Using recurrent neural networks to predict the time for an event

Abstract

[en] One of the main concerns of the manufacturing industry is the constant threat of unplanned stops. Even if the maintenance guidelines are followed for all the components of the line, these downtimes are common and they affect the productivity. Most of what is done nowadays in the manufacturing plants involves classic statistics, and sometimes online monitoring. However, in most of the industries the data related to the process is monitored and saved for regulatory purposes. Unfortunately it’s barely used, while the actual technologies offer a wide horizon of possibilities. The time to an event is a primary outcome of interest in many fields e.g., medical research, customer churn, etc. And we think that it’s also very interesting for Predictive Maintenance. The time to an event (or in this context time to failure) is typically positively skewed, subject to censoring, and explained by time varying variables. Therefore conventional statistic learning techniques such as linear regression or random forests don’t apply. Instead we have to relate on more complex methods. In particular we focus on the WTTE-RNN framework proposed by Egil Martinsson, which employs Recurrent Neural Networks to predict the parameters of a Weibull Distribution. The result is a flexible and powerful model specially suited for timedistributed data that can be organized in batches.