Compounding process optimization for recycled materials using machine learning algorithms

The sustainable manufacturing of goods is one of the factors to minimize natural resource depletion and CO2 emissions. In the last decade a big effort has been done to transition from linear economy to circular economy. This transition requires to implement re-manufacturing processes into the current industrial manufacturing framework, replacing the sourcing of raw materials by re-manufacturing technologies. However, this transition is very challenging since it requires the transformation of the companies and more specially their processes, from traditional to circular. To speed up this transformation, the use of tools provided by the 4th industrial revolution are crucial. In particular, the use of artificial intelligence techniques enables the optimization of the re-manufacturing processes and make those optimizations available to all the stakeholders. This paper presents an optimization system for re-manufacturing of recycled fiber through compounding processes with materials that come from composite waste or end of life of products. The proposed approach has been trained with the data collected from several experiments carried out with a compounding machine under different specifications, fiber reinforcement grades, and output material properties. The system will allow to set up a compounding machine for different types of reinforced plastics needless of setting point experiments. The algorithms have been tested with previously unseen scenarios and they have proved to be efficient for giving the optimal material characteristics.