How injection molding experts collaborate with AI / Jonathan Lambers in PLASTICS INSIGHTS, Vol. 113, N° 9 (2023)  

[article]  inPLASTICS INSIGHTS > Vol. 113, N° 9 (2023) . - p. 55-57 Titre : How injection molding experts collaborate with AI : Combining expert knowledge and process data for monitoring and controlling the IM process Type de document : texte imprimé Auteurs : Jonathan Lambers, Auteur ; Jakob Schüder, Auteur ; Giovanni Schober, Auteur Année de publication : 2023 Article en page(s) : p. 55-57 Langues : Anglais (eng) Catégories : Assurance qualité Industrie 4.0 Le concept d’Industrie 4.0 correspond à une nouvelle façon d’organiser les moyens de production : l’objectif est la mise en place d’usines dites "intelligentes" ("smart factories") capables d’une plus grande adaptabilité dans la production et d’une allocation plus efficace des ressources, ouvrant ainsi la voie à une nouvelle révolution industrielle. Ses bases technologiques sont l'Internet des objets et les systèmes cyber-physiques. Logiciels Matières plastiques -- Moulage par injection Numérisation Réseau bayésien Index. décimale : 668.4 Plastiques, vinyles Résumé : The German Plastics Center SKZ and Fraunhofer IPA are collaboratively developing a process monitoring and control system for the injection molding (IM) process based on Bayesian Networks. In their research project “ProBayes”, the researchers build a fully networked injection molding cell in the SKZ lab demonstrating a system in live operation that detects deviations in product quality, identifies the most likely cause and issues specific recommendations for action to the machine operator. Note de contenu : - Connecting machine, periphery, and quality measurement systems - Generation of training data and extension by simulations - Validating the bayesian network in production - Fig. 1 : Software architecture of the injection molding cell. MQTT is a communication protocol for machine-to-machine communication - Fig. 2 : Link to dataset published on EUDAT platform - Fig. 3 : Structure of the Bayesian Network for the part weight quality characteristic - Fig. 4 : "Human-in-the-Loop" : Schematic of the demonstrator’s architecture. The data from the injection molding machine and peripheral devices are aggregated by the middleware (Connectware) and transferred to the Bayesian Network for inference En ligne : https://drive.google.com/file/d/1V4o-uKCt6c3Z4De0raWmuQU-zTmmG48K/view?usp=drive [...] Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=40753 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
24326	-	Périodique	Bibliothèque principale	Documentaires	Disponible

Texture-based characterization of subskin features by specified laser speckle effects at λ = 650 nm region for more accurate parametric 'skin age' modelling / Ahmet B. Orun in INTERNATIONAL JOURNAL OF COSMETIC SCIENCE, Vol. 39, N° 3 (06/2017)

[article]  inINTERNATIONAL JOURNAL OF COSMETIC SCIENCE > Vol. 39, N° 3 (06/2017) . - p. 320-326 Titre : Texture-based characterization of subskin features by specified laser speckle effects at λ = 650 nm region for more accurate parametric 'skin age' modelling Type de document : texte imprimé Auteurs : Ahmet B. Orun, Auteur ; H. Seker, Auteur ; V. Uslan, Auteur ; E. Goodyer, Auteur ; G. Smith, Auteur Année de publication : 2017 Article en page(s) : p. 320-326 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Lasers à solide Peau -- analyse Peau -- Texture Perception de l'âge Réseau bayésien Index. décimale : 668.5 Parfums et cosmétiques Résumé : OBJECTIF : The textural structure of ‘skin age’-related subskin components enables us to identify and analyse their unique characteristics, thus making substantial progress towards establishing an accurate skin age model. METHODS : This is achieved by a two-stage process. First by the application of textural analysis using laser speckle imaging, which is sensitive to textural effects within the λ = 650 nm spectral band region. In the second stage, a Bayesian inference method is used to select attributes from which a predictive model is built. RESULTS : This technique enables us to contrast different skin age models, such as the laser speckle effect against the more widely used normal light (LED) imaging method, whereby it is shown that our laser speckle-based technique yields better results. CONCLUSION : The method introduced here is non-invasive, low cost and capable of operating in real time; having the potential to compete against high-cost instrumentation such as confocal microscopy or similar imaging devices used for skin age identification purposes. Note de contenu : - MATERIALS AND METHODS : Data sets for laser-based and normal light imaging - System configuration - Laser speckle imaging - Texture analysis method - Bayresian networks - RESULTS AND DISCUSSION : Optimization of light type and texture measure - Bayesian classification results - Results of laser speckle image-based configuration DOI : 10.1111/ics.12379 Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=28630 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
18959	-	Périodique	Bibliothèque principale	Documentaires	Disponible

---

1 (1 - 2 / 2)