Don’t get all worked up over the hype of a dystopian future about Artificial Intelligence (AI). We’ve been using pieces of it for many years. I had a junior programmer in the late 80s who was going off to become an expert in AI as our company was shutting down.
Much of AI we’re using falls into the voice assistant category. We’re seeing this pop up in the industrial space. I don’t want an always listening (and recording?) device in my house. Not sure if we want one in manufacturing. But, there are uses. Users had best figure out security, though.
The other pieces of AI usually involve some sort of machine learning. The program brings new data in, upgrades its algorithms, and provides better outputs—whether predictive analytics or alerts or process improvements.
Rockwell Automation has had a project for several years code named Project Sherlock. I’ve written previously here. It combines voice assistant along with predictive analytics. Engineers first showed it off with a smart phone. Now the company has added it as a module to its PLC line in classic Rockwell Automation fashion.
The new FactoryTalk Analytics LogixAI module, formerly known as Project Sherlock, uses artificial intelligence (AI) to detect production anomalies and alert workers so they can investigate or intervene, as necessary.
Many existing analytics technologies require deep expertise in both data science and industrial processes. But this add-on module for ControlLogix controllers reduces that burden by doing the job of a data scientist. It fits directly into a control chassis and streams controller data over the backplane to build predictive models. It can continuously monitor a production operation, detecting anomalies against its derived understanding.
“The FactoryTalk Analytics LogixAI module makes predictive analytics more accessible to help more workers make better production decisions,” said Jonathan Wise, product manager, Rockwell Automation. “The module learns your ControlLogix application and tells operators and technicians when things are changing in unexpected ways. This can help them get ahead of product quality issues and protect process integrity.”
For example, the module can help operators spot performance deviations in equipment like mixers that could affect product quality or lead to downtime. It can also be used as a virtual sensor. Instead of workers taking a reading, like the humidity of a packaged food product, the module can analyze variables from line assets like sprayers, dryers and burners to predict a measurement, virtually.
Workers can then be notified of problems by configuring alarms on a human machine interface (HMI) or dashboard. Future features of the module will go further, helping workers focus their problem-solving or automate the optimization of a process.
The FactoryTalk Analytics LogixAI module is the newest addition to the FactoryTalk Analytics portfolio from Rockwell Automation. The portfolio includes FactoryTalk Analytics for Devices, which learns about an automation system’s structure to tell workers about problems with individual devices. The LogixAI module expands on this by learning about an automation system’s application and helping identify anomalies with its overall function.
Both products work individually, but each will benefit the other in future iterations. The FactoryTalk Analytics platform aggregates multiple sources of data, so workers can discover new insights. FactoryTalk Analytics for Devices and the LogixAI module will both be data sources for the platform going forward.