A Method for Aero-Engine Gas Path Anomaly Detection Based on Markov Transition Field and Multi-LSTM

Yang Jin,Chaoqi Zhang,Yixuan Wang,Langfu Cui,Junle Wang,Qingzhen Zhang,Yan Shi,Cong Lin

doi:10.3390/aerospace8120374

Abstract

There are some problems such as uncertain thresholds, high dimension of monitoring parameters and unclear parameter relationships in the anomaly detection of aero-engine gas path. These problems make it difficult for the high accuracy of anomaly detection. In order to improve the accuracy of aero-engine gas path anomaly detection, a method based on Markov Transition Field and LSTM is proposed in this paper. The correlation among high-dimensional QAR data is obtained based on Markov Transition Field and hierarchical clustering. According to the correlation analysis of high-dimensional QAR data, a multi-input and multi-output LSTM network is constructed to realize one-step rolling prediction. A Gaussian mixture model of the residuals between predicted value and true value is constructed. The three-sigma rule is applied to detect outliers based on the Gaussian mixture model of the residuals. The experimental results show that the proposed method has high accuracy for aero-engine gas path anomaly detection.

Highlights

Aero-engine is the heart of an aircraft, and is the system with high failure rate and complex maintenance
The aero-engine gas path is composed of Bleed Monitoring Computer (BMC), Temperature Control Thermostat (ThC), Solenoid Thermostat (Ths), Regulated Pressure Transducer (Pr), Transferred Pressure Transducer (Pt), PreCooler Exchanger (PCE), OverPressure Valve (OPV), Fan Air Valve (FAV), Intermediate Pressure Valve (IPCV), High Pressure Valve (HPV), and so on
The correlation among Quick Access Recorder (QAR) data is analyzed by Markov transition matrix and hierarchical clustering method

Summary

Introduction

Aero-engine is the heart of an aircraft, and is the system with high failure rate and complex maintenance. Gas path anomaly detection is the top priority in aero-engine anomaly detection research [2]. The Quick Access Recorder (QAR) data records the complete flight process of aircraft [3], and its sampling frequency is up to 1 Hz, which can be applied to detect anomalies of aero-engine gas path. Hao Sun [4] proposed a weakly supervised method based on mapping relationship mining and improved density peak clustering for gas-path anomaly detection of civil aero-engines. LSTM model has advantages of processing the nonlinear aero-engine gas path monitoring data, automatically selecting the optimal time interval and memorizing long-time historical data.

Introduction of Aero-Engine Gas Path and Monitoring Data

Gaussian Distribution Model Based on Prediction Error

Findings

Conclusions