Particle swarm optimization algorithm (PSOA) is an advantage optimization tool. However, it has a tendency to get stuck in a near optimal solution especially for middle and large size problems and it is difficult to improve solution accuracy by fine-tuning parameters. According to the insufficiency, this paper researches the local and global search combine particle swarm algorithm (LGSCPSOA), and its convergence and obtains its convergence qualification. At the same time, it is tested with a set of 8 benchmark continuous functions and compared their optimization results with original particle swarm algorithm (OPSOA). Experimental results indicate that the LGSCPSOA improves the search performance especially on the middle and large size benchmark functions significantly.

In this study, a velocity sharing historical best particle swarm optimization algorithm (VSHBPSO) and its variants are proposed to improve the performance of the original particle swarm optimization (PSO). The shared information in the improved algorithms includes the historical best position of each particle searched in the previous experiments, the updated velocity and the present global best position. An orthogonal design trial is conducted to discuss the parameters of the proposed algorithms by using 10 non-linear functions with different dimensions. Furthermore, the performance of the new algorithms is evaluated. Experimental results show that the novel algorithms can derive better solutions than the PSO algorithm and indicate their effectiveness in optimizing non-linear functions. Finally, the proposed algorithm is applied in soft sensing the outlet ammonia content in the ammonia synthesis process. The VSHBPSO-based soft sensor is found to be effective in the real-time assessment of ammonia content.

In this paper, a self-government particle swarm optimizer (SGPSO) is proposed to improve the performance of original PSO, in which particle updating depends on local best information searched at anterior runs as well as individual history best and global best at present. To evaluate the novel algorithm, some benchmark functions are employed in comparison with PSO. Experimental results show that the proposed algorithm can search more optimal solution than PSO and indicate the effectiveness of the novel algorithm to solve optimization problems. Finally, the proposed algorithm is applied in soft-sensing the Texaco furnace temperature. It is convinced that SGPSO based soft sensor is very capable of real-time assessment of the furnace temperature in the Texaco gasification process.

No abstract

No abstract