One of the main parts in hydraulic system is directional control valve, which is needed in order to operate hydraulic actuator. Practically, a conventional directional control valve has complex construction and moving parts, such as spool. Alternatively, a proposed Magneto-rheological (MR) directional control valve can offer a better solution without any moving parts by means of MR fluid. MR fluid consists of stable suspension of micro-sized magnetic particles dispersed in carrier medium like hydrocarbon oil. The main objectives of this present research are to design a MR directional control valve using MR fluid, to analyse its magnetic circuit using FEMM software, and to study and simulate the performance of this valve. In this research, a

This research adopts the estimation of mass transfer coefficient in batch packed bed distillation column as function of physical properties, liquid to vapour molar rates ratio (L / V), relative volatility (α), ratio of vapour and liquid diffusivities (DV / DL), ratio of vapour and liquid densities (ρV / ρL), ratio of vapour and liquid viscosities (μV/ μL).
The experiments are done using binary systems, (Ethanol Water), (Methanol Water), (Methanol Ethanol), (Benzene Hexane), (Benzene Toluene). Statistical program (multiple regression analysis) is used for estimating the overall mass transfer coefficient of vapour and liquid phases (KOV and KOL) in a correlation which represented the data fairly well.

KOV = 3.3 * 10^-10

Imitation learning is an effective method for training an autonomous agent to accomplish a task by imitating expert behaviors in their demonstrations. However, traditional imitation learning methods require a large number of expert demonstrations in order to learn a complex behavior. Such a disadvantage has limited the potential of imitation learning in complex tasks where the expert demonstrations are not sufficient. In order to address the problem, we propose a Generative Adversarial Network-based model which is designed to learn optimal policies using only a single demonstration. The proposed model is evaluated on two simulated tasks in comparison with other methods. The results show that our proposed model is capable of completing co

Botnet detection develops a challenging problem in numerous fields such as order, cybersecurity, law, finance, healthcare, and so on. The botnet signifies the group of co-operated Internet connected devices controlled by cyber criminals for starting co-ordinated attacks and applying various malicious events. While the botnet is seamlessly dynamic with developing counter-measures projected by both network and host-based detection techniques, the convention techniques are failed to attain sufficient safety to botnet threats. Thus, machine learning approaches are established for detecting and classifying botnets for cybersecurity. This article presents a novel dragonfly algorithm with multi-class support vector machines enabled botnet

Patients infected with the COVID-19 virus develop severe pneumonia, which typically results in death. Radiological data show that the disease involves interstitial lung involvement, lung opacities, bilateral ground-glass opacities, and patchy opacities. This study aimed to improve COVID-19 diagnosis via radiological chest X-ray (CXR) image analysis, making a substantial contribution to the development of a mobile application that efficiently identifies COVID-19, saving medical professionals time and resources. It also allows for timely preventative interventions by using more than 18000 CXR lung images and the MobileNetV2 convolutional neural network (CNN) architecture. The MobileNetV2 deep-learning model performances were evaluated

A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an