State-of-Health Assessment for Aero-Engine Based on Density-Distance Clustering and Fuzzy Bayesian Risk

Ning Ma,Laifa Tao,Mingliang Suo,Fan Yang

doi:10.1109/access.2021.3050792

Abstract

State-of-health (SOH) assessment for aero-engine can effectively reduce maintenance cost and operational risk, and is also a significant part of the prognostics and health management (PHM) system. However, the current SOH assessment is usually closely coordinated with other parts of PHM to achieve specific functions. This is not conducive to generalizing the function of SOH assessment. Therefore, this paper proposes a data-driven framework of SOH assessment that mainly includes data preprocessing, pseudo label generation, weight assignment and feature selection, and assessment, which enhances the systematicness of SOH assessment. A combination model based on density-distance clustering and fuzzy Bayesian risk models is designed to generate a pseudo label, select optimal parameter subset, and assign weight. Then, two assessment indicators including state membership degree and health degree are produced based on two fuzzy models for horizontal and vertical comparisons. These two indicators expand the dimensions and perspectives of SOH measurement, which can more comprehensively characterize the health state of the engine. Finally, the correctness and effectiveness of the proposed methodology are verified by the widely used Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset.

Highlights

Aero-engine is one of the typical representatives of complex industrial equipment, who is called ‘‘the heart of airplane’’ [1], [2]
After an in-depth analysis of the characteristics of the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset, we propose a theoretical framework based on labeled-multiple attribute decision-making (LMADM) for data-driven SOH assessment, which mainly includes data preprocessing, pseudo label generation, weight assignment and feature selection, and assessment
We propose a pseudo label generation strategy assisted by a density-distance based clustering (DDC) method proposed in [32]

Summary

INTRODUCTION

Aero-engine is one of the typical representatives of complex industrial equipment, who is called ‘‘the heart of airplane’’ [1], [2]. After an in-depth analysis of the characteristics of the C-MAPSS dataset, we propose a theoretical framework based on labeled-multiple attribute decision-making (LMADM) for data-driven SOH assessment, which mainly includes data preprocessing, pseudo label generation, weight assignment and feature selection, and assessment. The main contributions of this paper are concluded as follows: 1) A framework of data-driven state-of-health assessment is proposed that mainly includes data preprocessing, pseudo label generation, weight assignment and feature selection, and assessment. This highlight tries to make up for the shortcoming that there is no independently and systematically research on the SOH assessment, which can expand the theoretical scope of the PHM system and enhance its application value.

PSEUDO LABEL GENERATION BASED ON DENSITY-DISTANCE CLUSTERING

Findings

CONCLUSION