Deformation-Induced Strengthening Mechanism in a Newly Designed L-40 Tool Steel Manufactured by Laser Powder Bed Fusion

The microstructural and mechanical properties of a newly designed tool steel (L-40), specifically designed to be employed in the laser powder bed fusion (LPBF) technique, were examined. Melt pool boundaries with submicron dendritic structures and about 14% retained austenite phase were evident after printing. The grain orientation after high cooling rate solidification is mostly < 110 >  _α∥ building direction (BD). Then, the heat treatment converted the microstructure into a conventional martensitic phase, reduced the retained austenite to about 1.5%, and increased < 111 >  _α∥BD texture. The heat-treated sample exhibits higher tensile strength (1720 ± 14 MPa) compared to the as-printed sample (1540 ± 26 MPa) along the building direction, mainly due to hardening caused by a lower volume fraction of retained austenite phase and precipitation of carbides. As a consequence of the strength-to-ductility trade-off, the heat-treated sample showed lower elongation (10% ± 2%) than that of the as-printed sample (18% ± 2%). It was observed that transformation-induced plasticity (TRIP) occurs in both the as-printed and heat-treated samples during tensile testing, which dynamically transforms the retained austenite into martensite, leading to improved ductility. The minimum driving force to initiate the displacive phase transformation is about 6000 J/mol, which was achieved during tensile testing. The strength and ductility of LPBF-produced L-40 were compared with the other LPBF-produced tool steels in literature; the data indicate that heat-treated L-40 has an excellent combination of strength and ductility complemented with high printability.     

Deep Learning ResNet101 Deep Features of Portable Chest X-Ray Accurately Classify COVID-19 Lung Infection

This study is designed to develop Artificial Intelligence (AI) based analysis tool that could accurately detect COVID-19 lung infections based on portable chest x-rays (CXRs). The frontline physicians and radiologists suffer from grand challenges for COVID-19 pandemic due to the suboptimal image quality and the large volume of CXRs. In this study, AI-based analysis tools were developed that can precisely classify COVID-19 lung infection. Publicly available datasets of COVID-19 (N = 1525), non-COVID-19 normal (N = 1525), viral pneumonia (N = 1342) and bacterial pneumonia (N = 2521) from the Italian Society of Medical and Interventional Radiology (SIRM), Radiopaedia, The Cancer Imaging Archive (TCIA) and Kaggle repositories were taken. A multi-approach utilizing deep learning ResNet101 with and without hyperparameters optimization was employed. Additionally, the features extracted from the average pooling layer of ResNet101 were used as input to machine learning (ML) algorithms, which twice trained the learning algorithms. The ResNet101 with optimized parameters yielded improved performance to default parameters. The extracted features from ResNet101 are fed to the k-nearest neighbor (KNN) and support vector machine (SVM) yielded the highest 3-class classification performance of 99.86% and 99.46%, respectively. The results indicate that the proposed approach can be better utilized for improving the accuracy and diagnostic efficiency of CXRs. The proposed deep learning model has the potential to improve further the efficiency of the healthcare systems for proper diagnosis and prognosis of COVID-19 lung infection.     

Spinodal Decomposition of B2-phase and Formation of Cr-Rich Nano-precipitates in AlCoCrFeNi2.1 Eutectic High-Entropy Alloy

Herein, the occurrence of a B2-phase separation and formation of Cr-rich nano-precipitates during the solidification process of AlCoCrFeNi_2.1 eutectic high-entropy alloy is addressed. Toward this end, various advanced characterizations, including high-resolution transmission electron microscopy and atom probe tomography combined with thermodynamic calculations, are employed. The as-solidified microstructure is composed of face-centered cubic (FCC) dendrites and interdendritic regions consisting of a eutectic mixture of FCC and body-centered cubic (BCC) phases. The presence of uniformly distributed Cr-rich nano-precipitates is traced through the BCC B2 phase in the interdendritic area. Regarding the occurrence of upward diffusion and Gibbs free energy variation, the formation of Cr-rich nano-precipitates is attributed to the spinodal decomposition where the critical temperature of 800 °C is passed behind during the solidification process. The formation of dense dislocation array in the interdendritic region due to thermal stress induced during solidification is introduced as a pathway for diffusion of alloying elements in the course of cooling stage.