How predictive analytics can optimise asset maintenance
Collecting and distilling digital information and extracting meaning from it holds great potential to enhance customer satisfaction, reduce total cost of ownership, optimise resources and improve compliance.
Little wonder then that predictive analytics – a process of using statistical and data mining techniques to analyse historic and current data sets, create rules and predictive models, and predict future events – is fast becoming a vital instrument to realise asset life cycle cost reduction and improve the speed and accuracy of decision-making.
Predictive analytics for assets
Assets are seldom standalone. They exist as a system of assets where they feed off each other. Between asset procurement/commissioning and decommissioning/salvage lies the productive life of an asset. Regular upkeep or maintenance is needed to maximise this life. There are two perspectives on how predictive analytics can help optimise asset maintenance:
- Individual equipment perspective: Typically, maintenance frequency is defined based on various parameters such as asset age, asset criticality, operating environments, risk of failure and so forth. As a result, more frequent maintenance would mean higher maintenance expenses. Often the risk of failure forces over-maintenance of assets. Over-maintaining can mean replacing lubricants or bearings that still have life left. The ability to predict a failure can help moving maintenance activities closer to the real need for maintenance and reduce over-maintenance.
- Productivity perspective: As can be imagined, a system of assets, designed and scheduled for maximum productivity, can benefit immensely if a failure of an event requiring maintenance is known in advance. Alternative schedules or plans can be prepared to ensure maintaining productivity levels.
Power of predictive analytics
Let us reimagine the same scenario with predictive analytics capability. Predictability does not mean the maintenance software will tell you to replace a certain bearing on a certain piece of equipment in a certain process on a certain date at a certain time.
But it would indicate the probability (for example, there is 89 percent chance) of a bearing failing at a given time. Business rules can be built to instruct a bearing replacement above a certain threshold (for example, when there is a more than 70 percent probability of failure). Evidently, this allows risks one is willing to take to be quantified (for example, 70 percent is the risk threshold). This can help widen maintenance intervals, push maintenance activities closer to when needed and consequently, optimise asset operations.
It is not difficult or expensive
Does building predictive analytics capability cost lots of time, money and effort? The answer to this big question is an emphatic ‘no’. There is always a sweet spot where savings from predictive capabilities (reduction in maintenance expenses, Capex, spares utilisation and so on) outweigh the cost of building those capabilities (software, human resources etc). Once done, the benefits through direct asset-related saving (fewer maintenance dollars, fewer spares, longer life span), and organisational saving (optimal teams, increased operational efficiencies) are immense.
KPIs to monitor assets
KPIs (key performance indicators) are different for different asset types, operating conditions, criticality and so forth. Due consideration needs to be given to the role of statistics and the related process changes and change management, among others, required to build a predictive maintenance culture. Data and statistics will provide quantification, but will need to be applied with business insights to derive benefits (for example, the 70 percent risk quantification mentioned earlier).
Here are a few commonly used KPIs:
- Reliability given time: This indicates the probability that a unit will operate successfully at a particular point in time. For example, there is an 88 percent chance that the product will operate successfully after three years of operation.
- Probability of failure given time: This indicates the probability that a unit will fail at a particular point in time. This is also known as ‘unreliability’. For example, a 12 percent chance that the unit could potentially fail after three years of operation (probability of failure or unreliability) is the same as an 88 percent chance that it will operate successfully (reliability).
- Mean life: This indicates the average time that the units in the population are expected to operate before failure. This metric is often referred to as ‘mean time to failure’ (MTTF) or ‘mean time before failure’ (MTBF).
- B(X) life: This indicates the estimated time when the probability of failure will reach a specified point (X percent). For example, if 10 percent of the products are expected to fail by four years of operation, then the B(10) life is four years.
Predictive analytics and maintenance practices
Traditionally, maintenance practices are classified as reactive, preventive, predictive and reliability-centred maintenance (RCM). However, predictive and RCM approaches are the ones that best leverage predictive capabilities.
- Reactive maintenance: In this, practice equipment is allowed to run until it breaks. No actions or efforts are taken to maintain the equipment.
- Preventive maintenance: This involves activities carried out for the purpose of maintaining equipment in satisfactory operating condition by systematic inspection, detection and correction of failures either before they occur or before they develop into major defects.
- Predictive maintenance: In this, practice statistical techniques are used to determine the condition of in-service equipment in order to predict when maintenance should be performed. This approach promises cost-savings over routine, time-based preventive maintenance, because the tasks are performed only when warranted.
- RCM: This emphasises the use of predictive maintenance techniques in addition to traditional preventive measures. When properly implemented, RCM provides companies with a tool to achieve lowest asset Net Present Costs (NPC) for a given level of performance and risk.
Predictive analytics is the process of moving from hindsight to insight. While data and distilling data are the key, equally important is the way in which organisations instrument, capture, create and use data to address their strategic objectives.
The author, Badrinath Setlur, is assistant vice president – Consulting, Manufacturing, Logistics, Energy and Utilities at Cognizant, a provider of information technology, consulting and business process outsourcing services.