Authors: Peiman Abbasi, Javad Ahadiyan
A dense jet stream is used in discharging of wastewater and concentrated currents into the acceptor water source. Wastewater is discharged through the medium of the jet causes mixture between the discharged and receptive fluid to reduce the destructive impact on the environment. Using neural networks and artificial BP and CP intelligence algorithms, this study aimed at investigating the influence of a dense jet fluid density which was extended by means of trajectory curve. In this regard, the hydraulic jet data, environmental parameters, and geometric parameters which affect submerged circular jet stream, was collected and introduced to neural network. In that model, data were gathered from a physical model, various tests on geometry and different viscous flow. The performed physical tests consisting five variables in the environmental, geometric, and hydraulic parameters. Also, presented data to the network, was the coordinates of the (x,y) and was the curves trajectory. The employed data were obtained from 215 Experiments, which consisted of 1995 coordinate data for trajectory curve. Network training data with 60% of them, test with 20% and data validation with 20% of the data were performed. Artificial neural network algorithms were used from propagation of error (BPNN) and (CPNN) types with different structures. In this respect, neural networks in terms of structure and function of the transfer function test for the up and down trajectory and suitable network is selected, Generally 4 inputs for the neural network were defined. The interesting results were one hidden layer with 7 neurons and two layers. The network structure of the compound (1-7-4) was calculated. The RMSE error for the test network with 20 % of the data in this case was 0/1425 and R2 was calculated 0/8982. Simulation results indicated that the network is able to estimate trajectory submerged jet which is in congruent with physical model results.
Comments: 17 Pages.
Download: PDF
[v1] 2014-05-08 03:46:06
Unique-IP document downloads: 98 times
Vixra.org is a pre-print repository rather than a journal. Articles hosted may not yet have been verified by peer-review and should be treated as preliminary. In particular, anything that appears to include financial or legal advice or proposed medical treatments should be treated with due caution. Vixra.org will not be responsible for any consequences of actions that result from any form of use of any documents on this website.
Add your own feedback and questions here:
You are equally welcome to be positive or negative about any paper but please be polite. If you are being critical you must mention at least one specific error, otherwise your comment will be deleted as unhelpful.