Adaptive Neural Network Control of Hard Disk Drives With Hysteresis Friction Nonlinearity

In this brief, an adaptive neural network (NN) friction compensator is presented for servo control of hard disk drives (HDDs). The existence of the hysteresis friction nonlinearity from pivot bearing, which is represented as the LuGre hysteresis friction model here, increases the position error signal of read-write head and deteriorates the performance of HDD servo systems. To compensate for the effect of the hysteresis friction nonlinearity, NN is adopted to approximate its unknown bounding function. With the proposed control, all the closed-loop signals are ensured to be bounded while the tracking error converges into a neighborhood of zero. Comprehensive comparisons between the conventional proportional-integral-derivative control (without friction compensator) and the proposed adaptive NN control (with friction compensator) are provided in experiment results. It is shown that the proposed control can mitigate the effect of the hysteresis friction nonlinearity and improve the track seeking performance.