Application of ACO for pavements

November 19, 2007

Hi all.

Of late I have been working on my algorithm called GenACO with Prof. K. Sudhakar Reddy. I thought I should give you an insight into it.

Basically our aim is to determine the pavement layer modulus values and thickness values of the pavements using a back calculation approach using ACO. We know deflections of the pavement from a standard Falling Weight Deflectometer(FWD). We now need to calculate the pavement details so as to determine is life period of the pavement.

Here is a brief flowchart of the algorithm:

ACO Algo - Version 1.0

(Click on the thumbnail to enlarge)

We have been successful to complete this algorithm for three layers, for which it takes a time of approx 3 minutes. This accounts for every 1 sec sleep whenever the function for calculating the deflections is called. This is because I have to rewrite a file again and again whenever I need to find the deflections for a particular combination of the modulus values and thicknesses. If you happen to know how to send parameters directly to an executable file from Java or C++ or any other language, then please lemme know. It would be greatful to you forever.

Right now, we are working to extend this result for a pavement system of five layers. Though the result obtained for three layers is worth publishing (Right now under draft). I just believe there might be a catch in the algo here that will help us to achieve our goal for pavement systems more than 3 layers.

More on this later,

Shrey Modi.

Entry Filed under: Ant Colony Optimization, Genetic Algorithms, My Pen, Pavements, Project. .

1 Comment Add your own

  • 1. VJ  |  November 19, 2007 at 10:06 pm

    No comments….
    except that modi kuch gawd hai bhaai!!!!!

    Reply

Leave a Comment

Required

Required, hidden

Some HTML allowed:
<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <pre> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>

Trackback this post  |  Subscribe to the comments via RSS Feed


RSS Feeds

RSS A few good ideas

Recent Posts

Categories

Archives