1 June 2019 in Ocean Engineering
4 May 2010 in Neural Computing and Applications
1 December 2006 in Proceedings of the Institution of Mechanical Engineers, Part A: Journal of Power and Energy
The flow in damping orifices when using water as the working media is of high Reynolds number and cavitation is inevitable. In this article, experimental studies are made on the flow and cavitation characteristics of water hydraulic orifices and the coefficient formulae in previous documents are testified with the Reynolds number ranging from 104 to 105. All the orifices are made of transparent materials, so the flow and the occurrence process of the cavitation can be observed with the naked eye. The experiments for each orifice are carried out under the two cases with and without backpressure, respectively. Experimental results show that the flow coefficient with backpressure is larger than the case without it. The larger the aspect ratio, the less the flow characteristics are influenced by backpressure. The cavitation first occurs at the inlet of orifices and then shifts to the outlet gradually. When there is cavitation happening at the outlet, flow saturation emerges simultaneously.
1 January 2021 in Computational Intelligence and Neuroscience
As a new type of artificial neural network model, HTM has become the focus of current research and application. The sparse distributed representation is the basis of the HTM model, but the existing spatial pool learning algorithms have high training time overhead and may cause the spatial pool to become unstable. To overcome these disadvantages, we propose a fast spatial pool learning algorithm of HTM based on minicolumn’s nomination, where the minicolumns are selected according to the load‐carrying capacity and the synapses are adjusted using compressed encoding. We have implemented the prototype of the algorithm and carried out experiments on three datasets. It is verified that the training time overhead of the proposed algorithm is almost unaffected by the encoding length, and the spatial pool becomes stable after fewer iterations of training. Moreover, the training of the new input does not affect the already trained results.