Rockwell Automation has launched a new artificial intelligence system which the company says “models, monitors and optimizes industrial operations”.
The company says that the “novel” AI system learns specific applications and alerts operators to errors, and suggests solutions.
Creating diagnostic analytics solutions in industrial operations has long required expert data scientists with a deep understanding of the specific application to be analyzed, says Rockwell.
Those experts then require weeks, months or even years to understand and model the system.
That expertise has been boxed in Rockwell’s new “Project Sherlock AI” module, unveiled by the company at its Automation Fair event in Houston.
The data-driven analytics algorithm is delivered inside a module that fits directly into the controller chassis.
Once installed, Project Sherlock AI uses “novel physics-based modeling” to learn the application that controller manages, says Rockwell.
The solution scours controller tags to identify the application or allows users to choose what they would like modeled by selecting inputs and outputs via an add-on-instruction.
Project Sherlock AI will then “quickly learn” from the stream of data passing through the controller to build a model, says Rockwell.
This process can be accomplished in a matter of minutes, claims Rockwell, which adds that “vast quantities of historical data are not required”, nor must the data ever leave the automation layer.
Once the model is built, the Project Sherlock solution continuously watches the operation looking for anomalies against its derived, principled understanding.
If it spots a problem, it can trigger an alarm on an human machine interface screen or dashboard.
Future iterations will go beyond diagnostics to direct users on how to remedy the issue or to automatically adjust system parameters to fix the problem without human intervention.
Jonathan Wise, platform leader for the control and visualization business, Rockwell Automation, says: “Project Sherlock brings industrial producers amazingly smart analytics in a package that is easy to implement.
“As our customers undergo digital transformation – using production data to help improve business outcomes – they can’t wait on expert-driven analytics.
“Even if there were enough industrial data scientists out there, not every company has the time or funds to employ them.
“This machine-learning tool creates powerful analytics from your automation infrastructure, painlessly – delivering value moments after it’s dropped in the Logix backplane.”
Project Sherlock diagnostics offer “drastically reduced false-positive alarms”, claims Rockwell, as compared to other artificial intelligence solutions due to its physics-based modeling and foundation in industrial applications.
For example, Project Sherlock AI can tell if a boiler temperature shift is related to a benign change in upstream operations or an abnormality that requires correction.
The initial version of Project Sherlock AI will include ready-to-use templates for boiler, pump and chiller operations, ideal for process or hybrid applications. Users can model additional applications with guided configuration.
Communications with the module are prioritized by the controller, so users can select how much data is sent and intervals of communication.
The module does not add to controller CPU-load nor add to network traffic.
Project Sherlock AI pilots have been running and producing results for the past 18 months. Customers will be able to purchase the module in mid-2018.
This new artificial intelligence engine is part of a larger, expanding ecosystem of analytics offerings from Rockwell Automation that run across the plant floor for devices, machines and systems, as well as throughout the enterprise.
Rockwell Automation developers are building connections so users who employ FactoryTalk Analytics for Devices tools will be able to interface with Project Sherlock AI via the Shelby chatbot and action cards.
Analytics from Project Sherlock AI will be easily integrated into the FactoryTalk Analytics Platform to integrate plant-floor data into business intelligence strategies.
