Improve Uptime and Asset Reliability
Challenge
A Fortune 500 biotechnology company, with a wide portfolio of medicines and diagnostics for chronic and life-threatening conditions, set a strategic priority to leverage AI / machine learning solutions to improve manufacturing asset reliability and optimize maintenance costs.
Prior to engaging C3 AI, production sites relied on conventional systems to monitor a critical biomanufacturing asset, centrifuges. However, site operators were inundated with alarms that captured only a small percentage of failures and provided only minutes of lead time prior to a failure event. As a result of unanticipated centrifuge failures, millions of dollars were lost due to interrupted operations and discarded products. The company searched for an AI-enabled solution that can predict impending centrifuge failures with more accuracy and more lead time to reduce unplanned downtime and maintenance costs.
Approach
In 12 weeks, the C3 AI team partnered with subject matter experts from the biotechnology company to configure the C3 AI Reliability application to monitor and predict impending failures of 3 centrifuges across 2 manufacturing plants.
With C3 AI Reliability, the biotechnology company can predict 93% of impending failures, take preventative action with 48x more lead time, and reduce false alarms by 80%, improving production margins with reduced downtime.
About the Company
- $60B+ annual revenue
- 15M+ patients worldwide
- 10+ manufacturing sites
Project Objectives
- Integrate and unify over 6 years of historical data from 6 disparate data sources
- Apply machine learning to predict centrifuge failures in advance
- Configure C3 AI Reliability user interface to surface AI insights and unified analytics for end users
Project Highlights
- 12 weeks from kickoff to pre-production application
- Integrated over 6 years of historical data from 6 enterprise IT systems
- Developed over 300 reusable analytics
- Tested over 500 machine learning model permutations
- Configured C3 AI Reliability application user interface