This study demonstrates improved tracking accuracy using neural network control in precision toolposts, suggesting advancements in positional feedback systems.
A nano-metric precision toolpost is designed and fabricated based on piezo-electric actuator. The toolpost positioning system has single degree of freedom. A capacitive gap sensor with less than 1 nm resolution is used for position feedback. The closed loop controller is implemented using C-language on a 486-IBM PC compatible computer and 16-bit A/D and D/A converter card. The output of the D/A converter is amplified by a specially designed high voltage amplifier. Two different classes of control algorithms are tested: 1. PID, 2. CMAC neural network control algorithms. The closed loop system has about 2 nm positioning accuracy and a bandwidth of about 250 Hz. The CMAC algorithm improved the tracking accuracy compared to PID algorithm. The steady state accuracy of both algorithms were same due to the fact that the accuracy is limited by the sensor resolution in steady state.
No takes yet. Share an insight, caveat, or question.
Pinsopon et al. (1995) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: