• Title/Summary/Keyword: Remaining Useful Life Prediction

Search Result 41, Processing Time 0.027 seconds

A Study on the Remaining Useful Life Prediction Performance Variation based on Identification and Selection by using SHAP (SHAP를 활용한 중요변수 파악 및 선택에 따른 잔여유효수명 예측 성능 변동에 대한 연구)

  • Yoon, Yeon Ah;Lee, Seung Hoon;Kim, Yong Soo
    • 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.

Deep Learning Approaches to RUL Prediction of Lithium-ion Batteries (딥러닝을 이용한 리튬이온 배터리 잔여 유효수명 예측)

  • Jung, Sang-Jin;Hur, Jang-Wook
    • Journal of the Korean Society of Manufacturing Process Engineers
    • /
    • v.19 no.12
    • /
    • pp.21-27
    • /
    • 2020
  • Lithium-ion batteries are the heart of energy-storing devices and electric vehicles. Owing to their superior qualities, such as high capacity and energy efficiency, they have become quite popular, resulting in an increased demand for failure/damage prevention and useable life maximization. To prevent failure in Lithium-ion batteries, improve their reliability, and ensure productivity, prognosticative measures such as condition monitoring through sensors, condition assessment for failure detection, and remaining useful life prediction through data-driven prognostics and health management approaches have become important topics for research. In this study, the residual useful life of Lithium-ion batteries was predicted using two efficient artificial recurrent neural networks-ong short-term memory (LSTM) and gated recurrent unit (GRU). The proposed approaches were compared for prognostics accuracy and cost-efficiency. It was determined that LSTM showed slightly higher accuracy, whereas GRUs have a computational advantage.

Prediction of Remaining Useful Life of Lithium-ion Battery based on Multi-kernel Support Vector Machine with Particle Swarm Optimization

  • Gao, Dong;Huang, Miaohua
    • Journal of Power Electronics
    • /
    • v.17 no.5
    • /
    • pp.1288-1297
    • /
    • 2017
  • The estimation of the remaining useful life (RUL) of lithium-ion (Li-ion) batteries is important for intelligent battery management system (BMS). Data mining technology is becoming increasingly mature, and the RUL estimation of Li-ion batteries based on data-driven prognostics is more accurate with the arrival of the era of big data. However, the support vector machine (SVM), which is applied to predict the RUL of Li-ion batteries, uses the traditional single-radial basis kernel function. This type of classifier has weak generalization ability, and it easily shows the problem of data migration, which results in inaccurate prediction of the RUL of Li-ion batteries. In this study, a novel multi-kernel SVM (MSVM) based on polynomial kernel and radial basis kernel function is proposed. Moreover, the particle swarm optimization algorithm is used to search the kernel parameters, penalty factor, and weight coefficient of the MSVM model. Finally, this paper utilizes the NASA battery dataset to form the observed data sequence for regression prediction. Results show that the improved algorithm not only has better prediction accuracy and stronger generalization ability but also decreases training time and computational complexity.

A Study on Reliability Prediction of System with Degrading Performance Parameter (열화되는 성능 파라메터를 가지는 시스템의 신뢰성 예측에 관한 연구)

  • Kim, Yon Soo;Chung, Young-Bae
    • Journal of Korean Society of Industrial and Systems Engineering
    • /
    • v.38 no.4
    • /
    • pp.142-148
    • /
    • 2015
  • Due to advancements in technology and manufacturing capability, it is not uncommon that life tests yield no or few failures at low stress levels. In these situations it is difficult to analyse lifetime data and make meaningful inferences about product or system reliability. For some products or systems whose performance characteristics degrade over time, a failure is said to have occurred when a performance characteristic crosses a critical threshold. The measurements of the degradation characteristic contain much useful and credible information about product or system reliability. Degradation measurements of the performance characteristics of an unfailed unit at different times can directly relate reliability measures to physical characteristics. Reliability prediction based on physical performance measures can be an efficient and alternative method to estimate for some highly reliable parts or systems. If the degradation process and the distance between the last measurement and a specified threshold can be established, the remaining useful life is predicted in advance. In turn, this prediction leads to just in time maintenance decision to protect systems. In this paper, we describe techniques for mapping product or system which has degrading performance parameter to the associated classical reliability measures in the performance domain. This paper described a general modeling and analysis procedure for reliability prediction based on one dominant degradation performance characteristic considering pseudo degradation performance life trend model. This pseudo degradation trend model is based on probability modeling of a failure mechanism degradation trend and comparison of a projected distribution to pre-defined critical soft failure point in time or cycle.

Statistical Life Prediction of Corroded Pipeline Using Bayesian Inference (베이지안 추론법을 이용한 부식된 배관의 통계적 수명예측)

  • Noh, Yoojeong
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.16 no.4
    • /
    • pp.2401-2406
    • /
    • 2015
  • Pipelines are used by large heavy industries to deliver various types of fluids. Since this is important to maintain the performance of large systems, it is necessary to accurately predict remaining life of the corroded pipeline. However, predicting the remaining life is difficult due to uncertainties in the associated variables, such as geometries, material properties, corrosion rate, etc. In this paper, a statistical method for predicting corrosion remaining life is proposed using Bayesian inference. To accomplish this, pipeline failure probability was calculated using prior information about pipeline failure pressure according to elapsed time, and the given experimental data based on Bayes' rule. The corrosion remaining life was calculated as the elapsed time with 10 % failure probability. Using 10 and 50 samples generated from random variables affecting the corrosion of the pipe, the pipeline failure probability was estimated, after which the estimated remaining useful life was compared with the assumed true remaining useful life.

Comparison of the Machine Learning Models Predicting Lithium-ion Battery Capacity for Remaining Useful Life Estimation (리튬이온 배터리 수명추정을 위한 용량예측 머신러닝 모델의 성능 비교)

  • Yoo, Sangwoo;Shin, Yongbeom;Shin, Dongil
    • 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.

Remaining Useful Life of Lithium-Ion Battery Prediction Using the PNP Model (PNP 모델을 이용한 리튬이온 배터리 잔존 수명 예측)

  • Jeong-Gu Lee;Gwi-Man Bak;Eun-Seo Lee;Byung-jin Jin;Young-Chul Bae
    • 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.

Prognostics and Health Management for Battery Remaining Useful Life Prediction Based on Electrochemistry Model: A Tutorial (배터리 잔존 유효 수명 예측을 위한 전기화학 모델 기반 고장 예지 및 건전성 관리 기술)

  • Choi, Yohwan;Kim, Hongseok
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.42 no.4
    • /
    • pp.939-949
    • /
    • 2017
  • Prognostics and health management(PHM) is actively utilized by industry as an essential technology focusing on accurately monitoring the health state of a system and predicting the remaining useful life(RUL). An effective PHM is expected to reduce maintenance costs as well as improve safety of system by preventing failure in advance. With these advantages, PHM can be applied to the battery system which is a core element to provide electricity for devices with mobility, since battery faults could lead to operational downtime, performance degradation, and even catastrophic loss of human life by unexpected explosion due to non-linear characteristics of battery. In this paper we mainly review a recent progress on various models for predicting RUL of battery with high accuracy satisfying the given confidence interval level. Moreover, performance evaluation metrics for battery prognostics are presented in detail to show the strength of these metrics compared to the traditional ones used in the existing forecasting applications.

Degradation-Based Remaining Useful Life Analysis for Predictive Maintenance in a Steel Galvanizing Kettle (철강 도금로의 예지보전을 위한 열화 기반 잔존수명 분석)

  • Shin, Joon Ho;Kim, Chang Ouk
    • Journal of the Korea Convergence Society
    • /
    • v.10 no.12
    • /
    • pp.271-280
    • /
    • 2019
  • Smart factory, a critical part of digital transformation, enables data-driven decision making using monitoring, analysis and prediction. Predictive maintenance is a key element of smart factory and the need is increasing. The purpose of this study is to analyze the degradation characteristics of a galvanizing kettle for the steel plating process and to predict the remaining useful life(RUL) for predictive maintenance. Correlation analysis, multiple regression, principal component regression were used for analyzing factors of the process. To identify the trend of degradation, a proposed rolling window was used. It was observed the degradation trend was dependent on environmental temperature as well as production factors. It is expected that the proposed method in this study will be an example to identify the trend of degradation of the facility and enable more consistent predictive maintenance.

Remaining Useful Life Prediction of Li-Ion Battery Based on Charge Voltage Characteristics (충전 전압 특성을 이용한 리튬 이온 배터리의 잔존 수명 예측)

  • Sim, Seong Heum;Gang, Jin Hyuk;An, Dawn;Kim, Sun Il;Kim, Jin Young;Choi, Joo Ho
    • Transactions of the Korean Society of Mechanical Engineers B
    • /
    • v.37 no.4
    • /
    • pp.313-322
    • /
    • 2013
  • Batteries, which are being used as energy sources in various applications, tend to degrade, and their capacity declines with repeated charging and discharging cycles. A battery is considered to fail when it reaches 80% of its initial capacity. To predict this, prognosis techniques are attracting attention in recent years in the battery community. In this study, a method is proposed for estimating the battery health and predicting its remaining useful life (RUL) based on the slope of the charge voltage curve. During this process, a Bayesian framework is employed to manage various uncertainties, and a Particle Filter (PF) algorithm is applied to estimate the degradation of the model parameters and to predict the RUL in the form of a probability distribution. Two sets of test data-one from the NASA Ames Research Center and another from our own experiment-for an Li-ion battery are used for illustrating this technique. As a result of the study, it is concluded that the slope can be a good indicator of the battery health and PF is a useful tool for the reliable prediction of RUL.