Smart Industry: What’s the status of data-use among enterprises?
Steve: In the industrial market, large organizations have been collecting and using operational data for years. The IIoT is beginning to provide the ability to easily and securely connect this OT information with sensor and streaming data, along with transactional information from traditional IT systems. There is new intelligence and insight in this combined data set, and enterprises are now looking at how to turn this into business advantage.
Smart Industry: What does the IIoT enable you to do with data?
Steve: There is often excessive latency between when events happen, get recognized, then acted upon and finally resolved. IIoT enables you to reduce this lag time, and close the loop by orchestrating complete event flows all the way from diverse sensors and data sources to specific business actions. Our visual environment allows engineers to quickly create and deploy applications for a wide range of use cases with little or no coding. We empower those closest to the problem to create their own solutions.
Smart Industry: What unique opportunities does the digital transformation enable?
Steve: The Industrial IoT is all about transformative change. Some of the mega use cases include predictive maintenance and operations, smart and connected supply chains, and the new service offerings and revenue models that are enabled by intelligent products.
Smart Industry: Who is taking most advantage?
Steve: Our specific focus is on asset-intensive industries–manufacturing, oil & gas, utilities, and mining. Large physical assets with digital footprints are being targeted for predictive maintenance, and different organizations are currently at various levels of maturity. We have a five-step approach to IoT-based predictive maintenance which provides a roadmap for success, and also offer tools which can help justify IoT projects to management.
Smart Industry: How does predictive maintenance work with elements of IIoT?
Steve: Live sensor data from critical operating assets is combined with other streaming and contextual data, then run through a machine-learning predictive model. The model compares the real-time inputs with historical information to calculate the likelihood of failure or remaining useful life for the asset. With this information, maintenance technicians can be dispatched with proper information and parts to service a machine before it fails, and can access and capture key information while onsite using their mobile devices. Engineers can simultaneously be notified to take any necessary corrective actions or perform failure-mode analysis. You see, it’s not enough to simply raise an alert or update a dashboard, you really need to drive actions to realize the business value in IIoT. At XMPro, we often refer to this closed-loop approach as Sense, Decide, Act. And predictive maintenance is just one of many such applications.
