Authors:
Ivan Ryzhikov
1
;
Mika Liukkonen
2
;
Ari Kettunen
2
and
Yrjö Hiltunen
1
Affiliations:
1
Department of Environmental Science, University of Eastern Finland, Yliopistonranta 1, 70210, Kuopio, Finland
;
2
Sumitomo SHI FW Energia OY, Relanderinkatu 2, 78200, Varkaus, Finland
Keyword(s):
Fault Detection, Feature Creation, Data-driven Modeling, Machine Learning, Risk Estimation, Deep Neural Network.
Abstract:
In this study, we consider a fault prediction problem for the case when there are no variables by which we could determine that the system is in the fault state. We propose an approach that is based on constructing auxiliary variable, thus it is possible to reduce the initial problem to the supervised learning problem of risk estimation. The suggested target variable is an indicator showing how close the system is to the fault that is why we call it a risk estimation variable. The risk is growing some time before the actual fault has happened and reaches the highest value in that timestamp, but there is a high level of uncertainty for the times when the system has been operating normally. We suggest specific criterion that takes uncertainty of risk estimation into account by tuning three weighting coefficients. Finally, the supervised learning problem with risk variable and specific criterion can be solved by the means of machine learning. This work confirm that data-driven risk esti
mation can be integrated into digital services to successfully manage plant operational changes and support plant prescriptive maintenance. This was demonstrated with data from a commercial circulating fluidized bed firing various biomass and residues but is generally applicable to other production plants.
(More)