Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 6 of 6

Full-Text Articles in Engineering

Reinforcement-Learning-Based Output-Feedback Control Of Nonstrict Nonlinear Discrete-Time Systems With Application To Engine Emission Control, Peter Shih, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier Oct 2009

Reinforcement-Learning-Based Output-Feedback Control Of Nonstrict Nonlinear Discrete-Time Systems With Application To Engine Emission Control, Peter Shih, Brian C. Kaul, Jagannathan Sarangapani, J. A. Drallmeier

Electrical and Computer Engineering Faculty Research & Creative Works

A novel reinforcement-learning-based output adaptive neural network (NN) controller, which is also referred to as the adaptive-critic NN controller, is developed to deliver the desired tracking performance for a class of nonlinear discrete-time systems expressed in nonstrict feedback form in the presence of bounded and unknown disturbances. The adaptive-critic NN controller consists of an observer, a critic, and two action NNs. The observer estimates the states and output, and the two action NNs provide virtual and actual control inputs to the nonlinear discrete-time system. The critic approximates a certain strategic utility function, and the action NNs minimize the strategic utility …


Using Abet Assessment Requirements As A Catalyst For Change: Enhancing And Streamlining The Engineering Management Undergraduate Program At Missouri S&T, Stephen A. Raper, Susan L. Murray, Christa Moll Weisbrook, William Daughton Jun 2009

Using Abet Assessment Requirements As A Catalyst For Change: Enhancing And Streamlining The Engineering Management Undergraduate Program At Missouri S&T, Stephen A. Raper, Susan L. Murray, Christa Moll Weisbrook, William Daughton

Engineering Management and Systems Engineering Faculty Research & Creative Works

The Engineering Management (EM) undergraduate degree program at Missouri University of Science & Technology (formerly University of Missouri-Rolla) was the first program of its kind. The program started over 40 years ago and it is one of only five ABET accredited undergraduate EM programs [1]. The initial degree program included a senior year of management courses in conjunction with three years of courses in common engineering disciplines such as mechanical, electrical, and civil engineering. In the 1990s the program underwent a major restructure and students combined core engineering management classes with an emphasis area inside the department. Industrial, manufacturing, packaging, …


What New Faculty Need To Know, But Don't Know To Ask, Susan L. Murray, Elizabeth A. Cudney, Suzanna Long, Katie Grantham Jun 2009

What New Faculty Need To Know, But Don't Know To Ask, Susan L. Murray, Elizabeth A. Cudney, Suzanna Long, Katie Grantham

Engineering Management and Systems Engineering Faculty Research & Creative Works

A smooth transition to life at an academic institution and the surrounding community is essential to the professional careers of new faculty members. The transition begins during the hiring process and startup package negotiations. Once at an institution, aspects of academia including teaching, proposal writing, and the tenure process inevitably generate issues and concerns for new faculty members. Research has shown that mentoring new faculty members early in their academic career can have significant impact on professional success. This is especially true at a research-based institution where the demands of funded scholarship add an extra level of complexity. A survey …


Neural Network Control Of Mobile Robot Formations Using Rise Feedback, Jagannathan Sarangapani, Travis Alan Dierks Apr 2009

Neural Network Control Of Mobile Robot Formations Using Rise Feedback, Jagannathan Sarangapani, Travis Alan Dierks

Electrical and Computer Engineering Faculty Research & Creative Works

In this paper, an asymptotically stable (AS) combined kinematic/torque control law is developed for leader-follower-based formation control using backstepping in order to accommodate the complete dynamics of the robots and the formation, and a neural network (NN) is introduced along with robust integral of the sign of the error feedback to approximate the dynamics of the follower as well as its leader using online weight tuning. It is shown using Lyapunov theory that the errors for the entire formation are as and that the NN weights are bounded as opposed to uniformly ultimately bounded stability which is typical with most …


Multi-Objective Stochastic Heuristic Methodology For Tradespace Exploration Of A Network Centric System Of Systems, Atmika Singh, Cihan H. Dagli Mar 2009

Multi-Objective Stochastic Heuristic Methodology For Tradespace Exploration Of A Network Centric System Of Systems, Atmika Singh, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

System of systems (SoS) architecting techniques rely on traditional, static tools that were designed for classical stove-piped systems. There is a need for tools that can capture the complex adaptive nature of such SoS. An architecture search methodology using genetic algorithms and a fuzzy assessor was applied to the conceptual architecture design of a generic smart grid and a set of architectures with high fitness was obtained. This set of architectures is intended to serve as a starting point for a systems architect to ultimately be able to converge on the best system design. The SoS architecting process has largely …


Using Extensible Modeling In Systems Engineering And Architectural Search, Jason Paul Dauby, Cihan H. Dagli Jan 2009

Using Extensible Modeling In Systems Engineering And Architectural Search, Jason Paul Dauby, Cihan H. Dagli

Engineering Management and Systems Engineering Faculty Research & Creative Works

The system architecting process is the hierarchical reduction of ambiguity associated with user needs and system design. Design allocation, and subsequent integration, implicitly requires a mechanism by which levels of detail can be added and removed from a decision scenario. This paper addresses the idea of engineering model sharing through the concept of vertical and horizontal extensibility as one mechanism by which hierarchical reduction in ambiguity can be facilitated. Extensible modeling introduces a systems architecting approach to the modeling community by identifying model interfaces and carefully decomposing the model domain. While the actual system hardware is not known at the …