Sheet metal manufacturers currently face very long lead times because work spends up to 95% of the production time waiting between operations.
To address this inefficiency, this project will develop an AI-driven scheduling system that optimizes the release and sequencing of jobs across the entire production flow. By creating a digital twin of the factory and using a reinforcement learning agent to decide when and what to produce, the system will reduce idle waiting times by up to 50% and increase the machines’ productive time. The result will be significantly shorter order completion times, more efficient use of resources, and a pioneering example of smart, data-driven manufacturing in the sheet metal industry. The scheduling system will be demonstrated in the production process of Suplacon, an SME company specializing in the manufacturing of sheet metal components.