Once the objective function is defined, the next step is to solve it. The problem on hand will have many
combinations, owing to the fact that there are hundreds of components to place on each board. It will not be possible
to solve for all combinations and choose the best one. Thus a quicker and easier solution is to use GAs [1].
To solve the TSP using GA, the first step is to find a method for representing the solutions. Once the representation
scheme is decided, the GA will generate an initial population of solutions at random and then test each member of the
population against the objective function. The surviving members of the population reproduce by the mutation and
crossover process, and the cycle repeats until the solutions converge to a near optimal solution.
Future research will concentrate on developing the objective function and deciding on the various parameters of the
GA, to effectively solve the problem. Once the solution is obtained, it will be tested on the placement machine, and
validated. The robustness of the algorithm will be tested by applying the same algorithm for different boards’ i.e.
different placement positions.