This article analyses vibration transmission on agricultural tractors with the excitation from the road to the driver’s seat. A multi-body model of agricultural tractors created in Adams is presented. The main parts for the investigation of vibration transmission are the tractor body, where the only suspension elements are tyres, the tractor cabin, spring-dampers suspended at the rear and bushings at the front, and the driver seat with its pneumatic spring. A series of measurements were performed, and the model was validated using vertical acceleration values on the tractor body at four different locations. The FTire model (physical FEM-based model) was chosen to describe the behaviour of tyres. The model was created using measured tyre characteristics. Measured characteristics of spring-dampers and front cabin bushings were also implemented. For comfort investigation, ride simulations on ISO 5008 rough roads were performed. The transmission of vibrations in ride simulations was examined. A modal analysis of the linearised model was performed to confirm assumptions of the contribution of suspension elements to overall vibration levels. Finally, three case studies were conducted to better understand the model’s vibration transmission properties.

This study proposes an AutoML-based surrogate-modeling framework for crash box design optimization. A dataset consisting of 96 explicit finite-element crash simulations was generated for crash boxes with a wall thickness of 1.0–2.5 mm and six cross-sectional profiles: square, rectangular, circular, elliptical, hexagonal, and octagonal. AutoGluon-TimeSeries was used to benchmark machine learning models for predicting absorbed crash energy and crush displacement from geometric design variables. Among the evaluated models, Weighted Ensemble achieved the highest accuracy for absorbed energy prediction, with an R² = 0.975, while Temporal Fusion Transformer achieved an R² = 0.9863 for deformation-history prediction. The selected surrogate models were then used to support iterative sampling of the design space, significantly reducing the number of expensive finite-element evaluations required for optimization. These results show that AutoML-based surrogate modeling can accelerate crash box design and provide a practical foundation for data-efficient crashworthiness optimization.

This paper presents a sensitivity analysis of a reinforcement learning (RL) controller for stabilization of the Furuta pendulum under parameter variations. A high-fidelity multibody model of the system is first developed in Adams and used for policy training and closed-loop assessment. The RL agent is trained on the nominal model to stabilize the pendulum about the upright equilibrium. The trained policy is then evaluated by independently perturbing selected physical parameters within prescribed intervals around their nominal values. The resulting responses are used to assess the sensitivity of the learned policy to parameter variations. A trial is classified as failed when either the pendulum angle or the rotary arm exceeds its prescribed limit. The analysis identifies the parameters that have the greatest influence on policy performance and estimates the parameter ranges over which the trained policy continues to stabilize the pendulum. These results provide insight into the sensitivity of the trained policy to modelling errors and physical parameter variations.