学术报告第202018期

报告题目：PHM Analytics for Industrial AI

报 告 人：Piero P. Bonissone （PPB Analytics）

报告时间：2020年12月19日10：00

报告地点：线上报告

Abstract: In the past, analytic model creation was an artisanal process, as models were handcrafted by experienced, knowledgeable model-builders. More recently, the use of meta-heuristics, such as evolutionary algorithms, has provided us with limited levels of automation in model building and maintenance. In the short future, we expect data-driven analytic models to become a commodity. We envision having access to a large number of data-driven models, obtained by a combination of crowdsourcing, cloud-based evolutionary algorithms, outsourcing, in-house development, and legacy models. In this context, the critical issue will be model ensemble selection and fusion, rather than model generation.

First, we will review the application of data-driven analytic models to assets Prognostics and Health Maintenance (PHM) such as aircraft engines, medical imaging devices, and locomotives. We will cover a few case studies on anomaly detection, diagnosis, prediction, and optimization.

Then we will describe the evolution of analytic models with the advent of cloud computing, and propose the use of customized model ensembles on demand, inspired by Lazy Learning. This approach is agnostic with respect to the origin of the models, making it scalable and suitable for a variety of applications. We successfully tested this approach in a regression problem for a power plant management application, using two different sources of models: bootstrapped neural networks, and GP-created symbolic regression models evolved in the cloud. We will present results on the fusion of models for FlyQuest, a GE-sponsored Kaggle competition, in which we crowdsourced the generation of models predicting the estimated runway and gateway arrival (ERA, EGA) over a month of US flights.

Finally, we will explore research trends, challenges and opportunities for Machine Learning techniques in this emerging context of big data and cloud computing.

Bio: Dr. Bonissone is an independent consultant specialized in the use of analytics for Industrial AI applications. He provides consulting services in machine learning (ML) analytic applications, covering project definition and risk abatement, project evaluation, transition from development to deployment, and model maintenance.

He has been an Advanced Analytics Advisor for Parkland. Stanley Black Decker, GE Oil & Gas (prior to their integration with Baker Hughes), and Schlumberger, where he played a key role in Digital Transformation initiatives, such as part forecasting, market intelligence, PHM projects related to equipment reliability, etc.

A former Chief Scientist at GE Global Research (GE GR), where he retired in 2014 after 34 years of service, Dr. Bonissone has been a pioneer in the field of analytics, machine learning, fuzzy logic, AI, and soft computing applications. Over the last decade of his tenure at GE GR, he developed multi-criteria decision making systems to support PHM applications (prescriptive models), ensemble learning to reduce the variance of predictive models, and model lifecycle automation to create, deploy, and maintain analytic models, providing customized performance while adapting to avoid obsolescence. He is a Life Fellow of the IEEE, a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), the International Fuzzy Systems Association (IFSA), and a Coolidge Fellow of GE Global Research. He received the 2012 Fuzzy Systems Pioneer Award from the IEEE CIS. From 2010 to 2015, he chaired the Scientific Committee of the European Centre for Soft Computing. In 2008 he received the II Cajastur International Prize for Soft Computing from the European Centre of Soft Computing. In 2005 he received the Meritorious Service Award from the IEEE CIS.

He served as Editor-in-Chief of the International Journal of Approximate Reasoning for 13 years. He is in the editorial board of five technical journals and is Editor at Large of the IEEE Computational Intelligence Magazine. He co-edited six books and has 150+ publications in refereed journals, book chapters, and conference proceedings, with 11,000+ citations, an H-Index of 55 and an i10-index of 166 (by Google Scholar). He received 74 patents issued by the US Patent Office. From 1982 until 2005 he has been an Adjunct Professor at Rensselaer Polytechnic Institute, in Troy NY, where he supervised 5 PhD theses and 34 Master theses. He co-chaired 12 scientific conferences focused on Multi-Criteria Decision-Making, Fuzzy sets, Diagnostics, Prognostics, and Uncertainty Management in AI. He has been a member of the IEEE Fellow Committee in 2007-09, 2012-14, and 2016-19. Currently he is the Vice-Chair of the IEEE Fellows Committee. In 2002, while serving as President of the IEEE Neural Networks Society (now CIS), he was a member of the IEEE Technical Activity Board. He has been an Executive Committee member of NNC/NNS/CIS society in 1993-2012 and 2016-18, and an IEEE CIS Distinguished Lecturer in 2004-14, and in 2017-19.