The foundation pit engineering is a work with large amount of use and high difficulty coefficient. It necessary to ensure the deformation soil in control range safety whole structure pit. In this paper, support project Shijiazhuang City, Hebei Province taken as research object, numerical analysis method used simulate pile-anchor First Section fourth section horizontal displacement value deep se...

By analyzing the monitoring data of excavation foundation, maximum lateral displacement depth and top vertical retaining wall, column are studied. Research indicates that 3rd power polynomial curve can better fit change law deformation wall at each point；the fourth support demolition has great influence on wall. The third layer greatly increased After second is removed, to negative. gradually d...

Relying on a deep foundation pit project in Beijing, using FLAC3D three-dimensional finite-difference software simulation combined with displacement monitoring data verification method, the excavation and three-pile two-anchor rod support system anhydrous sand pebble stratum are systematically analyzed, summed up variation law of formation stress, internal force soil nail, axial bolt, stress pi...

The foundation pit of Yamansu hydropower station has an average depth 70 m and been excavated with five-level slopes. Lowering groundwater level is important in excavation. In this study, drainage pumping were conducted dewatering. Pumping tests performed to reverse hydraulic parameters calibrate numerical models. Numerical simulations evaluate the dewatering scheme. first stage, powerhouse tai...

Privacy preserving multi-party machine learning approaches enable multiple parties to train a machine learning model from aggregate data while ensuring the privacy of their individual datasets is preserved. In this paper, we propose a privacy preserving multi-party machine learning approach based on homomorphic encryption where the machine learning algorithm of choice is deep neural networks. W...

We present a method for explaining the image classification predictions of deep convolution neural networks, by highlighting the pixels in the image which influence the final class prediction. Our method requires the identification of a heuristic method to select parameters hypothesized to be most relevant in this prediction, and here we use Kullback-Leibler divergence to provide this focus. Ov...

Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently on sparse networks. Several methods exist for pruning connections of a neural network after it was trained without connectivity constraints. We present an algorithm, DEEP R, that enables us to train...