Applying Edge Analytics on Rotating Equipment for Predictive Maintenance.
- Jack Hancock: Solution Consultant, Rockwell Automation. Jack has 25 years of experience working in automation. He focuses on digital transformation for industrial companies with technologies like IIoT, Edge applications, Analytics, MES and DCS.
- Richard Resseguie: Product Manager, Analytics (AI & ML), Rockwell Automation.
In today's fast-paced and ever-changing industrial environment, minimizing operating costs and maximizing yield are critical to success. When plant equipment goes down due to a failure, both key performance indicators are impacted. Maintenance teams regularly rely on mature maintenance techniques that focus on scheduled maintenance planning and periodic equipment inspection to keep equipment running.
One of the most common industrial devices are AC induction motors which are frequently controlled by variable frequency drives (VFD). As VFD’s become increasingly intelligent and AI technology evolves. new maintenance techniques have emerged to predict failures prior to their occurrence.
Today’s topic will explore the concepts of motor current signature analysis (MCSA) and how AI can interpret it. Using a machine learning based supervisory application, we can establish a baseline of each asset’s behavior under normal operating conditions. Then, it monitors the assets for any deviation from baseline. Once a deviation is detected, a notification can be sent to maintenance which can include the anomalies first principle faults like: angular misalignment, bearing fault, flow restrictions, cavitation and others depending on the application.