Statistics – Applications
Scientific paper
Feb 2004
adsabs.harvard.edu/cgi-bin/nph-data_query?bibcode=2004aipc..699..623w&link_type=abstract
SPACE TECHNOLOGY AND APPLICATIONS INTERNAT.FORUM-STAIF 2004: Conf.on Thermophys.in Microgravity; Commercial/Civil Next Gen.Space
Statistics
Applications
Spaceborne And Space Research Instruments, Apparatus, And Components, Reactor Control Systems
Scientific paper
Control law adaptation that includes implicit or explicit adaptive state estimation, can be a fundamental underpinning for the success of intelligent control in complex systems, particularly during subsystem failures, where vital system states and parameters can be impractical or impossible to measure directly. A practical algorithm is proposed for adaptive state filtering and control in nonlinear dynamic systems when the state equations are unknown or are too complex to model analytically. The state equations and inverse plant model are approximated by using neural networks. A framework for a neural network based nonlinear dynamic inversion control law is proposed, as an extrapolation of prior developed restricted complexity methodology used to formulate the adaptive state filter. Examples of adaptive filter performance are presented for an SSME simulation with high pressure turbine failure to support extrapolations to adaptive control problems.
No associations
LandOfFree
Restricted Complexity Framework for Nonlinear Adaptive Control in Complex Systems does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Restricted Complexity Framework for Nonlinear Adaptive Control in Complex Systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Restricted Complexity Framework for Nonlinear Adaptive Control in Complex Systems will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-1601379