Automotive Science and Engineering

---

In this paper, Front Engine Accessory Drive (FEAD) system of automotive engine is modeled with ADAMS software. The model is validated using engine test data. It is then used to investigate the effect of design parameters on the system performance such as belt vibration and loads on the idlers. Three alternative layouts were developed in order to improve the performance of original EEAD system. The validated model was used to study the effect of changes made to the layouts on the reduction of vibration and loads. Several system outputs indicated that for the modified layouts, large reductions in vibration and loads were achieved. It was concluded that one of proposed layouts was more appropriate and could be a useful substitution to the original layout. The developed model also proved useful for the design of engine FEAD systems and could be used for further developments.

---

the primary objective of this work is to introduce a gear ratio selection strategy for a CVT equipped vehicle and show its effectiveness on the fuel consumption reduction. AFuzzy control algorithm is designed for this purpose. Anonlinear model is developed for simulating the longitudinal vehicle dynamics with accelerator pedal applied by the driver as an input. In order that pedal input values can be used for evaluation of control strategy, a pedal cycle concept was introduced. With the help of these cycles different driving conditions were simulated and the fuel consumption results were obtained using Advisor software. Results showed that the control system was successful in reducing the fuel consumption, especially in low acceleration driving cycles

---

Ensuring that ethically sound decisions are made under complex, real-world conditions is a central challenge in deploying autonomous vehicles (AVs). This paper introduces a human-centric risk mitigation framework using Deep Q-Networks (DQNs) and a specially designed reward function to minimize the likelihood of fatal injuries, passenger harm, and vehicle damage. The approach uses a comprehensive state representation that captures the AV’s dynamics and its surroundings (including the identification of vulnerable road users), and it explicitly prioritizes human safety in the decision-making process. The proposed DQN policy is evaluated in the CARLA simulator across three ethically challenging scenarios: a malfunctioning traffic signal, a cyclist’s sudden swerve, and a child running into the street. In these scenarios, the DQN-based policy consistently minimizes severe outcomes and prioritizes the protection of vulnerable road users, outperforming a conventional collision-avoidance strategy in terms of safety. These findings demonstrate the feasibility of deep reinforcement learning for ethically aligned decision-making in AVs and point toward a pathway for developing safer and more socially responsible autonomous transportation systems.