An integrated system for gear condition monitoring and predictive maintenance

The management and reliability analysis of gear-driven rotating equipment is critical for the mining industry. The current maintenance practice employs non-destructive inspection methods to perform the assessment of health status. However, the assessment requires the machine under inspection to be shut down for the duration of the inspection. The associated cost is high. An ideal solution for gear inspections would, therefore, allow the device under inspection to continue its normal operation, take frequent or continuous measurements on the gear, and reduce the frequency of travel required by inspectors to the testing site. This research is to develop such a solution by integrating online sensor monitoring and offline inspection for a comprehensive assessment. The predictive analytics will be applied to model the gear degradation through the acquired monitoring signal and inspection data. Thus, predictive maintenance can be achieved to benefit the industry with an efficient solution at a lower cost.

Faculty Supervisor:

Zheng Liu

Student:

Teng Wang

Partner:

Global Physical Asset Management Inc.

Discipline:

Engineering

Sector:

University:

Program: