ML and Analytics in Operations and Maintenance

​​With maintenance and operations data being generated, stored, and shared across a wide variety of locations and systems, making practical use of ​​it can be a challenge, since mining such disparate data can be difficult.  This is why data quality and data excellence is so important to these teams today.

In addition, ease-of-use and the  democracy of analytics is important as well.  Until recently, most software programs available required specialized expertise and investments in traditional, and costly, analytics solutions.  These solutions also have all the attendant services costs such as implementation and maintenance. In addition, the skill sets needed to use these solutions have traditionally been left to trained data scientists and statisticians assigned to organizations' quant staffs.

For years, analytics and deep learning solutions were deemed suitable only for large organizations with dedicated quant staffs.  More recently, ML and AI capabilities are increasingly in demand.  IT and OT teams commonly consisted of people with skills that ranged from report writing, BI, and SQL programming expertise, to statisticians and data scientists skilled in various forms of predictive analytics and quantitative analysis.  Often, many industrial organizations had been reluctant to fund analytics and AI and ML projects at the operations and maintenance levels.

More recently, however, such​ higher-level solutions have been introduced to the market that are designed for both IT and OT users.  These solutions are designed for use by quant staff and business users alike.  In terms of industrial digital transformation, the latter​ now have more powerful and accurate tools from which to run various operations-specific predictive models and scenarios, in real-time if necessary, which is something that had not been generally available until recently.

These topics, and more, will be discussed in our presentations and panel discussions.

S3: 3:00 PM Track 2 (Oceans 5&7)