Integration of process planning with scheduling by considering the manufacturing system's capacity, cost and capacity in its workshop is a critical issue. The concurrency between them can also eliminate the redundant process and optimize the entire production cycle, but most integrated process planning and scheduling methods only consider the time aspects of the alternative machines when constructing schedules. In this paper, a fuzzy inference system (FIS) in choosing
alternative machines for integrated process planning and scheduling of a job shop manufacturing system is presented. Instead of choosing alternative machines randomly, machines are being selected based on the machines reliability. The mean time to failure (MTF) values is input in a fuzzy inference mechanism, which outputs the machine reliability. The machine is then being penalized based on the fuzzy output. The most reliable machine will have the higher priority to be
chosen. In order to overcome the problem of un-utilization machines, sometimes faced by unreliable machine, the particle swarm optimization (PSO) have been used to balance the load for all the machines. Simulation study shows that the system can be used as an alternative way of choosing machines in integrated process planning and scheduling.
The Particle Swarm Optimization (PSO) method was originally designed by Kennedy and Eberhart in 1995 and has been applied successfully to various optimization problems. The PSO idea is inspired by natural concepts such as fish schooling, bird flocking and human social relations. Backpropagation (BP) is generally used for neural network training. It is very important to choose a proper algorithm for training a neural network. In this paper, we present a modified particle swarm optimization based training algorithm for neural network. The proposed method modify the trajectories (positions and velocities) of the particle based on the best positions visited earlier by themselves and other particles, and also incorporates population diversity method to avoid premature convergence. Experimental results have demonstrated that the modified PSO is a useful tool for training neural network.