Plastics Processing Machine Learning and Artificial Intelligence Framework Launched

Oden says its new offering stands in contrast to most (ML) systems available to plastics manufacturers, which Oden notes are not developed specifically for manufacturing; require customization; don’t operate in real-time; and can’t be deployed straight into production.

In contrast, Oden says its ML and AI framework is open, utilizing algorithms and data science tools specifically developed for extrusion and injection molding. This allows manufacturers, for instance, to take preventative actions to avoid machine failure, eliminate waste, and optimize production in real-time.

Oden says this new offering applies a patent-pending infrastructure that spans both the cloud and the “edge”. In this context, Oden’s VP of Data Science, Deepak Turaga, said “edge” refers to the use of low-power sensing and computing devices that are embedded within the manufacturing environment, close to the end-users. “With this framework, we are able to deploy ML applications all the way at the edge, i.e. on these lower power computing devices, so that mission-critical applications should continue to function even in the case of unreliable network connectivity to the cloud,” Turaga told Plastics Technology.

Oden’s ML and AI framework is tailored specifically for manufacturing processes. Turaga said this is accomplished with manufacturing algorithms specifically for data capture, cleaning and preparation; modeling and analysis; and result presentation and validation.

The framework can be used to continuously monitor manufacturing; predict quality and machine health; detect abnormal behavior; and provide recommendations on recipes and process settings.

In a release, Oden Technologies co-founder and CEO Willem Sundblad said, “The future of manufacturing demands intelligent systems that can provide real answers to the production issues manufacturers have been asking for decades. Only then can they achieve perfect production, with zero waste.”