Simplex particle swarm optimization algorithm and its application

An improved particle swarm optimization algorithm-simplex particle swarm optimization algorithm (SPSO) was proposed based on PSO and simplex method (SM). Then, SPSO, PSO and SM are used to resolve five widely used test functions' optimization problems. Results show that SPSO has greater efficiency and better performance than PSO and SM. Next, SPSO is applied to train artificial neural network to construct a practical soft-sensor of gasoline endpoint of main fractionator of fluid catalytic cracking unit (FCCU). The obtained results and comparison with actual industrial data indicate that the new method proposed by this paper is feasible and effective in soft-sensor of gasoline endpoint.