Insight to Action: the OODA Loop in Manufacturing

"Gathering the sensor and usage data is one thing. Organizing the information in databases and using data mining with predictive analytics to discover patterns is quite another."

Welcome to Part 4 of Adaptive Digital Factory (ADF) series. As you may recall, Part 1 covered the  Industrial Internet and Industrie 4.0, Part 2 dealt with IoT and Supply Chain Transformation, and Part 3 looked at the omni-device customer and the impact of these connected devices on manufacturers.

IoT connectivity gives manufacturers many opportunities to watch how their devices behave. They can also observe the consumer or customer and see how, where, how often, and by whom the device is used or maintained. And the dynamic interaction between connected devices and users is also captured through sensor data.

Gathering the sensor and usage data is one thing. Organizing the information in databases and using data mining with predictive analytics to discover patterns is quite another.

That allows the manufacturer to extract the embedded knowledge from the device and consumer usage patterns. Ultimately we gain the insight or wisdom that can help us be even more pro-active to optimize the device and the customer experience.

But even insight is not sufficient. Ultimately, whatever is learned, mined, or extracted needs to be acted upon: Insight must be followed by action.

As we’ll soon see, the actions are taken in the context of dynamic cases involving processes with people (field service, for example) and connected devices or things.

The OODA Loop: All About Strategy

OODA stands for “observe, orient, decide, and act.” It’s also known as the Boyd Cycle, named for the late USAF Colonel James Boyd, a former fighter pilot who created it as a strategy for gaining advantage over enemies in battle. OODA stresses the need to observe data and events, determine the meaning, filter out the noise, reorient as new information comes in, and above all take action – all in a continuous loop.

In a tough market challenged by low operating margins, the ability to think and act more quickly than the competition creates a distinct advantage. In fact, improved supply chain management and lower operational costs are the key drivers of many current IoT initiatives in manufacturing and technology.

Let’s look at how the components of OODA apply within the digital factory, from insight to action.

  • Observation relates to either the experience or intuition of a digital factory knowledge worker or the collection of data (increasingly, “thing data”) for discovery. Sources of the data are many: things, processes, enterprise applications, and many more.

  • Orientation stems from the knowledge and insight within a particular context – either through capturing and digitizing the expert’s knowledge, through business rules, or by using predictive analytics to discover models.

  • Decision. From the observations and orientation, you can create a prioritized set of decisioning options. The user or the system needs to pick the course of action, which in most cases will be the first option or best action from a list of potential actions.

  • Actions. These are actions taken to apply and implement a decision in a particular context within the digital factory. In this step, the user acts on a prioritized list of decisions and uncovers the Next-Best-Action in a particular context or situation.

    Here’s a real-life example: Based on certain machine readings and operating conditions, a repair case could be generated automatically, then assigned to the maintenance engineer, who would then do the task proactively to prevent downtime. The case might also include information on how to perform the right repair the first time.

Coming up next

Part 5 of the Adaptive Digital Factory series will cover “Evolved Product Lifecycle Management with IoT.” For a sneak peek, check out the entire Adaptive Digital Factory eBook at pega.com.