SENSITIVITY ANALYSIS VIA ARTIFICIAL NEURAL NETWORK OF BIOMASS BOILER EMISSION

Authors

  • Ahmad Razlan Yusoff Faculty of Mechanic al Engineering University College of Engineering and Technology Malaysia (KUKTEM) Locked Bag 12, 25000 Kuantan, Pahang, Malaysia
  • Ishak Abdul Aziz School of Mechanical Engineering Engineering Campus, Universiti Sains Malaysia, 14300 Nibong Tebal, Pulau Pinang, Malaysia

Keywords:

Correlation coeffficient sensitivity analysis, artificial neural networks, biomass boiler emission

Abstract

According to a survey in J999, only 76% of the palm oil mills in Malaysia meet the regulation of
Department of Environment (DOE) regarding emission. The emission is released through the
chimney from the process of fuel combustion and steam generation in order to produce power to the mill. The complex and very highly lion-linear process involves several variables in fuel,
turbine and boiler as factors producing pollutants. Therefore. Sensitivity Analysis via Artificial
Neural Networks (SAANN) and Correlation Coefficient (CC) were used to find the major and
minor input variables to each pollutant from 15 input variables. The result shows the major and
minor input variables for both methods are similar.

References

Weisman, J and Eckart, R.,(1985). Modern Power Plant Engineering. London :Prent ice Hall Inc.

Li, K. W. and Priddy, A.P. (1985). Power Plant System Design. John Wiles & Sons.

Andersson , F. 0., Aberg, M. and Jacobson, S. P., (2000 ). Algorithm Approaches for Studies of Variable Influence, Contribution and Selccti in Neural Networks, Cheometrics and Intelligent Laboratory Systems 51. 61-72.

Sun, II, (1998). Rangking Importance of Input Parameters of Neural Networks. Expert Systems with Application . 15,405-411.

Howes, P. and Crook, N., ( 1999). Using Input Param eter Influences to Support the Dicissions of Feedforward Neural Network, Neurocomputing 24, 191-26.

Ricott i, M. E. and Zio, E, (1999). Neural Netwo rk Approach to Sensitivity and Uncertainly Analysis. Reliability Engineering and System Safety. 64, 59-77.

Maren, A. J., Harston, C. T. and Pap, R. M., (1990). Hanlcbook Of Neural Computing Application. 1-250, Academic Press Inc.

Radhakrishnan, V.R. ,Moha med, A R (2000). Neural Networks for Identification and Control of Blast Furnace Hot Metal Qual ity. Journal of Process Control. 10,509-524.

Crowther, W. J. & Cooper, J. E. (200 I). Flight Test Flutter Prediction Using Neural Network, Proc.lnsth Mech Eng. 215 Part G ImechE 2001.

Syu, MJ. & Liu J. Y. ( 1998). Neural Network Sensi tivity Analysi s of the Detected Signal From an S02 electrode . Sensor and Actuators B. 50, 1-8.

Ender, L & Filho, R. M. (2000). Design ofMultivariable Controller Based on Neural Network. Computer & Chemical Engineering, 24, 937-943.

Hung, S.L., Kao, CY. and Lee. l .L., (2000). Active Pulse Structural Control Using AI"N. Jo urnal Engineering Mechanic. 8, 839-849.

Lennox, B., Montague, G.A., Frith, A.M., Gent , C. and Beven, V., (2001). Industrial Application of Neural Networks- An Investigation. Journal of Process Control. 11, 497-507.

Mu, H. H. ,Kahad, Y. P. and Sherlock, B.G. (2001). Design of Control Systems Using Neural Network. CARS & FOF 2001,Durban.

Baines, G.H., Hayes, R.L. and Stabell, J .A. (1997). Predicting Boiler Emission With Neural Networks, TAPPI Proceeding, 57-61.

Noble, T.H. & Mayhew ( 1997). Keys to Succcsful Power Boiler Predictive Emission Monitoring System Installation (PEMS). TAPPI Proceeding. 593· 597.

Vue, H.H, Valle, Sand Qin, 5.1.(1998). Comparison of Several Methods of Multivariate Soft Sensor For Emission Monitoring . Journal of Environmental Engineering. 3(6), 23-28.

Walpole, R.E., Myers, R.ll . and Myers, S.L.(1 998). Probability and Stat istics for Engineers and Scienticts , 6lh ed. New Jersey: Prentice Hall Kovindasamy, M,( 1997). Neural Network Model of A Cement Plant Kiln. Master Thesis, School of Chemical Enginee ring, Universiti Sains Malaysia.

Kovindasamy, M,( 1997}. Neural Network Model of A Cement Plant Kiln. Master Thesis, School of Chemical Engineering. Universiti Sains Malaysia.

Devore, J.L. & Peck, R. (I993). Statistics the Exploration and Analysis of Data. 2nd cd. Belmont, California: Warswon h.

Cho, A. 5., par, W. 5., Chi, B W, Chi, B.W. and Lew, M.C. (2000). Determining Optimal Parameters for Stereolithography Process via Genetic algorithms. Journal of Manufacturing System. 9, 8-27.

Downloads

Published

2018-04-25

How to Cite

Yusoff, A. R., & Abdul Aziz, I. (2018). SENSITIVITY ANALYSIS VIA ARTIFICIAL NEURAL NETWORK OF BIOMASS BOILER EMISSION. Jurnal Mekanikal, 18(2). Retrieved from https://jurnalmekanikal.utm.my/index.php/jurnalmekanikal/article/view/208

Issue

Section

Mechanical

Similar Articles

<< < 2 3 4 5 6 7 8 9 10 11 > >> 

You may also start an advanced similarity search for this article.