Dr. Brad Burchett | |

Dept. of Mechanical Engineering | |

Office: C-107 Moench Hall | |

Office Phone: 877-8929 | |

E-mail: bradley.t.burchett@rose-hulman.edu |

- a. Optimize cost functions using Genetic Algorithms
- b. Design Fuzzy Logic Controllers
- c. Design Neural Networks for pattern recognition and control
- d. Implement GAs, FL, and NNs in Matlab using the appropriate toolboxes.

- Matlab Fuzzy Logic and Neural Network Toolboxes
- Classic Unconstrained Optimization
- Genetic Algorithms
- Fuzzy Logic
- Neural Networks
- Gauss Pseudo-Spectral Optimal Control

No textbook is required, however the following references are suggested, most of which are freely available online:

*Computational Intelligence
in Control Engineering*, by Robert E. King, *Dekker*, 1999.
The book is currently out of print, however many used copies are available online. Chapters listed on the course calendar are from this book.

*Genetic Algorithms in Search , Optimization, and Machine Learning*,
by David E. Goldberg, *Addison Wesley,* 1989. Available in the Library

*Neuro-Fuzzy Control of Industrial Systems with Actuator Nonlinearities*, by Frank L. Lewis, Javier Campos, Rastko Selmic, SIAM Press, 2002.

*Robust Control Systems with Genetic Algorithms,* by Mo Jamshidi,
et al., *CRC Press,* 2003.

*Adaptive Fuzzy Systems and Control,* by Li-Xin Wang, *Prentice
Hall,* 1994.

Ben J.A. Krose, P.Patrick van der Smagt, An Introduction to Neural Networks, *Univesity of Amsterdam, Faculty
of Mathematics Computer Science* , January 1993.

S. N. Sivanandam, and S. N. Deepa, Introduction to Genetic Algorithms, Springer.

Steven C. Chapra, Applied Numerical Methods w/MATLAB, McGraw-Hill, 2012.

David Benson, A Gauss pseudospectral transcription for optimal control, *MIT Ph.D. Thesis*, 2005.

There is also a great deal of info on the web regarding Neural Networks. See the links page for these.

Five homework sets will be issued during the quarter. These problem sets are intended to deepen understanding of the material. The homework set grade is a substantial portion of the course grade and should be addressed accordingly.

Two projects will be assigned. These require significantly more effort than the homework sets, and as such count for 50% of the final grade.

Grades in ME 536 will be determined based on proficiency on Homework Sets, and Term Projects. and In-Class Quizzes. There are no exams in ME 536. The relative weighting of each graded event is shown below:

Homework Sets | 500 pts |

Term Projects | 500 pts |

Occasionally, students will be offered the opportunity to obtain extra credit points. These points are added to the student's total while the total points for the course remain at 1000.