Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Publication
- Publication Type
Articles 1 - 5 of 5
Full-Text Articles in Entire DC Network
Theoretical And Experimental Application Of Neural Networks In Spaceflight Control Systems, Pavel Galchenko
Theoretical And Experimental Application Of Neural Networks In Spaceflight Control Systems, Pavel Galchenko
Doctoral Dissertations
“Spaceflight systems can enable advanced mission concepts that can help expand our understanding of the universe. To achieve the objectives of these missions, spaceflight systems typically leverage guidance and control systems to maintain some desired path and/or orientation of their scientific instrumentation. A deep understanding of the natural dynamics of the environment in which these spaceflight systems operate is required to design control systems capable of achieving the desired scientific objectives. However, mitigating strategies are critically important when these dynamics are unknown or poorly understood and/or modelled. This research introduces two neural network methodologies to control the translation and rotation …
Modeling And Control Of Fuel Cell-Battery Hybrid Energy Sources, Nima Lotfi
Modeling And Control Of Fuel Cell-Battery Hybrid Energy Sources, Nima Lotfi
Doctoral Dissertations
"Environmental, political, and availability concerns regarding fossil fuels in recent decades have garnered substantial research and development in the area of alternative energy systems. Among various alternative energy systems, fuel cells and batteries have attracted significant attention both in academia and industry considering their superior performances and numerous advantages. In this dissertation, the modeling and control of these two electrochemical sources as the main constituents of fuel cell-battery hybrid energy sources are studied with ultimate goals of improving their performance, reducing their development and operational costs and consequently, easing their widespread commercialization. More specifically, Paper I provides a comprehensive background …
Discrete-Time Neural Network Based State Observer With Neural Network Based Control Formulation For A Class Of Systems With Unmatched Uncertainties, Jason Michael Stumfoll
Discrete-Time Neural Network Based State Observer With Neural Network Based Control Formulation For A Class Of Systems With Unmatched Uncertainties, Jason Michael Stumfoll
Masters Theses
"An observer is a dynamic system that estimates the state variables of another system using noisy measurements, either to estimate unmeasurable states, or to improve the accuracy of the state measurements. The Modified State Observer (MSO) is a technique that uses a standard observer structure modified to include a neural network to estimate system states as well as system uncertainty. It has been used in orbit uncertainty estimation and atmospheric reentry uncertainty estimation problems to correctly estimate unmodeled system dynamics. A form of the MSO has been used to control a nonlinear electrohydraulic system with parameter uncertainty using a simplified …
Model Checking Control Communication Of A Facts Device, Bruce M. Mcmillin, J. K. Townsend, David Cape
Model Checking Control Communication Of A Facts Device, Bruce M. Mcmillin, J. K. Townsend, David Cape
Computer Science Faculty Research & Creative Works
This paper concerns the design and verification of a realtime communication protocol for sensor data collection and processing between an embedded computer and a DSP. In such systems, a certain amount of data loss without recovery may be tolerated. The key issue is to define and verify the correctness in the presence of these lost data frames under real-time constraints. This paper describes a temporal verification that if the end processes do not detect that too many frames are lost, defined by comparison of error counters against given threshold values, then there will be a bounded delay between transmission of …
Adaptive Neural Network Identifiers For Effective Control Of Turbogenerators In A Multimachine Power System, Ganesh K. Venayagamoorthy, Ronald G. Harley, Donald C. Wunsch
Adaptive Neural Network Identifiers For Effective Control Of Turbogenerators In A Multimachine Power System, Ganesh K. Venayagamoorthy, Ronald G. Harley, Donald C. Wunsch
Electrical and Computer Engineering Faculty Research & Creative Works
This paper provides a novel method for nonlinear identification of multiple turbogenerators in a five-machine 12-bus power system using continually online trained (COT) artificial neural networks (ANNs). Each turbogenerator in the power system is equipped with all adaptive ANN identifier, which is able to identify/model its particular turbogenerator and rest of the network to which it is connected from moment to moment, based on only local measurements. Each adaptive ANN turbogenerator can be used in the design of a nonlinear controller for each turbogenerator in a multimachine power system. Simulation results for the adaptive ANN identifiers are presented