Yan Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yan Shen has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Lijuan Shen
Future Resilient Systems, Singapore-ETH Centre, Singapore
3 shared publications Zhenlin Yang
School of Economics, Singapore Management University, Singapore
2 shared publicationsLi-Juan Shen
National University of Singapore
1 shared publication- Linjie Qin
Department of Statistics and Data Sciences, School of Economics, Xiamen University
1 shared publication - Loon Ching Tang
Department of Industrial Systems Engineering and Management, National University of Singapore
1 shared publication - Min Lu
School of Statistics and Data Science, Nanjing Audit University, Nanjing 211815, China
1 shared publication
Latest Publications
- 8 October 2025
- Published by Taylor & Francis in Technometrics
- Vol. 68 (1) , 79-95
Degradation Data Analysis based on Wiener Process with a Nonlinear Drift and a Stochastic Volatility
- 8 October 2025
- Published by Taylor & Francis in Technometrics
- Vol. 68 (1) , 79-95
Degradation Data Analysis based on Wiener Process with a Nonlinear Drift and a Stochastic Volatility
- Open Access
- 19 August 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (16) , 2991
Degradation Modeling for Lithium-Ion Batteries with an Exponential Jump-Diffusion Model
The degradation of Lithium-ion batteries is usually measured by capacity loss. When batteries deteriorate with usage, the capacities would generally have a declining trend. However, occasionally, considerable capacity regeneration may occur during the degradation process. To better capture the coexistence of capacity loss and regeneration, this paper considers a jump-diffusion model with jumps subject to the exponential distribution. For estimation of model parameters, a jump detection test is first adopted to identify jump arrival times and separate observation data into two series, jump series and diffusion series; then, with the help of probabilistic programming, the Markov chain Monte Carlo sampling algorithm is used to estimate the parameters for the jump and diffusion parts of the degradation model, respectively. The distribution functions of failure time and residual useful life are also approximated by the Monte Carlo simulation approach. Simulation results show the feasibility and good performance of the combined estimation method. Finally, real data analysis indicates that the jump-diffusion process model with the combined estimation method could give a more accurate estimation when predicting the failure time of the battery.
- 19 August 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (16) , 2991
Open AccessDegradation Modeling for Lithium-Ion Batteries with an Exponential Jump-Diffusion Model
The degradation of Lithium-ion batteries is usually measured by capacity loss. When batteries deteriorate with usage, the capacities would generally have a declining trend. However, occasionally, considerable capacity regeneration may occur during the degradation process. To better capture the coexistence of capacity loss and regeneration, this paper considers a jump-diffusion model with jumps subject to the exponential distribution. For estimation of model parameters, a jump detection test is first adopted to identify jump arrival times and separate observation data into two series, jump series and diffusion series; then, with the help of probabilistic programming, the Markov chain Monte Carlo sampling algorithm is used to estimate the parameters for the jump and diffusion parts of the degradation model, respectively. The distribution functions of failure time and residual useful life are also approximated by the Monte Carlo simulation approach. Simulation results show the feasibility and good performance of the combined estimation method. Finally, real data analysis indicates that the jump-diffusion process model with the combined estimation method could give a more accurate estimation when predicting the failure time of the battery.
- 13 June 2020
- Published by World Scientific Pub Co Pte Ltd in International Journal of Reliability, Quality and Safety Engineering
- Vol. 27 (06) , 2050018
Model Selection Methods for Reliability Assessment Based on Interval-Censored Field Failure Samples
Incomplete field failure data from automated production are often applied for evaluating the system reliability. But the evaluation could be impacted by the uncertainty of the product’s lifetime distribution, which is usually predetermined but may be misspecified. In this paper, we assume that the system lifetime distribution follows a location-scale family with several candidates instead of a certain distribution. Two model selection procedures are proposed to assign the most likely candidate distribution from a pool of the location-scale distributions based on interval-censored field failure samples. The maximum likelihood estimates (MLE) of parameters of the candidate distribution are estimated by using the Newton–Raphson method and the MLE of a quartile is assigned as the reliability measure for assessing the reliability of systems. To illustrate the applications of the proposed model selection procedures, an example of high-speed motor with interval-censored field failure data is given. Monte Carlo simulations are carried out to evaluate the performance of the proposed model selection procedures. Simulation results show that the proposed methods are efficient for model identification and can provide reliable reliability assessment.
- 13 June 2020
- Published by World Scientific Pub Co Pte Ltd in International Journal of Reliability, Quality and Safety Engineering
- Vol. 27 (06) , 2050018
Model Selection Methods for Reliability Assessment Based on Interval-Censored Field Failure Samples
Incomplete field failure data from automated production are often applied for evaluating the system reliability. But the evaluation could be impacted by the uncertainty of the product’s lifetime distribution, which is usually predetermined but may be misspecified. In this paper, we assume that the system lifetime distribution follows a location-scale family with several candidates instead of a certain distribution. Two model selection procedures are proposed to assign the most likely candidate distribution from a pool of the location-scale distributions based on interval-censored field failure samples. The maximum likelihood estimates (MLE) of parameters of the candidate distribution are estimated by using the Newton–Raphson method and the MLE of a quartile is assigned as the reliability measure for assessing the reliability of systems. To illustrate the applications of the proposed model selection procedures, an example of high-speed motor with interval-censored field failure data is given. Monte Carlo simulations are carried out to evaluate the performance of the proposed model selection procedures. Simulation results show that the proposed methods are efficient for model identification and can provide reliable reliability assessment.
- 9 August 2019
- Published by Springer Nature
- p. 297-329
A Degradation Model Based on the Wiener Process Assuming Non-Normal Distributed Measurement Errors
- 9 August 2019
- Published by Springer Nature
- p. 297-329
A Degradation Model Based on the Wiener Process Assuming Non-Normal Distributed Measurement Errors
- 24 May 2018
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 34 (6) , 1289-1303
A Wiener‐based degradation model with logistic distributed measurement errors and remaining useful life estimation
Degradation data analysis, which investigates degradation processes of products to extrapolate the lifetime properties, is an effective method for reliability analysis. But degradation data that reflect a product's inherent randomness of degradation are often contaminated by measurement errors. To deal with the problem, this paper proposes a Wiener‐based model with an assumption of logistic distributed measurement errors and adopts the Monte Carlo expectation‐maximization method together with the Gibbs sampling for parameter estimation. Based on the model and parameter estimates, an efficient algorithm is proposed for a quick calculation of maximum likelihood value. Also, the estimation of remaining useful lifetime is discussed. Simulation results show that the proposed model is relatively better and more robust in comparison with the Wiener process with Gaussian noises. Finally, the application of the proposed model is illustrated by an example.
- 24 May 2018
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 34 (6) , 1289-1303
A Wiener‐based degradation model with logistic distributed measurement errors and remaining useful life estimation
Degradation data analysis, which investigates degradation processes of products to extrapolate the lifetime properties, is an effective method for reliability analysis. But degradation data that reflect a product's inherent randomness of degradation are often contaminated by measurement errors. To deal with the problem, this paper proposes a Wiener‐based model with an assumption of logistic distributed measurement errors and adopts the Monte Carlo expectation‐maximization method together with the Gibbs sampling for parameter estimation. Based on the model and parameter estimates, an efficient algorithm is proposed for a quick calculation of maximum likelihood value. Also, the estimation of remaining useful lifetime is discussed. Simulation results show that the proposed model is relatively better and more robust in comparison with the Wiener process with Gaussian noises. Finally, the application of the proposed model is illustrated by an example.
- 22 November 2017
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 171, 87-98
Reliability analysis of repairable systems with recurrent misuse-induced failures and normal-operation failures
- 22 November 2017
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 171, 87-98
Reliability analysis of repairable systems with recurrent misuse-induced failures and normal-operation failures
- 26 May 2017
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 87 (12) , 2349-2371
Improved likelihood inferences for Weibull regression model
A general procedure is developed for bias-correcting the maximum likelihood estimators (MLEs) of the parameters of Weibull regression model with either complete or right-censored data. Following the bias correction, variance corrections and hence improved t-ratios for model parameters are presented. Potentially improved t-ratios for other reliability-related quantities are also discussed. Simulation results show that the proposed method is effective in correcting the bias of the MLEs, and the resulted t-ratios generally improve over the regular t-ratios.
- 26 May 2017
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 87 (12) , 2349-2371
Improved likelihood inferences for Weibull regression model
A general procedure is developed for bias-correcting the maximum likelihood estimators (MLEs) of the parameters of Weibull regression model with either complete or right-censored data. Following the bias correction, variance corrections and hence improved t-ratios for model parameters are presented. Potentially improved t-ratios for other reliability-related quantities are also discussed. Simulation results show that the proposed method is effective in correcting the bias of the MLEs, and the resulted t-ratios generally improve over the regular t-ratios.
- 20 January 2015
- Published by Cambridge University Press (CUP) in Probability in the Engineering and Informational Sciences
- Vol. 29 (2) , 291-308
ON THE BEHAVIORS OF THE PERCENTILE RESIDUAL LIFE FOR COMPONENTS AND FOR K-OUT-OF-N SYSTEMS
This paper investigates properties of the percentile residual life (PRL) function for a single component and for a k-out-of-n system. The shape of the component PRL function can be determined by the component failure rate function. The intimate relations between these two functions are studied first. Then we generalize the results to a k-out-of-n system by assuming independent and identical components. We show that the behavior of the PRL for a k-out-of-n system is quite different from the component PRL. We also find that for series and parallel systems, the location of the change point of the PRL is monotone in the number of components in a system.
- 20 January 2015
- Published by Cambridge University Press (CUP) in Probability in the Engineering and Informational Sciences
- Vol. 29 (2) , 291-308
ON THE BEHAVIORS OF THE PERCENTILE RESIDUAL LIFE FOR COMPONENTS AND FOR K-OUT-OF-N SYSTEMS
This paper investigates properties of the percentile residual life (PRL) function for a single component and for a k-out-of-n system. The shape of the component PRL function can be determined by the component failure rate function. The intimate relations between these two functions are studied first. Then we generalize the results to a k-out-of-n system by assuming independent and identical components. We show that the behavior of the PRL for a k-out-of-n system is quite different from the component PRL. We also find that for series and parallel systems, the location of the change point of the PRL is monotone in the number of components in a system.
- 19 August 2014
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 85 (15) , 3017-3046
Bias-correction for Weibull common shape estimation
A general method for correcting the bias of the maximum likelihood estimator (MLE) of the common shape parameter of Weibull populations, allowing a general right censorship, is proposed in this paper. Extensive simulation results show that the new method is very effective in correcting the bias of the MLE, regardless of censoring mechanism, sample size, censoring proportion and number of populations involved. The method can be extended to more complicated Weibull models.
- 19 August 2014
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 85 (15) , 3017-3046
Bias-correction for Weibull common shape estimation
A general method for correcting the bias of the maximum likelihood estimator (MLE) of the common shape parameter of Weibull populations, allowing a general right censorship, is proposed in this paper. Extensive simulation results show that the new method is very effective in correcting the bias of the MLE, regardless of censoring mechanism, sample size, censoring proportion and number of populations involved. The method can be extended to more complicated Weibull models.
- 1 July 2009
- Published by Elsevier in Nonlinear Analysis
- Vol. 72 (1) , 527-532
Fixed point theorems in symmetric spaces and applications to probabilistic spaces
- 1 July 2009
- Published by Elsevier in Nonlinear Analysis
- Vol. 72 (1) , 527-532
Fixed point theorems in symmetric spaces and applications to probabilistic spaces