Authentise, a leader in data-driven workflow tools for additive manufacturing, and nebumind, a provider of visualization and analytics tools for manufacturing data, are collaborating on the integration of the nebumind digital twin tools into the Authentise Manufacturing Execution System (AMES).
nebumind produces ‘digital twin’ visualizations, which fuse machine parameters and sensor data with the original part geometry. The integration of these visualizations with AMES will help users identify problem zones of each part more easily and lead to less time intensive and more accurate inspections. In addition, real-time alerts generated by the nebumind system inside AMES will help the user address any deviations during the process, reducing waste.
“Additive users need to be able to review data at a single glance,” said Franz Engel, co-CEO at Nebumind. “To date all they are given is long and complex tables of sensor data that are difficult to make head or tail of. Thanks to the integration with AMES, we can get this data automatically and fuse it with the shape being produced. That way the user can see an instant heatmap of potential problem areas, and deep dive into every voxel to understand the underlying data if necessary. This view can help customers identify rework needs up to 10 times faster and reduce production rejects by up to 90%. Integrating this view with AMES makes sense, since that’s where production is managed, and data is held. We’re excited to be collaborating with Authentise to make the additive process more seamless and reliable for users.”
Since AMES already captures data from the machines and manages the printable geometry, the system passes this information on to nebumind automatically, saving the user from locating and uploading this information separately. The insight generated is appended to the existing AMES part report to ensure end-to-end traceability.
“We’re excited to be welcoming nebumind to the Authentise platform,” added Andre Wegner, CEO of Authentise. “Together we can accomplish the goal of a seamless, failproof additive process. The collaboration proves once again that trying to do so single-handedly leads to failure and harms customers. For years they have had to put up with sub-optimal data analysis, in