School of Manufacturing and Mechanical Engineering (SMME), National University of Science and Technology (NUST), Sector H-11, Islamabad, Pakistan
The pheromone update phase in Ant Colony Optimization (ACO) has been addressed by various researchers in the context of scheduling problems. Various artificial intelligence (AI) techniques have also been used to investigate and improve the pheromone trail in worker assignment issue at the workshop floor level. This paper proposes a novel way of investigating and analyzing the issue of pheromone assignment through Neural Augmented Ant Colony Optimization (NaACO) technique. The technique thus developed has its roots in combining the strengths of Artificial Neural Networks (ANN) and the extra ordinary convergence capabilities of Ant Colony Optimization (ACO) thus formulating NaACO (Neural Augmented ACO). A set of hundred problems has been taken and an extensive methodology has been formulated to address the issue of pheromone updates in worker assignment on these problems. The results have been formulated and areas of future research have also been indicated.