Scribd
Upload
24 views3 pages

Prediction of Discharge of Simple Conical Flume by Using Artificial Neural Network (ANN) Tool of Matlab Software

This paper discusses the use of MATLAB software and Artificial Neural Networks (ANN) to predict the discharge of a simple conical flume, highlighting the effectiveness of ANN models in civil engineering applications. The results indicate that the ANN model predictions closely match measured discharges, with a maximum error of ± 10% in most cases. The study demonstrates that ANNs can outperform traditional methods in predicting flow rates.

Uploaded by

archana.shirbhate
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
24 views3 pages

Prediction of Discharge of Simple Conical Flume by Using Artificial Neural Network (ANN) Tool of Matlab Software

This paper discusses the use of MATLAB software and Artificial Neural Networks (ANN) to predict the discharge of a simple conical flume, highlighting the effectiveness of ANN models in civil engineering applications. The results indicate that the ANN model predictions closely match measured discharges, with a maximum error of ± 10% in most cases. The study demonstrates that ANNs can outperform traditional methods in predicting flow rates.

Uploaded by

archana.shirbhate
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

© 2017 IJSRST | Volume 3 | Issue 2 | Print ISSN: 2395-6011 | Online ISSN: 2395-602X

National Conference on Advances in Engineering and Applied Science (NCAEAS)


16th February 2017
In association with
International Journal of Scientific Research in Science and Technology

Prediction of Discharge of Simple Conical Flume by using Artificial


Neural Network (ANN) Tool of Matlab Software
Shubhangi Larokar, Rani Sayam, Vikrant Mate, Rajaram Jogpethe, Rushabh Bhiwapurkar,
Vallabh Hadge, Shubham Rangankar

Civil Engineering Department, KDK College of Engineering, R.T.M. N.U., Nagpur, Maharashtra, India

ABSTRACT

MATLAB is a high-level language enables us to perform computational intensive tasks faster than with traditional
programming language. This paper presents some of the positive aspects of MATLAB software. In this paper,
MATLAB software is used for the prediction of discharge of simple conical flume by using Artificial Neural
Network (ANN) Tool. A simple portable conical flume in the form of cone inserted axially into the channel is
referred as simple conical flume. ANN is one of the tool of MATLAB software which is used for development of
the ANN model for various purposes. ANN model can provide reasonable accuracy for civil engineering problems,
and more effective tool for engineering applications. Predicted discharge by ANN model is compared with the
measured discharge. It has been observed that the ANN model results are in close agreement with the measured data
except one reading.
Keywords : MATLAB, Flume, ANN

I. INTRODUCTION II. MATLAB

Water is precious resource and water demand is very The name MATLAB stands for MATrix LABoratory
much high. Hence, improvement of water management
can encourage the conservation and make best use of our MATLAB is a high performance language for technical
limited water resources. Water management depends computing. It integrates computations, visualization and
upon the ability to preciously measure and manage the programming environment. It has a sophisticated data
flow of water at important points in canal irrigation structures, contains built in editing and debugging tools
system. A simple portable conical flume in the form of and supports object oriented programming. MATLAB,
cone inserted axially into the channel is referred as MATrix LABoratory is a programming package
simple conical flume, can be used for such purpose. specially designed for quick and easy scientific
MATLAB software is used for the prediction of calculations. It has literally hundreds of built-in
discharge of simple conical flume by using Artificial functions for a wide variety of computations and many
Neural Network (ANN) Tool of MATLAB software. tool boxes design for specific research disciplines,
ANN is one of the tool of MATLAB software which is including statistics, optimization, solution for partial
used for the prediction of discharge of simple conical differential equation, data analysis.
flume. ANN model can provide reasonable accuracy for
civil engineering problems, and more effective tool for
engineering applications.

NCAEAS2302 | NCAEAS | ACET | January-February-2017 [(3)2: 04-06]


4
Volume 3 | Issue 2 | IJSRST/Conf/NCAEAS/ACET/2017/02

V. NEURAL NETWORK TRAINING

Next, we create a training vector for the neural network


in order to match the input accepted by the neural
network function. The steps performed in creating and
training the neural network has been illustrated below:

The 'nntool' of Matlab opens a dialog box where we


required to Import the Inputs and Targets files from the
MATLAB workspace. After importing files, the created
network appears in the network list. Open the network
Figure 1 : starting window of MATLAB and select training tab. Here, we can choose the training
parameters and data (inputs and targets) and finally click
III. ARTIFICIAL NEURAL NETWORKS on Train option to train the network. we used feed
forward back propagation neural network. There were
Artificial neural network emerged from the studies of two hidden layers used with TANSIG (tan-sigmoid)
how brain performs. The human brain consists of many function.
millions of individual processing elements called neuron
that are highly interconnected. ANNs are made up of
simplified individual models of biological neurons that
are connected together to form a network. Information
stored in the network in the form of weight or different
connecting strengths associated with the synapses in the
artificial neuron models.

Many different type of neuron networks are available


and multi-layered neural network are the most popular
which are extremely successful in pattern reorganization
problems. Each neuron input is weighted by wi.
Changing the weights of an element will alter the
behaviour of the whole network. The output y is
obtained summing the weighted inputs and passing the
result through a non-linear activation function.

IV. DATA MANAGER

By using this window input, Training & Target file are


imported to ANN tool of Matlab.

Figure 3 : Network training

Calculation of percentage error between measured


and predicted discharge for 151mm diameter cone
Figure 2 : NN tool data manager (NN Tool)

International Journal of Scientific Research in Science and Technology (www.ijsrst.com)


5
Volume 3 | Issue 2 | IJSRST/Conf/NCAEAS/ACET/2017/02

Table 1 shows the measured discharge Qm and


discharge predicted by ANN model and percentage
error between measured discharge and predicted
discharge by 'nntool' of Matlab.

Table 1 : Comparison of Measured & Predicted


Discharge

VI. CONCLUSION

The predicted flow rates based on the ANN model were


compared with the corresponding measured ones. The
comparison showed a good agreement. The proposed
model predicted measured flow rates with a maximum
error of ± 10% except one reading out of thirteen. Based
on the results of case study it is evident that ANNs
perform well than conventional methods.

VII. REFERENCES

[1]. T Application of Neural Network in Civil


Engineering Problems by D.S. Jeng, D.H. Cha and
M. Blumenstein.
[2]. Application of Artificial Neural Networks in Civil
Engineering by Marijana Lazarevska, Milos
Knezevic, Meri Cvetkovska, Ana Trombeva-
Gavriloska.

International Journal of Scientific Research in Science and Technology (www.ijsrst.com)


6

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy