Diesel Engine Emissions Reduction Using Particle Swarm Optimization

Abstract

This study implemented a particle swarm optimization (PSO) algorithm to accelerate the engine development process in order to achieve low emissions. The PSO algorithm is a stochastic, population-based evolutionary optimization algorithm. In this study, PSO was integrated with diesel engine experiments to reduce emissions while maintaining high fuel efficiency. A merit function was defined to help reduce multiple emissions simultaneously. Engine operations using both single- and double-injection strategies were optimized. The present PSO algorithm was found to be very effective in finding the favorable operating conditions for low emissions. The optimization usually took 40–70 experimental runs to find the most favorable operating conditions under the constraints specified in the present testing. High EGR levels, small pilot amount, and late main injection were suggested by the PSO. Multiple emissions were reduced simultaneously without a compromise in the brake specific fuel consumption. In a favorable case that produced low emissions in this study, the NOx and PM emissions were reduced to as low as 0.41 and 0.0092 g/kW-h, respectively. The operating conditions at this point were 34% EGR, 5 ATDC main SOI, −24 ATDC pilot SOI, and 5% pilot fuel.

Keywords:

• Diesel engine
• Emissions
• Particle swarm optimization

ACKNOWLEDGEMENTS

The authors acknowledge the financial support by John Deere for this research.