校准
人工智能
计算机科学
拉伤
极限抗拉强度
校准曲线
拉伸应变
特征(语言学)
线性回归
变形(气象学)
计算机视觉
机器学习
材料科学
数学
复合材料
内科学
哲学
检出限
统计
医学
语言学
作者
Lucas Daniel Chiba de Castro,Leonardo F. S. Scabini,Lucas Correia Ribas,Odemir Martinez Bruno,Osvaldo N. Oliveira
标识
DOI:10.1016/j.eswa.2022.118792
摘要
A computer vision (CV) system is proposed for real-time prediction of strain by monitoring the color-changing feature of mechanochromic sensors. Pictures of the sensors subjected to calibration tensile tests were treated with standard image processing methods and analyzed using supervised machine learning (ML) algorithms. Visual strain sensing was demonstrated by linear regression models capable of learning a relation between the applied strain and the reflected structural color. The ElasticNet regression model provided the highest accuracy in the strain prediction task, with a remarkable performance in monitoring real-time strain variation of sensors during a tensile-relaxion cycle. Using calibration curves, the predicted strain can also be employed for estimating the tensile force applied on the mechanochromic sensors. Taken together these results point to potential intelligent systems for noninvasive in-situ visual monitoring of deformations and tensions.
科研通智能强力驱动
Strongly Powered by AbleSci AI