Big data comes to coatings / Partha Majumdar in EUROPEAN COATINGS JOURNAL (ECJ), N° 11 (11/2021)  

[article]  inEUROPEAN COATINGS JOURNAL (ECJ) > N° 11 (11/2021) . - p. 40-47 Titre : Big data comes to coatings : Novel formulation optimisation using big data, modelling, and predictive tools Type de document : texte imprimé Auteurs : Partha Majumdar, Auteur ; Jonathan DeRocher, Auteur ; Michael Tran, Auteur ; Nipun Bisht, Auteur ; Rose Bohling, Auteur ; Adeline Ossola, Auteur ; Ivan Boronat Monfort, Auteur ; Philip Harsh, Auteur ; James Bohling, Auteur ; Jeff Sweeney, Auteur Année de publication : 2021 Article en page(s) : p. 40-47 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Agent mattant Analyse des données Données massives Essais (technologie) Formulation (Génie chimique) Modélisation prédictive Plan d'expérience Revêtements organiques Index. décimale : 667.9 Revêtements et enduits Résumé : Big data analytics and machine learning (ML) have disrupted nearly every industry, and are now being embraced by the coatings sector, whose formulations offer an almost infinite formulation landscape. This paper reviews recent work in this area, explores the use of iterative experimental design to map the performance of a matting resin and discusses the use of advanced data analysis through the application of applying various algorithms. Note de contenu : - EXPERIMENTAL : Materials - FORMULATIONS - TEST METHODS : Block - Tack - Coefficient of friction - Scrub - Stain - OUTLINE OF DESIGN OF EXPERIMENTS (DOE) - DATA ANALYSIS AND MODELS - OPTIMISATION - MODEL DEPLOYMENT - Fig. 1 :Distribution of gloss, scrub, and scatter plot of gloss vs. scrub with CoF overlay - Fig. 2 : Plots of LSMeans for comparing the impact of matting additives on (a) scrub and (b) CoF in white base, no extender formulations and the impact of both matting additives and extenders on (c) scrub and (d) CoF in white base with extender formulations - Fig. 3 : Plots of LSMeans for comparing the impact of matting agents on (a) tack, (b) CoF, and (c) scrub in deep base, no extender formulations - Fig. 4 : Plots of LSMeans for comparing the impact of interactions between matting agents and extenders on (a) tack, (D) CoF, and (c) scrub in deep base with extender formulations - Fig. 5 : Expansion of initial input parameters from material type to characteristic properties - Fig. 6 : Optimised formulation maps (a) all properties are equally important and (b) gloss, scrub, and CoF are twice as important as AKU and stain - Fig. 7 : Interactive formulation map implemented in Plotly Dash and deployed in RStudio - Table 1 : Typical white base formulations - Table 2 : Typical deep base formulation - Table 3 : Design variables including ingredient types and levels of interest - Table 4 : Model R2 values of key paint properties - Table 5 : Training and Test R2 values for the combined white base data set comparing methodologies applied to model paint properties using material property input parameters En ligne : https://drive.google.com/file/d/1jepJbW7hRp6AOq_tJ4cjI3SSB2OMKBfh/view?usp=drive [...] Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=36482 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
23041	-	Périodique	Bibliothèque principale	Documentaires	Disponible

ICME and materials data management for more agile design and engineering of advanced materials in JEC COMPOSITES MAGAZINE, N° 134 (05-06/2020)

[article]  inJEC COMPOSITES MAGAZINE > N° 134 (05-06/2020) . - p. 35-36 Titre : ICME and materials data management for more agile design and engineering of advanced materials Type de document : texte imprimé Année de publication : 2020 Article en page(s) : p. 35-36 Langues : Anglais (eng) Catégories : Composés de moulage en feuille Composites Conception assistée par ordinateur Conception technique Gestion de données Logiciels Modélisation prédictive Simulation par ordinateur Index. décimale : 668.4 Plastiques, vinyles Résumé : Reducing development times and costs of composites materials is high on the agenda for all manufacturers to remain competitive and penetrate the market. A powerful approach to achieve tis in Integrated Computational Materials Engineering (ICME) - or in simple words - an integrative design approach where materials, processing and final products are connected thourgh various scales. When organizations apply this method to composite materials, they quickly realize the amount of materials data that needs to be captured and validated, whether generated from virtual or physical testing. Note de contenu : - Advanced materials modelling and virtual allowables - A platform to capture all physical and virtual composites information - Fig. 1 : Composite ICME integrated materials data management at every scale considered - Fig. 2 : Full-field homogenization with Digimat to predict composite failure envelopes - Fig. 3 : Validation of UD strength predictions with Digimat 2019.1 - Fig. 4 : Example of managing both physical and virtual data Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=35375 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
21794	-	Périodique	Bibliothèque principale	Documentaires	Disponible

A stearns-Noechel colour prediction model reconstructed from gridded colour solid of nine primary colours and its application / Xianqiang Sun in COLORATION TECHNOLOGY, Vol. 140, N° 4 (08/2024)  

[article]  inCOLORATION TECHNOLOGY > Vol. 140, N° 4 (08/2024) . - p. 571-584 Titre : A stearns-Noechel colour prediction model reconstructed from gridded colour solid of nine primary colours and its application Type de document : texte imprimé Auteurs : Xianqiang Sun, Auteur ; Yuan Xue, Auteur ; Jingli Xue, Auteur ; Guang Jin, Auteur Année de publication : 2024 Article en page(s) : p. 571-584 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Colorimétrie Couleur Mélange de couleurs Modélisation prédictive Spectroscopie de réflectance Index. décimale : 535.6 Couleur Résumé : A full gamut colour solid model consisting of three lightness planes, 18 colour mixing units and 360 grid points is constructed from nine primary coloured fibres: red (R), yellow (Y), green (G), cyan (C), blue (B), magenta (M), dark grey (O1), medium grey (O2) and light grey (O3). Subsequently, the 213 coloured yarns and fabrics containing different lightness, hue and saturation were prepared according to the mixing ratio parameters in the colour solid. The Stearns–Noechel colour prediction algorithm, which predicts reflectance using coloured fibre mixing ratios, was improved and applied according to the requirements of colour prediction; and the Stearns–Noechel proportion prediction algorithm, which predicts coloured fibre mixing ratios by reflectance, was refined and employed in accordance with the demands of proportion prediction. Then, the 12 additional coloured fabrics were fabricated and their corresponding measurement data were used on the algorithm for validating its forecasting capabilities. The final experimental results reveal that the maximum colour difference for colour prediction is 5.5, the minimum is 1.7, and the average is 3.7; the maximum colour difference for proportion prediction is 3.3, the minimum is 0.3, and the average is 1.6. Therefore, this approach is promising to improve the colour reproduction issues encountered in the processing of three-channel computer numerical control (CNC) spinning. Note de contenu : - COLOUR SOLID BUILT BY NINE PRIMARY COLOURED FIBRES AND ITS SPINNING PATTERN : Construction of colour solid of colour mixing of nine primary coloured fibres - The principle of spinning coloured yarn using three-channel CNC spinning - STEARNS–NOECHEL COLOUR PREDICTION MODEL : Stearns–Noechel colour prediction model built from colour mixing pattern of full colour gamut - Prediction of reflectance at arbitrary points within the gridded colour mixing model - Colour prediction by full colour gamut mixing model and its colour difference - Prediction of mixing ratios of coloured fibres by colour values of full colour gamut mixing model - EXPERIMENTAL ANALYSIS : Preparation of yarn - Preparation of fabric - Acquisition of spectral reflectance DOI : https://doi.org/10.1111/cote.12724 En ligne : https://drive.google.com/file/d/1TnyeuL6ZBCDs7304Ai_EI4oDhzhivqBy/view?usp=drive [...] Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=41318 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
24746	-	Périodique	Bibliothèque principale	Documentaires	Disponible

Using AI to rapidly develop new and improved high-performance coatings in COATINGS TECH, Vol. 21, N° 3 (05-06/2024)  

[article]  inCOATINGS TECH > Vol. 21, N° 3 (05-06/2024) . - p. 45-49 Titre : Using AI to rapidly develop new and improved high-performance coatings Type de document : texte imprimé Année de publication : 2024 Article en page(s) : p. 45-49 Langues : Américain (ame) Catégories : Analyse multivariée Formulation (Génie chimique) Intelligence artificielle Modélisation prédictive Recherche industrielle Revêtements organiques Simulation par ordinateur Index. décimale : 667.9 Revêtements et enduits Résumé : In the era of big data and digitalization, applying AI in product development is becoming essential for manufactures to stay competitive in their industry. Gone are the days where a limited group of domain experts plan and execute design of experiments (DOE) until a set of target properties are achieved. R&D teams across many industries are transforming their workflows by embracing AI initiatives to intelligently glean information from their historical, experimental, and product databases. AI models built on past data can be used to reduce experimentation through simulation and achieve optimal properties much faster using numerical optimization. In this article, a high-performance coating dataset will be used along with ProSensus’ FormuSense software. The article will examine the typical steps to effectively utilize R&D datasets including : 1. Data preparation to ensure that the dataset is appropriate for model building. Common pitfalls such as missing data, insufficient variation, and data anomalies are investigated and resolved. 2. Model building using multivariate analysis and its intuitive plots that help subject matter experts interpret their dataset highlighting key correlations and trade-offs. 3. Simulation using the model to predict the outcome of potential experiments without running the actual physical experiment. 4. Constrained numerical optimization to calculate the ideal formulation and processing conditions required to achieve a targeted quality or set of qualities. Note de contenu : - Predictive modeling : PLS for product development - Constrained optimization - Coatings case study : Assemble dataset - Mixture properties - Build & interpret PLS model - Simulate new experiments - Predicted quality - Model validity - Cost - Opitmmization - Table 1 : Model validity metrics and formulation cost - Table 2 : Ingredients used per class En ligne : https://drive.google.com/file/d/12cX85i3IxmOIIQ0uBD58rEdYqkTmiOkV/view?usp=drive [...] Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=41093 [article]

Exemplaires

Code-barres	Cote	Support	Localisation	Section	Disponibilité
aucun exemplaire

---

1 (1 - 4 / 4)