Calculation of coating consumption quota for ship painting : a CS-GBRT approach / Henan Bu in JOURNAL OF COATINGS TECHNOLOGY AND RESEARCH, Vol. 17, N° 6 (11/2020)  

[article]  inJOURNAL OF COATINGS TECHNOLOGY AND RESEARCH > Vol. 17, N° 6 (11/2020) . - p. 1597-1607 Titre : Calculation of coating consumption quota for ship painting : a CS-GBRT approach Type de document : texte imprimé Auteurs : Henan Bu, Auteur ; Xingyu Ji, Auteur ; Xin Yuan, Auteur ; Ziyan Han, Auteur ; Lei Li, Auteur ; Zhuwen Yan, Auteur Année de publication : 2020 Article en page(s) : p. 1597-1607 Note générale : Bibliogr. Langues : Américain (ame) Catégories : Bateaux -- Revêtements:Bateaux -- Peinture Calcul Peinture -- Consommation Prévision, Théorie de la Index. décimale : 667.9 Revêtements et enduits Résumé : This paper focuses on the prediction of the coating amount before the construction of ship painting, i.e., the calculation of coating consumption quota. At present, each shipyard uses a larger coating loss coefficient to calculate the coating consumption quota ; after the construction, there is often a lot of inventory left, which is not conducive to the scientific management of the ship coating process and the cost control of shipbuilding. Therefore, this paper proposes a coating consumption prediction method based on ensemble learning, using cosine similarity and gradient boosting regression tree hybrid algorithm (CS-GBRT) to calculate the coating loss coefficient under different working conditions. Cosine similarity is used to select similar data with less difference from the target to be predicted as the training set, and the loss function in GBRT is improved based on similarity weight to improve the prediction performance and calculation accuracy of GBRT. The coating data recorded by a shipyard from 2014 to 2019 are randomly selected to evaluate the prediction ability of the model established in the paper. The results show that when the proposed CS-GBRT algorithm is used to calculate the coating loss coefficient, the mean absolute error of training set and test set are both < 1.4, and the mean absolute error percentages are both < 4%. Compared with other research methods, the prediction accuracy is obviously improved, and the output feature importance is also consistent with the trend calculated by Spearman method, which proves the validity of the model again. Note de contenu : - GBRT IMPROVED BY SIMILARITY : Ensemble learning method - Gradient boosting regression tree (GBRT) - Similarity calculation - Algorithm flow - CONSTRUCTION OF COATING CONSUMPTION PREDICTION MODEL : Analysis of factors affecting coating consumption - Feature selection and data preprocessing - Feature coding and normalization - Feature importance analysis - PREDICTION RESULTS ANALYSIS AND MODELS COMPARISON DOI : https://doi.org/10.1007/s11998-020-00376-7 En ligne : https://link.springer.com/content/pdf/10.1007/s11998-020-00376-7.pdf Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=34963 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
22458	-	Périodique	Bibliothèque principale	Documentaires	Disponible

Effect mechanism of acidification and vulcanization on SBS-modified asphalt / Feng Zhang in INTERNATIONAL POLYMER PROCESSING, Vol. 37, N° 5 (2022)  

[article]  inINTERNATIONAL POLYMER PROCESSING > Vol. 37, N° 5 (2022) . - p. 559-567 Titre : Effect mechanism of acidification and vulcanization on SBS-modified asphalt Type de document : texte imprimé Auteurs : Feng Zhang, Auteur ; Lei Li, Auteur Année de publication : 2022 Article en page(s) : p. 559-567 Note générale : Bibliogr. Langues : Anglais (eng) Catégories : Analyse thermique Asphalte Caractérisation Chromatographie sur gel Copolymère styrène butadiène styrène Matériaux -- Propriétés physiques Matériaux bitumineux Morphologie (matériaux) Polyphosphorique, Acide Rhéologie Soufre Vieillissement Index. décimale : 668.4 Plastiques, vinyles Résumé : A styrene-butadiene-styrene (SBS) modified asphalt compound was prepared by the addition of polyphosphoric acid (PPA) and sulfur. The effect of PPA and sulfur on major physical properties, including toughness and tenacity, aging resistance, and storage stability was investigated. The structural characteristics of SBS-modified (SM) asphalt, SBS/PPA-modified (SPM) asphalt, and SBS/PPA/sulfur-modified (SPSM) asphalt were investigated using scanning electron microscopy (SEM), gel filtration chromatography (GPC), and thermal analysis. It has been found that acidification prompted the clustering of SBS particles and confined the swelling of SBS, making SPM asphalt more susceptible to aging. Vulcanization changed the morphological characteristics of SBS in asphalt, improved the compatibility between SBS and asphalt, and weakened the aging susceptibility. Therefore, it is reasonable to modify SM asphalt by using PPA and sulfur together. Note de contenu : - MATERIALS AND METHODS : Materials - Sample preparation - Morphological characterization - Physical properties - Aging of asphalt - Rheological properties - GPC - Thermal analysis - RESULTS AND DISCUSSION : Morphology - Physical properties - Rheological properties - GPC analysis - The experimental curve of a sam - Thermal analysis - Table 1 : Physical properties of base asphalt - Table 2 : Pore size and effective molecular weight range - Table 3 : Physical properties of SM, SPM, SPSM asphalts - Table 4 : Mn, Mw, Pd of SM, SPM, SPSM asphalts DOI : https://doi.org/10.1515/ipp-2022-4233 En ligne : https://drive.google.com/file/d/1QUvhoIlOPwABi5t62ihU1YUuOzT-PmB-/view?usp=share [...] Format de la ressource électronique : Pdf Permalink : https://e-campus.itech.fr/pmb/opac_css/index.php?lvl=notice_display&id=38330 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
23740	-	Périodique	Bibliothèque principale	Documentaires	Disponible

---

1 (1 - 2 / 2)