Informatics Publishing Limited

N. Jayaramappa ¹, A. Krishna ¹, B. P. Annpurna ¹, T. Kiran ¹

Affiliations
1 Faculty of Engineering-Civil, UVCE, JBC, Bangalore University, Bangalore-560056, IN

Abstract

The main objective of this paper is to predict the base shear for a three dimensional four storey single bay RC frame, subjected to lateral load, using Artificial Neural Network. Analytical Pushover analysis is carried out using ETAB software. Pushover curve is plotted for Base shear versus roof displacement, to the prototype model tested at Central Power Research Institute (CPRI) Bangalore. The analytical results obtained from ETAB analysis are compared with the results predicted from Artificial Neural Network (ANN). Displacement and plastic hinges are selected as input vectors to ANN. Back propagation algorithm has been used for training. A learning rate constant of 0.85, error tolerance 0.001, and 5500 cycles are used for training ANN. Delta rule is used for adjusting the weights. It is found that a four-layer network (5-6-6-1) which consists of 5 input neurons, two hidden layers of 6 neurons each and one output neuron efficiently converges almost close to analytical results with an error range of 0.17% to 8.25%.

Keywords

ANN, Back Propagation, Base Shear, Delta Rule, Pushover

Full Text

   

T. V. Mallesh ¹, S. M. Prakash ², L. Prasanna Kumar ³, N. Jayaramappa ⁴

Affiliations
1 Department of Civil Engineering, Sri Siddhartha Institute of Technology, Tumkur-572 105, Karnataka, IN
2 KNSIT, Bangalore, Karnataka, IN
3 PESCE, Mandya, Karnataka, IN
4 Department of Civil Engg, UVCE, Bangalore, Karnataka, IN

Abstract

This paper deals with the application of artificial neural network (ANN) for the evaluation of bacteriological parameters in water. It dependents on temperature, conductivity, dissolved oxygen, total dissolved solids, depth of water, chlorides, phosphates, nitrates, biochemical oxygen demand, total Kjeldahl nitrogen, fecal coliform, total coliform and fecal steptococci before and after the domestic waste mixing zone of River Kabini, tributary of Cuavery at Nanjanagud, Mandya district, Karnataka. The ANN predicted values are close to the actual laboratory tested values. In this paper 150 actual measured values and laboratory tested values have been taken. For predictions of values using ANN, input and outputs parameters, learning rate parameters, error tolerance, number of cycles to reduce the randomly assigned weights are required, for processing this, the back propagation algorithm and delta rule are required, to input these values to ANN the actual measured and laboratory tested values are used as input and output parameters. The learning rate parameter is 0.55, error tolerance is 0.001 and 5600 number of cycles have been chosen. The first ANN pattern chosen is 10-11-11-3 (ten neuron in input layer, two hidden layers of eleven neuron each and three neuron in output layer) and second parameter is 0.55, error tolerance is 0.001 and 4500 number of cycles, have been chosen. The ANN pattern chosen is 10-12-12-13 (ten neuron in input layer, two hidden layers of eleven neuron each and three neuron in output layer). Back propagation algorithm has been used to train the network, and delta rule is used to adjust the weights and to reduce the errors. The network predicted values, measured and laboratory tested values have been shown in figures and graphs.

Keywords

Artificial Neural Network, Bacteriological Parameters, River Kabini, Coliforms.

Full Text