Practical options for selecting data-driven or physics-based prognostics algorithms with reviews

doi:10.1016/j.ress.2014.09.014

Return

Practical options for selecting data-driven or physics-based prognostics algorithms with reviews

2015-01-01

341

PRE

Dawn An

Nam Ho Kim

Joo-Ho Choi *

DOI：10.1016/j.ress.2014.09.014

Original

Original request for help

Save

Abstract

En 中文

This paper is to provide practical options for prognostics so that beginners can select appropriate methods for their fields of application. To achieve this goal, several popular algorithms are first reviewed in the data-driven and physics-based prognostics methods. Each algorithm's attributes and pros and cons are analyzed in terms of model definition, model parameter estimation and ability to handle noise and bias in data. Fatigue crack growth examples are then used to illustrate the characteristics of different algorithms. In order to suggest a suitable algorithm, several studies are made based on the number of data sets, the level of noise and bias, availability of loading and physical models, and complexity of the damage growth behavior. Based on the study, it is concluded that the Gaussian process is easy and fast to implement, but works well only when the covariance function is properly defined. The neural network has the advantage in the case of large noise and complex models but only with many training data sets. The particle filter and Bayesian method are superior to the former methods because they are less affected by noise and model complexity, but work only when physical model and loading conditions are available. (C) 2014 Elsevier Ltd. All rights reserved.

Keywords:

Data-driven prognostics

Physics-based prognostics

Neural network

Gaussian process regression

Particle filter

Bayesian inference

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.