There are many valid maintenance strategies available. These should not be thought of as “good” or “bad,” but rather as different approaches to the efficient and reliable operation of your critical assets.

Our maintenance strategies have moved on considerably since run to failure. The Industrial Age gave rise to preventative maintenance and now, with the help of connectivity, sensors and analytics, predictive and financially optimised maintenance is also achievable. With the advent of IoT and digitalisation, a new era of prescriptive and autonomous maintenance is coming.

Let’s examine how maintenance has evolved over the years, and where it is headed in 2017 and beyond... Many of the methods discussed have been available for years, but for some teams, daily maintenance tasks can still feel like a grind. It is important for these organisations to understand where they are on the asset management maturity scale, so they can determine:

• Where their operations currently are;
• Where they want to be and why;
• How to evolve their maintenance programs.

Reactive Maintenance (Run to Failure)

If your strategy involves running assets to failure and then fixing them, you are in reactive mode. Properly implemented, a reactive approach will prevent you from over-servicing equipment. Most businesses will use this for lower value or non-critical assets. When applied in the right circumstances, it can be an effective component of your maintenance strategy.

Some unplanned maintenance activities however may be very expensive and can impact health, safety and production. Breakdown repair can also interrupt the scheduled work that was already in place for the week which takes away from the availability of your crews.

Preventative Maintenance or Planned Maintenance (PM)

Time-based preventative maintenance involves maintenance based on external requirements such as manufacturers’ recommendations, or for regulatory compliance. This type of maintenance is scheduled regardless of its usage or condition. Some equipment will also have a warranty period which needs to be tracked.

Traditional preventative maintenance programs can effectively improve asset reliability, however, many organisations have more PMs than they have staff to execute them. Studies have shown that 40% of PM costs are spent without negligible effect on uptime, and 30% of PM activities are carried out too frequently. This consumes expensive resources and can potentially introduce failure by disrupting stable systems. Products themselves have become far more reliable now due to superior engineering. Preventative maintenance is therefore a tactical component of a more sophisticated strategy.

Condition-Based Maintenance

Organisations are now able to capture more data on their assets and understand reasons for failure by embracing analytics driven approaches and the IoT (previously done by physical inspections etc.) By monitoring and measuring the condition of assets in real time using sensor technology, they can engage in condition-based maintenance. This method looks at an asset’s actual condition to determine the need for maintenance and triggers an advanced warning of asset degradation or failure.

In our experience, our customers have either adopted or are working towards implementing condition-based maintenance programs. This helps to avoid high costs through excessive interval-based maintenance. Yet, real time information is not always possible in environments where connectivity is a problem such as offshore or moving assets. New technologies such as edge computing and high speed data transmission are addressing this issue.

Predictive Maintenance (PdM)

Predictive maintenance goes a step further and is quickly becoming an important strategic investment for organisations with advanced processes and high-value equipment. It involves projections of wear or degradation characteristics. By applying advanced data analytics to the asset data, we can predict the point of failure, gain a better understanding of asset performance, and lower the frequency of maintenance. Replacement plans for long lead time assets and supply chain forecasting can be put in place.

Predictive isn’t for everyone right now, but it is slowly catching on. There are a lot of prerequisites including good quality operational data, sensors, mobile, an EAM system and other data sources such as SCADA or weather. The key to using this strategy is statistical analysis and pattern recognition so specialised software products are available for predictive forecasting. This creates a potentially fragmented product strategy.

Prescriptive Maintenance

Prescriptive and autonomous maintenance is the future. These cutting-edge methods will use advanced analytics to make predictions about maintenance. The difference is that prescriptive systems not only make recommendations but also act on them!

Prescriptive maintenance requires that various asset management and maintenance systems are well integrated. For example, a predictive maintenance solution might recommend that a piece of equipment get overhauled based on analysis of vibration and temperature readings, but a prescriptive system would trigger a work order to field technicians based on this information and oversee the entire maintenance workflows.

Systems like this must be cognitive, or have the ability to think. This technology is at the intersection of big data, analytics, machine learning, and artificial intelligence. Companies such as IBM, with cognitive systems such as Watson and comprehensive EAM systems such as Maximo, are pioneering in this space.

The Brink of a Transformation

There are many valid maintenance strategies available. These should not be recognised as "good" or "bad", "right" or "wrong", but rather as different approaches. Each organisation has widely different cultures, budgets, skills and opportunities in asset management. It is important to therefore consider the context of each unique business.

However, what we are seeing is that those businesses who have evolved their maintenance systems have gone from being simply efficient towards achieving maintenance excellence. Those who do reactive and time-based maintenance see it as an expense. The further you move towards predictive maintenance, it becomes an investment (giving businesses the opportunity to enter new business models). With the science of maintenance on the brink of a transformation, cognitive systems can integrate maintenance and operations data with other data sources, to become critical to how entire organisations operate.

Even as Maximo users, you could be anywhere on the asset management maturity scale. Remember, there is no right or wrong way: asset management is a continuous journey!