Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Distributed Fault Tolerance In Optimal Interpolative Nets, Daniel J. Simon
Distributed Fault Tolerance In Optimal Interpolative Nets, Daniel J. Simon
Electrical and Computer Engineering Faculty Publications
The recursive training algorithm for the optimal interpolative (OI) classification network is extended to include distributed fault tolerance. The conventional OI Net learning algorithm leads to network weights that are nonoptimally distributed (in the sense of fault tolerance). Fault tolerance is becoming an increasingly important factor in hardware implementations of neural networks. But fault tolerance is often taken for granted in neural networks rather than being explicitly accounted for in the architecture or learning algorithm. In addition, when fault tolerance is considered, it is often accounted for using an unrealistic fault model (e.g., neurons that are stuck on or off …
Dsp-Based Field-Oriented Step Motor Control, Daniel J. Simon, Dennis L. Feucht
Dsp-Based Field-Oriented Step Motor Control, Daniel J. Simon, Dennis L. Feucht
Electrical and Computer Engineering Faculty Publications
The SMC3 motor drive has been built using an Analog Devices ADSP-2101 digital signal processor (DSP). The SMC3 is designed to work with two-phase step motors, which are permanent magnet motors with many (typically 100) poles. The firmware in the SMC3 DSP drives the step motor phase windings using field-oriented control rather than using single steps. This method derives the maximum theoretical performance from the motor. This paper describes field-oriented control, and how the SMC3 hardware and firmware implements it.