An improved neural networks with transient chaos method for job-shop scheduling problems

Having considered all the constraints of the job-shop scheduling problem (JSP), we present a new computational energy function of Hopfield neural networks for JSP. By introducing transient chaos and time-variant gain, an improved method to solve JSP by a neural network model with transient chaos is proposed, which can avoid Hopfield neural networks being sucked into local minima. The simulation results show that the modified method not only has the ability of searching for the global minimum, but can also converge to minimum quickly. More importantly, it can keep the steady output of neural networks as a feasible solution for JSP.