Linhan Ouyang
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
Linhan Ouyang has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Chanseok Park
Pusan National University
8 shared publications - Min Wang
The University of Texas at San Antonio
4 shared publications - Yizhong Ma
School of Economics and Management, Nanjing University of Science and Technology, Nanjing, China
3 shared publications Dequn Zhou
College of Economics and Management Nanjing University of Aeronautics and Astronautics Nanjing P.R. China
2 shared publications- Jianjun Wang
Nanjing University of Science and Technology
2 shared publications Mei Han
Nanjing University of Aeronautics and Astronautics, Nanjing, China
2 shared publications
Latest Publications
- 15 October 2026
- Published by Springer Nature in Annals of Operations Research
- p. 1-29
Does digital transformation improve the supply chain resilience?
- 15 October 2026
- Published by Springer Nature in Annals of Operations Research
- p. 1-29
Does digital transformation improve the supply chain resilience?
- Open Access
- 10 April 2026
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 42 (5) , 2415-2429
Data‐Driven Methods for Multiple and Dual Response Optimization on Operational Data Using Stochastic PRIM
Upon establishing multiple response optimization (MRO) or dual response optimization (DRO), response surface methodology (RSM) acts as a conventional model‐driven framework for optimizing small‐sized experimental data to derive an input condition in which a decent response is expected. RSM conducts multiple experiments to estimate response surfaces via empirical prediction models, but it suffers from predictive uncertainty upon fitting strict models onto large, complex operational data. Data‐driven approaches on MRO and DRO have gained attention by employing supervised data mining algorithms to discover outstanding input subrange options from operational data, while effectively circumventing the predictive capability issues of RSM. In this study, we propose two new stochastic data‐driven methods for response optimization to automatically derive numerous gratifying input conditions from industrial operational data. The random subspace method is incorporated into the patient rule induction method in accordance with valid objective function designs for MRO and DRO. Comparative case studies demonstrate the superior performance of our stochastic methods over deterministic baselines through N‐fold validation and sensitivity analyses.
- 10 April 2026
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 42 (5) , 2415-2429
Open AccessData‐Driven Methods for Multiple and Dual Response Optimization on Operational Data Using Stochastic PRIM
Upon establishing multiple response optimization (MRO) or dual response optimization (DRO), response surface methodology (RSM) acts as a conventional model‐driven framework for optimizing small‐sized experimental data to derive an input condition in which a decent response is expected. RSM conducts multiple experiments to estimate response surfaces via empirical prediction models, but it suffers from predictive uncertainty upon fitting strict models onto large, complex operational data. Data‐driven approaches on MRO and DRO have gained attention by employing supervised data mining algorithms to discover outstanding input subrange options from operational data, while effectively circumventing the predictive capability issues of RSM. In this study, we propose two new stochastic data‐driven methods for response optimization to automatically derive numerous gratifying input conditions from industrial operational data. The random subspace method is incorporated into the patient rule induction method in accordance with valid objective function designs for MRO and DRO. Comparative case studies demonstrate the superior performance of our stochastic methods over deterministic baselines through N‐fold validation and sensitivity analyses.
- 26 March 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 272
An efficient adaptive multi-fidelity ensemble of surrogates method for structural reliability analysis
- 26 March 2026
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 272
An efficient adaptive multi-fidelity ensemble of surrogates method for structural reliability analysis
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 24585-24598
A Neural Network-Based Survival Analysis Model Considering Censored Data for Failure Prediction
With the rapid development of sensor and information technology, multi-sensor data related to system degradation processes are now readily available for condition monitoring and remaining useful life (RUL) prediction. However, this process is often complicated by the presence of censored sensor data. In this article, we propose a novel method called Bayesian LSTM-SURV, which integrates Survival Analysis (SA) with Neural Networks (NNs) to model the nonlinear relationship between degradation signals and RUL. This method addresses censored signals and the lack of RUL labels through a novel loss function. Additionally, we employ a Bayesian procedure to transfer information from the training data, enhancing the accuracy of predictions for the test data and maximizing the utilization of existing data. Instead of directly predicting RUL values, we assume that the lifetime follows a Weibull distribution. By modeling the lifetime distribution and survival function, we can calculate and predict RUL values while quantifying the uncertainty of these predictions. The advantageous features of the proposed method are demonstrated through simulation studies and its application to a high-fidelity gas turbine engine dataset.
- 4 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 22 (15455955) , 24585-24598
A Neural Network-Based Survival Analysis Model Considering Censored Data for Failure Prediction
With the rapid development of sensor and information technology, multi-sensor data related to system degradation processes are now readily available for condition monitoring and remaining useful life (RUL) prediction. However, this process is often complicated by the presence of censored sensor data. In this article, we propose a novel method called Bayesian LSTM-SURV, which integrates Survival Analysis (SA) with Neural Networks (NNs) to model the nonlinear relationship between degradation signals and RUL. This method addresses censored signals and the lack of RUL labels through a novel loss function. Additionally, we employ a Bayesian procedure to transfer information from the training data, enhancing the accuracy of predictions for the test data and maximizing the utilization of existing data. Instead of directly predicting RUL values, we assume that the lifetime follows a Weibull distribution. By modeling the lifetime distribution and survival function, we can calculate and predict RUL values while quantifying the uncertainty of these predictions. The advantageous features of the proposed method are demonstrated through simulation studies and its application to a high-fidelity gas turbine engine dataset.
- 18 June 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 328 (1) , 216-231
Bayesian variable selection in Kriging metamodeling for quality design
- 18 June 2025
- Published by Elsevier in European Journal of Operational Research
- Vol. 328 (1) , 216-231
Bayesian variable selection in Kriging metamodeling for quality design
- 10 September 2024
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 41 (1) , 51-70
A probabilistic uncertain linguistic approach for FMEA‐based risk assessment
Failure Mode and Effect Analysis (FMEA) is acknowledged as a beneficial instrument for identifying and mitigating system failures. However, the traditional FMEA method has its limitations. For instance, crisp numbers fail to adequately represent the intricate information and cognitive nuances of experts. Additionally, the conventional approach overlooks the significance of weights assigned to FMEA experts and risk factors (RFs). Furthermore, the simplistic ranking of failure modes in traditional FMEA does not accurately reflect priorities. In light of these drawbacks, this paper introduces an innovative, fully data‐driven FMEA method, leveraging a probabilistic uncertain linguistic term sets (PULTSs) environment and the Weighted Aggregates Sum Product Assessment (WASPAS) method. In the assessment process, PULTSs serve as linguistic tools that express probability distribution, allowing for a more reasonable and precise description of information. To address the issue of weights for RFs, the regret theory and Modified CRITIC method are employed. Subsequently, the WASPAS method is applied to determine the risk rankings of failure modes. To illustrate the feasibility and rationality of this novel FMEA model, the paper includes an example involving the production of Lithium‐ion batteries. To emphasize the excellence of the proposed FMEA model, sensitivity and comparative analyses are carried out.
- 10 September 2024
- Published by Wiley in Quality and Reliability Engineering International
- Vol. 41 (1) , 51-70
A probabilistic uncertain linguistic approach for FMEA‐based risk assessment
Failure Mode and Effect Analysis (FMEA) is acknowledged as a beneficial instrument for identifying and mitigating system failures. However, the traditional FMEA method has its limitations. For instance, crisp numbers fail to adequately represent the intricate information and cognitive nuances of experts. Additionally, the conventional approach overlooks the significance of weights assigned to FMEA experts and risk factors (RFs). Furthermore, the simplistic ranking of failure modes in traditional FMEA does not accurately reflect priorities. In light of these drawbacks, this paper introduces an innovative, fully data‐driven FMEA method, leveraging a probabilistic uncertain linguistic term sets (PULTSs) environment and the Weighted Aggregates Sum Product Assessment (WASPAS) method. In the assessment process, PULTSs serve as linguistic tools that express probability distribution, allowing for a more reasonable and precise description of information. To address the issue of weights for RFs, the regret theory and Modified CRITIC method are employed. Subsequently, the WASPAS method is applied to determine the risk rankings of failure modes. To illustrate the feasibility and rationality of this novel FMEA model, the paper includes an example involving the production of Lithium‐ion batteries. To emphasize the excellence of the proposed FMEA model, sensitivity and comparative analyses are carried out.
- 25 December 2023
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 188, 109856
Condition-based maintenance considering imperfect inspection for a multi-state system subject to competing and hidden failures
- 25 December 2023
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 188, 109856
Condition-based maintenance considering imperfect inspection for a multi-state system subject to competing and hidden failures
- 11 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (1) , 589-601
A Novel Active-Learning Kriging Reliability Analysis Method Based on Parallelized Sampling Considering Budget Allocation
Active-learning Kriging models have gained more and more popularity for structural reliability analysis (SRA) in recent years. Improving the efficiency of simulations while maintaining high accuracy is essential for building Kriging-based SRA approaches. In this article, we propose a novel active-learning Kriging reliability analysis method based on parallelized sampling considering budget allocation (ALK-PBA). A parallelized sampling strategy based on clustering and budget allocation is developed. The low-discrepancy candidate samples are employed to provide representative candidate samples, and the adaptive truncated region is applied to select samples of relative high probability density. Then, the method is used for clustering samples. After identifying clusters, ALK-PBA allocates new training samples to each cluster according to a chosen learning function. This process is repeated iteratively to renew the Kriging model. Several numerical cases have been evaluated using the proposed ALK-PBA, and the results have demonstrated its high accuracy and efficiency for SRA. Moreover, the proposed method is employed to simulate three performance functions of different dimensions under various learning functions, and recommendations for choosing learning functions for the discussed problems are provided in this article.
- 11 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (1) , 589-601
A Novel Active-Learning Kriging Reliability Analysis Method Based on Parallelized Sampling Considering Budget Allocation
Active-learning Kriging models have gained more and more popularity for structural reliability analysis (SRA) in recent years. Improving the efficiency of simulations while maintaining high accuracy is essential for building Kriging-based SRA approaches. In this article, we propose a novel active-learning Kriging reliability analysis method based on parallelized sampling considering budget allocation (ALK-PBA). A parallelized sampling strategy based on clustering and budget allocation is developed. The low-discrepancy candidate samples are employed to provide representative candidate samples, and the adaptive truncated region is applied to select samples of relative high probability density. Then, the method is used for clustering samples. After identifying clusters, ALK-PBA allocates new training samples to each cluster according to a chosen learning function. This process is repeated iteratively to renew the Kriging model. Several numerical cases have been evaluated using the proposed ALK-PBA, and the results have demonstrated its high accuracy and efficiency for SRA. Moreover, the proposed method is employed to simulate three performance functions of different dimensions under various learning functions, and recommendations for choosing learning functions for the discussed problems are provided in this article.