- July 2023
The ideal conditions for making things are created when machines, facilities, and people work together to add value without generating any waste.
Kiichiro Toyoda, founder of Toyota Motor Corporation
As the rise of Lean Manufacturing has exploded in the 21st century, organizations have become hyper-focuse on continuous improvement (CI).
85% of manufacturing organizations are prioritizing CI in 2022 (APQC).
One of the biggest contributors to CI within manufacturing in recent years has stemmed from the advent of Industry 4.0. The rise of Industry 4.0 allows for machinery and the Industrial Internet of Things (IIoT) to integrate seamlessly which has allowed for predictive maintenance to explode in manufacturing across asset intensive industries. These industries are inclusive of oil & gas, chemical manufacturing, energy, construction, aviation, and life sciences.
Predictive maintenance is enabled by real-time data, advanced analytics, and artificial intelligence
The term predictive maintenance may often be confused with its predecessor, preventative maintenance; however, the two account for different concepts which drive varying bottom-line results in practice:
Preventative maintenance: performance of maintenance of an asset at regular intervals to prevent unexpected downtime.
Predictive maintenance: performance of maintenance of an asset on an as-needed basis to prevent unexpected downtime.
The largest driver that separates these two practices of maintenance is the availability, utilization, and application of large data sets. Predictive maintenance is enabled by real-time data, the usage of advanced analytics, and artificial intelligence, which have all been advanced greatly by Industry 4.0 and the subsequent boom of IIoT. In order for organizations to take advantage of predictive maintenance, there is a critical need for a strong data strategy and analytics capabilities. The downstream impact of this is accuracy in asset utilization, performance, and integrity.
So, what does this look like in practice and how does predictive maintenance connect to Kiichiro Toyoda’s idea of adding value without generating waste?
Components of predictive maintenance
At its core, there are four primary components that empower predictive maintenance (SAP):
- Real-time data: the use of high-quality sensors capable of streaming large quantities of data, covering multiple metrics, without bias.
- Cloud integration: the secure storage of large quantities of data capable of transmitting between multiple integrated systems.
- Advanced analytics: the utilization of artificial intelligence to absorb, aggregate, and synthesize complex data to provide valuable insights on when assets require maintenance and time to failure.
- Action on insight: the actual maintenance work performed on an asset as a result of the predictive insights found upstream.
Delivering significant benefits
The result of these four components is a highly cost-effective maintenance program, saving roughly 8% to 12% over preventive maintenance, and up to 40% over reactive maintenance. Additionally, a 40% reduction in downtime in organizations that utilize predictive maintenance, resulting in a savings opportunity exceeding 30%-40% (U.S. Department of Energy).
The benefits found through the utilization of preventative maintenance contribute directly to Kiichiro Toyoda’s “ideal state” by means of increased uptime and cost savings, which in turn add value and decrease waste across an organization’s manufacturing processes.
In addition to bottom line results, predictive maintenance enables organizations to better forecast the procurement of parts, materials, MRO items, and labor. With data and analytics driving maintenance activities, organizations are empowered to further drive forecasting to influence key sourcing activities, contractor management and compliance, and spend management and control.
- 40% reduction in downtime - savings opportunity exceeding 30%-40% (U.S. Department of Energy).
- Increased uptime and added value across the manufacturing processes.
- Improved procurement forecasting - parts, materials, MRO items, and labor.
- Better contractor management and compliance, and spend management and control.
Realizing the full potential of predictive maintenance – How BearingPoint can help
There is often a challenge in the full implementation of a predictive maintenance project with only 4% of organizations exploiting their expected potential. BearingPoint helps clients with Big Data and advanced analytics married with technology solutions (e.g. IFS EAM, SAP EAM, IoT, Comengy, ETM.Next) to better understand asset utilization, to predict future failures, to drive cost control through enhanced forecasting for procurement, and to improve maintenance planning and efficiency. Our team of experts enable our clients to reap operational and maintenance benefits by harnessing data that is already available in most cases but not fully used.
BearingPoint helps clients with Big Data and advanced analytics married with technology solutions
