InTech

JUL-AUG 2019

Issue link: http://intechdigitalxp.isa.org/i/1151003

Contents of this Issue

Navigation

Page 13 of 53

14 INTECH JULY/AUGUST 2019 WWW.ISA.ORG COVER STORY analytics available to analyze the data from plant sensors. Jay Cei, COO at Ulbrich, says, "Col- lecting machine and sensor data from our factories and integrating that with ERP system data will help us under- stand the intricate relationships be- tween equipment, people, suppliers, and customers. Learning what their IoT data means is critical for understanding how the company can become more productive and efficient in the future, Cei says. DJ Penix, president of SAS implementa- tion partner Pinnacle Solutions, says, "Streaming analytics will not only help Ulbrich understand what is happening now with their machines. It will also enable them to predict future events, such as when a machine needs mainte- nance before it breaks down." The software provides a simplified way for any user to prepare station - ary and streaming IoT data for analysis without specialized skills, says Penex. Whether a data scientist, business manager, or someone in between, they can use SAS Analytics for IoT to that it had installed "AI-based autopi- lots" for its rotary kiln and clinker cool- er systems that will "autosteer" its ce- ment plants and enable autonomous, operator-supervised plant operations. Cemex used OSIsoft PI systems to power Petuum Industrial AI Autopi- lot products. The two work with plant control systems to provide precise real-time forecasts for significant pro- cess variables, prescriptions for critical control variables, and a supervised au- tosteer function aligned with business objectives while staying within appli- cable static and dynamic constraints. The PI systems fuel real-time predictive and prescriptive recommendations. Rodrigo Quintero, operations digital technologies manager for Cemex, says, "Petuum Industrial AI Autopilot helped us achieve something we didn't think was possible at this time: yield improve- ments and energy savings up to 7 per- cent, which is game changing for our industry. Additionally, this is a giant step in digital transformation toward safe, highly standardized operations, that will help us strengthen our high-quality products portfolio while also ensuring we meet our operational and sustain- ability goals, and minimize costs." The Autopilot products can ingest data from a variety of sources, including unstructured, images, structured, time series, customer relationship manage- ment (CRM) data, enterprise resource planning (ERP) data, and others. The Petuum platform provides sophisti- cated data processing, data cleansing, and machine/deep learning pipelines to implement advanced AI that is sen- sitive to linear, temporal, long range, and nonlinear data patterns in a range of industrial use cases. AI for operational excellence Staying ahead of maintenance and pro- duction challenges to keep precision metals rolling out of its plants on time is a high priority for Ulbrich Stainless Steel & Specialty Metals. That is why the global company chose SAS Analytics for IoT to gain access to the latest suite of AI, machine learning, and streaming Industrial AI applications fall into three categories: AI for assets, AI for processes, and AI for operational excellence and/or business agility. The following specific examples have been implemented by users of SAS Artificial Intelligence Solutions. • Turbine engines. Model drivers of unscheduled downtime; identify optimal maintenance scheduling. • Wind turbines. Identify turbines performing below average; model drivers of capital component failures; improve planned maintenance. • Gas treatment. Identify predictors of foaming/flooding events; identify optimal operational parameters; optimize reagent utilization. • Aircraft parts maintenance. Generate removal advice for specific parts; forecast part removal and alert dispatching for optimized part delivery and availability. n Examples of industrial AI/IoT applications Kyoka Nakagawa is chief engineer, Value Creation Depart- ment, Digital Transformation Division, Digital Solution Center at Honda R&D Co., Ltd., Japan. She is also one of 40 women driving the adoption of artificial intelligence in business and industry profiled in IBM's List of Women Leaders in AI. Kyoka is leading Honda research and development's ef- forts to train its automotive engineers to use advanced IBM analytics tools, helping them to better understand driver behavior, to increase the reliability of cars, and to design a more personalized driving experience. What was the challenge you sought to address with AI? The challenge was to raise our engineers' interest in wanting to use other people's data that could enhance their analysis. I offered an open proof of concept for people who have different engineering expertise for data they had never used, which helped engineers imagine how they can enlarge their analysis capability with other sources of data. What benefits are you realizing? Teaching AI helps people to organize their own thinking and their processes and helps focus their core of knowledge. It was a surprise to me that when AI functions well at work, business people seem to create more ideas to do better work. It may be because AI helps unburden some of their workload. What do you wish you knew when you first started with your work with AI that you know now? AI planning requires special skills, and not every project ends in success. n Honda R&D: AI planning requires special skills

Articles in this issue

Links on this page

Archives of this issue

view archives of InTech - JUL-AUG 2019