[SEO Subhead]
This Guidance demonstrates how Eigen Industrial Vision integrates machine vision in addition to manufacturing process and quality data on every machine part. It shows how process parametric data from machines' programmable logic controllers (PLCs) and visual defects are used to build scalable machine learning (ML) models for predicting quality. With these insights, you can then take actions that prevent defective products by adjusting process controls to reduce or eliminate quality issues. You can also access, search, and compare quality results and process data to conduct root cause analysis.
Please note: [Disclaimer]
Architecture Diagram
[Architecture diagram description]
Step 1
Industrial devices at the plant level collect product quality data, such as parametric and visual data from in-line or end-of line inspection, and send data to edge gateways for processing.
Step 2
Manufacturing process data is also collected in sync with the product and production flow and sent to the edge gateways.
Step 3
Eigen Smart Modules (ESMs) connect to cameras, the control network, and the AWS Cloud. In disconnected scenarios, the following services allow for buffering data at the edge: Eigen Web Application (EWA) allows local configuration.
Eigen Video Application (EVA) processes streaming camera feeds, video processing, and inference. Eigen Virtual Render (EVR) provides 3D service. Eigen Alignment Service (EAS) supports part alignment and image stitching.
Step 4
ESMs communicate with the Eigen software-as-a-service (SaaS) platform on the AWS Cloud through HTTPS. All traffic is outbound only and routed through the Eigen.io domain to AWS.
Step 5
The Eigen SaaS platform receives events and camera data from edge locations and creates ML and predictive models. The trained models are pushed to the ESMs for edge inference.
Step 6
Users access the Eigen front-end app for advanced insights, quality causation analysis, search, labeling, historical data, and predictive parameters. All process data is correlated with machine vision data capture.
Step 7
Line operators, plant managers, and quality managers use the Eigen human machine interface (HMI) for near real-time results and predictive quality on the manufacturing line. Process experts analyze part quality and image data presented part over part.
Step 8
Production data from control network can be sent to AWS using the Industrial Data Fabric (IDF) (AWS IoT SiteWise and Amazon Simple Storage Service [Amazon S3]) and then can be pushed to Eigen through an AWS Lambda function invoking Eigen API.
Step 9
Manufacturing Execution System (MES) systems collect data from the control network and send it to the IDF using Amazon API Gateway.
Step 1
Industrial devices at the plant level collect product quality data, such as parametric and visual data from in-line or end-of line inspection, and send data to edge gateways for processing.
Step 2
Manufacturing process data is also collected in sync with the product and production flow and sent to the edge gateways.
Step 3
Eigen Smart Modules (ESMs) connect to cameras, the control network, and the AWS Cloud. In disconnected scenarios, the following services allow for buffering data at the edge: Eigen Web Application (EWA) allows local configuration.
Eigen Video Application (EVA) processes streaming camera feeds, video processing, and inference. Eigen Virtual Render (EVR) provides 3D service. Eigen Alignment Service (EAS) supports part alignment and image stitching.
Step 4
ESMs communicate with the Eigen software-as-a-service (SaaS) platform on the AWS Cloud through HTTPS. All traffic is outbound only and routed through the Eigen.io domain to AWS.
Step 5
The Eigen SaaS platform receives events and camera data from edge locations and creates ML and predictive models. The trained models are pushed to the ESMs for edge inference.
Step 6
Users access the Eigen front-end app for advanced insights, quality causation analysis, search, labeling, historical data, and predictive parameters. All process data is correlated with machine vision data capture.
Step 7
Line operators, plant managers, and quality managers use the Eigen human machine interface (HMI) for near real-time results and predictive quality on the manufacturing line. Process experts analyze part quality and image data presented part over part.
Step 8
Production data from control network can be sent to AWS using the Industrial Data Fabric (IDF) (AWS IoT SiteWise and Amazon Simple Storage Service [Amazon S3]) and then can be pushed to Eigen through an AWS Lambda function invoking Eigen API.
Step 9
Manufacturing Execution System (MES) systems collect data from the control network and send it to the IDF using Amazon API Gateway.
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
This Guidance uses Amazon Managed Grafana to monitor metrics that relate to operational performance and are configured to alert directly to teams on operational exceptions. Eigen has built-in custom metrics that are tracked to help ensure and measure operational performance. Additionally, Eigen streamlines resource management through automated job scheduling, enhancing responsiveness to varying demands.
-
SecurityRead the Security whitepaper
This Guidance uses AWS IAM Identity Center for single sign-on (SSO), protected by multi-factor authentication (MFA). IAM Identity Center simplifies user authentication, providing a seamless and secure log-in experience. Eigen uses IAM Identity Center for user access control, reducing the complexity of managing multiple credentials and improving overall system usability.
-
ReliabilityRead the Reliability whitepaper
This Guidance is implemented using a loosely-coupled architecture that leverages queues to help ensure data ingestion is scalable. Edge devices employ their own queues, allowing network interrupts to be queued and retried. This Guidance uses the following reliability-focused strategies:
- Amazon Simple Queue Service (Amazon SQS) queues are designed for scalable and reliable data ingestion. This design allows the system to handle varying data loads without compromising performance or reliability.
- Edge devices use their own queues, allowing network interrupts to be queued and retried. This mechanism helps ensure that interruptions or failures in data transmission are managed and retried systematically for improved reliability.
- All API calls are designed to be stateless and idempotent, reducing the risk of errors and promoting consistent behavior, even in the event of network interruptions or transient failures.
-
Performance EfficiencyRead the Performance Efficiency whitepaper
In this Guidance, Lambda enables serverless computing which allows for the ability to run code without the need for provisioning or managing servers. By utilizing Lambda functions, Eigen can automate tasks to ensure quick and efficient execution of operations, reduce latency, and enhance overall responsiveness.
-
Cost OptimizationRead the Cost Optimization whitepaper
This Guidance optimizes costs through AWS Cost Explorer, Lambda, and AWS Auto Scaling. AWS Cost Explorer enables users to perform regular bill analysis, helping them understand the cost breakdown of storage and compute resources. Lambda automates resource management and schedules the start and stop of compute resources based on predefined patterns. This serverless approach enhances efficiency and reduces costs by helping ensure that resources are active only when required. Additionally, AWS Auto Scaling allows for dynamic resource adjustments. The custom auto-scaling monitoring mechanisms respond to fluctuations in customer load by automatically scaling compute resources. This helps optimal performance during peak times, while minimizing costs during periods of lower demand.
-
SustainabilityRead the Sustainability whitepaper
Using Lambda functions, this Guidance helps ensures optimal compute resource allocation by stopping and starting resources based on predefined schedules. By efficiently managing compute resources based on demand, Lambda minimizes unnecessary energy consumption during idle periods. This approach ensures that resources are only active when needed, reducing overall energy consumption.
Additionally, serverless Lambda functions contribute to a more sustainable computing model. Serverless architectures, such as those employed by Lambda, enable optimal resource utilization by automatically scaling based on demand. This results in reduced energy usage compared to traditional server-based models.
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.