A Robust Health Indicator for Rotating Machinery Under Time-Varying Operating Conditions

Seokgoo Kim,Joo-Ho Choi,Yun-Ho Seo,Hyung Jun Park

doi:10.1109/access.2022.3140755

Abstract

Bearing is an essential component whose failure leads to costly downtime in operation. Therefore, it is important to establish an accurate health indicator (HI), using which the remaining useful life can be reliably predicted. To date, most of the health assessment for bearing have been focused on the constant operating condition while in practice, it operates under various operating conditions (rotating speed and loading). Motivated by this, this paper proposes a method to extract robust HI which undergoes variable operating conditions. The idea is to cluster the operating conditions regimes, and develop HI based on the Mahalanobis distance using the optimal features subset in each regime. To validate the effectiveness, bearing run-to-fail experiment is performed under variable operating condition, and proposed HI is compared with the traditional statistical features. The remaining useful life is predicted by the data augmentation prognostics algorithm which was to overcome data deficiency problem.

Highlights

Bearings are considered as one of the most critical components in many rotating machineries since their failure leads to the high costs in the maintenance
In the fault diagnosis and prognosis of bearing, effective features extracted from the vibration signal may differ greatly by the operating conditions
The health assessment of the bearings when subjected to the variable operating conditions should incorporate this aspect to implement the prognosis successfully

Summary

Introduction

Bearings are considered as one of the most critical components in many rotating machineries since their failure leads to the high costs in the maintenance. To prevent these failures, Prognostics and Health Management (PHM) techniques have been actively developed, which is an enabling discipline that uses sensors to extract features, perform diagnosis to assess the health and prognosis to predict the remaining useful life (RUL) [1]. Many review papers have addressed the PHM techniques for bearing applications from anomaly detection to RUL prognosis (e.g., [2]–[4] among others). The HI construction has been driven by the time statistical features

Objectives

Methods

Findings

Conclusion