Kunkun Wang^1,2, Xianda Liu^2,3,4,*

Journal on Artificial Intelligence, Vol.3, No.1, pp. 9-19, 2021, DOI:10.32604/jai.2021.016706

Abstract With the development of Internet technology, the computing power of data has increased, and the development of machine learning has become faster and faster. In the industrial production of industrial control systems, quality inspection and safety production of process products have always been our concern. Aiming at the low accuracy of anomaly detection in process data in industrial control system, this paper proposes an anomaly detection method based on stacking integration using the machine learning algorithm. Data are collected from the industrial site and processed by feature engineering. Principal component analysis (PCA) and integrated rule tree method are adopted to… More >

Yuetian Wang, Chuanjing Zhang, Xuxin Liao, Xingang Wang, Zhaoquan Gu^*

Journal on Artificial Intelligence, Vol.3, No.1, pp. 1-8, 2021, DOI:10.32604/jai.2021.014175

Abstract Deep neural networks (DNNs) are widely adopted in daily life and the security problems of DNNs have drawn attention from both scientific researchers and industrial engineers. Many related works show that DNNs are vulnerable to adversarial examples that are generated with subtle perturbation to original images in both digital domain and physical domain. As a most common application of DNNs, face recognition systems are likely to cause serious consequences if they are attacked by the adversarial examples. In this paper, we implement an adversarial attack system for face recognition in both digital domain that generates adversarial face images to fool… More >

Lei Liu^*, Chuanhui Huang, Xinghua Lu, Ping Yu, Longhai Li, Huafeng Guo

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 501-509, 2021, DOI:10.32604/fdmp.2021.015161

Abstract In order to study the effect of Al₂O₃ nanoparticles in the cavitation-based strengthening process of magnesium alloys, the impact of a micro-jet generated by bubble collapse has been considered. The strengthening mechanism is based on the transfer of the energy of cavitation due to bubble collapse to Al₂O₃ particles, which then undergo collision with the surface of the sample. The hardness, surface morphology, element content and chemical state of the strengthened samples have been analyzed by microhardness tests, SEM (scanning electron microscopy) and XPS (X-ray photoelectron spectroscopy) techniques. The results show that: after 5 min of strengthening, nanoparticles can be… More >

Guozhi Li¹, Yihua Cao^2,*

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 235-252, 2021, DOI:10.32604/fdmp.2021.014814

Abstract The wake generated by the rotor of a helicopter can exert a strong interference effect on the fuselage and the horizontal/vertical tail. The occurrence of icing on the rotor can obviously make this interplay more complex. In the present study, numerical simulation is used to analyze the rotor wake in icing conditions. In order to validate the overall mathematical/numerical method, the results are compared with similar data relating to other tests; then, different simulations are conducted considering helicopter forward flight velocities of 0, 10, 20, 50, and 80 knots and various conditions in terms of air temperature (atmospheric temperature degrading… More >

Dongling Yu¹, Zuoxiang Zhu¹, Jiangen Zhou¹, Dahai Liao^1,*, Nanxing Wu^1,2,*

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 487-500, 2021, DOI:10.32604/fdmp.2021.014712

Abstract In order to control the accumulation of SiC ceramic particles on the wall of the rotating chamber in the frame of a dry granulation process, the effect of the wall reverse speed on the mixing process is investigated. In particular, an Euler-Euler two-phase flow model is used to analyze the dynamics of both SiC particles and air. The numerical results show that by setting a certain reverse rotating speed of the rotating chamber, the accumulation of SiC particles on the wall can be improved, i.e., their direction of motion in proximity to the wall can be changed and particles can… More >

Yin Wang^1,*, Lingling Wang², Yong Ji¹, Zhicheng Xi¹, Wenwen Zhang¹

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 471-485, 2021, DOI:10.32604/fdmp.2021.014652

Abstract A three dimensional (3D) numerical wave flume is used to investigate carefully the ISWs (Internal solitary wave) forces acting on cylinders interacting with a stratified shear environment. Using the Large-Eddy Simulation (LES) approach and analyzing the distribution of shear stress and pressure along the surface of the cylinder, the differential pressure resistance and the viscous force are obtained. The method of multiple linear regression analysis is adopted and a comprehensive influence coefficient is determined accordingly to account for the dimensionless forces acting on the cylinder. Results show that the differential pressure resistance on a square cylinder is 1.5 times higher… More >

D. R. V. S. R. K. Sastry¹, Peri K. Kameswaran², Mohammad Hatami^3,*

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 285-300, 2021, DOI:10.32604/fdmp.2021.014429

Abstract The problem of Marangoni mixed convection in the presence of an inclined magnetic field with uniform strength in a nanofluid (formed by the dispersion of two metallic nanoparticles, i.e., Copper (Cu), and alumina (Al₂O₃) in water) is addressed numerically. The effects of viscous dissipation and Ohmic heating are also considered. The original set of governing partial differential equations is reduced to a set of non-linear coupled ordinary differential equations employing the similarity transformation technique. The simplified equations are numerically solved through MATLAB ‘bvp4c’ algorithm. The results are presented in terms of graphs for several parameters. It is found that enhancing… More >

Jinli Song¹, Nabil Kharoua^2,*, Lyes Khezzar¹, Mohamed Alshehhi¹

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 455-470, 2021, DOI:10.32604/fdmp.2021.014370

Abstract Turbulent swirling flow inside a short pipe interacting with a conical bluff body was simulated using the commercial CFD code Fluent. The geometry used is a simplified version of a novel liquid/gas separator used in multiphase flow metering. Three turbulence models, belonging to the Reynolds averaged Navier-Stokes (RANS) equations framework, are used. These are, RNG k-ε, SST k-ω and the full Reynolds stress model (RSM) in their steady and unsteady versions. Steady and unsteady RSM simulations show similar behavior. Compared to other turbulence models, they yield the best predictions of the mean velocity profiles though they exhibit some discrepancies in… More >

Pradeep Gurrala¹, Saravanan Balusamy¹, Sayak Banerjee¹, Kirti Chandra Sahu^2,*

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 253-284, 2021, DOI:10.32604/fdmp.2021.014126

Abstract The wetting and evaporation dynamics of sessile droplets have gained considerable attention over the last few years due to their relevance to many practical applications, ranging from a variety of industrial problems to several biological systems. Droplets made of binary mixtures typically undergo complex dynamics due to the differential volatility of the considered components and the ensuing presence of thermocapillary effects. For these reasons, many research groups have focused on the evaporation of binary droplets using a variegated set of experimental, numerical, and purely theoretical approaches. Apart from reviewing the state-of-the-art about the existing experimental, analytical, and computational techniques used… More >

Chenguang Guo^1,2,*, Yu Sun^1,2, Qiang Li¹, Haitao Yue¹, Chuang Wang¹

FDMP-Fluid Dynamics & Materials Processing, Vol.17, No.2, pp. 349-370, 2021, DOI:10.32604/fdmp.2021.013535

Abstract

To improve the agglomeration of powder in a coaxial powder feeding nozzle used in the frame of a laser energy deposition technique, the influence of several parameters must be carefully assessed. In the present study the problem is addressed by means of numerical simulations based on a DEM-CFD (Discrete Element Method and Discrete Element Method) coupled model. The influence of the powder flow concentration, powder flow focal length and the amount of powder at the nozzle outlet on the rate of convergence of the powder flow is considered. The role played by the nozzle outlet width, the angle between the… More >