The Centre for Modelling & Simulation (CFMS) and the National Composites Centre (NCC) are working to demonstrate the integration of predictive machine learning to drive improvements and minimise variability within a composites manufacturing process.
The collaborative project, Computer Learning in Automated Manufacturing Processes, (CLAMPS) has resulted in a physical demonstrator at the NCC, which automatically adjusts the manufacturing process parameters to ensure consistently high-quality parts. The project highlights the digitalisation and automation steps necessary for incorporation into a liquid composite moulding process to reduce the need for rework, scrap, or repair, ultimately saving costs.
The ability to detect and control defect formation is based on the output of over 15,000 virtual manufacturing simulations of a liquid composite resin infusion process. A machine learning algorithm has been used to process the data and classify the decisions made during the infusion process to minimise the formation of porosity and dry-spot defects. In the physical manufacturing process, the flow of resin is monitored using intelligently positioned sensors, enabling a real-time understanding of the flow inside a closed mould. The machine learning model developed from the virtual manufacturing simulations, will be used to predict and mitigate the formation of defects by selectively opening and closing inlet and outlet valves to influence the flow of resin.
The project is a proof-of-principle for the application of machine learning to control a composites manufacturing process. It has the potential to be upscaled to complex composite part geometries for industries including aerospace, automotive and renewables.
Giuseppe Dell’Anno, Chief Engineer at the NCC, explains that “many composites manufacturing processes require the intervention of experienced engineers to overcome process and material variability. In this demonstration, the in-process decision making is being automated, using digital process modelling and advanced machine learning techniques. The NCC and CFMS are helping to bring the composites industry one step closer to intelligently automated production.”
For CFMS, the project embodies the company vision of its neutral, digital test bed being used by organisations to explore the potential for improvements and accelerated development cycles in the design and manufacturing process. Sam Paice, Chief Operating Officer at CFMS comments, “The automation and digitalisation of complex industrial design and manufacturing processes will drive productivity and competitiveness for UK organisations.”
Organisations interested in learning further about the demonstrator, and applying the techniques to their own products and facilities are invited to register their interest in attending ‘Developing Smart Composites through Machine Learning’ event, hosted by CFMS and NCC, taking place 21st June 2018 at CFMS.