Liming Yang^1,2, Junjian Bai¹, Qun Sun³

CMES-Computer Modeling in Engineering & Sciences, Vol.108, No.1, pp. 49-65, 2015, DOI:10.3970/cmes.2015.108.049

Abstract Extreme learning machine (ELM) has demonstrated great potential in machine learning and data mining fields owing to its simplicity, rapidity and good generalization performance. In this work, a general framework for ELM regression is first investigated based on least absolute deviation (LAD) estimation (called LADELM), and then we develop two regularized LADELM formulations with the l₂-norm and l₁-norm regularization, respectively. Moreover, the proposed models are posed as simple linear programming or quadratic programming problems. Furthermore, the proposed models are used directly to analyze the hard rate of licorice seeds using near-infrared spectroscopy data. Experimental results on eight different spectral regions… More >

N.S.Mera¹, L. Elliott², D.B.Ingham²

CMES-Computer Modeling in Engineering & Sciences, Vol.15, No.2, pp. 107-114, 2006, DOI:10.3970/cmes.2006.015.107

Abstract The purpose of this study is to investigate the efficiency, accuracy and rate of convergence of an evolutionary algorithm for detecting inclusions parametrised by superellipses in non-destructive evaluation and testing. The inverse problem investigated consists of identifying the geometry of discontinuities in a conductive material from Cauchy data measurements taken on the boundary. Temperature and heat flux are measured on the outside boundary of the domain and the position and the size of a super-elliptical inclusion are determined by minimising an objective functional using an evolution strategy. The super-elliptical form allows the parametric model to characterise a variety of shapes… More >

Tae-Jong Yun¹, Won-Bin Oh¹, Bo-Ram Lee¹, Joon-Sik Son², Ill-soo Kim^1,*

FDMP-Fluid Dynamics & Materials Processing, Vol.15, No.1, pp. 1-14, 2019, DOI:10.32604/fdmp.2019.04759

Abstract Detection of weld defects using real-time monitoring and controlling algorithm is of the significant task in manufacturing industries due to the increased production and liability costs that result when weld defects are not identified early in the production cycle. Monitoring and controlling for robotic arc welding process employed should be reliable, flexible and cost-effective in non-clean, high-volume production environments. Also, the robotic welding system has been utilized a complex jigging and mechanical devices to move the workpiece which related to the stationary welding head for getting higher efficiency and lower costs. To develop the fully robotic welding system, people make… More >

A. Khourchafi¹, M. El Alami^2,3, M. Najam², M. Belhaq⁴

FDMP-Fluid Dynamics & Materials Processing, Vol.8, No.3, pp. 323-338, 2012, DOI:10.3970/fdmp.2012.008.323

Abstract A spectral radiation study has been carried out in the framework of a statistical narrow-band model based on an inverse-tailed exponential law and the socalled P1 approximation. This new spectral formulation, which may be also regarded as a grey band formulation with a local absorption coefficient, leads to two implementation methods: a non correlated form in which the averaged formulation of the P1 approximation does not take into account the correlation between fundamental quantities and a pseudo-correlated variant consisting basically of a technique for improving the anisotropy of the radiative intensity. Real gases (H₂O, CO₂) are considered. The resulting tests… More >