A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine learning-based prediction of surface checks and bending properties in weathered thermally modified timber
Highlights Surface checking and mechanical properties of weathered Thermally modified timber (TMT) were predicted. Board’s dynamic stiffness is the most crucial predictor variable. Initial moisture content is an important predictor of TMT’s bending strength. Models failed to accurately predict the degree of surface checking in weathered TMT. Decision tree and ANFIS outperform regression models when predicting TMT’s bending properties.
Abstract Machine learning (ML)-based models, decision tree and ANFIS, were used to predict the degree of surface checking and bending properties of 30-month weathered thermally modified timber. The results showed that the investigated initial board properties did not allow accurate predictions of surface checks. ML regression and clustering analysis confirmed important variables for accurate predictions of bending properties were dynamic stiffness, acoustic velocity, density and lowest local bending modulus. ML models performed better than conventional regression models used for timber grading, and a prediction accuracy of 80–90% for bending stiffness and 50–70% for bending strength could be achieved.
Machine learning-based prediction of surface checks and bending properties in weathered thermally modified timber
Highlights Surface checking and mechanical properties of weathered Thermally modified timber (TMT) were predicted. Board’s dynamic stiffness is the most crucial predictor variable. Initial moisture content is an important predictor of TMT’s bending strength. Models failed to accurately predict the degree of surface checking in weathered TMT. Decision tree and ANFIS outperform regression models when predicting TMT’s bending properties.
Abstract Machine learning (ML)-based models, decision tree and ANFIS, were used to predict the degree of surface checking and bending properties of 30-month weathered thermally modified timber. The results showed that the investigated initial board properties did not allow accurate predictions of surface checks. ML regression and clustering analysis confirmed important variables for accurate predictions of bending properties were dynamic stiffness, acoustic velocity, density and lowest local bending modulus. ML models performed better than conventional regression models used for timber grading, and a prediction accuracy of 80–90% for bending stiffness and 50–70% for bending strength could be achieved.
Machine learning-based prediction of surface checks and bending properties in weathered thermally modified timber
van Blokland, Joran (author) / Nasir, Vahid (author) / Cool, Julie (author) / Avramidis, Stavros (author) / Adamopoulos, Stergios (author)
2021-09-18
Article (Journal)
Electronic Resource
English
ANFIS , Adaptive neuro-fuzzy inference system , ANN , Artificial neural network , CI , Confidence interval , FIS , Fuzzy inference system , MC , Moisture content , ML , Machine learning , MLP , Multilayer perceptron , NN , Neural network , PLS , Partial least squares , RI , Relative importance , SD , Standard deviation , TM , Thermally modified , TMT , Thermally modified timber , Acoustic velocity , Adaptive neuro-fuzzy inference system (ANFIS) , Decision tree , Non-destructive testing , Norway spruce , Outdoor above-ground exposure , Timber grading , ThermoWood®
Are timber checks and splits serious
| Engineering Index Backfile | 1944
Bending Strength and Stiffness of Glulam Beams Made of Thermally Modified Beech Timber
| Springer Verlag | 2014