A method of predicting the onset of wrinkling in the Yoshida Buckling Test, devised to simulate the wrinkling behavior in press-forming of sheet metal, has been developed in the present work by using an artificial neural network. The influence of different network architectures, learning parameters, and material coefficients has been investigated. The neural network was trained using data obtained by finite element analysis. The effectiveness of a neural network as a tool for predicting wrinkling limits in sheet metal-forming is examined. It is found that the trained neural network is capable of covering a wide range of material properties and its prediction of nominal strain at the onset of wrinkling is in reasonable agreement with the analytical results.
The vane shear test (VST) is comprehensively analyzed by means of empirical method, which on soft ground of one offshore foundation engineering project in Jiangsu province of China. The methods of judgment of soil stress history are summarized. Based on the shear strength of soft clay, consolidation state of the soft clay is obtained. The conclusion shows that it belongs to slight over-consolidation state. In the meantime, the two evaluation methods are comparatively analyzed. In the depth more than 5 m, the curves of over consolidation ratio (OCR) of two methods show a good consistency. The methods and applications can provide useful reference for engineers.
The rock mass with polycrystalline aggregates is common geomaterial in civil and architectural engineering as well as hydraulic and hydro-power engineering. For this kind of geometerials, the study on the joint deformation parameters Kn and Ks and the calculation method are not enough so far. Focusing on the rock mechanics and engineering problems of columnar jointed rock mass related to Baihetan hydropower project, analytical models and numerical method based on 3DEC are employed to study the mechanical parameters. The joint deformation parameters Kn and Ks are back analysis using GRNN and the field data of load-bearing plate tests. The application shows that the calculation results are in good accordance with in-situ test results.
Characterization of the shear wave velocity of soils is an integral component of various seismic analysis, including site classification, hazard analysis, site response analysis, and soil-structure interaction. Shear wave velocity at offshore sites of the coastal regions can be measured by the suspension logging method according to the economic applicability. The study presents some methods for estimating the shear wave velocity profiles in the absence of site-specific shear wave velocity data. By applying generalized regression neural network (GRNN) for the estimation of in-situ shear wave velocity, it shows good performances. Therefore, this estimation method is worthy of being recommended in the later engineering practice.
The mechanical behavior of group piles under lateral load is a very complex process of pile-soil interaction. Due to the group effect, the lateral capacity of individual piles can not be fully developed. Deduction factors are applied to the lateral soil reaction, and then lateral analysis is performed for individual piles. After p-y curve for each pile is constructed, the soil pressure of group piles is the sum of soil pressure of single pile at the same deflection under one pile cap. The mechanical different behaviors of the front piles and the back piles are analyzed and compared based on a practical engineering.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.