Author:
Jiang Zhilin,Liang Yi,Su Zihua,Chen Aonan,Sun Jianping
Abstract
The bamboo–wood composite container floor (BWCCF) has been wildly utilized in transportation in recent years. However, most of the common approaches of mechanics detection are conducted in a time-consuming and resource wasting way. Therefore, this paper aims to provide a frugal and highly efficient method to predict the short-span shear stress, the modulus of rupture (MOR) and the modulus of elasticity (MOE) of the BWCCF. Artificial neural network (ANN) models were developed and support vector machine (SVM) models were constructed for comparative study by taking the characteristic parameters of image processing as input and the mechanical properties as output. The results show that the SVM models can output better values than the ANN models. In a prediction of the three mechanical properties by SVMs, the correlation coefficients (R) were determined as 0.899, 0.926, and 0.949, and the mean absolute percentage errors (MAPE) were obtained, 6.983%, 5.873%, and 4.474%, respectively. The performance measures show the strong generalization of the SVM models. The discoveries in this work provide new perspectives on the study of mechanical properties of the BWCCF combining machine learning and image processing.
Funder
National Natural Science Foundation of China
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献