[SEO Subhead]
This Guidance shows how you can improve failure predictions for large equipment and complex assemblies without requiring supervised machine learning (ML). Amazon Lookout for Equipment analyzes data from your sensors and systems—such as pressure, flow rate, revolutions per minute, temperature, and power—to automatically train a model specific to your equipment. This unique model can then identify early warning signs, pinpoint issues, and predict the magnitude of impact of a detected event. Your SAP system then creates maintenance notifications or measurement readings to help you proactively address the predicted event.
Please note: [Disclaimer]
Architecture Diagram
[Architecture diagram description]
Step 1
The manufacturing facility’s shop floor contains on-premises systems: a programmable logic controller (PLC), Supervisory Control and Data Acquisition (SCADA) systems, or tags that generate Internet of Things (IoT) sensor data.
Step 2
AWS IoT Core receives the messages containing sensor data and transmits the data stream to Amazon Kinesis Data Firehose.
Step 3
Kinesis Data Firehose delivers the data stream to an Amazon Simple Storage Service (Amazon S3) bucket.
Step 4
A trained Amazon Lookout for Equipment anomaly model inferences the data stream to predict failure or provide scheduled inferences. This model is originally trained with historical sensor and service data.
Step 5
When the inferences arrive in an Amazon S3 bucket, they invoke an AWS Lambda function, which checks for failure predictions at a component level.
If there are predictions, the Lambda function calls an API endpoint hosted by SAP Business Technology Platform (SAP BTP) with SAP API Management. The Lambda function interfaces with AWS Secrets Manager and Amazon DynamoDB to get lookup and credential values for payload and authentication.
Step 6
The SAP BTP Events-to–Business Actions framework provides a proxy endpoint to measurement documents, work orders, and notifications in the SAP system.
Step 7
A service order or notification gets created in the SAP S/4HANA system.
Step 1
The manufacturing facility’s shop floor contains on-premises systems: a programmable logic controller (PLC), Supervisory Control and Data Acquisition (SCADA) systems, or tags that generate Internet of Things (IoT) sensor data.
Step 2
AWS IoT Core receives the messages containing sensor data and transmits the data stream to Amazon Kinesis Data Firehose.
Step 3
Kinesis Data Firehose delivers the data stream to an Amazon Simple Storage Service (Amazon S3) bucket.
Step 4
A trained Amazon Lookout for Equipment anomaly model inferences the data stream to predict failure or provide scheduled inferences. This model is originally trained with historical sensor and service data.
Step 5
When the inferences arrive in an Amazon S3 bucket, they invoke an AWS Lambda function, which checks for failure predictions at a component level.
If there are predictions, the Lambda function calls an API endpoint hosted by SAP Business Technology Platform (SAP BTP) with SAP API Management. The Lambda function interfaces with AWS Secrets Manager and Amazon DynamoDB to get lookup and credential values for payload and authentication.
Step 6
The SAP BTP Events-to–Business Actions framework provides a proxy endpoint to measurement documents, work orders, and notifications in the SAP system.
Step 7
A service order or notification gets created in the SAP S/4HANA system.
Well-Architected Pillars
The AWS Well-Architected Framework helps you understand the pros and cons of the decisions you make when building systems in the cloud. The six pillars of the Framework allow you to learn architectural best practices for designing and operating reliable, secure, efficient, cost-effective, and sustainable systems. Using the AWS Well-Architected Tool, available at no charge in the AWS Management Console, you can review your workloads against these best practices by answering a set of questions for each pillar.
The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.
-
Operational ExcellenceRead the Operational Excellence whitepaper
Amazon CloudWatch lets you independently monitor each architecture layer and component for key performance indicators, with automated resolution for each managed service. This observability helps you focus on meaningful data to understand your workload's interactions and output.
-
SecurityRead the Security whitepaper
All the resources in this Guidance run within a VPC so that you can keep them separate from other resources. And, you can encrypt data at rest using AWS server-side keys. Additionally, Secrets Manager provides key rotation policies that you can use to store your SAP authentication information.
-
ReliabilityRead the Reliability whitepaper
Amazon S3, DynamoDB, and Lambda are serverless services and scale horizontally, automatically responding to the velocity of data ingestion and processing. The use of serverless services across multiple Availability Zones provides redundancy in the event of a failure in any single Availability Zone.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
Lookout for Equipment helps you detect abnormal equipment behavior by analyzing sensor data so that you can avoid unplanned downtime. With this service, you can accurately monitor sensor data and analyze historical maintenance trends to support workloads that are more scalable and efficient.
-
Cost OptimizationRead the Cost Optimization whitepaper
This Guidance uses highly available and serverless services like Amazon S3, DynamoDB, and Lambda, so you only pay for the resources you use. Features like Lambda warm starts and Amazon S3 Intelligent-Tiering help minimize compute and storage requirements and costs. You can further optimize costs by extracting only the business data group that you need and minimizing the number of implemented flows based on the granularity of your reporting needs.
-
SustainabilityRead the Sustainability whitepaper
Serverless services maximize overall resource utilization by only using compute when it is needed, reducing the overall energy required to operate your workloads. You can also use the AWS Billing Conductor carbon footprint tool to calculate and track the environmental impact of your workloads over time at the account, AWS Region, and service levels.
Implementation Resources
A detailed guide is provided to experiment and use within your AWS account. Each stage of building the Guidance, including deployment, usage, and cleanup, is examined to prepare it for deployment.
The sample code is a starting point. It is industry validated, prescriptive but not definitive, and a peek under the hood to help you begin.
Related Content
[Title]
Disclaimer
The sample code; software libraries; command line tools; proofs of concept; templates; or other related technology (including any of the foregoing that are provided by our personnel) is provided to you as AWS Content under the AWS Customer Agreement, or the relevant written agreement between you and AWS (whichever applies). You should not use this AWS Content in your production accounts, or on production or other critical data. You are responsible for testing, securing, and optimizing the AWS Content, such as sample code, as appropriate for production grade use based on your specific quality control practices and standards. Deploying AWS Content may incur AWS charges for creating or using AWS chargeable resources, such as running Amazon EC2 instances or using Amazon S3 storage.
References to third-party services or organizations in this Guidance do not imply an endorsement, sponsorship, or affiliation between Amazon or AWS and the third party. Guidance from AWS is a technical starting point, and you can customize your integration with third-party services when you deploy the architecture.