A Latent Variable-Based Multitask Learning Approach for Degradation Modeling of Machines With Dependency and Heterogeneity
- 7 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-15
Abstract
Remaining useful lifetime (RUL) prediction based on degradation signals of sensors is of critical importance in prognostics and health management (PHM) of machines in manufacturing systems. The machines are often under the same operational and environmental condition and thus show dependent but heterogeneous degradation profiles. However, many existing studies ignored these characteristics among machines, leading to poor RUL prediction results especially when missing data exists. To address this issue, this paper develops a latent variable-based multi-task learning (LVMTL) approach for degradation modeling and prognostics of machines based on multiple sensor signals. Specifically, we first adopt a polynomial model to fit the degradation processes of machines’ health indices (HIs), which are estimated based on multiple sensor signals. Taking the HIs as latent variables, we develop an LVMTL model aiming to capture the dependency and heterogeneity among machines. For parameter estimation, we develop a unique iterated quadratic optimization-integrated expectation-maximum (QOIEM) algorithm that updates model parameters via quadratic programming (QP) and maximum a posteriori-based expectation-maximum (MAP-EM) considering the principles for estimating an HI. The QOIEM has been proven to have satisfactory convergence performance in theory in this study. Numerical experiments and a real case study on aircraft turbine engines have been implemented to compare the prognosis performance and robustness of incomplete datasets for the proposed and benchmark methods.Keywords
Funding Information
- National Key Research and Development Program of China (2022YFB3402100)
- National Science Foundation of China (72101148)
- National Aeronautics and Space Administration through the University of Central Florida's NASA Florida Space Grant Consortium and Space Florida
- National Science Foundation of Shanghai (22ZR1433000)
- Shanghai Chenguang Program (21CGA12)
This publication has 39 references indexed in Scilit:
- A study of the relationship between coulombic efficiency and capacity degradation of commercial lithium-ion batteriesEnergy, 2018
- Iterative multi-task learning for time-series modeling of solar panel PV outputsApplied Energy, 2018
- Bearing performance degradation assessment based on a combination of empirical mode decomposition and k-medoids clusteringMechanical Systems and Signal Processing, 2017
- A review on prognostic techniques for non-stationary and non-linear rotating systemsMechanical Systems and Signal Processing, 2015
- Proton exchange membrane fuel cell degradation prediction based on Adaptive Neuro-Fuzzy Inference SystemsInternational Journal of Hydrogen Energy, 2014
- qpOASES: a parametric active-set algorithm for quadratic programmingMathematical Programming Computation, 2014
- A naive Bayes model for robust remaining useful life prediction of lithium-ion batteryApplied Energy, 2014
- An integrated framework for online diagnostic and prognostic health monitoring using a multistate deterioration processReliability Engineering & System Safety, 2014
- Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful lifeReliability Engineering & System Safety, 2012
- A generic probabilistic framework for structural health prognostics and uncertainty managementMechanical Systems and Signal Processing, 2012