Skip to main content
Open Access Publications from the University of California

UC Berkeley

UC Berkeley Electronic Theses and Dissertations bannerUC Berkeley

Direct and Indirect Adaptive Feedforward Repetitive Control of Servo Systems

  • Author(s): Shahsavari, Behrooz
  • Advisor(s): Horowitz, Roberto
  • et al.

Control methodologies for deterministic disturbance rejection and trajectory tracking have been of great interest to researchers in the fields of controls, mechatronics, robotics and signal processing in the past two decades. The applications of these methods span a wide range from satellite attitude control requiring an accuracy of a few meters, to positioning of the read/write head in hard disk drives with an accuracy of less than one nanometer. This dissertation addresses the problem of trajectory tracking and deterministic disturbance rejection in discrete time systems when the trajectory/disturbance is unknown, but can be realized as an a ne combination of known basis functions. Despite the prior work on this problem that assumes known and time invariant plant dynamics, we consider multi input single output systems with unknown dynamics. Moreover, we investigate the cases where the disturbance or system dynamics varies slowly or abruptly but infrequently. Within the broad class of disturbances/trajectories that satisfy the stated criteria, an elaborate study is conducted on periodic and superposition of multiple sinusoidal sequences. We propose two novel adaptive control methods for the aforementioned problem. The first scheme can be classified as an indirect adaptive algorithm since it consists of two parts, namely a system identification mechanism that provides a dynamic model of the closed loop system, and the adaptive compensator which deploys the aforementioned dynamic model to synthesize the control law. The second proposed method is a direct adaptive controller, meaning that the control law is generated directly and the stated separation is not possible.

Besides providing theoretical guarantees, we experimentally evaluate our algorithms on a challenging control task for nano-scale positioning of the read write head in a dual stage hard disk drive (HDD). Even with the advent of NAND ash based data storage devices, the HDD continues to thrive as the most cost effective, reliable solution for rewritable, very high density data storage. It remains a key technology particularly with the tremendously growing popularity of server based cloud computing and novel hybrid enterprise storage solutions. We described that the control methodologies that can address the problem under our study are crucial for Bit Patterned Media Recording which is one of the two breakthroughs in magnetic recording that have been immensely investigated in the past few years. Extensive computer simulations and implementation on a digital signal processor unit are performed to validate the effectiveness of our proposed algorithms in full spectrum compensation of the repeatable runout in dual stage HDDs. This application introduces unique control challenges since it requires estimating a very large number of parameters that is order(s) of magnitude greater than prior work and frequency contents span from 120Hz to extremely large values (above 20KHz) where the plant dynamic uncertainties are large.

Main Content
Current View