A Multi-Input Residual Network for Non-Destructive Prediction of Wood Mechanical Properties

Modulus of elasticity (MOE) and modulus of rupture (MOR) are crucial indicators for assessing the application value of wood. However, traditional physical testing methods for the mechanical properties of wood are typically destructive, costly, and time-consuming. To efficiently assess these properties, this study proposes a multi-input residual network (MIRN) model, which integrates microscopic images of wood with physical density data and leverages deep learning technology for rapid and accurate predictions. By using larger convolution kernels to enhance the receptive field, the model captures fine microstructural features in the images. Batch normalization layers were removed from the ResNet architecture to reduce the number of parameters and improve training stability. Shortcut connections were utilized to enable deeper network architectures and address the vanishing gradient problem. Two types of residual blocks, convolutional block and identity block, were defined based on input dimensional changes. The MIRN method, based on multi-input residual networks, is proposed for non-destructive testing of wood mechanical properties. The experimental results show that MIRN outperforms convolutional neural networks (CNNs) and ResNet-50 in predicting MOE and MOR, with an R2 of 0.95 for MOE and RMSE reduced to 46.88, as well as an R2 of 0.85 for MOR and an RMSE of 0.44. Thus, this method offers an efficient and cost-effective tool for wood processing and quality control.