Predictive Analytics for Condition-Based Maintenance

Many mining maintenance departments perform preventative maintenance based on elapsed time, engine hours, or easily observable indicators such as a check engine light. These intervals and limits are typically set conservatively in order to ensure that driveline lubricants are not contaminated or degraded to unacceptable levels prior to service. Oil analysis is used in some cases to fine tune this approach. 


Unfortunately, both elapsed time and engine hours, while highly observable, make for poor proxies of driveline wear and lubricant deterioration. The most dramatic example of this is the relative effect of an hour spent idling vs an hour in full production. 

Fuel consumption is a far superior proxy for lubricant deterioration as it is directly proportional to soot contamination, engine wear and other factors affecting lubricant life.  Organizations can set fuel burn targets for maintenance, then fine tune and validate these limits with highly predictive oil analysis. A negative trend in fuel efficiency can be used to trigger equipment maintenance at the moment it is needed, not according to an arbitrary calendar date. The result is extended lubricant replacement intervals and lowered costs without increased risk to engine components.   

Blutip's cloud-based SmartRView fuel analytics portal tracks data on fuel efficiency, tons moved, consumption per 1000 tonne km, and other vital metrics, by truck type. Trucks are ranked by fuel efficiency, helping site operators make smarter maintenance decisions based on accurate, condition-based data.


Cascadia Scientific's extensive diesel fuel, operator behavior, and equipment maintenance data can help you save 4-5% of your fuel costs and make intelligent decisions about truck maintenance and asset retirement. Contact us today for a no-charge, site-specific Mine Audit to drive down fuel costs at your site.