to the optimal ANN revealed that notch distance from the edge and notch depth are the key design parameters influencing stress distributions.