What are Predictive Analytics and how important are they to effective Asset Management?
In the asset-intensive Process Industry, could predictive analytics hold the key to massive leaps forward in asset reliability? Our in-depth analysis sheds some light on the issue.
Effective predictive maintenance programmes result in savings
“As the wealth of information generated by sensors and machines in asset-intensive organisations increases, the opportunity for data-driven optimization drastically increases as well,” says Mario Montag, CEO of Predikto – a predictive analytics company focused on developing solutions to predict equipment failures in asset-intensive industries.
For a non-intrusive method of predictive maintenance, predictive analytics could well be the answer for asset-intensive industries. Montag continues, “Until now, data overload had served as a challenge and a threat to decision clarity and the ability to provide accurate, actionable information.
“According to past studies, an effective predictive maintenance programme can result in a savings of eight percent to 12 percent over a programme simply utilizing preventive maintenance strategies.”
The advice is clear: executing predictive analytics initiatives is easy to initiate and yields significant benefits.
The benefits of predictive analytics
‘Predictive analytics’ encompasses a spectrum of disciplines from statistics, mathematical modelling and simulations, data mining and machine learning. But in essence it’s a tool for predicting the “likelihood of future events” or the “attributes associated with such asset failures.”
Ostensibly, this type of strategy maximises “big data” by analysing historical data to forecast future events at “up to real-time speed” to enhance future operating procedures.
“Whether predicting asset remaining useful life (RUL), probability of failure, conditional trending, or any other arbitrarily defined feature, all will result in elevated efficiency and effectiveness throughout daily processes, which translates into reduced maintenance costs and increased revenue,” says Montag.
Implementing a predictive maintenance programme can result in:
- Savings of 30-40 percent
- 10-fold return on investment (ROI)
- Maintenance cost reduction of 25-30 percent
- Breakdown elimination of up to 75 percent
- Reduction in downtime from 35-45 percent
- Increase in production of 20-25 percent. A manufacturer has the ability to shift from reactive maintenance to dispatch a technician with a preventive maintenance work order on an ‘as needed’ basis and ensure that repair parts are in inventory prior to downtime.
These factors combined help increase operational efficiency and output, leading to increased safety and cost savings.
Getting started with predictive analytics
Understanding the intricacies and capabilities of predictive analytics is vital to the movement towards reliability centred maintenance (RCM) initiatives. “Predictive analytics is one of the main steps within RCM, but organizations don’t know how to deploy it or get started,” says Montag.
He adds, “It is strongly recommended that organizations start small with a few key assets in one or two facilities to understand the deployment process and achieve actual results using their own data and equipment.”
There are three defined routes for success when using predictive analytics results.
First, consider hiring a team of data scientists and purchasing the necessary statistical software and IT ‘big data’ infrastructure.
Second, at the most expense, you could purchase enterprise-wide software licenses with services to monitor and manually create actionable reports.
Or thirdly, acquire analytics as a service (AaaS) from niche providers of predictive analytics.
The bottom line
Montag predicts, “As machine to machine (M2M) deployments and the Internet of Things (IoT) phenomena continue to grow, it is safe to assume predictive analytics will follow in close pursuit.”
That seems a sound assertion considering claims of “results as high as 90 percent in accuracy” amongst industry-leading companies using predictive analytics to forecast potential asset failures.
What do you think? Could predictive analytics be the future or are they too good to be true? Send us your thoughts.