Fatigue database of additively manufactured alloys

Auto-generating a database on the fabrication details of perovskite solar devices

The rapid development of perovskite solar devices has led to a rising number of publications over the past decade. As a result, a project aiming to compile all published device data was initiated in 2022. However, with its method of manual data collection, one of the project's hurdles is encouraging the participation of the perovskite community to spend time and effort in inputting new device data. To ensure the project's sustainability, adequate participation is necessary but is challenging to achieve. In response to this, we propose the utilization of natural language processing algorithms to extract various attributes of perovskite solar devices from journal articles. When data collection is performed by programs instead of humans, the lack of community participation can be overcome. For each device, the identifying device information, intrinsic device data, extrinsic cell definition, and the details of the fabrication procedure were extracted. A total of 30 attributes from 3164 journal articles were compiled, with an average accuracy of 0.899. The dataset and source code are made publicly available.

Effects of Process Parameters and Process Defects on the Flexural Fatigue Life of Ti-6Al-4V Fabricated by Laser Powder Bed Fusion

The fatigue performance of laser powder bed fusion-fabricated Ti-6Al-4V alloy was investigated using four-point bending testing. Specifically, the effects of keyhole and lack-of-fusion porosities along with various surface roughness parameters, were evaluated in the context of pore circularity and size using 2D optical metallography. Surface roughness of Sa = 15 to 7 microns was examined by SEM, and the corresponding fatigue performance was found to vary by 102 cycles to failure. The S-N curves for the various defects were also correlated with process window examination in laser beam power-velocity (P-V) space. Basquin's stress-life relation was well fitted to the experimental S-N curves for various process parameters except keyhole porosity, indicating reduced importance for LPBF-fabricated Ti-6Al-4V alloy components.

Prediction method of longitudinal surface settlement caused by double shield tunnelling based on deep learning

The deep learning method faces the challenges of small sample data and high dimensional shield operational parameters in predicting the longitudinal surface settlement caused by shield excavation. In this study, various optimization algorithms were compared, and the slime mould algorithm (SMA) was optimally chosen to optimize the hyperparameters of random forest (RF), and SMA-RF was used for dimensionality reduction and feature contribution analysis. A double-input deep neural network (D-DNN) framework was proposed for the prediction of surface settlement, which considers the influence of twin tunnels and effectively increases the high-fidelity data in the database. The results show that SMA performs best among various optimization algorithms; employing features that have a cumulative contribution value exceeding 90% as input can result in high prediction accuracy; there is significant uncertainty in the feature contribution analysis for small sample data; the reduced shield running parameters show a strong nonlinear relationship with surface settlement; compared with S-DNN, D-DNN takes into account the excavation of twin tunnels and expands the database capacity by more than 1.5 times, with an average increase of 27.85% in the R2 and an average decrease of 53.2% in the MAE.

Fatigue database of complex metallic alloys

The past few decades have witnessed rapid progresses in the research and development of complex metallic alloys such as metallic glasses and multi-principal element alloys, which offer new solutions to tackle engineering problems of materials such as the strength-toughness conflict and deployment in harsh environments and/or for long-term service. A fatigue database (FatigueData-CMA2022) is compiled from the literature by the end of 2022. Data for both metallic glasses and multi-principal element alloys are included and analyzed for their statistics and patterns. Automatic extraction and manual examination are combined in the workflow to improve the efficiency of processing, the quality of published data, and the reusability. The database contains 272 fatigue datasets of S-N (the stress-life relation), ε-N (the strain-life relation), and da/dN-ΔK (the relation between the fatigue crack growth rate and the stress intensity factor range) data, together with the information of materials, processing and testing conditions, and mechanical properties. The database and scripts are released in open repositories, which are designed in formats that can be continuously expanded and updated.