Highly nonlinear process model using optimal artificial neural network

The application of artificial neural network (ANN) for modeling, combined steam-carbon dioxide reforming of methane over nickel-based catalysts, was investigated. The artificial neural network model consisted of a 3-layer feed forward network, with hyperbolic tangent function. The number of hidden neurons is optimized by minimization of mean square error and maximization of R2 (R square, coefficient of determination) and set of 8 neurons. With feed ratio, flow rate, and temperature as independent variables, methane, carbon dioxide conversion, and H2/CO ratio, were measured using artificial neural network. Coefficient of determination (R2) values of 0.9997, 0.9962, and 0.9985 obtained, and MAE (Mean Absolute Error), MSE (Mean Squared Error), RMSE (Root Mean Squared Error), and MAPE (Mean Absolute Percentage Error) showed low value. This study indicates ANN can successfully model a highly nonlinear process and function.

Download Full-text

Artificial neural network based inverse model control of a nonlinear process

2015 International Conference on Computer, Communication and Control (IC4) ◽

10.1109/ic4.2015.7375581 ◽

2015 ◽

Cited By ~ 3

Author(s):

R J Rajesh ◽

R Preethi ◽

Parth Mehata ◽

B Jaganatha Pandian

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Nonlinear Process ◽

Inverse Model ◽

Model Control ◽

Artificial Neural

Download Full-text

Performance Prediction of Pulse Tube Refrigerator Using Artificial Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.984-985.1147 ◽

2014 ◽

Vol 984-985 ◽

pp. 1147-1149

Author(s):

Pankaj Kumar ◽

Sachindra Ku Rout ◽

Ajay Ku Gupta ◽

Rajit Ku Sahoo ◽

Sunil Ku Sarangi

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Numerical Model ◽

Process Model ◽

Fluid Dynamic ◽

Coefficient Of Performance ◽

Pulse Tube ◽

Time Saving ◽

Pulse Tube Refrigerator ◽

Artificial Neural

The present study proposes a numerical model to analyze the effect of four dimensional parameters on performance characteristics such as Coefficient of performance (COP), of the Inertance-Type Pulse Tube Refrigerator (ITPTR). The numerical model is validated by comparing with previously published results. The detail analysis of cool down behaviour, heat transfer at the cold end and the pressure variation inside the whole system has been carried out by using the most powerful computational fluid dynamic software package ANSYS FLUENT 13. The operating frequency for all the studied cases is (34 Hz). In fact, to get an optimum parameter experimentally is a very tedious for iterance pulse tube refrigerator job, so that the CFD approach gives a better solution. Finally, an artificial neural network (ANN) based process model is proposed to establish relation between input parameters and the responses. The model provides an inexpensive and time saving substitute to study the performance of ITPTR. The model can be used for selecting ideal process states to improve ITPTR performance.

Download Full-text

Quarter Circular Breakwater: Prediction of Transmission Using Multiple Regression and Artificial Neural Network

Marine Technology Society Journal ◽

10.4031/mtsj.48.1.7 ◽

2014 ◽

Vol 48 (1) ◽

pp. 92-98 ◽

Cited By ~ 3

Author(s):

Rushil Goyal ◽

Kriti Singh ◽

Arkal Vittal Hegde

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Physical Model ◽

Multiple Regression ◽

Mean Squared Error ◽

Nonlinear Process ◽

Wave Transmission ◽

Physical Models ◽

Mathematical Tool ◽

Artificial Neural

AbstractThe physical model study of coastal structures is a nonlinear process influenced by innumerable parameters. As a result of a lack of definite systems, intricacies, and high costs involved in the physical models, we need a simple mathematical tool to predict wave transmission through quarter circular breakwater (QBW). QBW is a state-of-the-art breakwater essentially based on the exploitation of the concepts of semicircular breakwater. This paper discusses the use of soft computing tools such as MATLAB-based multiple regression (MR) and artificial neural network (ANN) to predict the wave transmission coefficient of QBW. To assess the accuracy of the proposed model and its ability to forecast, correlation coefficient and mean squared error are availed. On comparing the results obtained from MR and ANN, it is concluded that ANN gives more accurate results and can be used as a powerful tool for the modeling of hydrodynamic breakwater transmission through QBW. It serves as a viable alternative to the conventional physical model to simulate the hydrodynamic transmission performance of QBW.

Download Full-text

Artificial Neural Network for Response Inference of a Nonvolatile Resistance-Switch Array

Micromachines ◽

10.3390/mi10040219 ◽

2019 ◽

Vol 10 (4) ◽

pp. 219 ◽

Cited By ~ 1

Author(s):

Guhyun Kim ◽

Vladimir Kornijcuk ◽

Dohun Kim ◽

Inho Kim ◽

Cheol Hwang ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Applied Voltage ◽

High Resistance State ◽

Input Vector ◽

Crossbar Array ◽

Input And Output ◽

Highly Nonlinear ◽

Resistance State ◽

Artificial Neural

An artificial neural network was utilized in the behavior inference of a random crossbar array (10 × 9 or 28 × 27 in size) of nonvolatile binary resistance-switches (in a high resistance state (HRS) or low resistance state (LRS)) in response to a randomly applied voltage array. The employed artificial neural network was a multilayer perceptron (MLP) with leaky rectified linear units. This MLP was trained with 500,000 or 1,000,000 examples. For each example, an input vector consisted of the distribution of resistance states (HRS or LRS) over a crossbar array plus an applied voltage array. That is, for a M × N array where voltages are applied to its M rows, the input vector was M × (N + 1) long. The calculated (correct) current array for each random crossbar array was used as data labels for supervised learning. This attempt was successful such that the correlation coefficient between inferred and correct currents reached 0.9995 for the larger crossbar array. This result highlights MLP that leverages its versatility to capture the quantitative linkage between input and output across the highly nonlinear crossbar array.

Download Full-text

Prediction of water discharge and sediment in teak forested area using artificial neural network model

Jurnal Penelitian Kehutanan Wallacea ◽

10.18330/jwallacea.2017.vol6iss1pp73-89 ◽

2017 ◽

Vol 6 (1) ◽

pp. 73

Author(s):

Nining Wahyuningrum

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Water Discharge ◽

Ann Modeling ◽

Highly Nonlinear ◽

Condition Modeling ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Relationship Of ◽

The Relationship

Information on the relationship of rainfall with discharge and sediment are required in watershed management.This relationship is known to be highly nonlinear and complex. Although discharge and sediment has been monitored continuously, but sometimes the information is not or less complete. In this condition, modeling is indispensable.The research objective is to create a model to predict the monthly direct runoff and sediment using Artificial Neural Network (ANN).The model was tested using rainfall data at t-3 and t-4 as input, and discharge and sediment at t+3 and t+4 as output. The data used is the data from 2001 to 2014. The results showed that of some models tested there are two models for the prediction of discharge and two models for sediment.The model was chosen because it has the smallest MSE, the largest R2 and satisfying K (0.5 to 0.65).Thus, these models can be used to predict discharge andsediment for a period of t+3 and t+4. Prediction of discharge of t+3 and t+4 may use Q t+3 = 0,64 Q t-3 + 0,05 and Q t+4 = 0,65 Q t-4 + 0,074 res pectively, while for predicting sediment of t+3 and t+4 may use equations QS t+3 = 0,45 QS t-3 + 0,052 and QS t+4 = 0,45 QS t-4 + 0,052. This ANN modeling can be applied to predict the flow and sediment in other locations with an architecture adapted to the conditions of available data.

Download Full-text

The Research on Simulation Model in EDM of Insulating Ceramic Si3N4

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.538-541.556 ◽

2012 ◽

Vol 538-541 ◽

pp. 556-559 ◽

Cited By ~ 2

Author(s):

Xiao Bing Xu ◽

Tian Kai Xiong ◽

Li Jun Tan ◽

Yi Zeng

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Simulation Model ◽

Large Scale ◽

Ceramic Materials ◽

Back Propagation Algorithm ◽

Processing Application ◽

Highly Nonlinear ◽

Artificial Neural ◽

Low Efficiency

Insulating ceramic materials has been regarded as one of leading materials that promotes the industrial progress of the 21st century due to its unique electric and magnetic functions, and its special qualities such as high hardness, wear resistance, high temperature resistance and high pressure resistance also help a lot. Yet its modeling process is quite difficult. The traditional method is to grind it with a diamond after sintering into a certain shape. However, the low efficiency and the high cost certainly affect its widely application. Over the past 20 years, EDM has developed rapidly in ceramic material processing application, and EDM of conductive ceramic materials has become more and more practical. EDM is of the highly nonlinear characteristic, and it is quite difficult to use any specific mathematical expressions to describe its technological system, therefore, the developing trend of the researches in this field lies in the studies of its processing characters and its simulation techniques, of which, the artificial neural network, as a new technology, has provided an effective way for the further researches of EDM. It uses the computer to do a certain abstract, simplification and simulation of the functions of human brain, which can constitute a highly nonlinear large-scale continuous dynamic system. This paper employs the BP (Back Propagation) algorithm of the artificial neural network and makes the result of the orthogonal experiments on the processing technology effect as the learning samples of neural networks, thus establishes the simulation model of the multi-objective technology effect in EDM of insulating ceramic.

Download Full-text