[2E1] Digital transformation in condition monitoring and predictive maintenance yields financial benefits from improved engineering context, holistic condition and operational monitoring, analytical automation and system integration
P Johnson
Cutsforth Inc, USA
Condition monitoring is automating, and predictive maintenance is becoming more digital.
Equipment context, such as nameplate data, equipment performance expectations and equipment design data, is more digital. This contextual data yields physics-based models of failure. Condition monitoring technologies now automatically collect inspection data from all technologies including vibration, motor current, lubrication, temperature and more. Analytics automatically look for signs of equipment defects, based on the likely and probable failure modes. When coupled with the plant data historian, process and operational data supplements condition monitoring data to enable anomaly detection and advanced pattern recognition.
Maintenance is predictive as trend analysis combines early defect detection, rate of change and likely failure mode. Connection with the maintenance management system generates a work request calling on digital maintenance job plans. Subject matter experts spend more time on identified problems and less on data collection and common analysis tasks. Early detection and planning eases supply chain constraints. Improvements include reduced maintenance costs, higher equipment availability, lower energy costs and extended equipment lifecycle.
Case studies are used to illustrate concepts.
Equipment context, such as nameplate data, equipment performance expectations and equipment design data, is more digital. This contextual data yields physics-based models of failure. Condition monitoring technologies now automatically collect inspection data from all technologies including vibration, motor current, lubrication, temperature and more. Analytics automatically look for signs of equipment defects, based on the likely and probable failure modes. When coupled with the plant data historian, process and operational data supplements condition monitoring data to enable anomaly detection and advanced pattern recognition.
Maintenance is predictive as trend analysis combines early defect detection, rate of change and likely failure mode. Connection with the maintenance management system generates a work request calling on digital maintenance job plans. Subject matter experts spend more time on identified problems and less on data collection and common analysis tasks. Early detection and planning eases supply chain constraints. Improvements include reduced maintenance costs, higher equipment availability, lower energy costs and extended equipment lifecycle.
Case studies are used to illustrate concepts.
