The volume of data being collected by industrial companies has increased exponentially. Enabled by IIoT sensors, high-performance computing and cloud technologies, analysis and predicting outcomes around complex problems has been made a reality in a way that conventional engineering, operations and maintenance technologies have not been able to in the past.
Many companies approach Digital Transformation by ‘sensorizing’ all their equipment, collecting data and hoping it turns out insights on what to improve. Rather, they should start with an area that needs fixing. The key to benefiting from digitalization is to select those areas of investment that create the most value and use data to enable sustained operational excellence. And it’s the combination of data, analytics and process knowledge with organizational excellence — meaning the alignment of talented, experienced professionals with the most critical needs of the business through coherent and effective processes — will make the difference between digital transformation’s success and failure.
One of the biggest areas of opportunity for asset-intensive companies is in asset optimization, or driving value across an asset’s entire lifecycle.
Asset performance management as a digitalization focus
Changing market dynamics require industrial companies to consistently obtain the highest possible returns from their assets. The time is ripe – computing costs are at their lowest ever and hardware and software developments such as sensors on and around machines, Windows, Linux, Hadoop and industrialized machine learning can leverage existing infrastructure like plant historian sensor data streams and enterprise asset management (EAM) systems inside plants and factories.
There is a rare opportunity right now to do things differently – by optimizing maintenance with operations and with the ability of analytics to predict a problem early on, when there is enough time to do something about a problem or at least mitigate its impact. Operational analytics gives industrial companies a science-based ability – from past, present and future insights – to make the right decisions that enables them to run their equipment and design their processes in a way that avoids the damage and degradation that leads to breakdowns.
These challenges can only be solved with a greater understanding of how the process impacts the asset and vice versa, and it takes deep process domain and modeling expertise combined with data science to provide the rich context necessary to predict and avoid asset performance issues accurately.
Reliability as one leg of the asset optimization “stool”
Reliability is often looked at in isolation. It should, though, be viewed as one key leg of the asset optimization “stool.” High-performing organizations pursue asset optimization in a framework encompassing the total asset lifecycle, involving the design-operate-maintain continuum. Each aspect impacts the other, and improving overall asset lifecycle performance will naturally improve reliability.
There are several ways to use digital transformation to do this. One is through better design, which can be facilitated through digitalization and integration. Data from operations, over time, when properly analyzed, can identify the equipment, process units and designs operating with the best reliability and performance. Feeding this data back into design, and re-using the most reliable designs which have already been executed, can drive to design for reliability.
A second approach is to employ modeling to understand where conditions for low reliability are being created and to look at alternative operating cases that will achieve higher reliability. A third approach is through probabilistic, enterprise reliability modeling, which can identify the “pressure points” where, in the specific interconnected process manufacturing and supply chain system, investment will have the highest reliability and profitability returns.
Homing in your digital transformation strategy now
Industry leaders are moving from the hype and buzz of digital transformation into the implementation of real projects. Reliability and machine learning are easy areas to progress, because the efficacy of a solution can be easily tested and proved with a historical data set of process performance and equipment and unit failure events. As asset optimization and asset performance management is adopted by industry leaders as a sustainable driver of growth, maximizing the net return on production assets will become a strategic priority, not just an operational metric.
We are experiencing the next big wave of technology – all about driving uptime in operations and extending the life of assets, especially as CAPEX budgets become tighter. The key is to define a pragmatic technology roadmap that will realize value quickly, enable operational excellence at a cultural level and from which initial success can be scaled. Operational excellence is what will separate the winners from the losers.
Sourced from IoT Evolution