Sensor-Based Channel-Wise Remaining Useful Life Estimation and Multi-Threshold Maintenance Policy for Steel-Cord...

Area of Science:

• Mechanical Engineering
• Materials Science
• Industrial Maintenance

Background:

• Traditional steel-cord conveyor belt assessments rely on average damage indicators, which fail to capture spatially non-uniform degradation.
• This limitation hinders accurate condition assessment and maintenance planning.

Purpose of the Study:

• To develop a sensor-based, channel-wise framework for condition assessment and remaining useful life (RUL) estimation of steel-cord conveyor belts.
• To provide enhanced maintenance decision support by accounting for localized degradation patterns.

Main Methods:

• Utilized data from consecutive non-destructive diagnostic scans, representing the belt cross-section as active measurement channels.
• Employed an accelerating degradation model to estimate local damage intensity and channel-wise RUL.
• Introduced decision thresholds for refurbishment and critical removal, alongside cross-sectional indicators like critical zone width and life-uniformity measures.

Main Results:

• Demonstrated that localized degradation can necessitate earlier belt replacement than average indicators suggest.
• The framework provides channel-wise RUL, cross-sectional indicators, and cost-oriented interpretations of non-uniform degradation.
• Illustrated applicability using industrial conveyor belt data.

Conclusions:

• The proposed channel-wise framework offers a practical basis for condition-based maintenance and refurbishment planning.
• It enables more accurate RUL estimation by considering spatial degradation patterns.
• Facilitates future integration with loading-condition analysis and digital-twin diagnostics.