State Space Parameters Estimation Using Online Genetic Algorithms †

Abstract

Abstract –Accurate on-line estimates of critical system states and parameters areneeded in a variety of engineering applications, such as condition monitoring, faultdiagnosis, and process control. In these and many other applications it is required toestimate a system variable which is not easily accessible for measurement, using onlymeasured system inputs and outputs.The classical identification methods, such as least-square method, are calculus-basedsearch method. They have many drawbacks such as requiring a good initial guess of theparameter and gradient or higher-order derivatives of the objective function aregenerally required also there is always a possibility to fall into a local minimum. In thispaper we develop on-line, robust, efficient, and global optimization identification forparameters estimation based on genetic algorithms. The simulation results show that theproposed algorithm is very fast to find and adapt the estimated parameters.