Search

This paper proposes a convolutional neural network (CNN) model of the signal distribution control algorithm (SDCA) to maximize the dynamic vehicular traffic signal flow for each junction phase. The aim of the proposed algorithm is to determine the reward value and new state. It deconstructs the routing components of the current multi-directional queuing system (MDQS) architecture to identify optimal policies for every traffic scenario. Initially, the state value is divided into a function value and a parameter value. Combining these two scenarios updates the resulting optimized state value. Ultimately, an analogous criterion is developed for the current dataset. Next, the error or loss value for the present scenario is computed. Furthermore, utilizing the Deep Q-learning methodology with a quad agent enhances previous study discoveries. The recommended method outperforms all other traditional approaches in effectively optimizing traffic signal timing. [ABSTRACT FROM AUTHOR]

Non-exhaust brake dust and pollution arising from metal, semi-metal, and ceramic brake pads have made recent research consider their replacement by potential natural fibers such as hemp, flax, sisal, etc. These natural fibers are lightweight, biodegradable, and cheap. This paper discusses the wear and friction analysis of hemp fiber reinforced polymer brake pad material. Three test specimens viz. HF4P20, HF5P20, and HF6P20 were prepared per ASTM G99 standards for the pin-on disc tribo-test. The test trials and validation were done using the Taguchi design of experiments and ANOVA. The optimum result showed a consistent coefficient of friction and lowered specific wear rate for HF6P20 brake pad material. Worn surface morphology was done using scanning electron microscopy. [ABSTRACT FROM AUTHOR]

Electric, hybrid, and fuel cell vehicles are the future of the automobile industry, and power source design is one of the most crucial steps in designing these vehicles. This paper aims to design and structurally simulate a custom accumulator—which powers an electric vehicle, for a lightweight, single-seater formula-style racecar. The work is dependent on the model-based design and CAD model approach. Mathematical modeling on SCILAB is used to model equations to get the characteristics of the accumulator, such as the energy, capacity, current, voltage, state of charge, and discharge rates. The output of this model gives the configuration of the battery pack as several cells in series and parallel to adequately power the tractive system. An accumulator container is designed to safeguard the cells from external impacts and vibrational loads, which otherwise can lead to safety hazards. Following this, the Finite Element Analysis (FEA) performed on the accumulator resulted in maximum peak deformation of 0.56 mm, ensuring the safety check against various external loads. Further, the finer stability of the battery pack was virtually validated after performing the vibrational analysis, resulting in a deformation of 3.5493 mm at a 1760.8 Hz frequency. [ABSTRACT FROM AUTHOR]