Reliance Steel & Aluminum uses AWS IoT and Amazon SageMaker for predictive maintenance in industrial manufacturing

Reliance Steel & Aluminum Co. partnered with AWS and TensorIoT to implement an Industrial IoT and machine learning solution for predictive maintenance. Legacy industrial machinery was connected to the internet using IoT sensors and AWS IoT services to collect telemetry data. Data collected from sensors is ingested and analyzed using AWS IoT Analytics and Amazon SageMaker, which trains models to predict machine failures. The predictive maintenance approach reduces unplanned downtime and maintenance costs, improving operational efficiency. Amazon Cognito enables secure role-based access for device management and data access control.

Published
November 2019

Reported outcomes

Strategic outcomes

Scale & capacityReduced unplanned production downtimeCost efficiencyLowered maintenance costs through preventionSpeed & agilityImproved maintenance scheduling efficiencyRisk & complianceEnhanced industrial IoT security controls

Primary read

Use case focus

Showing 3 of 3

  • 1Predictive maintenance
  • 2Industrial IoT
  • 3Machine learning
  • High downtime and maintenance costs due to legacy machinery failures.
  • Need to improve operational efficiency and avoid production disruptions caused by machine breakdowns.
  • Connectivity challenge for older industrial machinery not designed for internet.
  • Data collection and analysis for actionable predictive maintenance insights.
  • Integration of IoT sensors with legacy industrial machines.
  • Utilization of AWS IoT Core, AWS IoT Greengrass, AWS IoT Analytics to manage data ingestion, processing, and storage.
  • Use of Amazon SageMaker to train and deploy ML models for fault prediction and preventive maintenance.
  • Creation of a secure feedback loop from machines to cloud enabling real-time monitoring and control.
  • Implementation of role-based access management with Amazon Cognito for secure device operation.
  • Reduced unplanned production downtime and higher machine uptime.
  • Cost savings through preventative maintenance before breakdowns.
  • Improved overall operational efficiency and maintenance scheduling.
  • Enhanced security and access controls in industrial IoT deployment.
Architecture

Architecture includes IoT sensors on legacy machines feeding data into AWS IoT Core and Greengrass, with AWS IoT Analytics for data processing and Amazon SageMaker for training ML models for predictive maintenance. Notifications are sent via Amazon SNS.

Implementation partners1
Sources & evidence1
Groundedness: 4/5

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Similar cases