A machine learning study on the fatigue crack path of short crack on an α titanium alloy.

In the present study, a physics-informed neural network model based on Bayesian hyperparameter optimization is proposed for the prediction of short crack growth paths. A large number of cyclic loadings at a lower amplitude were applied to an α titanium sample by an ultrasonic fatigue machine to ensure a sufficient amount of data for machine learning. The grain size, grain orientation and grain boundary direction on the path, as well as crack growth direction, were selected as feature data for training the prediction model. The optimizations of the size ratio and the angle operation were conducted to compare different data processing methods, respectively. After evaluation, eventually, a model for predicting crack growth path is obtained with a reliable performance of 10% tolerance on the path angle at each grain boundary. And the prediction effect of the proposed model is better than that of some classic machine learning models and slip trace analysis. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.

Effects of Thermal Treatment on the Mechanical Properties of Bamboo Fiber Bundles.

Bamboo is known as a typical kind of functional gradient natural composite. In this paper, fiber bundles were extracted manually from various parts of the stem in the radial direction, namely the outer, middle, and inner parts. After heat treatment, the mechanical properties of the fiber bundles were studied, including the tensile strength, elastic modulus, and fracture modes. The micromechanical properties of the fiber cell walls were also analyzed. The results showed that the mean tensile strength of the bamboo fiber bundles decreased from 423.29 to 191.61 MPa and the modulus of elasticity increased from 21.29 GPa to 27.43 GPa with the increase in temperature. The elastic modulus and hardness of the fiber cell walls showed a positive correlation with temperature, with the modulus of elasticity and the hardness increasing from 15.96 to 18.70 GPa and 0.36 to 0.47 GPa, respectively. From the outside to the inside of the bamboo stems, the tensile strength and elastic modulus showed a slight decrease. The fracture behavior of the fiber bundles near the outside approximates ductile fracture, while that of the bundles near to the inside tend to be a brittle fracture. The fracture surfaces of the bamboo bundles and the single fibers became smoother after heat treatment. The results show that bamboo fiber bundles distributed near the outside are most suitable for industrial development under heat treatment at 180 °C. Therefore, this study can provide a reasonable scientific basis for the selective utilization, functional optimization, and bionic utilization of bamboo materials, which has very important theoretical and practical significance.