While preventative maintenance is a better approach than waiting for assets to fail, it’s still an inefficient strategy for maintaining equipment and preventing costly unplanned downtime.
One problem with this method is that it’s easy to miss something if an issue occurs outside the scheduled maintenance window. Call it Murphy’s law, but unplanned machine failures frequently happen before or between planned maintenance times. According to mining.com, “Calendar-based maintenance often proves to be inefficient because 82% of machine failures occur at random patterns.”
While preventative maintenance is better than reactive maintenance, implementing predictive maintenance can help create a 30% reduction in maintenance costs and as much as 70% cut in production downtime.
DINGO uses its exclusive pre-configured interfaces to capture health information from each of your machines. This information is fed into Trakka®, its proprietary predictive analytics platform, to assess equipment health and make maintenance recommendations based on machine or component conditions.
What is Predictive Analytics?
Predictive analytics is the analysis of current and historical data to make predictions about future outcomes.
Wikipedia describes predictive analytics as “…a variety of statistical techniques from data mining, predictive modeling, and machine learning that analyze current and historical facts to make predictions about future or otherwise unknown events.”
Predictive analytics is used in many industries for a variety of different purposes. For example, in the healthcare industry, practitioners may use predictive models with patient data to manage high-risk patients or prepare for future healthcare trends. In other industries, predictive analytics may be used to determine inventory requirements.
In our case, we have developed a series of sophisticated predictive analytics models that provide anomaly detection and failure prediction for asset-intensive industries. DINGO utilizes artificial intelligence and machine learning to predict impending equipment failures, allowing you to proactively perform corrective maintenance actions to minimize downtime and optimize asset health and life.
Mining Industry Not Maximizing Existing Data
Currently, many mining operations are not effectively using data to increase availability and extend equipment life. On average, less than 1% of the mining industry’s available data is being utilized, which is unfortunate because it’s a critical part of preventing time-consuming and costly equipment breakdowns.
For example, a typical new haul truck has over 200 sensors, with some generating multiple readings a second. Yet, even with this information, mines still experience unplanned breakdowns and shorter than expected equipment lives.
Why is this? In some cases, operations feel the existing maintenance strategy is already working ‘well enough.’ In DINGO’s experience, most mines don’t realize just how well they could perform if they had the right technology in place.
We have also found that large mines worry that it’s impossible to collect all their data and derive meaningful insights. And smaller mines feel they don’t have enough data to perform predictive maintenance properly.
Either way, the specific focus and concern on the amount of data are not nearly as important as collecting the correct data. And in most cases, existing and historical data and processes can be used to implement predictive maintenance.
Having a clear goal and being able to answer the question, “What are we going to do with this information?” is critical to transforming your data into meaningful actions that make a material impact on your mine’s performance and productivity.
Transform Your Data into Actionable Intelligence
When operations use predictive analytics to optimize maintenance planning and tasks and reduce unplanned failures, it is proven to increase availability, extend component life and reduce operating costs.
It can seem daunting to bring all your data together into one system and change the status quo. Still, DINGO makes it easy with dedicated experts to help you smoothly transition to predictive maintenance.