Marsha, the reliability engineer, logs into IBM Maximo® APM - Health to determine which assets require her attention. She can dig into the potential problems of a specific asset and determine its cause and potential impact.

Marsha reviews the health of key assets to understand factors contributing to poor performance, including temperature, vibration, life expectancy, and predicted survival rate. She can do this in near real-time in the dashboard rather than having to export data into a spreadsheet for manual analysis. She can then update the workstreams back into her enterprise asset management system.

Marsha created customized, visual dashboards to remotely monitor critical assets and bad actors. She uses AI-powered anomaly detection to generate meaningful alerts, eliminate false-positives, and better understand failure factors.

Once Marsha understands the key factors contributing to an asset’s poor health, she can dig deeper into the predictive maintenance to see the current failure probability, expected failure date, and key drivers. She quickly gains insights by using existing pre-built analytics models such as days to failure, failure probability, and factors contributing to failure to find correlations in the data.

Marsha can then compare the predicted failure date against the next preventive maintenance date. If the asset is predicted to fail before the next scheduled maintenance, she can expedite that repair by executing a work order and dispatching a repair technician.