Rethinking Maintenance Terminology for an Industry 4.0 Future.

Area of Science:

• Engineering
• Computer Science
• Data Science

Background:

• Sensors and mathematical models have been utilized since the 1990s for system health assessment and anomaly detection.
• The Internet of Things (IoT) and cloud computing are enabling cost-effective data collection and democratizing prognostic health management (PHM) technologies.
• Industry 4.0 developments are transforming maintenance planning and execution towards predictive approaches.

Purpose of the Study:

• To demonstrate the need for revised maintenance terminology in the context of Industry 4.0.
• To propose new definitions for consistent evaluation of work management performance.
• To offer recommendations for improved detection of work related to PHM activities.

Main Methods:

• Case studies were employed to illustrate the limitations of current maintenance terminology.
• Analysis of maintenance work management metrics in the context of predictive and condition-based maintenance.

Main Results:

• Current metrics often fail to capture the value of proactive maintenance driven by PHM.
• A shift in maintenance is occurring, where work is initiated based on detected potential failures rather than after functional failure.
• Existing definitions of corrective work do not adequately encompass PHM-driven interventions.

Conclusions:

• Rethinking maintenance terminology is crucial for accurately measuring performance in an Industry 4.0 environment.
• Consistent definitions are needed to evaluate work management effectiveness for PHM-driven maintenance.
• Improved methods for identifying and tracking PHM-related maintenance tasks are recommended.