Finite element dataset and Artificial Neural Networks algorithms to predict the mechanical properties of innovative CLT

This folder includes the data collected from the finite element simulations of the innovative CLT to compute its mechanical properties, the error of the closed-form solutions predicting the bending stiffness in the minor direction D22, the variation of the distance between the Reissner Mindlin and Bending Gradient theory in terms of spacing between lateral lamellas, the hyperparameters tuning of several Artificial Neural Networks algorithms with or without prior knowledge, the ML evaluations, the saved artificial neural network algorithms to predict each mechanical property of innovative CLT, and the ML application to use it.

本文件夹包含以下数据：针对创新正交胶合木（CLT, Cross-Laminated Timber）开展有限元模拟所采集的、用于计算其力学性能的数据集；预测其弱轴方向D22弯曲刚度的闭式解误差；赖斯纳-明德林（Reissner-Mindlin）理论与弯曲梯度（Bending Gradient）理论之间的差值随横向板条间距变化的规律；多种带或不带先验知识的人工神经网络（Artificial Neural Network, ANN）算法的超参数调优结果；机器学习（Machine Learning, ML）评估结果；用于预测创新正交胶合木各项力学性能的已保存人工神经网络模型；以及基于该模型的机器学习应用程序。