Науковий вісник НГУ

Optimization of hydrogen-fueled engine ignition timing based on the particle swarm optimized fuzzy neural network

• 
• 

User Rating:  / 0

PoorBest 

Details

Category: Information technologies, systems analysis and administration

Last Updated on 04 February 2016

Published on 04 February 2016

Hits: 3857

Authors:

Wang Lijun, North China University of Water Resources and Electric Power, Zhengzhou, Henan, China

Liu Yuan, North China University of Water Resources and Electric Power, Zhengzhou, Henan, China

Song Yufeng, North China University of Water Resources and Electric Power, Zhengzhou, Henan, China

Yang Zhenzhong, North China University of Water Resources and Electric Power, Zhengzhou, Henan, China

Abstract:

Purpose. In order to solve the increasingly serious energy crisis and environmental pollution problems, to find a clean and renewable alternative fuel for vehicle engines becomes the only way. In this paper, a hydrogen-fueled engine experiment system has been established. And because of some combustion characteristics of hydrogen, abnormal combustion such as pre-ignition and backfire usually happens. Ignition timing optimization is very helpful for the suppression of abnormal combustion.

Methodology. On the basis of ignition timing data calibrated on hydrogen-fueled engine experiment system, an ignition timing optimization model, which is the function of rotating speed and loading of the engine, is established by the fuzzy neural network (FNN) combined with the particle swarm optimization (PSO). A simulation experiment has been carried out on the model.

Findings. The experiment results show that the mean absolute error of the prediction is 0.704 and the mean relative error is 2.2%. The algorithm is capable of fast, accurate forecasts on the best ignition timing of the hydrogen fueled-engine.

Originality. In this paper, a PSO-FNN model was firstly used in the hydrogen-fueled engine experiment system and it promotes the application of artificial intelligence algorithm in Engineering.

Practical value. The PSO-FNN model is proved to be a very effective approach to optimize the ignition timing, because it avoids a large number of engine calibration tests and greatly reduces the workload of the experiment and improves the efficiency.

References:

1. Sebastian Verhelst and Thomas Wallner (2009), “Hydrogen-fueled internal combustion engines”, Progress in Energy and Combustion Science, vol.35, no.6, pp. 490−527.

2. Junfa Duan, Fushui Liu and Baigang Sun (2014), “Backfire control and power enhancement of a hydrogen internal combustion engine”, International Journal of Hydrogen Energy, vol.39, no.9, pp. 4581−4589.

3. Tien Ho and Vishy Karria (2010), “Basic tuning of hydrogen powered car and artificial intelligent prediction of hydrogen engine characteristics”, International Journal of Hydrogen Energy, vol.35, no.18, pp. 10004−10012.

4. Anuj Pal and Avinash Kumar Agarwal (2015), “Comparative study of laser ignition and conventional electrical spark ignition systems in a hydrogen fuelled engine”, International Journal of Hydrogen Energy, vol.40, no.5, pp. 2386−2395.

5. Kaname Naganuma and Toru Honda (2010), “Efficiency and Emissions-Optimized Operating Strategy of a High-pressure Direct Injection Hydrogen Engine for Heavy-duty Trucks”, SAE International Journal of Engines, vol.2, no.2, pp. 132−140.

6. Salama, M.M.A (2002), “Determination of neural-net-work topology for partial discharge pulse pattern recognition”, IEEE Transactions on Neural Networks, vol.13, no.2, pp. 446−456.

7. Yu, Jiang (2008), “Research of PSO-BP optimal algorithm in material moisture measurement”, The 2nd International Symposium on Intelligent Information Technology Application, vol.2, pp. 293−297.

8. Li, Rui (2010), “A particle swarm optimized fuzzy neural network for bankruptcy prediction”, International Conference on Future Information Technology and Management Engineering, vol.2, pp. 557−560.

9. Kennedy, J., Eberhart, R.C. (1995), “Particle swarm optimization”, Proceedings IEEE International Conference on Neural Networks, vol.4, pp. 1942−1948.

10. Wang Lijun (2006), “Research on optimal calibration technology for hydrogen-fueled engine based on nonlinear programming theory”, International Journal of Hydrogen Energy, vol.32, no.7, pp. 2747−2753.

11. Kim Y.Y., Lee Jong T. and Caton, J.A. (2006), “The development of a dual-injection hydrogen-fueled engine with high power and high efficiency”, Journal of Engineering for Gas Turbines and Power, vol.128, no.1, pp. 203−212.

2015_05_lijun
2016-02-03  490.94 KB  1020

• < Prev