Accueil
Catégories
Ajouter le résultat dans votre panier Affiner la recherche
Etendre la recherche sur niveau(x) vers le bas
A novel approach to using neural networks to predict the colour of fibre blends / Caroline Hemingray in COLORATION TECHNOLOGY, Vol. 132, N° 4 (08/2016)
[article]
Titre : A novel approach to using neural networks to predict the colour of fibre blends Type de document : texte imprimé Auteurs : Caroline Hemingray, Auteur ; Stephen Westland, Auteur Année de publication : 2016 Article en page(s) : p. 297-303 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Mélanges de fibres
Prévision, Théorie de la
Réseaux neuronaux (informatique)
ViscoseIndex. décimale : 667.9 Revêtements et enduits Résumé : This work is concerned with the colour prediction of viscose fibre blends, comparing two conventional prediction models (the Stearns–Noechel model and the Friele model) and two neural network models. A total of 333 blended samples were prepared from eight primary colours, including two-, three-, and four-colour mixtures. The performance of the prediction models was evaluated using 60 of the 333 blended samples. The other 273 samples were used to train the neural networks. It was found that the performance of both neural networks exceeded the performance of both conventional prediction models. When the neural networks were trained using the 273 training samples, the average CIELAB colour differences (between measured and predicted colour of blends) for the 60 samples in the test set were close to 1.0 for the neural network models. When the number of training samples was reduced to only 100, the performance of the neural networks degraded, but they still gave lower colour differences between measured and predicted colour than the conventional models. The first neural network was a conventional network similar to that which has been used by several other researchers; the second neural network was a novel application of a standard neural network where, rather than using a single network, a set of small neural networks was used, each of which predicted reflectance at a single wavelength. The single-wavelength neural network was shown to be more robust than the conventional neural network when the number of training examples was small. DOI : 10.1111/cote.12220 En ligne : https://onlinelibrary.wiley.com/doi/epdf/10.1111/cote.12220 Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=26731
in COLORATION TECHNOLOGY > Vol. 132, N° 4 (08/2016) . - p. 297-303[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 18246 - Périodique Bibliothèque principale Documentaires Disponible Optimal prediction of PKS: RSO modified alkyd resin polycondensation process using discrete-delayed observations, ANN and RSM-GA techniques / Chigozie F. Uzoh in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH, Vol. 14, N° 3 (05/2017)
[article]
Titre : Optimal prediction of PKS: RSO modified alkyd resin polycondensation process using discrete-delayed observations, ANN and RSM-GA techniques Type de document : texte imprimé Auteurs : Chigozie F. Uzoh, Auteur ; Okechukwu D. Onukwuli, Auteur Année de publication : 2017 Article en page(s) : p. 607-620 Note générale : Bibliogr. Langues : Américain (ame) Catégories : Algorithmes génétiques
Analyse multivariée
Plan d'expérience
Polyalkydes
Polycondensation
Réseaux neuronaux (informatique)
Surfaces de réponse (statistique)Index. décimale : 667.9 Revêtements et enduits Résumé : Alkyd resins are widely used in the paint industry and although they have a long history about 70–100 years, today the developments in alkyds are still welcome and innovations are still needed. Artificial neural network (ANN) and response surface methodology based on a 25−1 fractional factorial design were used as tools for simulation and optimization of the polycondensation process for autooxidative drying alkyd resin from palm kernel stearin: rubber seed oil blend of 70:30 ratio. A feed forward neural network model with Levenberg–Marquardt back propagation training algorithm was adapted to predict the responses (conversion Y1, viscosity Y2, and molecular weight average Y3). The studied input variables were reaction time, temperature, catalyst concentration, oil ratio, and stirring rate. The performance of the RSM and ANN model showed adequate prediction of the responses in terms of the process factors, with MRPD of ±4.47% (Y1), ±2.08% (Y2), ±8.92% (Y3) and ±6.50% (Y1), ±3.31% (Y2), ±10.20% (Y3), respectively. The sensitivity analysis showed that while reaction time is the most effective process parameter, the interaction of the five process variables produced the most significant effect on the studied responses with the overall minimum MSE of 0.079. The optimization task performed using a genetic algorithm linked to the RSM model gave a viable, nondominated optimal response and optimum operating conditions regarding the route to high-quality resin at reduced material and operational costs. Overall, coupled RSM-GA was found to be a better tool for modeling and optimization of the alkyd resin production. Note de contenu : - MATERIALS AND METHODS : Materials - Synthesis of alkyd resin from modified palm kernel stearin - System prediction via RSM - Sensitivity analysis and system prediction via artificial neural network (ANN) model
- RESULTS AND DISCUSSION : Predictive model for system response aproximation via RSM - Reaction prediction via ANN - Optimization by coupled RSM-GA techniqueDOI : 10.1007/s11998-016-9881-6 En ligne : https://link.springer.com/content/pdf/10.1007%2Fs11998-016-9881-6.pdf Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=28569
in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH > Vol. 14, N° 3 (05/2017) . - p. 607-620[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 18899 - Périodique Bibliothèque principale Documentaires Disponible Predicting critical micelle concentration values of non-ionic surfactants by using artificial neural networks / Gonzalo Astray in TENSIDE, SURFACTANTS, DETERGENTS, Vol. 50, N° 2 (03-04/2013)
[article]
Titre : Predicting critical micelle concentration values of non-ionic surfactants by using artificial neural networks Type de document : texte imprimé Auteurs : Gonzalo Astray, Auteur ; A. Iglesias-Otero, Auteur ; Oscar Adrian Moldes, Auteur ; Juan Carlos Mejuto, Auteur Année de publication : 2013 Article en page(s) : p. 118-124 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Concentration micellaire critique
Réseaux neuronaux (informatique)
SurfactantsIndex. décimale : 668.1 Agents tensioactifs : savons, détergents Résumé : Critical Micelle Concentration is a fundamental property on studying behaviour of surfactants. In general terms it depends on temperature, pressure and on the existence and concentration of other surface-active substances and electrolytes. In this work it is presented a model based on Artificial Neural Networks to obtain predictive values of Critical Micelle Concentration (CMC) of some non-ionic surfactants. ANN model works using topological descriptors of the molecules involved together with already known CMC values and provides predictive values for new cases. It is proposed a specific architecture for ANN consisting of an input layer with seven neurons, one intermediate layer with fourteen neurons and one neuron in the output layer. This ANN model seems to be a good method for forecast CMC. DOI : 10.3139/113.110242 Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=17890
in TENSIDE, SURFACTANTS, DETERGENTS > Vol. 50, N° 2 (03-04/2013) . - p. 118-124[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 14844 - Périodique Bibliothèque principale Documentaires Disponible Prediction of architectural coating performance using titanium dioxide characterization applying artificial neural networks / Pablo René Aragon Candelaria in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH, Vol. 7, N° 4 (07/2010)
[article]
Titre : Prediction of architectural coating performance using titanium dioxide characterization applying artificial neural networks Type de document : texte imprimé Auteurs : Pablo René Aragon Candelaria, Auteur ; Aaron J. Owens, Auteur Année de publication : 2010 Article en page(s) : p. 431-440 Note générale : Bibliogr. Langues : Américain (ame) Catégories : Caractérisation
Dioxyde de titane
Réseaux neuronaux (informatique)
Revêtement mural:Peinture murale
Revêtements en bâtiment:Peinture en bâtiment
Revêtements en phase aqueuse:Peinture en phase aqueuseIndex. décimale : 667.9 Revêtements et enduits Résumé : Prediction of paint properties is a critical issue for the coatings industry, since experimentation is time consuming and a lot of financial and human resources are needed to test or develop new products. In current market conditions, cost savings and product innovation are critical issues. In this article, an artificial neural network, of the feed forward type, was trained using as inputs key properties of titanium dioxide and two formulation parameters (pigment volume concentration and titanium dioxide content) for a water-based architectural coating. The outputs of this research were spread rate, color (L*, a*, b*) and tinting strength. Test data were used to check the accuracy of the model, demonstrating the viability of paint properties prediction related to the properties of the titanium dioxide formulation with high correlation (>95%). DOI : 10.1007/s11998-009-9215-z En ligne : https://link.springer.com/content/pdf/10.1007%2Fs11998-009-9215-z.pdf Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=9765
in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH > Vol. 7, N° 4 (07/2010) . - p. 431-440[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 012362 - Périodique Bibliothèque principale Documentaires Disponible Processing and wear analysis of blast furnace slag filled polypropylene composites using Taguchi model and ANN / P. K. Padhi in INTERNATIONAL POLYMER PROCESSING, Vol. XXIX, N° 2 (05/2014)
[article]
Titre : Processing and wear analysis of blast furnace slag filled polypropylene composites using Taguchi model and ANN Type de document : texte imprimé Auteurs : P. K. Padhi, Auteur ; A. Satapathy, Auteur Année de publication : 2014 Article en page(s) : p. 233-244 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Charges (matériaux)
Composites à fibres courtes
Composites à fibres de verre
Composites à fibres de verre -- Détérioration
Composites à fibres de verre -- Moulage par injection
Essais de résilience
Laitiers (métallurgie)En sidérurgie, le laitier est un coproduit de la métallurgie contenant des oxydes métalliques, essentiellement des silicates, des aluminates et de la chaux, qui sont formés en cours de fusion ou d'élaboration de métaux par voie liquide.
Il est issu de la fabrication de la fonte au haut fourneau, où il correspond à la gangue stérile du minerai de fer, isolée de la fonte liquide dont il se sépare par différence de densité.
La quantité de laitier produite correspond directement à la richesse du minerai de fer utilisé.
De composition chimique très stable, est souvent valorisé dans la fabrication de ciment (BFS-OPC) et dans les travaux publics (ballast, enrobé bitumé,...).
Plan d'expérience
Polypropylène
Réseaux neuronaux (informatique)
Taguchi, Méthodes de (Contrôle de qualité)
Usure (mécanique)Index. décimale : 668.9 Polymères Résumé : This paper analyses and reports on processing and solid particle erosion wear response of a new class of hybrid composites prepared by reinforcement of short glass fibers (SGF) in blast furnace slag (BFS) filled polypropylene (PP) matrix. In this investigation, composites with different BFS content (0, 10, 20 and 30?wt%) in a polypropylene matrix base, with and without 20?wt% SGF reinforcement, are prepared by injection molding route. To study the erosion wear response of these BFS filled composites, a plan of experiments based on the Taguchi technique is followed to acquire the wear data in a controlled way. This systematic experimentation has led to identification of significant process parameters and material variables that predominantly influence the erosion rate and also enables us to determine optimal parameter settings that lead to minimization of the erosion rate. An artificial neural network (ANN) approach is also implemented to predict the wear rate of the composites. The morphology of eroded surfaces is then examined by scanning electron microscopy (SEM) and possible erosion mechanisms are discussed. This study reveals that addition of blast furnace slag improves the erosion resistance of glass-polypropylene composites significantly and thus makes them suitable for tribological applications. Note de contenu : - EXPERIMENTAL DETAILS : Composite fabrication - Erosion test - Taguchi experimental design - Prediction based on neural computation
- RESULTS AND DISCUSSION : Erosion test results - Predictive equation for determination of erosion rate - Wear analysis and prediction using neural computation - Steady state erosion - Morphology of the worn surfaceDOI : 10.3139/217.2841 En ligne : https://drive.google.com/file/d/18CfE8_JQqHPhBYx6jPlGnD_PMkTTNjur/view?usp=drive [...] Format de la ressource électronique : Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=21318
in INTERNATIONAL POLYMER PROCESSING > Vol. XXIX, N° 2 (05/2014) . - p. 233-244[article]Réservation
Réserver ce document
Exemplaires (1)
Code-barres Cote Support Localisation Section Disponibilité 16222 - Périodique Bibliothèque principale Documentaires Disponible Real-world tasks for virtual sensors / Thomas Hochrein in KUNSTSTOFFE INTERNATIONAL, Vol. 102, N° 2 (02/2012)
PermalinkRepercussion of cenosphere filler size on mechanical and dry sliding wear peculiarity of glass fiber-reinforced polyester composites using Taguchi analysis and neural network / Akant Kumar Singh in INTERNATIONAL POLYMER PROCESSING, Vol. XXX, N° 3 (07/2015)
PermalinkSeeking a paper for digital printing with maximum gamut volume : a lesson from artificial intelligence / Maryam Ataeefard in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH, Vol. 19, N° 1 (01/2022)
PermalinkSoft computing approaches for thermal conductivity estimation of CNT/water nanofluid / Mohammad Hossein Ahmadi in REVUE DES COMPOSITES ET DES MATERIAUX AVANCES, Vol. 29, N° 2 (04/2019)
PermalinkSoft computing in textile engineering / Abhijit Majumdar / Cambridge [United Kingdom] : Woodhead Publishing Ltd (2011)
PermalinkSpectrophotometric colour matching algorithm for top-dyed melange yarn, based on an artificial neural network / Jiajia Shen in COLORATION TECHNOLOGY, Vol. 133, N° 4 (08/2017)
PermalinkUV curable PSAs augment existing adhesive technologies / Tom Kauffman in ADHESIVES AGE, Vol. 41, N° 7 (07/1998)
PermalinkA warpage optimization method for injection molding using artificial neural network combined weighted expected improvement / H. Shi in INTERNATIONAL POLYMER PROCESSING, Vol. XXVII, N° 3 (07/2012)
PermalinkPermalink