Data modeling of the digital thread for intelligent sensing and device visualization
Up to
10x
The operational savings (maintenance downtime and energy consumption) scale with the number of connected data streams in the sampling patterns, e.g, an average 10% sampling ratio leads to a 10x speedup in computational rendering.
Unity Scene | Automated Work Order as viewed on the Microsoft HoloLens 2 by Chris Mulberry
The Industrial Metaverse
Rendering the digital thread relies on machine learning to reduce the computational complexity for on-prem and real-time applications by searching spatial metadata depending on the user-defined system health settings (high and low alarms)
Each data thread within the optimal sampling patterns is rendered as per usual by the application renderer, and the reconstruction algorithm finalizes the rendered feed based on the imported data sample sets. The reconstruction quality always follows the target quality, no matter how complex the project scene is.
Not all threads are created equal: Based on the integrated data model, thread rendering intelligently predicts which data points across the published streams and renders only those packets, significantly reducing computation cycles.
HAPPY CUSTOMERS DIGITALLY TRANSFORMED
Alongside trusted global brands
"My focus is on optimizing digital manufacturing processes across the entire product lifecycle. I strive to identify which key bottlenecks across the value chain can be positively impacted by emerging technology solutions (AR/IIoT/ML/5G) to contribute to higher productivity for OEMs and System Integrators.
CHRIS MULBERRY
Principal Field Applications Engineer
Vibed, Inc.
2261 Market Street #4582
San Francisco, CA
United States​​
Data modeling of the digital thread for intelligent sensing and
device visualization
​© 2024 Vibed, Inc. | All Rights Reserved | English