An improved artificial fish swarm algorithm and its application on system identification with a time-delay system

To remedy the low convergence rate and low optimization accuracy of the artificial fish swarm algorithm (AFSA), an improved artificial fish swarm algorithm (IAFSA) was proposed. In the improved algorithm, the artificial fish could adjust the vision and step and form a balance between the local search and global search by identifying the actual condition. Furthermore, when the artificial fish in the foraging behavior does not find a better position than the current location, it steps forward to the optimal artificial fish by introducing the guide behavior to improved algorithm. The results indicate that the improved algorithm has advantages such as convergence rate, optimization accuracy, and anti local extremum value. The improved algorithm was applied to the system identification with the time-delay model. This algorithm can obtain a precise mathematical model of the controlled object and acquire great identification accuracy in the case of external interference.