Manufacturing businesses need to continually improve productivity, and most would agree that basing decisions are hard facts is more constructive than following instinct. But, getting the right data to the skilled decision makers within an organization has traditionally been a laborious task hindered by delays. To address this issue, what if operational teams could have easy access to timely field data, with the right software tools to enable a more scientific approach?
A recent article in InTech titled, “Edge Analytics Speed Optimization Cycle Times,” explores how industrial internet of things (IIoT) methods and edge analytics can speed insights, and therefore reduce the cycle time of monitoring, analyzing, and improving operations.
Scientific MethodOperations have goals such as:
Achieving these goals requires organizations to follow an iterative cycle where they:
This operational continuous improvement cycle bears many similarities to the scientific method of research and investigation, and following this method is a great way to pursue a digital transformation journey for operational optimization.
“Little Data” SourcesMuch of the interesting and necessary field equipment functional data originates at programmable logic controllers (PLCs) in the operational technology (OT) domain, while other higher-level data related to assets, environmental, and production data comes from information technology (IT) systems. All of these “little data” sources must be consolidated, contextualized, and visualized so they can be aggregated into “big data” useful for analytics.
Users should begin by approaching high-value issues first, leading to early savings. For each objective, they must ask targeted questions and select the most useful data for analysis.
An Edge ApproachMany IIoT projects struggle with attempts to get little data from standalone and legacy systems. To overcome this challenge, these modern IIoT methods and products can be added to existing systems in a scalable manner:
Edge Controllers Create “Big Data”Edge controllers are uniquely positioned to directly access low-latency OT source data, preprocess it, perform analytics, transport data securely to IT systems, and loop results back into deterministic control.
Start Small and RepeatWith meaningful contextualized and analyzed data in hand, users have the information needed to improve their manufacturing processes.
After achieving initial success, the team will have proved a methodology they can repeat over and over, with increasing efficiency and speed, for applying the scientific method to process improvement.
Many times large software projects struggle to deliver results. However, breaking down IT/OT integration projects into small and approachable data-driven tasks is a more reliable way to achieve digital transformation wins to speed up process improvement cycles.