With its rich set of features and functions, PI Asset Framework (PI AF) is the preferred way for users to interact with their PI System data. However, the task of accurately identifying, classifying and naming massive amounts of individual PI Tags can be overwhelming. Subject matter experts, PI System administrators and other stakeholders can spend months researching and identifying unique assets, their various attributes and relationships to achieve the foundational naming convention and structure recommended for PI AF.
This session will review how one customer is using the Cascadence Asset Modeler (AM) to more rapidly and efficiently setup and maintain PI AF. Cascadence AM is a cognitive computing solution designed to dramatically accelerate a PI System customer’s transition from a flat PI Tag structure to the more robust and dynamic PI AF, giving industrial organizations a much more detailed description of equipment, their hierarchical relationships and associated metadata.
John has 20+ years of experience developing monitoring systems, gathering data, and using machine learning and predictive analytics to solve real-world problems—from improving efficiency to preventing system failures. His experience includes the oil and gas, energy, marine and aviation sectors in areas as diverse as advanced signal processing, artificial intelligence and machine learning through to big data architecture and analytics. Most recently John was Analytics Director for GE Oil & Gas. He has also held senior technology and product roles at Airbus and Rolls Royce. He holds a bachelor of engineering in Avionics from the University of Glasgow.