Identification of relevant wavelet functions for multiscale characterization of manufactured surfaces using a genetically optimized neural network
TypeArticles dans des revues avec comité de lecture
Multiscale surface characterization is a powerful tool that is used for process monitoring, surface quality control, and manufacturing optimization by establishing a link between process variables and functional performances. The multiscale decomposition approach using continuous and discrete wavelets is widely applied to take into account scales dependency. However, the optimal choice of the analysis wavelet function and the number of decomposition level is still a big issue. In this article, the artificial neural network theory was combined with the wavelet concept and was optimized based on the genetic algorithm to identify the relevant wavelet function for multiscale characterization of abraded surface topographies. Then, an extensive wavelet function library was developed and the proposed algorithm was applied to topographic data obtained from various abrasive finishing processes. The results show the pertinence of this approach to select the relevant wavelet, and a universal relevant wavelet function for abraded surface characterization was determined.
Fichier(s) constituant cette publication
Cette publication figure dans le(s) laboratoire(s) suivant(s)
Visualiser des documents liés par titre, auteur, créateur et sujet.
Energy efficiency optimization of engine by frictional reduction of functional surfaces of cylinder ring-pack system MEZGHANI, Sabeur; DEMIRCI, Ibrahim; EL MANSORI, Mohamed; ZAHOUANI, Hassan (Elsevier, 2013)Friction reduction, lower oil consumption, and limitation of greenhouse gases emissions are the chief objectives of the automotive industry in order to improve the environmental efficiency of vehicle engines. In this paper, ...
Correlation between mechanical scales and analysis scales of topographic signals under milling process of natural fibre composites CHEGDANI, Faissal; MEZGHANI, Sabeur; EL MANSORI, Mohamed (SAGE, 2017)This article aims to find the relation between the multiscale mechanical structure of natural fibre reinforced plastic composites and the analysis scales in the topographic signals of machined surfaces as induced by profile ...
CHEGDANI, Faissal; EL MANSORI, Mohamed; MEZGHANI, Sabeur; MONTAGNE, Alex (ELSEVIER, 2017)The nature of friction of vegetal fiber and polymeric matrix in bio-composite materials is very important for many industrial applications. In order to design natural fiber composites for structural applications, the ...
On the multiscale tribological signatures of the tool helix angle in profile milling of woven flax fiber composites CHEGDANI, Faissal; MEZGHANI, Sabeur; EL MANSORI, Mohamed (ELSEVIER, 2016)The present study is focused on tribological and multiscale analysis for the machined surfaces of bi-directional flax fibers reinforced polypropylene composites. This is to track the multiscale effect of the helix angle ...
CONIGLIO, Nicolas; MEZGHANI, Sabeur; EL MANSORI, Mohamed; CABRERO, J. (Elsevier, 2018)Surface texturation at micro- and meso-scales plays an important role in applications where cosmetic, aesthetic and self-cleaning functionalities are specified. This research paper deals with a multiscale surface, in which ...