Predictive maintenance is one of the most iconic use cases of IoT and industrial AI. While the productivity, operational efficiency, and cost saving benefits of predictive maintenance programs are easy to grasp, real life implementations are beset with false alerts, mis-calibrated algorithms, scaling issues, and poor ROI for monitoring asset portfolios. Maintenance planners and equipment operators need predictive insights they can trust to make smart decisions in the field.

Join this livestream to learn how C3 AI Predictive Maintenance is delivering in-field results at Shell, US Air Force, and others:

• Monitoring asset health based on telemetry data and using machine learning models for failure predictions, anomaly scores, and maintenance expense projections
• Enabling higher levels of availability by predictively managing failure risk of 100’s of thousands of assets, assemblies, and sub-assemblies
• Learning from individual asset failures and improving accuracy of failure predictions for the entire asset portfolio
• Enabling operators to create maintenance packages based on risk scores and launch work orders within work order management systems

Speakers:

• Kevin Thompson, Asset Information and Intelligence Leader, Duke Energy
• Steve Sundstrom, Vice President, Utilities, C3 AI
• Adrian Rami, Vice President, Applications, C3 AI