This work aims to optimize surface roughness, wall angle deviation, and average wall thickness as output responses of ALuminium-1050 alloy cone formed by the single point incremental sheet metal forming process. The experiments are accomplished based on the use of a mixed level Taguchi experimental design with an L18 orthogonal array. Six levels of step depth, three levels of tool diameter, feed rate, and tool rotational speed have been considered as input process parameters. The analyses of variance (ANOVA) have been used to investigate the significance of parameters and the effect of their levels for minimum surface roughness, minimum wall angle deviation, and maximum average wall thickness. The results indicate that step depth and tool rotational speed are the most significant parameters on the output responses. The predicted optimal values for the surface roughness, average wall thickness, and wall angle deviation are found to be 0.6363 μm, 0.9442 mm, and 0.0994° respectively. The results have been validated by the confirmation of the experiments and found to be 0.57, 0.9162, and 0.124, respectively, which are within the range of these values.
In this paper, an algorithm is suggested to train a single layer feedforward neural network to function as a heteroassociative memory. This algorithm enhances the ability of the memory to recall the stored patterns when partially described noisy inputs patterns are presented. The algorithm relies on adapting the standard delta rule by introducing new terms, first order term and second order term to it. Results show that the heteroassociative neural network trained with this algorithm perfectly recalls the desired stored pattern when 1.6% and 3.2% special partially described noisy inputs patterns are presented.
(5)
(4)
(5)
The unpredictable and huge data generation nowadays by smart computing devices like (Sensors, Actuators, Wi-Fi routers), to handle and maintain their computational processing power in real time environment by centralized cloud platform is difficult because of its limitations, issues and challenges, to overcome these, Cisco introduced the Fog computing paradigm as an alternative for cloud-based computing. This recent IT trend is taking the computing experience to the next level. It is an extended and advantageous extension of the centralized cloud computing technology. In this article, we tried to highlight the various issues that currently cloud computing is facing. Here
... Show More
(11)
(5)
Most Internet of Vehicles (IoV) applications are delay-sensitive and require resources for data storage and tasks processing, which is very difficult to afford by vehicles. Such tasks are often offloaded to more powerful entities, like cloud and fog servers. Fog computing is decentralized infrastructure located between data source and cloud, supplies several benefits that make it a non-frivolous extension of the cloud. The high volume data which is generated by vehicles’ sensors and also the limited computation capabilities of vehicles have imposed several challenges on VANETs systems. Therefore, VANETs is integrated with fog computing to form a paradigm namely Vehicular Fog Computing (VFC) which provide low-latency services to mo
... Show More
(12)
(10)
(7)
(3)
(3)
(55)
(52)
(4)
(4)