Interpretable Prognostics with Concept Bottleneck Models

TL;DR

This paper introduces Concept Bottleneck Models (CBMs) for prognostics, providing inherently interpretable RUL predictions that match or outperform black-box models, with the added benefit of domain expert intervention and high-level concept explanations.

Contribution

It applies CBMs to RUL prediction, demonstrating their interpretability and competitive performance compared to traditional black-box models in prognostics.

Findings

CBMs achieve comparable or better accuracy than black-box models.

CBMs offer high interpretability through high-level concepts.

Domain experts can intervene on concept activations at test-time.

Abstract

Deep learning approaches have recently been extensively explored for the prognostics of industrial assets. However, they still suffer from a lack of interpretability, which hinders their adoption in safety-critical applications. To improve their trustworthiness, explainable AI (XAI) techniques have been applied in prognostics, primarily to quantify the importance of input variables for predicting the remaining useful life (RUL) using post-hoc attribution methods. In this work, we propose the application of Concept Bottleneck Models (CBMs), a family of inherently interpretable neural network architectures based on concept explanations, to the task of RUL prediction. Unlike attribution methods, which explain decisions in terms of low-level input features, concepts represent high-level information that is easily understandable by users. Moreover, once verified in actual applications, CBMs enable domain experts to intervene on the concept activations at test-time. We propose using the different degradation modes of an asset as intermediate concepts. Our case studies on the New Commercial Modular AeroPropulsion System Simulation (N-CMAPSS) aircraft engine dataset for RUL prediction demonstrate that the performance of CBMs can be on par or superior to black-box models, while being more interpretable, even when the available labeled concepts are limited. Code available at \href{https://github.com/EPFL-IMOS/concept-prognostics/}{\url{github.com/EPFL-IMOS/concept-prognostics/}}.