Visual analytics and data science tools can be used to process historical sensor data to surface patterns that predict equipment stoppages. In the Energy sector, sensors attached to energy production equipment transmit readings on parameters like pump intake pressure, current, and temperature.

Accumulated data can be analyzed to produce models correlating parameter changes to equipment problems. These models can be deployed to operations and new sensor data scored against them to flag potential issues for investigation before production is affected.

The same machine learning methods can be applied to other industries to maximize product yield and other use cases.

In this event, we describe the visual analytics, data science, and real-time stream processing capabilities of the TIBCO® Connected Intelligence portfolio for ongoing, real-time equipment management and production optimization.