With
the coming age of Industry 4.0, it’s no longer prudent, strategic or
economically smart to wait until a critical mining asset has broken down to fix
the machine. Equipment breakdowns are often costly on many levels — downtime
means productivity is affected, parts can be expensive and then there are the
wasted outlays on labor and energy.
Data
analytics paired with predictive maintenance can be a virtual goldmine for
mining operations, with initial cost reduction and productivity gains of an
estimated 10% to 20%.
If
your organization hasn’t already, it’s time to take a look at modern
maintenance strategies, gather your company’s valuable data, and make sure that
you are Industry 4.0 ready.
The five stages of mining maintenance
The
evolution of maintenance in the mining industry has come a long way in the last
decade or so, aided by the availability of real-time data. There are five
common maintenance approaches that can be applied to mine assets: reactive,
preventative, condition-based, predictive and prescriptive.
Moving from reactive to preventative maintenance will help improve asset reliability, but it might not be effective as there will still be unplanned downtime and costly repairs that could have been avoided. Calendar-based maintenance often proves to be inefficient because 82% of machine failures occur at random patterns.
The evolution of maintenance in the mining industry has come a long way in the last decade or so, aided by the availability of real-time data
Condition-based
monitoring, the monitoring of machines when they are still running, is the
first step toward adopting a forward-looking maintenance strategy. Data can be
collected online through network connectivity to sensors or offline through
operator rounds or other means, depending on the criticality of the machine.
Predictive
maintenance advances the condition-based approach further by using model-based
anomaly detection. It relies on the online collation of sensing data and uses
data analytics to predict machine reliability.
The ultimate
level of maintenance, prescriptive maintenance, involves the integration of big
data, analytics, machine learning and artificial intelligence. It takes
predictive maintenance a step further by implementing an action to solve an
impending issue, rather than simply recommending an action.
The most
important factor in the digital transformation of your maintenance strategy is
access to real-time operational data. Reaching the fourth level of maintenance
(predictive) is achievable now, and requires the application of advanced
analytics.
Establish an operational data infrastructure
The first step is establishing an enterprise operational data
infrastructure that can capture real-time data coming from sensors,
manufacturing equipment and other devices, and transform it into rich,
real-time insights, connecting sensor-based data to systems and people.
This first step is fundamental to providing insights for later analysis.
Not only will a real-time operational data infrastructure help improve asset
reliability, but having a single infrastructure in place will improve process
productivity, energy and water management, environment, health and safety,
quality, as well as KPI and reporting.
Enhance and contextualize data
This step refers to how data is stored and enhanced (in other words,
providing context) to become information. For example, even though data is
collected from a sensor, analysts need to know if the equipment is running or
has stopped either due to a failure or activation of an emergency stop button.
Without this context, data doesn’t have much value. Also, recognizing what data
is important and relevant to an organization is equally as vital.
Implement condition-based maintenance
Next, your company will need to implement condition-based maintenance (CBM) using contextualized data. This involves prioritizing certain assets, identifying the conditions that lead to eventual failure and implementing those conditions on specific assets within a real-time operational data infrastructure to automate condition-based monitoring. For example, when a bearing temperature starts increasing outside of its normal operating temperature, it means the bearing will eventually fail.
Reliability engineers already
know a lot of these failure patterns, which are often found through reliability-centered
maintenance analysis following a failure. All of these known patterns should
then be implemented as CBM inside a real-time enterprise operational data
infrastructure.
Implement Predictive Maintenance 4.0
This is the final step. Your
chosen enterprise operational data infrastructure — in conjunction with
advanced analytics and pattern recognition tools — will provide real-time,
actionable intelligence that empowers your business to optimize operations.
Used together, these tools will automatically determine the patterns that lead
to an eventual failure.
Perhaps the best way to see the
benefits of condition-based and predictive maintenance is through real-life circumstances.
For example, Barrick Gold’s Pueblo Viejo, the largest producer of gold in the Caribbean, wanted to improve the asset health monitoring system of their haul truck fleet to improve maintenance efficiency and costs. The challenge involved providing real-time information of 34 haul trucks using installed systems and at minimum cost.
Prior to using condition-based maintenance, reliability and maintenance
managers relied on incomplete or delayed information to make decisions.
“We used to use the in-vehicle sensors to investigate why a truck failure had happened,” Ted Olsen-Tank, a senior metallurgist for Barrick Gold, said. “Now we can be one step ahead of a failure and be more proactive.”
Since its inception in 2018, the predictive maintenance project at Barrick’s Cortez mine has begun to pay off as more than half a dozen major equipment failures have been avoided
Barrick Gold saved $500,000 due to their newfound ability to detect and
address failures as well as reduced the total number of failures from engine,
brake or suspension issues by 30%.
Taking it a step further, Barrick is using predictive maintenance at their Cortez Mine in Nevada. The machinery involved in the gold refining process at that location is expensive, and so is downtime caused by mechanical failure. Barrick Gold invested in predictive maintenance at Cortez Mine by using sensors and machine learning to detect potential equipment problems before they escalated into failure. The machine learning algorithms use frequently collected sensor data to generate an equipment health score, which can be tracked for declines that might indicate a potential problem.
Since its inception in 2018, the predictive
maintenance project at Cortez has begun to pay off quickly as more than half a
dozen major equipment failures have been avoided. To put that into perceptive,
a single early fault detection for one piece of equipment alone saves the company
$600,000.
There are powerful economic incentives to leverage real-time data and predictive maintenance. Companies can benefit from reduced costs, open new revenue streams, extend equipment life and increase production capacity.
(Martin Provencher is Industry Principal of Mining, Metals and Materials at OSIsoft)