Applying a neural network to the adaptive control for JIT production systems

By applying a neural network (NN), this paper proposes an adaptive control system for the two types of just-in-time (JIT) production systems with unstable changes in demand. In the proposed system, a multilayer NN is applied to detecting the pattern change in the time series data on demand, and the detected pattern change is utilized for adjusting the buffer size in the JIT production systems. The performance of the proposed system is investigated and compared with that of the previous system by simulation experiments.