Drive innovation by implementing an industrial data strategy (MFG316)
Industrial Data Strategy and the AWS Industrial Data Fabric
Introduction
Steve Blackwell, the worldwide Tech lead for manufacturing at AWS, has been with Amazon for over 7 years and has experience in the manufacturing industry.
This session is a precursor to a more detailed chalk talk on industrial data and generative AI, which will be held the next day.
The Challenge of Industrial Data
Manufacturers have a vast amount of data from various core systems, including CRM, PLM, ERP, and MES/MOM systems, as well as industrial IoT data from PLCs and SCADA systems.
This creates a "data chaos" that manufacturers want to leverage, especially when dealing with quality issues that require data from multiple sources.
The Industrial Data Fabric (IDF) Framework
The IDF framework is an architectural framework with best practices and patterns to simplify the way manufacturers can make their data from various systems of record available in a contextualized way for different use cases.
The IDF framework has four layers:
Ingest: Bringing in data from various sources
Store: Storing data in multiple variations based on its life cycle
Contextualize: Associating data from different sources (e.g., IoT data, part data, and non-conformance data)
Act: Enabling the use of data for line-of-business users (e.g., triggering a maintenance workflow based on predictive maintenance insights)
Types of Industrial Data
Time series data: Data from PLCs, data historians, etc.
Structured data: Data from MES, PLM, ERP, and quality management systems
Unstructured data: Video, images, Excel files, CSV files, etc.
Data Lifecycle Management
Hot data: Data used in real-time for immediate decision-making (e.g., alerts, operator screens)
Warm data: Data used by manufacturing engineers and data analysts for analysis and queries (e.g., end-of-shift, end-of-week comparisons)
Cold data: Data used for data analytics, machine learning, and BI reporting
Bronze data: Raw, unprocessed data
Silver data: Curated data for specific use cases or problems
Gold data: Curated data for consumption by end-users (e.g., maintenance, production)
AWS Services for the Industrial Data Fabric
Hot data: AWS IoT SiteWise
Warm data: Amazon Timestream, Amazon RDS, and partner solutions like Hitachi
Reporting/Gold data: Amazon Redshift, partner solutions like Snowflake and Databricks
Conclusion
The Industrial Data Fabric framework provides a structured approach to managing and leveraging industrial data across the manufacturing value chain.
The chalk talk session the next day will go into more architectural details and include a live demo showcasing the end-to-end data flow and consumption.
These cookies are used to collect information about how you interact with this website and allow us to remember you. We use this information to improve and customize your browsing experience, as well as for analytics.
If you decline, your information won’t be tracked when you visit this website. A single cookie will be used in your browser to remember your preference.