Abstract: Optimization is necessary for the control of any manufacturing process to achieve better product quality, high productivity with low cost. The beltline moulding process is difficult task due to its low defects, making the material sensitive to reject. The efficient beltline moulding process involves the optimal selection of operating parameters to maximize the number of production while maintaining the required quality limiting beltline surface damage. In this research, objective is to obtain optimum process parameters which satisfies given limit, minimizes number of defects and maximizes the productivity at the same time. A recently developed optimization algorithm called particle swarm optimization is used to find optimum process parameters. Accordingly, the results indicate that a system where multilayer perceptron is used to model and predict process outputs and particle swarm optimization is used to obtain optimum process parameters can be successfully applied to beltline moulding process through Particle Swarm Optimization (PSO). Results obtained are superior in comparison with Genetic Algorithm (GA) approach.