The paper describes a fully automated process to generate a shell-based finite element model of a large hybrid truck chassis to perform mass optimization considering multiple load cases and multiple constraints. A truck chassis consists of different parts that could be optimized using shape and size optimization. The cross members are represented by beams, and other components of the truck (batteries, engine, fuel tanks, etc.) are represented by appropriate point masses and are attached to the rail using multiple point constraints to create a mathematical model. Medium-fidelity finite element models are developed for front and rear suspensions and they are attached to the chassis using multiple point constraints, hence creating the finite element model of the complete truck. In the optimization problem, a set of five load conditions, each of which corresponds to a road event, is considered, and constraints are imposed on maximum allowable von Mises stress and the first vertical bending frequency. The structure is optimized by implementing the particle swarm optimization algorithm using parallel processing. A mass reduction of about 13.25% with respect to the baseline model is achieved.

This paper presents a general approach for the free vibration analysis of curvilinearly stiffened rectangular and quadrilateral plates using the Ritz method by employing classical orthogonal Jacobi polynomials. Both the plate and stiffeners are modeled using first-order shear deformation theory (FSDT). The displacement and rotations of the plate and stiffeners are approximated by separate sets of Jacobi polynomials. The ease of modification of the Jacobi polynomials enables the Jacobi weight function to satisfy geometric boundary conditions without loss of orthogonality. The distinctive advantage of Jacobi polynomials, over other polynomial-based trial functions, lies in that their use eliminates the well-known ill-conditioning issues when a high number of terms are used in the Ritz method, e.g., to obtain higher modes required for vibro-acoustic analysis. In this paper, numerous case studies are undertaken by considering various sets of boundary conditions. The results are verified both with the detailed finite element analysis (FEA) using commercial software msc.nastran and with those available in the open literature. New formulation and results include: (i) exact boundary condition enforcement through Jacobi weight function for FSDT, (ii) formulation of quadrilateral plates with curvilinear stiffeners, and (iii) use of higher order Gauss quadrature scheme for required integral evaluations to obtain higher modes. It is demonstrated that the presented method provides good numerical stability and highly accurate results. The given new numerical results and convergence studies may serve as benchmark solutions for validating the new computational techniques.

In multi-objective optimization, standard evolutionary algorithms, such as NSGA-II, are computationally expensive, particularly when handling complex constraints. Constraint evaluations, often the bottleneck, require substantial resources. Pre-trained surrogate models have been used to improve computational efficiency, but they often rely heavily on the model’s accuracy and require large datasets. In this study, we use active learning to accelerate multi-objective optimization. Active learning is a machine learning approach that selects the most informative data points to reduce the computational cost of labeling data. It is employed in this study to reduce the number of constraint evaluations during optimization by dynamically querying new data points only when the model is uncertain. Incorporating machine learning into this framework allows the optimization process to focus on critical areas of the search space adaptively, leveraging predictive models to guide the algorithm. This reduces computational overhead and marks a significant advancement in using machine learning to enhance the efficiency and scalability of multi-objective optimization tasks. This method is applied to six challenging benchmark problems and demonstrates more than a 50% reduction in constraint evaluations, with varying savings across different problems. This adaptive approach significantly enhances the computational efficiency of multi-objective optimization without requiring pre-trained models.

Smartwatches are increasingly being used to recognize human daily life activities. These devices may employ different kind of machine learning (ML) solutions. One of such ML models is Gradient Boosting Machine (GBM) which has shown an excellent performance in the literature. The GBM can be trained on available data set before it is deployed on any device. However, this data set may not represent every kind of human behavior in real life. For example, a ML model to detect elder and young persons running activity may give different results because of differences in their activity patterns. This may result in decrease in the accuracy of activity recognition. Therefore, a transfer learning based method is proposed in which user-specific performance can be improved significantly by doing on-device calibration of GBM by just tuning its parameters without retraining its estimators. Results show that this method can significantly improve the user-based accuracy for activity recognition.