Minhee Kim

Bio: Minhee Kim is an academic researcher from University of Wisconsin-Madison. The author has contributed to research in topics: Prognostics & Recurrent neural network. The author has an hindex of 3, co-authored 7 publications receiving 36 citations.

A Bayesian deep learning framework for interval estimation of remaining useful life in complex systems by incorporating general degradation characteristics

Abstract: Deep learning has emerged as a powerful tool to model complicated relationships between inputs and outputs in various fields including degradation modeling and prognostics. Existing deep learning-b...

A Generic Health Index Approach for Multisensor Degradation Modeling and Sensor Selection

Abstract: With recent development in sensor technology, multiple sensors have been widely adopted to monitor the degradation of a single unit simultaneously. The challenge of multisensor degradation modeling lies in that the sensor signals are often correlated and may contain only partial or even no information on the degradation status of a unit. To address these issues, this paper proposes a novel data fusion method that constructs a 1-D health index (HI) via automatically selecting and combining multiple sensor signals to better characterize the degradation process. In particular, this paper develops a new latent linear model that constructs the HI and selects informative sensors in a unified manner. Compared to the existing literature, the proposed method enjoys several unique advantages: 1) being able to derive the best linear unbiased estimator of the fusion coefficients; 2) offering high computational efficiency; 3) not requiring to know the exact value of the failure threshold; and 4) exhibiting general applicability in practice by not imposing restrictive assumptions on the degradation process. Simulation studies are presented to illustrate the effectiveness and evaluate the sensitivity of the proposed method. A case study on the degradation of aircraft gas turbine engines is also performed which shows a better prognostic performance of the proposed method compared with existing approaches. Note to Practitioners —This paper is motivated by the practical issue of degradation modeling and prognostics when multiple sensors simultaneously monitor the degradation status of a unit. Specifically, there are two fundamental questions involved, including: 1) how to screen out noninformative sensors and 2) how to properly combine the information from the selected sensor signals to accurately estimate the underlying degradation status of the unit. The novelty of this paper lies in developing an innovative latent model that tackles these two challenging questions in an integrated manner. There are four main steps involved when implementing the proposed method: 1) collecting multiple sensor signals and failure time of historical units; 2) selecting the informative sensors and deriving the optimal weight for each selected sensor; 3) constructing the health indices (HIs) of in-service units; and 4) predicting the remaining useful life of the in-service units using the constructed HIs. The proposed method is very useful when the degradation is under a single failure mode in a single environmental condition. In the future research, we will study the extension of the proposed model when sensor signals have a nonlinear relationship, as well as when the degradation process is under more complex scenarios such as multiple failure modes and multiple operation conditions.

Transfer learning of memory kernels for transferable coarse-graining of polymer dynamics

Abstract: The present work concerns the transferability of coarse-grained (CG) modeling in reproducing the dynamic properties of the reference atomistic systems across a range of parameters. In particular, we focus on implicit-solvent CG modeling of polymer solutions. The CG model is based on the generalized Langevin equation, where the memory kernel plays the critical role in determining the dynamics in all time scales. Thus, we propose methods for transfer learning of memory kernels. The key ingredient of our methods is Gaussian process regression. By integration with the model order reduction via proper orthogonal decomposition and the active learning technique, the transfer learning can be practically efficient and requires minimum training data. Through two example polymer solution systems, we demonstrate the accuracy and efficiency of the proposed transfer learning methods in the construction of transferable memory kernels. The transferability allows for out-of-sample predictions, even in the extrapolated domain of parameters. Built on the transferable memory kernels, the CG models can reproduce the dynamic properties of polymers in all time scales at different thermodynamic conditions (such as temperature and solvent viscosity) and for different systems with varying concentrations and lengths of polymers.

An adaptive sensor selection framework for multisensor prognostics

Abstract: Recent advances in sensor technology have made it possible to monitor the degradation of a system using multiple sensors simultaneously. Accordingly, many neural network-based prognostic models hav...

A Survey on Industrial Information Integration 2016–2019

Abstract: Industrial information integration engineering (IIIE) is a set of foundational concepts and techniques that facilitate the industrial information integration process. In recent years, many applicat...

A Bayesian deep learning framework for interval estimation of remaining useful life in complex systems by incorporating general degradation characteristics

Abstract: Deep learning has emerged as a powerful tool to model complicated relationships between inputs and outputs in various fields including degradation modeling and prognostics. Existing deep learning-b...