3D Predictive Maintenance: Visualising IoT Data with AWS IoT TwinMaker and Matterport

Smart buildings and factories are increasingly relying on the power of sensors to gather valuable operational data and system health information. This data deluge not only boosts efficiency but also enables a shift from reactive, unplanned failures to predictive maintenance strategies, significantly reducing operational costs.

Operations managers and technicians in industrial settings like manufacturing lines, warehouses, and industrial plants are constantly striving to minimize downtime. While sensors and their measurements are valuable tools for predictive maintenance, isolating these measurements can hinder a comprehensive view. Maintenance teams focusing solely on individual sensor readings might miss crucial associations that would otherwise become apparent.

A single, unified view that presents assets in spatial context, consolidating measurements from multiple sensors, simplifies failure resolution and enhances predictive maintenance programs. In our previous blog, we introduced a solution for ingesting Amazon Monitron insights (AI/ML predictions based on sensor measurements) into a shop floor or work order system. This blog delves deeper into contextual predictive maintenance with Amazon Monitron, exploring its integration with AWS IoT TwinMaker to create immersive, three-dimensional (3D) spatial visualisations of your telemetry data. We also unveil an Amazon Bedrock-powered natural language chatbot that provides access to relevant maintenance documentation and measurement insights.

#

Use Cases and Benefits

By combining AWS IoT TwinMaker and Matterport, operations managers can leverage a 3D visualisation of their facility to monitor equipment status. This integration allows developers to combine existing data from multiple sources with real-world data, creating a fully integrated digital twin. Presenting information in a visual context enhances operator understanding and highlights potential problem areas, significantly reducing resolution times.

#

Key Components of the Solution

AWS IoT TwinMaker: This fully-managed service empowers developers to create digital twins of real-world systems. It provides:

Unified Data Access: Connects to diverse data sources, including operational data from sensors and industrial systems.

Entity Representation: Creates virtual representations of physical systems, defines their relationships, and connects them to relevant data sources.

Immersive 3D Visualisation: Combines existing 3D models with real-world data to create interactive 3D representations of physical environments.

Matterport: Matterport offers solutions for capturing and scanning real-world environments to generate immersive 3D models (known as Matterport spaces). AWS IoT TwinMaker seamlessly integrates with Matterport, enabling the import of these spaces into your AWS IoT TwinMaker scenes. Matterport is readily accessible to AWS customers via the AWS Marketplace.

#

Solution Overview: Creating a Contextual Digital Twin

To create an AWS IoT TwinMaker workspace connected to a Matterport space, follow these steps:

1. Connect Matterport to AWS IoT TwinMaker: Link your Matterport account and spaces to AWS IoT TwinMaker.
2. Associate Sensor Locations with Entities: Tag sensor locations within your Matterport space and associate these tags with AWS IoT TwinMaker entities.
3. Create an AWS IoT TwinMaker Data Connector: Utilize an AWS Lambda function to create a custom data connector that associates entities with Monitron sensor insights stored in an Amazon S3 data lake.
4. Visualise Monitron Predictions in 3D: Leverage the AWS IoT Application Kit to visualise your Monitron predictions within the spatial 3D context of your Matterport space.

Figure 1: This diagram provides a high-level overview of the solution architecture.

#

Prerequisites

Before embarking on this journey, ensure you have the following:

An active GitHub account with login credentials.

An AWS account with an AWS user.

AWS IAM Identity Center (successor to AWS Single Sign-On) deployed in either the US-East-1 (N. Virginia) or EU-West-1 (Ireland) Regions.

Amazon Monitron (sensors and gateway) - Refer to the Getting Started with Amazon Monitron documentation.

A smartphone running either iOS (iOS 14.0.0 or later) or Android (version 8.0 or later) with the Monitron mobile app installed (available on iTunes or Google Play).

An enterprise-level Matterport account and license, essential for AWS IoT TwinMaker integration. For detailed instructions, consult the AWS IoT TwinMaker Matterport integration guide. If needed, contact your Matterport account representative for assistance. If you don't have a representative, use the Contact us form on the Matterport and AWS IoT TwinMaker page.

Note: Ensure all deployed AWS resources reside within the same AWS Region. Links provided for AWS Management Console access point to the us-east-1 region. If using another region, you might need to switch back after following a console link.

#

Data Lake Setup and ETL Pipeline

Follow the instructions outlined in Part 1 of this blog series to build an IoT data lake from Amazon Monitron's data. The Understanding the data export schema documentation provides the Monitron schema definition.

Note: Live data exports enabled after 4th April 2023 utilise the Kinesis Data Streams v2 schema. Existing data exports enabled prior to this date adhere to the v1 format. We recommend using the v2 schema for this solution.

#

Creating the AWS IoT TwinMaker Data Connector

This section guides you through the creation of a sample AWS IoT TwinMaker custom data connector that connects your digital twins to the data in your data lake. No data migration is required before utilising AWS IoT TwinMaker. This data connector comprises two Lambda functions invoked by AWS IoT TwinMaker to access your data lake:

TWINMAKER_SCHEMA_INITIALIZATION: Retrieves the schema of your data source, enabling AWS IoT TwinMaker to identify the different data types available.

TWINMAKER_DATA_READER: Queries data from your data lake based on requests received from AWS IoT TwinMaker.

Note: All code references in this blog can be found in the GitHub repository under this link.

#

Creating AWS IoT TwinMaker Components and Entities

If you haven't already created an AWS IoT TwinMaker workspace, follow the instructions in the Create a workspace procedure. The workspace serves as a container for all resources created for your digital twin.

#

3D Visualisation of Your Physical Environment

After creating entities in AWS IoT TwinMaker, associate a Matterport tag with each entity (for information on Matterport, see Matterport's documentation on AWS IoT TwinMaker and Matterport). Adhere to the AWS IoT TwinMaker Matterport integration documentation to link your Matterport space to AWS IoT TwinMaker.

#

Viewing Your Matterport Space in Your AWS IoT TwinMaker Dashboard

Once your Matterport space is imported into an AWS IoT TwinMaker scene, you can view it in your Amazon Managed Grafana dashboard. If you've already configured Amazon Managed Grafana with AWS IoT TwinMaker, you can open the Grafana dashboard to access your scene with the imported Matterport space.

#

Conclusion

This blog outlined a solution leveraging the AWS IoT TwinMaker service to connect data from Amazon Monitron, creating a unified view of telemetry data visualised in a 3D representation within a Matterport space. Monitron provides predictive maintenance guidance, while AWS IoT TwinMaker enables the 3D visualisation of this data. This solution presents data contextually, enhancing operational response and maintenance.

Our final blog in this series - Build Predictive Digital Twins with Amazon Monitron, AWS IoT TwinMaker and Amazon Bedrock, Part 3: Accessing Knowledge through GenAI Chatbot - extends the Digital Twin to utilise generative artificial intelligence (GenAI) interfaces (chatbots) and make information readily accessible.