Artificial Intelligence, or AI, is quite the buzz word. Mention in general conversation, say if you are Axios or The New York Times, and public response is that it is something evil that will take all our jobs away.
Of course, like all technology from the beginning of human history AI can be good or bad depending upon who uses it for what reason.
Now, let me add a second stream to this brief essay. Advanced Process Control, or APC. There are some excellent APC products on the market that I’ve written about over the years. The problem I’ve heard about over those same years relates to keeping the model updated. Too many people (read managers) seem to think you set it up once and then it lasts forever. That could not be further from reality.
Yesterday I had a conversation with Pervez Choudhry, Vice President for Business at Petuum. This is a company started through AI research at Carnegie Mellon University by Eric Xing. He hired a number of Ph.D.s and post-doctoral researchers in AI along with domain experts in industries he targeted for markets and went to work.
My BS antennae always activate at the sound of AI in a press release. So, I asked Choudhry what Petuum meant by the term. That’s when he told me about the research and researchers. AI relates to machine learning. Getting a data set from a process and self-learning from new data feedback from the process.
I’m more impressed by the business model than the technology. The company hosts the application in the cloud deployed as “AI as a Service”. This system addresses the problem so many have run into about maintaining the model as the process morphs over time. A company worth watching. They could well disrupt (in a good way) this particular market.
The press release that provoked my curiosity promoted a new use case—supervised autonomous cement plant operations for CEMEX—a global building materials company.
The two companies entered into a global agreement where CEMEX can implement Petuum “Industrial AI Autopilot” with “autosteer” in all cement plants worldwide for autonomous cement plant operations. The Petuum Industrial AI Autopilot product for cement plant operations are being deployed at select CEMEX USA and Mexico plants, and will continue to be rolled out globally in 2019.
The Petuum Industrial AI Autopilot suite of products deliver real-time precise forecasts for key process variables, prescriptions for critical control variables and supervised autosteer aligned with business objectives for all cement plant operations including clinker cooler, preheater, rotary kiln, pyro process, ball mill and vertical mill processes to achieve lowered energy consumption, optimized fuel mix and increased throughput while maintaining stable operation and high product quality. Additionally, the fuel mix optimization Autopilot enables alignment of global operational excellence initiatives with local site priorities.
The joint CEMEX and Petuum teams achieved a cruise-control-like supervised “autosteer mode,” where the AI Autopilot could run operations with full engage/disengage control available to the operator.
“Petuum Industrial AI Autopilot helped us achieve something we didn’t think was possible at this time,” said Rodrigo Quintero, operations digital technologies manager at CEMEX. “We expect our yield improvements and energy savings to be up to seven percent, from the connected AI-based autopilots, which is game changing for our industry. Additionally, this is a giant step in digital transformation towards safe, highly standardized operations, that will help us strengthen our high-quality products portfolio while also ensuring we meet our operational and sustainability goals, and to minimize costs.”
The Autopilot products deployed at CEMEX for the rotary kiln and clinker cooler systems are integrated with plant control systems and OSIsoft PI data infrastructure for scalable, standardized and rapid deployments across multiple lines and plants globally.
The Autopilot products, developed and operationalized on the Petuum AI platform, can ingest data from a variety of sources including unstructured, images, structured, time series, CRM, ERP and others. The Petuum platform provides sophisticated data processing, cleansing and machine/deep learning pipelines used to implement advanced AI that is sensitive to linear, temporal, long range and non-linear data patterns in a range of industrial use cases.
“Our collaboration with CEMEX has allowed us to demonstrate that resource and skill-intensive advanced AI technologies, previously used to address complex problems only in limited settings, can now achieve tangible business impact in a wide range of real-world industrial environments,” said Dr. Eric Xing, CEO of Petuum. “We are able to achieve new levels of automation, accelerating the journey to Industry 4.0. Our vision is to bring AI benefits to a wide range of businesses in a highly cost-effective and fast manner, solving challenges that can’t be addressed by traditional techniques.”
CEMEX and Petuum will continue close collaboration to deploy additional Autopilot use-cases such as emissions reduction, fuel-mix (alternative fuel) optimization, kiln refractory, preventive maintenance, etc. for global cement plants and expand Petuum Industrial AI Autpilot to other operations worldwide.