Accuracy Improvement of a Degradation Model for Failure Prognosis of Miter Gates

Abstract

Aims to address the issue that the degradation model may not accurately represent the underly true degradation physics in failure prognostics of miter gates, this paper presents a framework for degradation model correction using historical strain measurements. A stochastic gap growth model with uncertain model parameters is employed as the simplified degradation model to predict the gap evolution. A dynamic model discrepancy quantification framework is then proposed to correct the simplified model by representing the model bias term as a data-driven surrogate model. After that, a maximum likelihood estimation method is developed to estimate the parameters of the data-driven surrogate model using strain measurements. Additionally, the uncertainty in the model parameters of the simplified model is reduced using Bayesian method. The corrected and updated simplified degradation model is then employed for failure prognostics of a miter gate. Results of a case study show that the updated degradation model can accurately predict multi-step ahead gap growth while performing damage prognostics and remaining useful life estimation.