Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Algorithms (2)
- Learning systems (2)
- Least squares approximations (2)
- Neural networks (2)
- Optimal Control (2)
-
- Recursive functions (2)
- Aerospace Control (1)
- Approximate Analytical Guidance Schemes (1)
- Architecture (1)
- Backpropagation (1)
- Boundary-Value Problems (1)
- Closed Form Solutions (1)
- Control System Synthesis (1)
- Convergence of numerical methods (1)
- Cutting force identification (1)
- Dynamical System (1)
- Feed rate (1)
- Feedforward Neural Networks (1)
- Force measurement (1)
- Guidance Laws (1)
- Homing Missile Guidance (1)
- Homing Missiles (1)
- Hopfield Neural Nets (1)
- Hopfield Neural Networks (1)
- Identification (control systems) (1)
- Intercept Dynamics (1)
- Learning (Artificial Intelligence) (1)
- Least Squares Approximations (1)
- Linear Quadratic Optimal Control (1)
- Mackey Glass time series prediction problem (1)
- Publication
- Publication Type
Articles 1 - 10 of 10
Full-Text Articles in Mechanical Engineering
Identification Of Cutting Force In End Milling Operations Using Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu
Identification Of Cutting Force In End Milling Operations Using Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu
Mechanical and Aerospace Engineering Faculty Research & Creative Works
The problem of identifying the cutting force in end milling operations is considered in this study. Recurrent neural networks are used here and are trained using a recursive least squares training algorithm. Training results for data obtained from a SAJO 3-axis vertical milling machine for steady slot cuts are presented. The results show that a recurrent neural network can learn the functional relationship between the feed rate and steady-state average resultant cutting force very well. Furthermore, results for the Mackey-Glass time series prediction problem are presented to illustrate the faster learning capability of the neural network scheme presented here
A Recursive Least Squares Training Algorithm For Multilayer Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu
A Recursive Least Squares Training Algorithm For Multilayer Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu
Mechanical and Aerospace Engineering Faculty Research & Creative Works
Recurrent neural networks have the potential to perform significantly better than the commonly used feedforward neural networks due to their dynamical nature. However, they have received less attention because training algorithms/architectures have not been well developed. In this study, a recursive least squares algorithm to train recurrent neural networks with an arbitrary number of hidden layers is developed. The training algorithm is developed as an extension of the standard recursive estimation problem. Simulated results obtained for identification of the dynamics of a nonlinear dynamical system show promising results.
Improved Techniques For Manufacturing Layered Laminate Composite Materials, Michael D. Grabber
Improved Techniques For Manufacturing Layered Laminate Composite Materials, Michael D. Grabber
Opportunities for Undergraduate Research Experience Program (OURE)
An increasingly important class of engineering materials are known as fiber reinforced composite materials. They offer outstanding mechanical properties, unique flexibility in design, and ease of fabrication. Because of this, fiber reinforced composites are being found more and more in such diverse applications as aircraft, space vehicles, automobiles, sporting goods, and appliances.
The main objective of this research project was to develop a procedure for which high quality composite plates could be manufactured. The procedure needed to be able to accommodate materials of various thicknesses as well as various sizes. We also wanted the procedure to be versatile enough to …
Automation Of The Electrostatic Aerosol Classifier And The Continuous Flow Cloud Diffusion Chamber, Daron W. Dryer
Automation Of The Electrostatic Aerosol Classifier And The Continuous Flow Cloud Diffusion Chamber, Daron W. Dryer
Opportunities for Undergraduate Research Experience Program (OURE)
Analyzing cloud condensation nuclei through the use of a Continuous Flow Thermal Diffusion Cloud Chamber (CFD) and an Electrostatic Aerosol Classifier (EAC) can be very time consuming. An alternative to manually monitoring these devices is to automate the equipment, thus freeing personnel for other research as well increasing CCN data collection.
Automation of the EAC will be carried out by digital command through the use of a Quick Basic program. This program will be run from an IBM personal computer outfitted with a digital input/output board.
RS-485 Standard will also be incorporated into the Quick Basic program in order to …
Fabrication Of Composite Laminates With Embedded Pizo-Ceramic Sensors And Actuators, Todd Nelson Kelsheimer
Fabrication Of Composite Laminates With Embedded Pizo-Ceramic Sensors And Actuators, Todd Nelson Kelsheimer
Opportunities for Undergraduate Research Experience Program (OURE)
The purpose of the research project is to investigate the methods for embedding pizo-ceramic sensors and actuators in a composite ( a fiber reinforced epoxy matrix). The importance of these sensors and actuators is vital in controlling the vibration and excessive strain on a structure causing fatigue or failure. With the control of these instabilities by the actuator, proper performance of the structure is achieved. Most sensors and actuators are surface mounted because (1) The sensor can pick up the greatest strain on the surface of a structure. (2) The actuator can create a stronger moment to counter balance the …
A Computer Graphic Teaching Aid For The Synthesis Of Four-Bar Linkages, Sew K. Woon
A Computer Graphic Teaching Aid For The Synthesis Of Four-Bar Linkages, Sew K. Woon
Opportunities for Undergraduate Research Experience Program (OURE)
This project involves developing software for the use as a teaching tool in the classroom. The "four-bar linkage mechanism", often used in kinematic movement, is the main subject
The software provides a working environment to perform a graphical synthesis of a four- bar linkage to move one of the links through three specified positions in the plane. The construction process is facilitated by the built in kinematic intelligence so that the student can quickly and easily visualize the process. The construction lines are dynamically updated as the free parameters in the design are modified. This is particularly beneficial because it …
Experiences In The Integration Of Design Across The Mechanical Engineering Curriculum, Ashok Midha, J. M. Starkey, D. P. Dewitt, R. W. Fox
Experiences In The Integration Of Design Across The Mechanical Engineering Curriculum, Ashok Midha, J. M. Starkey, D. P. Dewitt, R. W. Fox
Mechanical and Aerospace Engineering Faculty Research & Creative Works
The Faculty of the School of Mechanical Engineering at Purdue University have effected a major change in the Purdue Mechanical Engineering program by integrating design throughout the curriculum. In doing so, a significant level of faculty interaction has been achieved as well. The goals of the curriculum revision are: (1) to improve student skills in how to solve open-ended design problems, (2) to reduce the core of the curriculum to allow flexibility in course selection, and allow time for solving design problems, (3) to improve student skills in team work and communications, and (4) to improve student skills in using …
Use Of Hopfield Neural Networks In Optimal Guidance, S. N. Balakrishnan, James Edward Steck
Use Of Hopfield Neural Networks In Optimal Guidance, S. N. Balakrishnan, James Edward Steck
Mechanical and Aerospace Engineering Faculty Research & Creative Works
A Hopfield neural network architecture is developed to solve the optimal control problem for homing missile guidance. A linear quadratic optimal control problem is formulated in the form of an efficient parallel computing device known as a Hopfield neural network. Convergence of the Hopfield network is analyzed from a theoretical perspective, showing that the network, as a dynamical system approaches a unique fixed point which is the solution to the optimal control problem at any instant during the missile pursuit. Several target-intercept scenarios are provided to demonstrate the use of the recurrent feedback neural net formulation.
Approximate Analytical Guidance Schemes For Homing Missiles, S. N. Balakrishnan, Donald T. Stansbery
Approximate Analytical Guidance Schemes For Homing Missiles, S. N. Balakrishnan, Donald T. Stansbery
Mechanical and Aerospace Engineering Faculty Research & Creative Works
Closed form solutions for the guidance laws are developed using modern control techniques. The resulting two-point boundary value problem is solved through the use of the state transition matrix of the intercept dynamics. Results are presented in terms of a design parameter.
Adaptive Critic Based Neural Networks For Control, Victor Biega
Adaptive Critic Based Neural Networks For Control, Victor Biega
Masters Theses
"Dynamic Programming is an exact method of determining optimal control for a discretized system. Unfortunately, for nonlinear systems the computations necessary with this method become prohibitive.
This project investigates the use of adaptive neural networks that utilize dynamic programming methodology to develop near optimal control laws. First, a one dimensional infinite horizon problem is examined. The first part of this thesis considers problems involving cost functions with final state constraints for one dimensional linear and nonlinear systems. It also investigates a two dimensional linear problem. In addition to these examples, an example of the corrective capabilities of critics is shown. …