The second part of the Fusion Fundamentals series with Suchi Badrinarayanan, Business Consultant, at Fusion. This series focuses on liberating and normalizing OT data to accelerate enterprise-wide adoption and high business value realization of AI/ML. The second topic is “Things” in IIoT, Data Acquisition in IIoT, Operational Analysis in IIoT.

Read video transcript below for your own convenience:

Where does this data get created in the first place? 

The data gets created with the things at the bottom: pumps, rigs, drills, drives, motors, rollers, boilers, flues, breakers, compressors, conveyors, and cables. These assets all generate data; this can vary from temperature readings to pressure readings or to vibration readings. Any kind of information that these assets generate is then usually stored in some place, but first, they have to be generated by a process, and then it's communicated through multiple different ways to all of these data acquisition systems. 

Data Acquisition

Typical data acquisitions are operations management, historians, SCADA/ Control Systems, PLC/ controllers, field inspections, instrument analyzers, IoT devices/meters, and IoT Sensors/ video/ audio. All of those things are producing data that gets acquired by all of these different systems, and then companies are trying to figure out a way to join all of this different data from all of these different sources to do analytics on them. That data can be real-time streaming data. It can be batch data. Typically you want it to have pretty low latency because if you want to do any near to real-time optimization.

Furthermore, you want it to be able to acquire data from any sort of historian, any sort of PLC, and any sort of SCADA system because most companies have a variety of all of these systems and are all collecting this data from these systems in a regular fashion. It is typically not just a one done. You want to collect all of this data for prolonged periods of time, so all of the analysis is up to date. This data is not only just the historical data and the real-time streaming data, but you also want to collect any metadata from these assets as well. In order to leverage that as well as any events in your analysis going forward.

Operational Analysis

Now that you have access to that data, you want to make sure that that data gets accessed into one Central Industrial data hub. That Hub can then provide the data and any additional information (such as the metadata, the hierarchy, or any events) to other systems. Then it will create business value for your company. Some of those examples are listed above such as operational analytics and reporting, any machine learning, detection events and alarms.

Business Value

You are using all of this data to create models or to create reports for the purpose of business value.

Anything that could lower operations, lower energy costs, increase visibility into sustainability to can reach your ESG targets, and then also increase your return on assets. A lot of this data has a lot of valuable purposes if it's used in the right way and used for the right use cases. 

Fusion is doing exactly that – taking all of those data from all those “things,” acquiring it from all of those different locations, and then creating that industrial analytics data hub to use that data for any analytics they want to do and ultimately create business value.