Effect of Cyclic Ice Plug Deformation on Microstructure and Mechanical Behaviors of Nuclear-Grade Low-Carbon Tubular Steel.

This study subjected nuclear-grade 20# pipeline steel to cyclic freeze-thaw ice plugging tests, simulating the plastic deformation experienced by pipes during ice plug removal procedures. Subsequently, the dislocation morphology and mechanical properties of the specimens post cyclic ice plugging were examined. The cyclic ice plugging process led to an increase in the dislocation density within the specimens. After 20 and 40 cycles of ice plugging, the internal dislocation structures evolved from individual dislocation lines and dislocation tangles to high-density dislocation walls and dislocation cells. These high-density dislocation walls and cells hindered dislocation motion, giving rise to strain hardening phenomena, thereby resulting in increased strength and hardness of the specimens with an increasing number of ice plugging cycles. In addition, a large stress field was generated around the dislocation buildup, which reduced the pipe material's plastic toughness. The findings elucidate the effects of cyclic ice plugging on the microstructure and properties of nuclear-grade 20# pipeline steel, aiming to provide a theoretical basis for the safe and stable application of ice plugging technology in nuclear piping systems.

Deep neural learning based protein function prediction.

It is vital for the annotation of uncharacterized proteins by protein function prediction. At present, Deep Neural Network based protein function prediction is mainly carried out for dataset of small scale proteins or Gene Ontology, and usually explore the relationships between single protein feature and function tags. The practical methods for large-scale multi-features protein prediction still need to be studied in depth. This paper proposes a DNN based protein function prediction approach IGP-DNN. This method uses Grasshopper Optimization Algorithm (GOA) and Intuitionistic Fuzzy c-Means clustering (IFCM) based protein function modules extracting algorithm to extract the features of protein modules, utilizing Kernel Principal Component Analysis (KPCA) method to reduce the dimensionality of the protein attribute information, and integrating module features and attribute features. Inputting integrated data into DNN through multiple hidden layers to classify proteins and predict protein functions. In the experiments, the F-measure value of IGP-DNN on the DIP dataset reaches 0.4436, which shows better performance.