This presentation covers how Duke Energy's Monitoring & Diagnostic Center utilizes over 11,000 Advanced Pattern Recognition and Predictive Analytics software models to monitor the condition of over 40,000 MW (87%) of their power generation fleet. The focus of the presentation is to share key insights in terms of people, process and technology, and lessons learned from the 10+ year journey in successfully implementing the program.
Topics addressed will include:
• Evolution of Duke's monitoring and diagnostic center
• Case studies with showing predictive catches of asset failure
• How to develop and sustain management support of the program
• Maximizing reliability with digital transformation.
“R.A.I.” the Reliability.aiTMChatbot
You can ask "R.A.I." anything about maintenance, reliability, and asset management.