Assessment of mechanical properties based on the changes of chromatic values in heat treatment wood.

• Changes of chromatic values in heat treatment wood are systematically discussed. • Variation of modulus of elasticity and modulus of rupture with heat treatment temperature are explored. • Artificial neural networks are employed to predict mechanical properties based on the chromatic values. In this study, the modulus of elasticity (MOE) and modulus of rupture (MOR) of heat treatment (HT) radiata pine wood were assessed by artificial neural network (ANN) models based on the changes of chromatic values. In the established ANN models, the chromatic values, i.e. L *, a * and b * conjunction with HT temperature were as input variables, the MOE and MOR as output parameters. According to the results, the values of L *, a * and b * had a good consistency with HT intensity. The MOE changed with HT temperature in a fluctuating tendency, whereas the MOR generally deteriorated with increasing HT temperature. As for the established ANN models, the predicted values were in good agreement with the measured ones, the determination coefficient of the prediction model for MOE and MOR were 0.904 and 0.783, respectively. [ABSTRACT FROM AUTHOR]