Call For Paper Volume:7 Issue:1 Jan'2020 |

#### VELOCITY PREDICTION BY USING FUZZY LOGIC

Publication Date : 28/02/2015

Volume 2
,
Issue 2
(02 - 2015)

##### Abstract :

An artificial neural network (ANN), usually called neural network (NN) consists of mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks. Modern neural networks are non linear statistical modeling tools. They are usually used to model complex relationships between inputs and outputs or to find patterns in data. The bend of channel varies according to its radius, degree of angle at its curvature and depth at different sections of channel due to which the velocity of the flow of water at the bend of channel vary at different sections. Hence it is necessary to study and predict the velocity for planning and management of water resources. In this regard, prediction of velocity at a bend of channel was studied using experimental setup of flume and thus various experiments were conducted, The observations were recorded and data regarding varied radius, depth ,theta were collected and from this velocity was measured. In this regard prediction of velocity was done using artificial neural network with components in channel bend i.e. angel of bend, radius of bend, flow depth and Karmans constant as input data except Karmans constant, while the velocity as a target output, The total no. of samples recorded are 315. It was observed that different methods were used such as MLP, recurrent networks etc for prediction of parameters of hydrology but the method of Fuzzy Logic was never applied while using ANN. Hence depending on the data representation and the application the model Fuzzy logic is used to train and learn the data sets. Hence after training for number of runs, learning and testing the results obtained were satisfactory. Supervised neural networks that use an MSE cost function can use formal statistical methods to determine the confidence of the trained model. The MSE on a validation set can be used as an estimate for variance. This value can then be used to calculate the confidence interval of the output of the network, assuming a normal distribution. The results of the study showed that predictions of velocity using artificial neural network are reasonable, suitable and of acceptable accuracy. Hence prediction of velocity at the curvature of channel by ANN may be useful for water quality planning and management.  