An approach to improve flexible manufacturing systems with machine learning algorithms

摘要

The electricity consumption in the industry occupies considerable ratio in the gross electricity consumption compared with the consumption in other sectors e.g. residential, agriculture etc. One crucial solution to this problem is to optimize the production structure. The grand plan “Industry 4.0” provides a more adaptable and flexible perspective for the smart factory. The complexity of a manufacturing system, on the other hand, has been enhanced. Machine learning algorithms are a cluster of excellent approaches to control a complex system and to optimize a stochastic process. In order to improve the performance of a production system, it must be formulated to an executive model at first, then the optional control policies can be selected to cope with it. In this paper, the classification algorithm and the Q-learning algorithm have been implemented to reduce the electricity consumption in an automation system. The simulation results prove that they are capable for manipulating the multi routes transporting system and the system can performance better with the implementation of the machine learning algorithms.