• Journal of the Korean Institute of Gas
• /
• v.24 no.6
• /
• pp.91-97
• /
• 2020

Lithium-ion batteries (LIBs) have a longer lifespan, higher energy density, and lower self-discharge rates than other batteries, therefore, they are preferred as an Energy Storage System (ESS). However, during years 2017-2019, 28 ESS fire accidents occurred in Korea, and accurate capacity estimation of LIB is essential to ensure safety and reliability during operations. In this study, data-driven modeling that predicts capacity changes according to the charging cycle of LIB was conducted, and developed models were compared their performance for the selection of the optimal machine learning model, which includes the Decision Tree, Ensemble Learning Method, Support Vector Regression, and Gaussian Process Regression (GPR). For model training, lithium battery test data provided by NASA was used, and GPR showed the best prediction performance. Based on this study, we will develop an enhanced LIB capacity prediction and remaining useful life estimation model through additional data training, and improve the performance of anomaly detection and monitoring during operations, enabling safe and stable ESS operations.

• Nuclear Engineering and Technology
• /
• v.54 no.6
• /
• pp.2107-2119
• /
• 2022

Accurate remaining useful life (RUL) prediction for critical components of nuclear power equipment is an important way to realize aging management of nuclear power equipment. The electric gate valve is one of the most safety-critical and widely distributed mechanical equipment in nuclear power installations. However, the electric gate valve's extended service in nuclear installations causes aging and degradation induced by crack propagation and leakages. Hence, it is necessary to develop a robust RUL prediction method to evaluate its operating state. Although the particle filter(PF) algorithm and its variants can deal with this nonlinear problem effectively, they suffer from severe particle degeneracy and depletion, which leads to its sub-optimal performance. In this study, we combined the whale algorithm with regularized particle filtering(RPF) to rationalize the particle distribution before resampling, so as to solve the problem of particle degradation, and for valve RUL prediction. The valve's crack propagation is studied using the RPF approach, which takes the Paris Law as a condition function. The crack growth is observed and updated using the root-mean-square (RMS) signal collected from the acoustic emission sensor. At the same time, the proposed method is compared with other optimization algorithms, such as particle swarm optimization algorithm, and verified by the realistic valve aging experimental data. The conclusion shows that the proposed method can effectively predict and analyze the typical valve degradation patterns.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.1-11
• /
• 2021

Recently, the importance of preventive maintenance has been emerging since failures in a complex system are automatically detected due to the development of artificial intelligence techniques and sensor technology. Therefore, prognostic and health management (PHM) is being actively studied, and prediction of the remaining useful life (RUL) of the system is being one of the most important tasks. A lot of researches has been conducted to predict the RUL. Deep learning models have been developed to improve prediction performance, but studies on identifying the importance of features are not carried out. It is very meaningful to extract and interpret features that affect failures while improving the predictive accuracy of RUL is important. In this paper, a total of six popular deep learning models were employed to predict the RUL, and identified important variables for each model through SHAP (Shapley Additive explanations) that one of the explainable artificial intelligence (XAI). Moreover, the fluctuations and trends of prediction performance according to the number of variables were identified. This paper can suggest the possibility of explainability of various deep learning models, and the application of XAI can be demonstrated. Also, through this proposed method, it is expected that the possibility of utilizing SHAP as a feature selection method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1151-1156
• /
• 2023

In this paper, we propose a deep learning model that utilizes charge/discharge data from initial lithium-ion batteries to predict the remaining useful life of lithium-ion batteries. We build the DMP using the PNP model. To demonstrate the performance of DMP, we organize DML using the LSTM model and compare the remaining useful life prediction performance of lithium-ion batteries between DMP and DML. We utilize the RMSE and RMSPE error measurement methods to evaluate the performance of DMP and DML models using test data. The results reveal that the RMSE difference between DMP and DML is 144.62 [Cycle], and the RMSPE difference is 3.37 [%]. These results indicate that the DMP model has a lower error rate than DML. Based on the results of our analysis, we have showcased the superior performance of DMP over DML. This demonstrates that in the field of lithium-ion batteries, the PNP model outperforms the LSTM model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3242-3265
• /
• 2023

Ensuring reliability of a machinery system involve the prediction of remaining useful life (RUL). In most RUL prediction approaches, noise is always considered for removal. Nevertheless, noise could be properly utilized to enhance the prediction capabilities. In this paper, we proposed a novel RUL prediction approach based on noise injection and a Kalman filter ensemble of modified bagging predictors. Firstly, we proposed a new method to insert Gaussian noises into both observation and feature spaces of an original training dataset, named GN-DAFC. Secondly, we developed a modified bagging method based on Kalman filter averaging, named KBAG. Then, we developed a new ensemble method which is a Kalman filter ensemble of KBAGs, named DKBAG. Finally, we proposed a novel RUL prediction approach GN-DAFC-DKBAG in which the optimal noise-injected training dataset was determined by a GN-DAFC-based searching strategy and then inputted to a DKBAG model. Our approach is validated on the NASA C-MAPSS dataset of aero-engines. Experimental results show that our approach achieves significantly better performance than a traditional Kalman filter ensemble of single learning models (KESLM) and the original DKBAG approaches. We also found that the optimal noise-injected data could improve the prediction performance of both KESLM and DKBAG. We further compare our approach with two advanced ensemble approaches, and the results indicate that the former also has better performance than the latters. Thus, our approach of combining optimal noise injection and DKBAG provides an effective solution for RUL estimation of machinery systems.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.04a
• /
• pp.682-687
• /
• 2000

In this research the remaining service life of the concrete due to the steel corrosion was predicted by three cases; causing carbonation, using sea sand, using deicing salts. In case of deterioration by carbonation, effective carbonation depth, effective coverage depth and relative humidity are considered for predicting method. In case of using sea sand, predicting method is made of rust growth equation from polarization resistance method. In case of using deicing salts, predicting method is made of transformation of Fick's law. Three methods are very useful in predicting service life of concrete.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1998.10b
• /
• pp.731-736
• /
• 1998

Deteriorations of concrete are governed by combined factors such as environmental stressors, processes and rates of deteriorations. Due to this reason, it's very difficult and important issue to predict quantitatively the service life of concrete structure. From this pont of views, the purpose of this study is to propose the approaches on the further development for predicting the remaining service life of concrete by analyzing the deteriorations mechanism and evaluating the existing models.

• KEPCO Journal on Electric Power and Energy
• /
• v.3 no.1
• /
• pp.23-28
• /
• 2017

The life management technology becomes important as the failure risk of the aged power transformers increases. Asset management technology, therefore, has been developed to evaluate the remaining life and build replacement strategies of power transformers, which enables an optimal investment decisions based on reliability and economic feasibility. The remaining life assessment technology uses data related to such as installation, operation, maintenance, refurbishment, and disposed history of power transformers. The optimal investment decision additionally uses data related to failure and social costs. To develop the asset management technology in power transformers, it is important to find deterioration parameters directly indicating degradation of power transformers. In this study, 110,000 DGA data during the past 35 years have been analyzed in order to find the deterioration parameters related to the degradation of power transformers. The alarm rates of combustible gases ($H_2$, $C_2H_2$, $C_2H_4$, $CH_4$, $C_2H_6$), TCG CO, and $CO_2$ were analyzed as deterioration parameters. The origin of the gas was discussed in connection with discharge, overheating and insulation aging.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.10 s.181
• /
• pp.2597-2602
• /
• 2000

The most effective means of evaluating remaining life is through the creep testing of samples removed from the component. But sampling of large specimen from in-service component is actually impossible. So, sampling device and small-specimen creep tester have been applied. Sampling device has been devised to extract mechanically small samples by hemispherical, diamond -coated cutter from the surface of turbine rotor bores and thick-walled pipes without subsequent weld repairs requiring post weld heat treatment. A method of manufacturing small creep specimen, 2min gage diameter and 10min gage length, using electron beam welding to attach grip section, has been proven. Small-specimen creep tester has been designed to control atmosphere to prevent stress increment by oxidation during experiment. To determine whether the small specimens successfully reproduce the behavior of large specimens, creep rupture tests for small and large specimens have been performed at identical conditions. Creep rupture times based on small specimens have closely agreed within 5% error compared with that of large specimen. The errors in rupture time have decreased at longer test period. This comparison validates the procedure for fabricating and testing on small specimen. This technique offers potential as an efficient method for remaining life assessment by direct sampling from in -service high temperature components.

• Journal of the Korean Wood Science and Technology
• /
• v.42 no.2
• /
• pp.101-111
• /
• 2014

In this study the effect of heartwood-coating (HCO), vapor-dam (VD), bark-remaining (BR) and bark-remaining-coating (BRC) treatments on the air circulating oven-drying characteristics of Japanese larch hollowed round-post was evaluated. The drying times of the hollowed round-posts for control, VD, HCO and BR specimens were 72, 168, 204 and 240 hours, respectively, from the initial MC to about 8% MC, which was recommended as the indoor in-use MC. The temperature in the hole of the VD specimen was lower than that of wood and the difference between air temperature in the hole and wood temperature became large during drying period. The vapor pressure of air in the hole was higher than that of inside wood for all specimens except VD specimen. The surface checks on all specimens were observed in increasing order of BR, BRC, UC, HCO and VD specimens.