Overnight, AWS made lots of product announcements at re:Invent 2021, and while lots of these are getting good coverage, I wanted to quickly bring everyone up to speed on what I think is the hidden gem of re:Invent - AWS IoT TwinMaker.
Before I started as Head of Enablement for AI Machine Learning and Data at Blackbook.ai and before I became an AWS Community Builder for Machine Learning, I was actually User Experience Lead and then Analytics Lead at a global IoT Proptech platform, so I've actually got heaps of experience with digital twins for facilities optimisation, and I've seen a lot when it comes to integrating disparate data sources in the built environment.
This is why I'm so excited about AWS IoT TwinMaker which is a new service which makes it faster and easier for developers to create and use digital twins of real-world systems to monitor and optimise operations.
Diagram from the AWS IoT TwinMaker Product Page:
Data from sources like equipment sensors, video cameras, and business applications is being collected and processed by all sorts of organisations about their equipment and facilities. In order to optimise industrial operations, improve production output, and improve equipment performance, most companies want to combine these disparate data sets to create a digital replica of their physical systems. This is called a Digital Twin. Although creating and maintaining Digital Twins may seem difficult and time-consuming, it doesn't have to be anymore.
With AWS IoT TwinMaker, you can quickly get started with creating digital twins of equipment, processes, and facilities. This is done by connecting data from different data sources like time series sensor data from equipment, video feeds from cameras, and maintenance histories from business applications. Importantly, You won't have to move the data into a single repository for this to work.
Building a Digital Twin Graph allows your operators to make better data-driven decisions by understanding and connecting all the sources of your data into a 3D application of the physical environment that displays data and insights in a spatial context.
There's built-in data connectors for services like AWS IoT SiteWise for equipment and time-series sensor data, Amazon Kinesis Video Streams for video data, and Amazon S3 for storage of visual resources like CAD files and data from business applications.
AWS IoT TwinMaker forms a digital twin graph that combines and understands the relationships between virtual representations of your physical systems and connected data sources, so you can intuitively and accurately model what's happening in your real-world environment.
Once you've built the digital twin graph, you can visualise the data using the context of the physical data using your existing CAD files or point cloud scans to make 3D models of your space.
Example from Github repo of AWS IoT TwinMaker Samples:
From here, you can then overlay video and sensor data overlays from your connected data sources as well as insights from connected machine learning or simulation services. But it's not just forecasts and projections, you can also add practical elements like equipment maintenance records and manuals to the digital twin which becomes your single source of truth.
AWS IoT TwinMaker is available today in preview in US East, US West, Europe and Asia Pacific, and this is again just a preview service so this list will grow. The AWS Free tier will include 50 million API calls per month for 12 months, so I'm excited to get building with this!
About the Author: Brooke Jamieson is the Head of Enablement - AI/ML and Data at Blackbook.ai, an Australian consulting firm specialising in AI, Automation, DataOps and Digital. Learn more about Blackbook.ai here and learn more about Brooke here.
Top comments (0)