Overview of Publicly Available Degradation Data Sets for Tasks within Prognostics and Health Management

TL;DR

The paper addresses the fragmentation of degradation data for PHM by compiling and organizing publicly available datasets across diagnostic and prognostic tasks. It extends previous surveys to deliver a comprehensive, metadata-rich overview of datasets with domain, signals, and task, plus source URLs, to support data-driven prognostics. This resource enables researchers to select appropriate data for fault detection, diagnosis, health assessment, or prognosis, and to benchmark methods across domains. By proposing regular updates as new datasets emerge, the work aims to maintain a current, practitioner-oriented landscape for PHM data.

Abstract

Central to the efficacy of prognostics and health management methods is the acquisition and analysis of degradation data, which encapsulates the evolving health condition of engineering systems over time. Degradation data serves as a rich source of information, offering invaluable insights into the underlying degradation processes, failure modes, and performance trends of engineering systems. This paper provides an overview of publicly available degradation data sets.