Amazon Industrial Digitalization Platform

Summary

Discrete and process manufacturers constantly struggle to create integrated manufacturing systems using disparate automation systems within a facility. Amazon Web Services now provides a flexible and open solution for achieving effective holistic operations, from sensor to enterprise. The cloud-based architecture has the flexibility to integrate all automation and control into business operations to deliver manufacturing digitalization and the benefits of Industry 4.0. As AWS CEO Andy Jassy put it: “Companies who aren’t already reinventing themselves in some meaningful way are unwinding, whether they know it or not. The good news is, invention and reinvention is very doable if you’re intentional and focused on it.”

The AWS Industrial Digitalization reference architecture built on the Amazon Web Services (AWS) platform empowers manufacturing people to focus on optimizing factory operations with an integrated edge, on premise, and cloud infrastructure.  AWS is ideally positioned to provide this industrial digitalization architecture platform since they are not encumbered with legacy industrial automation architectures and are committed to open systems and standards. 

Leveraging the AWS Industrial Digitalization reference architecture enables users to improve manufacturing & production performance and profits based on their knowledge and know-how without having to design and maintain the entire platform. Over the last few years, I have talked with industrial automation people that have created their own plant historians and advanced analytics in process control applications using AWS, believing it is superior, more flexible, and lower cost than offerings from automation vendors.

The AWS open approach provides a large and growing ecosystem of partners leveraging a broad-based of knowledge, knowhow and creativity. This is important because the best platforms and technologies become a true center of gravity in a large ecosystem. 

“Customers I have spoken with are excited about the launch of AWS for Industrial because its gives them options to both buy and build purpose-built services and solutions, while also having access to the widest ecosystem of partners,” said Doug Bellin, head of smart factory for AWS. “We are taking pre-built capabilities with partners on top of our customers’ existing systems, as well as AWS services to create new capabilities that can help them achieve impactful improvements in operational efficiency, quality and agility. AWS for Industrial simplifies the process of locating, building and deploying these innovative IoT, AI/ML, analytics and edge solutions.”

Competitive imperative

Digital disruptions are very real, and manufacturers that aspire to survive and thrive in a competitive world need to transform by leveraging technology. Manufacturing companies are becoming more aware of the need to modernize production methods and automation to compete globally, but many still find themselves stuck in a sunk investment trap locked into industrial automation architectures. This focus on past investment could ruin their production competitiveness jeopardizing their future.  

Digitalization investments to achieve superior manufacturing competitiveness should be a conscious strategic business decision, within the framework of world manufacturing competition, not based on existing sunk costs.   Manufacturers in developing economies logically have a key advantage in this area, since they are typically not burdened with legacy automation system providing an opportunity to leapfrog competition.

Manufacturing digitalization to achieve superior operations in the future to be competitive requires a system-level analysis and design of manufacturing. The Industry 4.0 initiative clearly describe this approach. Many point to Henry Ford as the father of the third Industrial Revolution who rethought the manufacturing process at a systems level and the Model T crushed competitors with market share surging from 9 percent in 1908 to 61 percent in 1921. Manufacturers are at this type of crossroad today.

AWS open source commitment

Since its inception, Amazon Web Services (AWS) has been committed to open-source software supporting projects, foundations and partners.

Digital manufacturing business integration

The AWS platform provides a means for manufacturing companies to achieve digital manufacturing business integration from sensor to enterprise. Effective manufacturing digitalization requires efficient integration of traditional silos to achieve the benefits of Industry 4.0. Leveraging AWS Smart Factory - Manufacturing Operations in the Cloud empowers users to focus on optimizing manufacturing and process operations efficiency and profit improvement not on the infrastructure needed to make it happen.

AWS Moderna pharmaceutical application

Moderna Therapeutics applied AWS offerings to build a connected, intelligent biopharmaceutical manufacturing and supply chain system including artificial intelligence, machine learning, and data analytics. This was accomplished in a 200,000-square-foot Good Manufacturing Practices (GMP)–compliant manufacturing facility utilizing SAP S/4HANA and AWS services to facilitate a “batch of one” production facility. It recently won the ISPE Facility of the Future Award for Moderna’s highly automated digital enterprise to seamlessly integrate and orchestrate systems.

Video 2019 ISPE Facility of the Year Awards Category Winner for Facility of the Future - Moderna, Inc.

Novartis & AWS

In December 2019, Amazon Web Services (AWS) announced a strategic collaboration with Novartis to accelerate digital transformation of its business operations to build an enterprise-wide data and analytics platform to transform the way medicines are manufactured and delivered. Starting within Novartis Technical Operations, this multiyear alliance aims to put real-time analytics in the hands of associates, empowering them to make better business decisions and increase efficiencies across manufacturing processes and supply chain.

Video: Novartis Collaboration with AWS to accelerate digital transformation

AWS re:Invent video on demand.

New AWS building blocks

During re:Invent 2020, Amazon Web Services announced five new machine learning services to improve operational efficiency, quality control, security and workplace safety. The services combine sophisticated machine learning, sensor analysis and computer vision capabilities.

Predictive Maintenance - Amazon Monitron 

Amazon Monitron delivers an off-the-shelf end-to-end machine monitoring system that can be easily applied without analytic and machine learning knowledge by anyone including maintenance people, engineers and managers. Monitron is comprised of sensors, a gateway, and a machine learning service to detect anomalies and predict when industrial equipment require maintenance. The IoT sensors capture vibration and temperature data, the gateway to aggregates and transfers data to AWS, and a machine learning cloud service that detects abnormal equipment patterns and deliver results in minutes with no machine learning or cloud experience required.   

Amazon Monitron can be used on a variety of rotating equipment, such as bearings, motors, pumps and conveyer belts in industrial and manufacturing settings. Amazon Monitron also includes a mobile app for a customer’s onsite maintenance technicians to monitor equipment behavior in real time. With the mobile app, a technician can receive alerts of any abnormal equipment conditions across different machines, check up on the health of the machine, and decide if they need to schedule maintenance. Monitron Starter Kit: Gateway and 5 wireless sensors for $715. Additional sensors: 5-packs for $575. 

Amazon lookout for equipment 

Amazon Lookout for Equipment provides a way to send sensor data to AWS to build models and return predictions.  To get started, customers upload their sensor data to Amazon Simple Storage Service (S3) and provide the S3 location to Amazon Lookout for Equipment can also pull data from AWS IoT SiteWise, and works seamlessly with other popular machine operations systems like OSIsoft.

AWS Panorama–Computer Vision

AWS Panorama uses computer vision to improve industrial operations and workplace safety using existing video cameras. The AWS Panorama Appliance provides a new hardware appliance that allows organizations to add computer vision to existing on-premises cameras that customers may already have deployed. Customers start by connecting the AWS Panorama Appliance to their network. AWS Panorama Appliance is integrated with AWS machine learning services and IoT services to build custom machine learning models as well as run prebuilt machine learning models on their video streams.

The AWS Panorama Software Development Kit (SDK) enables hardware vendors to build new cameras that can run meaningful computer vision models at the edge.  

Amazon Lookout for Vision

Amazon Lookout for Vision is a machine learning (ML) service that spots defects and anomalies in visual representations using computer vision (CV). With Amazon Lookout for Vision, manufacturing companies can increase quality and reduce operational costs by quickly identifying differences in images of objects at scale. For example, Amazon Lookout for Vision can be used to identify missing components in products, damage to vehicles or structures, irregularities in production lines, miniscule defects in silicon wafers, and other similar problems. Amazon Lookout for Vision uses ML to see and understand images from any camera as a person would, but with an even higher degree of accuracy and at a much larger scale. Amazon Lookout for Vision allows customers to eliminate the need for costly and inconsistent manual inspection, while improving quality control, defect and damage assessment, and compliance. In minutes, you can begin using Amazon Lookout for Vision to automate inspection of images and objects–with no machine learning expertise required.

Thought & observations