NO_x Reduction Optimization Based on Distance Learning Particle Swarm Algorithm

To reduce the NO_x emission of coal-fired power plants by combustion optimization, a prediction model was established using ensembled support vector machine based on the 3 formation mechanisms of NO_x introduced, which was subsequently optimized by particle swarm algorithm. To overcome the premature problem of particle swarms, an improved distance learning particle swarm algorithm was proposed. The new method was applied to optimize the NO_x emission of a power plant, and was then compared with other methods. Results show that the ensembled support vector machine can effectively improve the accuracy of prediction results, while the new method is able to further lower the NO_x emission and makes the search results be more stable.