Final Report for CS5611 (Fuzzy Sets: Theory and Applications):

Mine Dredger

§d¿ü³ó(g853907, ¹qºÓ¤@)
ªL¥Ã±ö(g853904, ¹qºÓ¤@)
³¯ÂE¸R(g853902, ¹qºÓ¤@)

Table of Contents

Abstract	Problem Definition	Data Set Description	Our Approach
Simulation Results	Conclusions	Computer Programs	Division of labor
References

Abstract

"Traveling salesperson problem" is a typical problem for searching the optimal path to reach each desired point . In some cases , we must not be passing through each point exactly , instead of being close to some accepted distance . This is a new trial to find a optimal path to make each point be in a accepted distance.

Problem Definition

Today , we are asked to sweep 50 mines that are randomly distributed in the sea plane. And our mine dredger has a magnetic equipment to clear all the mines which are in the circle area ( the center of the circle is located in the mine dredger and the radius is r). Then, we try to find a ring path to cover all the points.

Data Set Description

• The data set is randomly generated.

Approach

Our approach to this problem can be explained in two aspects:

• Mountain clustering...
• TSP with simulated annealing...

Simulation Results

• Input selection:

This involves forming a grid on the data space where the intersections of the grid lines constitute the candidates for centers. A finer gridding increases the number of poential centers,but it also increases the compution required.

• Training method:

• Selects the grid points which include maximum numbers of mine.
• Simulated Annealing: The third step substitutes such points into TSP program which uses simulated annealing(SA).
• Simulation Results:

• Mountain construction with the corresponding numbers of mine:



• Distribution of mines and the centers which include maximum numbers of mine:(sweeping radius=0.5)

• Comparesions with the mountain clustering



• The path using TSP program:



Concluding Remarks and Future Work

• Concluding Remarks:

Extending traveling salesperson problem to solve some routine work is achived.

• Future Work:

Computer Programs

• The computer program for this project is available at mount26.m .

Division of Labor

• §d¿ü³ó: MATLAB Coding, simulation ,discussion
• ªL¥Ã±ö: Project presentation, report writing,discussion
• ³¯ÂE¸R: Idea providing, discussion

References

• [Jang97] J.-S. R. Jang, C.-T. Sun, and E. Mizutani, `` Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence,'' Prentice Hall, 1997.