Implementation of a mechanics-based system for estimating the strength of a board

The most accurate way of determining the strength of lumber involves destructive testing. An intelligent mechanics-based lumber grading system was developed to provide a better non-destructive estimation of the strength of a board. This system processed the X-ray-extracted geometric features (of 60 boards that eventually underwent destructive strength testing) by using Finite Element Methods (FEM) to generate associated stress fields. The stress fields were then fed to a feature-extracting-processor which produced several strength predicting features. The best strength predicting features are determined by calculating the coefficient of determination (r²) between the predicted and the actual strength of the board. Twenty six strength predicting features were generated by the processor. The estimated strength from each feature and from the combination of several features, was calculated and compared with the actual strength of the board. A coefficient of determination (r²) of 0.43 was achieved by using the longitudinal (to the grain angle) maximum stress concentration (MSC).