Manufacturing flow time estimation using the model-tree induction approach in a dynamic job shop environment

We describe an application of a supervised learning method, namely, model-tree induction, for the estimation of flow time in a dynamic job shop. An attempt is made to incorporate transfer batching as order review and release policy in the simulation model, whereas much of previous research appears to have ignored the order-review and release policy. The computational evaluation performance shows that the prediction accuracy of the model-tree induction method is superior to traditional methods such as total-work-content method and the dynamic-total-work-content method in estimating the flow time. This research work has been carried out with an open-source software in order to demonstrate the use of machine learning tools by the resource-constrained small- and medium-enterprises in their decision making processes.