Real-time predictive maintenance for industrial production lines
A React and AWS application that watches bottle-manufacturing production lines in real time and predicts maintenance needs before a line goes down.
SPX Flow
Jan 2023 – Oct 2023
London, UK
Industrial & Manufacturing
The challenge
SPX Flow needed to monitor and predict sensor data in real time across production lines responsible for bottle manufacturing, to keep production optimized and get ahead of unplanned downtime.
The approach
Built a React-based application on AWS tracking live sensor data from bottle production lines
Used AWS Lambda functions, DynamoDB, GraphQL with Apollo Server, and Highcharts for real-time monitoring and visualization
Applied Amazon SageMaker for predictive maintenance models, streamlining part pre-ordering
The impact
Production teams see equipment health in real time instead of reacting to breakdowns after the fact
Predictive models informed part pre-ordering, shortening the time between a predicted failure and a replacement part on hand