Deep Hierarchical Knowledge Loss for Fault Intensity Diagnosis

TL;DR

This paper proposes a deep hierarchical knowledge loss framework for fault intensity diagnosis, improving class dependency modeling and fault recognition accuracy in industrial datasets.

Contribution

It introduces a novel hierarchical tree loss, focal hierarchical tree loss, and group tree triplet loss, enhancing fault diagnosis performance with hierarchical constraints.

Findings

Outperforms recent state-of-the-art FID methods on four industrial datasets.

Improves recognition of subtle faults through hierarchical knowledge modeling.

Demonstrates superior results across diverse real-world datasets.

Abstract

Fault intensity diagnosis (FID) plays a pivotal role in intelligent manufacturing while neglecting dependencies among target classes hinders its practical deployment. This paper introduces a novel and general framework with deep hierarchical knowledge loss (DHK) to achieve hierarchical consistent representation and prediction. We develop a novel hierarchical tree loss to enable a holistic mapping of same-attribute classes, leveraging tree-based positive and negative hierarchical knowledge constraints. We further design a focal hierarchical tree loss to enhance its extensibility and devise two adaptive weighting schemes based on tree height. In addition, we propose a group tree triplet loss with hierarchical dynamic margin by incorporating hierarchical group concepts and tree distance to model boundary structural knowledge across classes. The joint two losses significantly improve the recognition of subtle faults. Extensive experiments are performed on four real-world datasets from various industrial domains (three cavitation datasets from SAMSON AG and one publicly available dataset) for FID, all showing superior results and outperforming recent state-of-the-art FID methods.