Nonlinear system identification and control using state transition algorithm

摘要

By transforming identification and control for nonlinear system intooptimization problems, a novel optimization method named state transitionalgorithm (STA) is introduced to solve the problems. In the proposed STA, asolution to a optimization problem is considered as a state, and the updatingof a solution equates to a state transition, which makes it easy to understandand convenient to implement. First, the STA is applied to identify the optimalparameters of the estimated system with previously known structure. With theaccurate estimated model, an off-line PID controller is then designed optimallyby using the STA as well. Experimental results have demonstrated the validityof the methodology, and comparisons to STA with other optimization algorithmshave testified that STA is a promising alternative method for systemidentification and control due to its stronger search ability, fasterconvergence rate and more stable performance.