Combining Genetic Algorithm and Artificial Neural Network to Optimize Biomass Steam Power Plant EmissionAhmad Razlan Yusoff & Ishak Abdul Aziz
Boiler emission released from the steam power plant of palm oil mill cause severe atmospheric pollutions. Genetic Algorithm and Artificial Neural Network (GAANN) were used to analyze the real data taken from palm oil mill power plant. A parametric study of Genetic Algorithms (GA) parameters such as population size, mutation rates and crossover rates are carried out to get optimal parameters for a GAANN model. GAANN is utilized to search several
optimal parameters for the boiler, turbine and furnace which released carbon monoxide (CO), nitrogen oxide (NOx), sulfur dioxide (SO2) and particulate matters (PM). Monitoring and controlling of the emissions are achieved with
optimum operating conditions of boiler parameters, i.e. below the level permitted by Department of Environment (DOE).
Keywords: Artificial Neural Network, biomass boiler emission, GeneticAlgorithms, optimization and emission
 Fisher-Rosemount Company (1997). Smart Process (Plant Opt Software Westinghouse). Industrial Report for Westinghouse Process Ctrl, July,1997.
 Booth, K.C. & Roland, W.B. Jr. (1998). Pegasus NN Based Combustion Opt Reduces NOx Emission While Simultaneously Improving Thermal Efficiency, Pegasus Technologies Ltd. KFx Net Power Sollution, 1-5, 15 May 1998.
 Radl, B. J. (1999). Neural Networks improve performance of Coal-fired Boiler, Pegasus Newsletter. 1, Jan 1999. CADDET Energy Efficiency.
 Kamal, R. (2000). Neural Modelling & Control of Coal-fired Boiler Plant (Neuromon). Project Profile of Dept. of Trade & Industry Project Profilein BCURA, Apr. 2000.
 Yue, H.H, Valle, S. and Qin, S.J. (1998). Comparison of Several Methods of Multivariate Soft Sensor For Emission Monitoring. Journal of Environmental Engineering. 3(6), 23-28
 Morimoto, T., Suzuki, J. and Hashimoto, Y. (1997). Optimization of a Fuzzy Controller for Fruit Storage Using Neural Networks and Genetic Algorithms. Engineering Application Artificial Intelligence, 10(5), 453-461.
 Sette, S., Boullart, L. and Langauhore, L.V. (1998). Using Genetic Algorithms to Design a Control Strategy of an Industrial Process. Control EngineeringPractice. 6, 523-527.
 Cho, A. S., Par, W. S., Chi, B. W, Chi, B.W. and Lew, M.C. (2000). Determining Optimal Parameters for Stereolithography Process via Genetic Algorithm. Journal of Manufacturing System. 9, 8-27.
 Zhao, W., Chen, D. and Hu, S. (2000). Optimizing Operating Conditions Based on ANN and Modified Gas. Computer and Chemical Engineering. 24, 61 65.
 Chow, T.T., Zhang, G. Q., Lin, Z. and Song, C.L. (2002). Global Optimization of Absorption Chiller System by Genetic Algorithm and Neural Network. Energy and Buildings. 34, 103-109.
 Hou, Z., Kefa, C. and Jianbo M. (2001). Combining Neural Network and Genetic Algorithms to Optimize Low NOx Pulverized Coal Combustion, Fuel. 80, 2162-2169.
 Ricotti, M. E. and Zio, E. (1999). Neural Network approach to sensitivity and uncertainly analysis. Reliability Engineering and System Safety. 64, 59-77.