ABSTRACT
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
Surface composites are viable choices for various applications in the aerospace and automotive industries. Friction Stir Processing (FSP) is a promising method for fabricating surface composites. Aluminum Hybrid Surface Composites (AHSC) are fabricated using the FSP to strengthen a hybrid mixture prepared with equal parts of Boron carbide (B4C), Silicon Carbide (SiC), and Calcium Carbonate (CaCO3) particles. Different hybrid reinforcement weight percentages (reinforcement content of 5% (T1), 10% (T2), and 15% (T3)) were used in fabricating AHSC samples. Furthermore, different mechanical tests were performed on hybrid surface composite samples with different weight percentages of the reinforcements. Dry sliding wear assessments were performed in standard pin-on-disc apparatus as per ASTM G99 guidelines to estimate wear rates. The presence of reinforcement contents and dislocation behavior was investigated using Scanning Electron Microscopy (SEM) and Transmission Electron Microscopy (TEM) studies. The results indicated that the Ultimate Tensile Strength (UTS) of sample T3 exhibited 62.63% and 15.17% higher than that of samples T1 and T2, respectively, while the Elongation (%) of T3 exhibited 38.46% and 15.38% lower than that of samples T1 and T2, respectively. Moreover, it was found that the hardness of sample T3 increased in the stir zone compared to samples T1 and T2, owing to its higher brittle response. The higher brittle response of sample T3 compared to samples T1 and T2 was confirmed by the higher value of Young's modulus and the lower value of Elongation (%).
ABSTRACT
Composites can be divided into three groups based on their matrix materials, namely polymer, metal and ceramic. Composite materials fail due to micro cracks. Repairing is complex and almost impossible if cracks appear on the surface and interior, which minimizes reliability and material life. In order to save the material from failure and prolong its lifetime without compromising mechanical properties, self-healing is one of the emerging and best techniques. The studies to address the advantages and challenges of self-healing properties of different matrix materials are very limited; however, this review addresses all three different groups of composites. Self-healing composites are fabricated to heal cracks, prevent any obstructed failure, and improve the lifetime of structures. They can self-diagnose their structure after being affected by external forces and repair damages and cracks to a certain degree. This review aims to provide information on the recent developments and prospects of self-healing composites and their applications in various fields such as aerospace, automobiles etc. Fabrication and characterization techniques as well as intrinsic and extrinsic self-healing techniques are discussed based on the latest achievements, including microcapsule embedment, fibers embedment, and vascular networks self-healing.
