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

Mechanical Engineering Commons

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

Articles 1 - 5 of 5

Full-Text Articles in Mechanical Engineering

A Recursive Least Squares Training Algorithm For Multilayer Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu Jun 1994

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.


Identification Of Cutting Force In End Milling Operations Using Recurrent Neural Networks, Q. Xu, K. Krishnamurthy, Bruce M. Mcmillin, Wen Feng Lu Jun 1994

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


Approximate Analytical Guidance Schemes For Homing Missiles, S. N. Balakrishnan, Donald T. Stansbery Jan 1994

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.


Experiences In The Integration Of Design Across The Mechanical Engineering Curriculum, Ashok Midha, J. M. Starkey, D. P. Dewitt, R. W. Fox Jan 1994

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 Jan 1994

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.