journal article·2022-03

Prediction and influence of the mass proportion of trichromatic colourants and acrylic substrate on the optical and thermal performance of external wall coatings: An artificial neural network approach

Siru Qian, Yuequan Deng, Xiaoxia Li, Zhenghao Jin, Enshen Long

Publisher page

Abstract

Colourants are the main components for the colour control of acrylic coatings for the external walls of buildings. Since the different mass proportions of cyan, magenta, and yellow colourants, the colour of the coating changes after mixing, which also affects the optical property and thermal performance of the coating. In this paper, an artificial neural network model is established, the BP algorithm is used for calculation, and the model is trained and verified by making and testing experimental samples to accurately predict the solar reflectivity by the mass proportions of trichromatic colourants and acrylic coating substrate. The mean square error is 0.0027. Meanwhile, the influence weights of the mass proportions of cyan, magenta, and yellow colourants and the acrylic coating substrate on the solar reflectivity are calculated by the model, which are 0.2863, 0.2209, and 0.4928, respectively. The increase in cyan colourant has a greater influence on the decrease in reflectivity of the blended coating. The outer surfaces of 11 samples were tested outdoors. Compared with the original solution of the acrylic coating, the maximum temperature difference of the mixed coating reached 16.03 °C. The highest temperature of the coating with the highest proportion of cyan colourant and the acrylic substrate is 10.61 °C higher than that of the coating with the lowest proportion.
Source: expertdata · Quality: candidate unverified · Source record ↗

Research context

OpenAlex topics: Urban Heat Island Mitigation · Building Energy and Comfort Optimization · Thermal Radiation and Cooling Technologies

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (31)

Show source-provided references
1. Molecular design and copolymerization to enhance the anti-corrosion performance of waterborne acrylic coatings10.1016/j.porgcoat.2021.106140 ↗
2. A systematic investigation of the factors affecting the optical properties of near infrared transmitting cool non-white coatings10.1016/j.solmat.2014.03.019 ↗
3. 2020
4. Xue · 2003
5. Kubelka-Munk double constant theory of digital rotor spun color blended yarn10.1016/j.dyepig.2019.02.008 ↗
6. Influence of weight ratio of black colorant to white paint on light reflectivity of coated surface
7. Pigmented glazed ceramic roof tiles in Brazil: thermal and optical properties related to solar reflectance index10.1016/j.solener.2017.10.076 ↗
8. Artificial intelligence in the colour and textile industry
9. Spectrophotometric prediction of pre-colored fiber blends with a hybrid model based on artificial neural network and Stearns–Noechel mode10.1177/0040517516629145 ↗
10. Modeling of property prediction from multicomponent analytical data using different neural networks10.1021/ac00109a039 ↗
11. A study on the application of an artificial neural algorithm in the color matching of Taiwanese cultural and creative commodities10.1002/col.21899 ↗
12. A Munsell colour-based approach for soil classification using fuzzy logic and artificial neural networks10.1016/j.fss.2019.11.002 ↗
13. Prediction of the spectrophotometric response of a carded fiber composed by different kinds of coloured raw materials: an artificial neural network-based approach10.1002/col.20623 ↗
14. Non-destructive measurement of internal browning in mangoes using visible and near-infrared spectroscopy supported by artificial neural network analysis10.1016/j.postharvbio.2020.111206 ↗
15. Artificial neural networks for colour prediction in leather dyeing on the basis of a tristimulus system10.1111/cote.12123 ↗
16. Long · 2009
17. Theoretical and practical aspects of selected fiber-blend color-formulation functions10.1002/col.5080090406 ↗
18. Formulation of blends of precolored nylon fiber10.1002/col.5080080210 ↗
19. Colouring of opaque ceramic glaze with zircon pigments: formulation with simplified Kubelka–Munk model10.1016/j.jeurceramsoc.2010.11.039 ↗
20. The beer–lambert law10.1021/ed039p333 ↗
21. Domain adaptation for regression under BeerLambert's law10.1016/j.knosys.2020.106447 ↗
22. A novel approach to using neural networks to predict the colour of fibre blends10.1111/cote.12220 ↗
23. Prediction of the color and of the color solidity of a jigger-dyed cellulose-based fabric: a cascade neural network approach10.1177/0040517510365952 ↗
24. Selection of training samples for model updating using neural networks10.1006/jsvi.2001.3915 ↗
25. Xiaojun · 2007 · 548
26. A strategy to apply machine learning to small datasets in materials science10.1038/s41524-018-0081-z ↗
27. 2014
28. Cooling the cities – a review of reflective and green roof mitigation technologies to fight heat island and improve comfort in urban environments10.1016/j.solener.2012.07.003 ↗
29. Determination of the weight of evaluation indexes with artificial neural network method
30. Consideration of cooling loss process of the emitter for radiative cooling10.1063/1.5132358 ↗
31. Radiative cooling: a review of fundamentals, materials, applications, and prospects10.1016/j.apenergy.2018.12.018 ↗