The week's pick
Reseach Article
An Intelligence Approach to Predict Fire Flame Length under Tunnel Ceiling
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 106 - Number 18 |
| Year of Publication: 2014 |
| Authors: Behzad Niknam, Kourosh Shahriar, Eng Hassan Madani |
10.5120/18709-9859
|
Behzad Niknam, Kourosh Shahriar, Eng Hassan Madani . An Intelligence Approach to Predict Fire Flame Length under Tunnel Ceiling. International Journal of Computer Applications. 106, 18 ( November 2014), 39-43. DOI=10.5120/18709-9859
Abstract
Various analytical models have developed to determine fire flame length under tunnel ceilings during fire emergency based on the regression and dimensional analysis. Artificial intelligence techniques are now being used as an alternate to statistical techniques. In this study, the artificial neural network (ANN) is applied to forecast fire flame length in tunnels. Moreover, particle swarm optimization algorithms were used for ANN training in order to overcome very slow convergence and easy entrapment in a local minimum of back propagation training algorithms. The model predicts flame length using Fire Heat Release Rate, Air velocity, Tunnel Width, Tunnel Height and Tunnel Cross Section. The predictive PSO-ANN model was implemented on the MATLAB and developed based on a database including 44 data sets from large scale fire test programs. The coefficient of determination (R2), the variance account for (VAF) and the root mean square error (RMSE) were calculated to check the prediction performance of the model. The R2, VAF and RMSE indices were obtained as95. 884, 99. 86% and 1. 05. These indices revealed that the developed model is suitable for practical use in tunnels.
References
- Baccard, E. , Corvisier, J. M. , Gaillardon, D. , Schuliar, Y. , Vignal, J. M. , 1999. Mont-Blanc Road tunnel mass disaster: forensic examination in dangerous surroundings. Journal of Clinical Forensic Medicine 6 (3), 193.
- Lönnermark A. 2005, On the Characteristics of Fires in Tunnels, Doctoral thesis, Department of Fire Safety Engineering, Lund University, Lund, Sweden,
- Wang, H. Y. and Joulain, P. ,2007, Numerical simulation of wind-aided ?ame propagation over horizontal surface of liquid fuel in a model tunnel. Journal of Loss Prevention in the Process Industries, 541–550.
- Lavid, M. , and Berlad, A. L. 1976. Gravitational effects on chemically reacting boundary layer ?ows over a horizontal ?at plate. In Proceedings of the 16th symposium (international) on combustion(p. 1157). Pittsburgh: The Combustion Institute.
- Putnam, A. A. ,1963,. A model study of wind-blown free-burning ?res. In Proceedings of the 10th symposium (international) on combustion (p. 1039). Pittsburgh: The Combustion Institute.
- Lonnermark ,A and Ingason,H,2006, Fire Spread and Flame Length in Large-Scale Tunnel Fires. Fire Technology, 42,283–302.
- Ingason H. , Li Y. Z. 2010, Model scale tunnel fire tests with longitudinal ventilation, Fire Safety Journal, , 45,371-384
- Ingason H. , Li Y. Z. 2010, Model scale tunnel fire tests with point extraction ventilation, SP Report 2010:03, SP Technical Research Institute of Sweden, Borås, Sweden,
- Chau, K. W. , Chen, W. , 2001. A fifth generation numerical modellingsystem in coastal zone. Applied Mathematical Modelling 25 (10),887–900.
- Rumelhart, D. E. , Hinton, E. , Williams, J. , 1986. Learning internal representation by error propagation. Parallel Distributed Processing 1, 318–362.
- Haykin, S. , 1999. Neural Networks, A Comprehensive Foundation. Prentice Hall, Upper Saddle River
- Rogers, L. L. , Dowla, F. U. , Johnson, V. M. , 1995. Optimal field-scale groundwater remediation using neural networks and the genetic algorithm. Environmental Science and Technology 29 (5), 1145–1155.
- Kumar, P. , Merchant, S. N. , Desai, U. B. , 2004. Improving performance in pulse radar detection using Bayesian regularization for neural network training. Digital Signal Processing 14 (5), 438–448.
- Kennedy, J. , 1997. The Particle swarm: Social adaptation of knowledge. In: Proceedings of the 1997 International Conference on Evolutionary Computation, Indianapolis, pp. 303–308.
- Kennedy, J. , Eberhart, R. , 1995. Particle swarm optimization. In: Proceedings of the 1995 IEEE International Conference on Neural Networks, Perth, pp. 1942–1948.
- Ingason H. , Li Y. Z. 2012. Runehamar Tunnel Fire Tests SP Report 2011:55, SP Technical Research Institute of Sweden, Borås, Sweden,.
- Massachusetts Highway Department and Federal Highway Administration, 1995. Memorial Tunnel Fire Ventilation Test Program—Test Report.
- French S. E. 1994, EUREKA 499—HGV Fire Test (Nov. 1992)—Summary Report, in Proceedings of the International Conference on Fires in Tunnels, E. Iverson (Ed. ), SP Swedish National Testing and Research Institute, Bor? as, Sweden ,pp. 63–85
- Raw . C and Deaves. D,1999, Fire Spread and Flame Length in Ventilated Tunnels—A Model Used in Channel Tunnel Assessments," Proceedings of the International Conference on Tunnel Fire sand Escape from Tunnels, Lyon, France, 5–7 May, 1999, pp. 397–406.
- Alvarez Grima M ,Babuska R 1999 Fuzzy model for the prediction of unconfined compressive strength of rock samples. Int J Rock Mech Min Sci;36:339–49. Bowman, M. , Debray, S. K. , and Peterson, L. L. 1993. Reasoning about naming systems.
Index Terms
Keywords