Interpretable prognostics with concept bottleneck models

doi:10.1016/j.inffus.2025.103427

Interpretable prognostics with concept bottleneck models

2025-06-27

0

OA

AI

DOI：10.1016/j.inffus.2025.103427

Original

Original request for help

Save

Abstract

En 中文

• Concept Bottleneck Models for interpretable deep learning-based RUL prediction using degradation modes as human-understandable concepts. • Evaluation and comparison of several black-box and concept-based models on N-CMAPSS datasets. • Adaptation of test-time interventions for prognostics applications. • Concept Embedding Models achieve both high performance and interpretability even with limited available concepts.

Keywords:

Prognostics

Remaining useful life

Concept Bottleneck Model

Explainable AI

XAI

Interpretability

Concepts

Interpretable prognostics with concept bottleneck models

Abstract

Journal

Organization