A predictive modelling of nanocomposite coating microhardness based on extremely randomised trees. (2019)

• Record Type: Journal Article
• Authors: Guo, Hai; Zhao, Jingying; Li, Xiaoniu
• Is Part Of: International journal of material & product technology. Volume 58:Number 1(2019)
• Page Start: 1
• Page End: 15
• Publication Date: 2019
• Subjects: nanocomposite coatings -- prediction model -- extremely randomised trees -- ERT -- ensemble learning; Manufacturing processes -- Periodicals; Materials -- Testing -- Periodicals; 620.11
• Languages: English
• ISSNs: 0268-1900

Abstract

Nanocomposite coating is a coating made of particles whose sizes are of nanoscale. The microhardness of the coating is an importance parameter. Currently, experimental method is mainly adopted in the coating's microhardness and performance research, with high research cost and long time period. In this paper, the content of the nano-particles in the plating liquid, current density, duty ratio, addition of additives and ultrasonic power are set as inputs; the micro hardness of the nanocomposite coating is set as output. Extremely randomised trees (ERT) are used to establish a strong prediction model. The prediction performance is the ERT model is superior to that of the single models such as linear regression, back-propagation neural network and radial basis function neural network, etc. and other ensemble learning methods. ERT model can be used for predicting the microhardness of nanocomposite coating, providing an efficient and highly reliable method for new material performance prediction.