Interaction models for remaining useful life estimation

TL;DR

This paper introduces a scalable interaction model that combines multiple feature extractors for improved remaining useful life estimation of industrial equipment, achieving state-of-the-art results on benchmark datasets.

Contribution

The paper presents a novel interaction model that integrates diverse feature extraction blocks for more accurate RUL prediction, advancing beyond existing single-approach methods.

Findings

Achieved state-of-the-art results on C-MAPSS benchmark

Validated model scalability and prediction stability

Demonstrated improved accuracy over traditional methods

Abstract

The paper deals with the problem of controlling the state of industrial devices according to the readings of their sensors. The current methods rely on one approach to feature extraction in which the prediction occurs. We proposed a technique to build a scalable model that combines multiple different feature extractor blocks. A new model based on sequential sensor space analysis achieves state-of-the-art results on the C-MAPSS benchmark for equipment remaining useful life estimation. The resulting model performance was validated including the prediction changes with scaling.