Aircraft Engine Prognostics Based on Informative Sensor Selection and Adaptive Degradation Modeling with Functional Principal Component Analysis

Abstract

Engine prognostics are critical to improve safety, reliability, and operational efficiency of an aircraft. With the development in sensor technology, multiple sensors are embedded or deployed to monitor the health condition of the aircraft engine. Thus, the challenge of engine prognostics lies in how to model and predict future health by appropriate utilization of these sensor information. In this paper, a prognostic approach is developed based on informative sensor selection and adaptive degradation modeling with functional data analysis. The presented approach selects sensors based on metrics and constructs health index to characterize engine degradation by fusing the selected informative sensors. Next, the engine degradation is adaptively modeled with the functional principal component analysis (FPCA) method and future health is prognosticated using the Bayesian inference. The prognostic approach is applied to run-to-failure data sets of C-MAPSS test-bed developed by NASA. Results show that the proposed method can effectively select the informative sensors and accurately predict the complex degradation of the aircraft engine.Sensors 2020, 20, 920 2 of 21 reducing unnecessary maintenance and minimizing operational costs, prognostics have been an active research field for aircraft engine applications [3].Generally, the existing methods pertaining to aircraft engine prognostics can be classified into two categories: model-based and data-driven methods. For model-based methods, a mathematical model that can describe the engine health degradation process that is normally required to be constructed according to physical failure characteristics before prediction. Some typical model-based methods have been developed for engine health estimation and RUL prediction, such as the Markov model-based [4,5] and particle filtering-based method [6,7]. While model-based methods enable improved accuracy of engine prognostics, certain assumptions and simplifications of the adopted models may pose limitations on their practical deployment. With the rapid development of data mining techniques and the growing availability of health monitoring data, data-driven methods attract increasing attention. Data-driven methods utilize the information extracted or learned from observed data to identify the degradation behavior and predict the future health condition without using any particular physical model [8,9]. In this view, data-driven methods may be the more applicable prognostic solution for complicated systems, as aero-engines that have limited knowledge of physics-of-failure but have massive multi-sensor monitoring data. Among the data-driven prognostic methods, machine learning and statistical approaches are two popular branches. The common machine learning techniques used for prognostics include support vector regression [10], artificial neural network [11,12], fuzzy logic [13], etc. Machine learning methods are capable of dealing with prognostic issues of complex systems, but the predicted results are hard to be explained because ...

Remaining Useful Life Estimation of Turbofan Engines with Deep Learning Using Change-Point Detection Based Labeling and Feature Engineering

“…Each training and test dataset of turbofan engines contained outputs from 21 sensors. The characteristics of sensors, such as prognosability, monotonicity, trendability, and robustness, along with detailed analyses, can be found in [33,[56][57][58].…”

Exploring rainfall variabilities using statistical functional data analysis

“…It is used to reduce the dimensionality of functional data, capturing the largest amount of variance and exhibiting various aspects of the underlying data. The FPCA has been used to interpret lactate curves [9], analyse kinematic data [10], gene classification [11], explore variations in glomerular filtration rate curves [12], and model aircraft degradation [13]. Suhaila [14] recently applied the FPCA techniques to determine the variations of the multivariate El Niño Southern Oscillation Index (MEI).…”

Comparative Study of Health Monitoring Sensors based on Prognostic Performance

“…Liu et al (Liu et al, 2015) proposed entropy-based strategy to quantitatively select sensors that reflect the monotonic trend during degradation to perform engine health prognosis. Zhang et al (Zhang et al, 2020) and Coble et al (Coble and Hines, 2011) developed an additional selection metric considering the trend consistency of sensor data among different systems and validated with engine simulation datasets. The existing literatures for sensor selections are mainly focused on evaluating the sensors data to the degradation trend using metrics of monotonicity, correlation and robustness (Li et al, 2015;Zhang, Zhang and Xu, 2016;Liu et al, 2017;She and Jia, 2021).…”