Machine Learning for Predictive Maintenance, 5 credits

The courses is for professionals and part of the programme MAISTR (hh.se/maistr) where participants can study the entire programme or individual courses. The course is part of the course track machine learning and is held online in English.

The course covers the following topics:
Definition and terminology of relevant concepts in PdM
PdM task formulation, i.e. determine approaches and learning settings for given problems
Data engineering for time series data, including transformation, anomalous value detection, missing value imputation, outlier removal, etc.
PdM evaluation metric, given concrete applications and its formulation
Benchmarking the performance with traditional approaches
Transfer learning for fault detection and remaining useful life prediction
Survival analysis for PdM focusing on the evaluation metric and specialized cost function learning
Interpretability of the PdM machine learning models, and hybrid approaches