National Instruments Partners with SparkCognition as IIoT Transformation Matures

As the IIoT transformation in manufacturing matures, more partnerships are developing and this week Austin, Tex.-based National Instruments (www.ni.com, NI) and IBM announced an agreement with SparkCognition. The goal of the collaboration, according to NI, “is to deliver an unprecedented level of interoperability among operational technology and informational technology as organizations search for better methods to manage and extend the life of aging assets in heavy machinery, power generation, process manufacturing and a variety of other industrial sectors.”

“We are excited that our platform can acquire the data and extract the features to drive SparkCognition analytics for IIoT solutions,” says Jamie Smith, director of embedded systems at NI. “Combined with existing technologies in the testbed, the addition of SparkCognition presents new ways to help automate the process of turning sensor data into business insight.”

NI may see a big opportunity with its open, software platform and SpakCognition’s machine learning products to create cost-savings for manufacturers’ in multiple industries. One industry that comes to mind is the power generation space, where I noted earlier this week that $32 billion dollars are being spent in 2016, alone, in the U.S. to build out grid distribution systems.

SparkCognition is also known quite well in the industrial machinery space, with its cognitive fingerprinting algorithm, called SparkPredict. According to a trade journal article from earlier this year, the company has been working with a major pump producer and using real-time data to provide better reliability:

SparkCognition has been working with one of the largest suppliers of industrial and environmental machinery-pumps, valves, mechanical seals to take real-time data off of their horizontal pumps and prevent future breakdown. By using three years of operational data to train on, SparkCognition’s algorithms were able to predict future failures with over five days of warning in just a few short weeks. This was a 20 fold operational improvement over existing models, which had been in development for decades by the client’s subject matter experts. The improvement was possible because of algorithmic advances in feature derivation, feature selection, and model building and ensembling—all of which come together in what we call Cognitive Fingerprinting.

This partnership seems like a good fit between two Austin-Tex. based companies with the ability to offer services and platforms to a wide range of equipment in multiple industries.

National Instruments, www.ni.com.
SparkCognition, www.sparkcognition.com.
IBM, www.ibm.com.