Search

Two previously unknown species of Rhinogobius have been discovered in the streams of the Upper Youshui River, within the Yuan River Basin, Xiushan County, Chongqing, China. These new species are named as Rhinogobius sudoccidentalis and Rhinogobius lithopolychroma. Phylogenetic analysis based on mitochondrial genomes revealed that R. sudoccidentalis is genetically closest to R. reticulatus, while R. lithopolychroma shares the greatest genetic similarity with R. leavelli. Morphological distinctions allow for the clear differentiation of these species. Rhinogobius sudoccidentalis sp. nov. is characterized by having VI–VII rays in the first dorsal fin and I, 8–9 rays in the second dorsal fin. The longitudinal scale series typically consists of 22–24 scales, while the transverse scale series comprises 7–8 scales. Notably, the predorsal scale series is absent and the total vertebrae count is 12+17=29. Rhinogobius lithopolychroma sp. nov. can be distinguished from other species by the presence of 13–15 rays on the pectoral fin. Its longitudinal scale series ranges from 30 to 33 scales, with no scales in the predorsal area. The total vertebral count is 30, with 12 precaudal and 18 caudal vertebrae. The head and body of this species are light gray with irregular orange markings on the cheeks and opercle. Through morphological and molecular analyses, it has been confirmed that R. lithopolychroma and R. sudoccidentalis represent novel species within the Rhinogobius genus. [ABSTRACT FROM AUTHOR]

Lamb wave-based damage quantification in large-scale composites has always been one of the concerning and intractable problems in aircraft structural health monitoring. In recent years, machine learning (ML) algorithms have been utilized to deeply explore the damage feature of Lamb wave signals, which aims to enhance the precision and accuracy of damage quantification. However, multi-damage quantification becomes one of the bottleneck problems because ML algorithms critically depend on the dataset. In this paper, a prioritizing selection and orderly permutation method is proposed to construct multi-damage dataset based on Born approximation principle, which shows the interaction between wave signals under multi- and single-damage conditions. Based on the multi-damage dataset, a multi-task deep learning algorithm is introduced to identify multiple damage, including the damage number, location, and size, in composite laminates. In the algorithm, a multi-branch 1D-convolution neural network framework, which includes a trunk network and branch networks is established to explore the damage features in Lamb wave scattering signals. Compared with single-task models, it has the ability to learn shared features for multiple tasks, effectively boosting the task results. The results show that the proposed multi-task learning (MTL) method saves 23.03% training time compared with the single-task learning method. In the task of quantifying multiple damage of composite laminate, the results of MTL are good for both the constructed test set and the measured test set, especially in the quantification of damage size, which shows the feasibility and reliability of this method. [ABSTRACT FROM AUTHOR]