Operational Intelligence: Repurposing Manufacturing Big Data

By Dick Slansky

Category:
Industry Trends

I recently blogged about the Factory of the Future, and one of my main points was that in many ways we are already implementing the Factory of the Future, and some manufacturers are already adopting and leading the way into the next generation of manufacturing. At the recent ARC Forum, I led a session on Advanced Manufacturing and focused on some the emerging technologies being deployed. One area that appeared to strike a chord with some of the attendees, and stimulated some discussion afterward, was the topic of Operational Intelligence, and the use of the vast amount of manufacturing data found in repositories and databases for completed production execution and operational records. There was agreement that there was indeed a lot of manufacturing data and information out there, but the question posed was just how do manufacturers access and get some actionable information out of it.

I will revisit some comments I made about Operational Intelligence in earlier blogs, and try to expand on those observations. Historically, when manufactures began to adopt the basic principles of Lean Manufacturing, quality assurance, statistical process control (SPC), continuous process improvement, Six Sigma, and other manufacturing improvement methods decades ago, they laid the foundation for operational excellence, and, today what we are calling Operational Intelligence. All of these basic principles have remained fundamentally sound for years, and still apply today. Back when we were trying to implement SPC we could build charts and graphs, but we had nothing like the analytical tools we have today. I believe that what have is a renaissance, if you will, in predictive and prescriptive analytics, but even further, a move to Operational Intelligence based on repurposing of manufacturing Big data and machine learning applied to the fundamentals of process improvement.

Manufacturing Big Data represents operational and executed work records, quality assurance records, work flow histories, operational deviations and variations, engineering changes, and many other records related to the production process for manufacturing. The point being that this Big Data for manufacturing is the real treasure trove of information that would allow advanced analytics applications to optimize and determine best practices for the production processes. In other words, if you want to implement continuous process improvement one must examine the complete production process record history to discover both the flaws (risks) and the best practice methods in the design/build lifecycle.

Looking further into the topic of performance analytics, operational intelligence, or closed-loop PLM, all apt descriptions of this notion of process improvement and validating as-built to as-designed. This is where I see the real payback of advanced analytics, that is, going beyond predictive to prescriptive analytics, where we bring together big data, statistical sciences, rules-based logic, and machine learning to empirically discover and reveal the origins of the complex problems, and then determine decision-based options to resolve them.

We could easily make the case that existing repositories of manufacturing Big Data represents a digital brain trust that is the primary source of basically unstructured data that needs to aggregated, analyzed, and converted into actionable information. Moreover, when this information is placed in the context of a design/build lifecycle, it becomes a closed-loop mechanism that is connected by a digital thread that includes product development, manufacturing, and services in the field. In essence, the data that is held in a repository which is the result of manufacturing execution operations records becomes a source for operational intelligence, product performance and production process improvement.

Currently, the focus appears to be on predictive analytics and the operational state of equipment, and maintenance and the preservation of assets with platforms like GE’s Predix and Siemens’ Mindsphere. I believe we are fast moving into a period in manufacturing where the focus will be on discovering and improving the manufacturing processes, as well as refining product development because there will be a more holistic approach on the end-to-end design/build lifecycle. This move by manufacturing into the Operational Intelligence phase will represent a renewed focus on operational excellence driven by the emergence of technologies like machine learning based prescriptive analytics that will drive the operational excellence vision started so many years ago.

 

 

Engage with ARC Advisory Group