Output feedback neurolinearization.
Output-feedback neurolinearization as a new method in model independent input/output linearization has been developed. In this method input-output linearization is done only based on the input-output data of the system. The performance of this new method is compared to the global linearizing control (GLC) and to a conventional PI controller. The systems selected for comparison purposes are temperature control of a CSTR reactor and pH control in a neutralization process. Output feedback neurolinearization, outperforms the other controllers both in setpoint tracking and disturbance rejection. The other important advantage of Output Feedback Neurolinearization is the fact that it does not depend upon the process model at all.
Journal Article↗