Hidden Markov Models and their Application for Predicting Failure Events - Free Tutorial at the 8th International Conference on Computer Technology Applications (ICCTA 2022)
We show how Markov mixed membership models (MMMM) can be used to predict the degradation of assets. We model the degradation path of individual assets, to predict overall failure rates. Instead of a separate distribution for each hidden state, we use hierarchical mixtures of distributions in the exponential family. In our approach the observation distribution of the states is a finite mixture distribution of a small set of (simpler) distributions shared across all states. Using tied-mixture observation distributions offers several advantages. The mixtures act as a regularization for typically very sparse problems, and they reduce the computational effort for the learning algorithm since there are fewer distributions to be found. Using shared mixtures enables sharing of statistical strength between the Markov states and thus transfer learning. We determine for individual assets the trade-off between the risk of failure and extended operating hours by combining a MMMM with a partially observable Markov decision process (POMDP) to dynamically optimize the policy for when and how to maintain the asset.
Lecturer: Prof. Dr. Paul Hofmann
Paul Hofmann is Associate Professor at FH Joanneum, Austria. Before joining FH Joanneum, he was Executive in Residence at Senseforce.io and Chief Innovation Officer at Alpega. He is an Advisory Board Member to Chimera IoT and a Computer Science Advisory Board Member at Stony Brook University. Paul served as CTO AI and Data Science NA, at Accenture Resources. He was the CTO of two successfully acquired startups, SpaceTime Insight (now Nokia) and Saffron Technology (now part of Intel). He also served from 2012 to 2014 as Board Member at Primal, an AI startup. Paul was Vice President Research at SAP Labs at Palo Alto from 2006 to 2011. Paul has also worked for the SAP Corporate Venturing Group. Prior to joining SAP, Paul was Senior Plant Manager at BASF’s Global Catalysts Business Unit in Ludwigshafen, Germany. Paul was visiting scientist at MIT, Cambridge in 2009. Paul was Researcher and Assistant Professor at top German and US Universities, like Northwestern University in Evanston/Chicago, Illinois, USA and at Technical University in Munich, Germany. He was a visiting scientist at MIT and gave lectures at UC Santa Cruz, HPI Postdam, Dresden Technical University and Joanneum Graz. He received his Ph.D. in Physics at the Darmstadt University of Technology, Germany, after completing his bachelor in biotechnology and a master’s degree in Chemistry from the University of Vienna.