Approaching the IIoT with Machine Learning and Edge Intelligence in Mind
Kagan Pittman posted on July 13, 2017 | 8218 views
(Image courtesy FogHorn Systems.)
(Image courtesy FogHorn Systems.)

Machine learning capabilities are a significant asset in IIoT platforms, assisting in the collection and organization of data between multiple edge devices within the network.

FogHorn Systems announced yesterday the availability of Lightning ML, an edge intelligence software platform for the Industrial Internet of Things (IIoT), which the company states is the industry’s first IIoT software platform with integrated machine learning capabilities and universal combability across all major IIoT edge systems, i.e. operational technology (OT) systems and IoT sensors.

“To date, machine learning is typically done in the cloud,” said David C. King, CEO of FogHorn Systems. “FogHorn Lightning ML is designed to deliver the same powerful machine learning (ML) insights on a very tiny footprint, less than 256MB.”

Lightning ML users can execute proprietary, domain-specific ML models or choose from ML algorithms which plug into streaming data from assets and machines. The ML platform abstracts the complexities of an IIoT setup and allows one to use ML at the edge, King explained.

Mike Guilfoyle, director of research and senior analyst at ARC Advisory Group, explained that the money and time required to move massive amounts of data to the cloud for analysis, only to send the results back to the edge, makes little sense.

“In many instances, cloud computing won’t be practical, necessary or desirable,” Guilfoyle said. “The reality is that edge intelligence is critical to a successful overall analytics strategy.”

King defines edge intelligence as the ability to sense, infer and act, in real time, on data as it is being generated at the network edge. This data would be used to monitor for failure conditions or other scenarios where immediate action should be taken.

“In the initial launch of FogHorn’s Lightning platform, we successfully miniaturized the massive computing capabilities previously available only in the cloud,” King said. “This allows customers to run powerful big data analytics directly on OT and IIoT devices right at the edge through our complex event processing (CEP) analytics engine.”

Lightning ML can leverage proprietary algorithms and machine learning models on live data streams produced by physical assets and industrial control systems, as well as provide ease-of-use frameworks and tools for OT.

“For example, VVM (Visual VEL Maker) is a drag-and-drop authoring tool that helps an OT professional create analytics on data streams,” King explained. 

(Image courtesy FogHorn Systems.)
(Image courtesy FogHorn Systems.)

“It has hundreds of built in mathematical and statistical functions that can be connected together to determine asset failure, predictive maintenance alerts and realize other common industrial use cases. Our ML utility facilitates the execution of models by the operator on the floor, even if the model was developed elsewhere by a remote data scientist. By providing a code-less way of creating these algorithms, OT staff can create what they need quickly and test it without waiting weeks for support from other experts, internally or externally.”

Due to its earlier mentioned size of only 256MB, Lightning ML also enables learning models to run on highly-constrained computer devices, such as PLCs, Raspberry Pi systems and small IIoT gateways, as well as more powerful industrial PCs and servers.

Lightning ML is on-premise centric and Cloud agnostic for flexibility in determining IT infrastructure, security policy and deployment models.

For more information about FogHorn Lightning ML, visit the FogHorn website.

Recommended For You