Yinuo Chen
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
Yinuo Chen has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
Kun Qian
2 shared publications- Rui He
Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore
2 shared publications Zhigang Tian
2 shared publications- Chenchen Sun
School of Engineering and Technology, China University of Geosciences (Beijing), Beijing, China
1 shared publication - Hang Zhang
College of Mechanical and Storage Engineering, China University of Petroleum, Beijing, China
1 shared publication Haotian Wei
1 shared publication
Latest Publications
- 26 August 2026
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 270
Embedding uncertainty inside CPTs: Bayesian risk analysis for hydrogen-blended pipelines
- 26 August 2026
- Published by Elsevier in International Journal of Hydrogen Energy
- Vol. 270
Embedding uncertainty inside CPTs: Bayesian risk analysis for hydrogen-blended pipelines
- 14 August 2026
- Published by ASME International in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B. Mechanical Engineering
- Vol. 12 (3)
A Lightweight Bayesian Network Framework for Risk Analysis of Hydrogen-Blended Pipelines With Large Language Model Integration
Probabilistic risk analysis is a fundamental approach for safety assessment in engineering systems. However, its application to emerging domains such as hydrogen-blended pipeline systems faces new challenges due to limited fault data and scarce expert knowledge. Bayesian networks (BNs) are widely adopted for risk analysis because they illustrate the relationships between risk factors and facilitate probabilistic reasoning. Under these conditions, two major challenges arise. First, the network structure, including the relevant risk factors and their dependencies, is typically unavailable. Second, when risk factors have multiple causes, the parameter space of conditional probabilities grows exponentially, which requires extensive expert input for parameter specification. To address these problems, this study presents a lightweight framework for risk analysis that minimizes the need for expert judgment and does not rely on data. The framework centers on a BN for probabilistic computation. A large language model identifies risk factors and their relationships from technical documentation. Additionally, a parameter reduction method named pre-conditional probability table (CPT) is developed to compress the dimensionality of conditional probability tables from an exponential to a polynomial scale through weighted combinations. This reduces the need for expert elicitation. The framework is validated through a case study on hydrogen-blended natural gas pipeline risk assessment and benchmark and numerical comparison. The results show less than a 5% deviation in posterior probabilities and over 90% consistency in BN structures compared with benchmark models. The workload for parameter specification is reduced to about 15% of that required in conventional BN modeling.
- 14 August 2026
- Published by ASME International in ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B. Mechanical Engineering
- Vol. 12 (3)
A Lightweight Bayesian Network Framework for Risk Analysis of Hydrogen-Blended Pipelines With Large Language Model Integration
Probabilistic risk analysis is a fundamental approach for safety assessment in engineering systems. However, its application to emerging domains such as hydrogen-blended pipeline systems faces new challenges due to limited fault data and scarce expert knowledge. Bayesian networks (BNs) are widely adopted for risk analysis because they illustrate the relationships between risk factors and facilitate probabilistic reasoning. Under these conditions, two major challenges arise. First, the network structure, including the relevant risk factors and their dependencies, is typically unavailable. Second, when risk factors have multiple causes, the parameter space of conditional probabilities grows exponentially, which requires extensive expert input for parameter specification. To address these problems, this study presents a lightweight framework for risk analysis that minimizes the need for expert judgment and does not rely on data. The framework centers on a BN for probabilistic computation. A large language model identifies risk factors and their relationships from technical documentation. Additionally, a parameter reduction method named pre-conditional probability table (CPT) is developed to compress the dimensionality of conditional probability tables from an exponential to a polynomial scale through weighted combinations. This reduces the need for expert elicitation. The framework is validated through a case study on hydrogen-blended natural gas pipeline risk assessment and benchmark and numerical comparison. The results show less than a 5% deviation in posterior probabilities and over 90% consistency in BN structures compared with benchmark models. The workload for parameter specification is reduced to about 15% of that required in conventional BN modeling.
- Open Access
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1135-1141
Explainable AI-Based Human Factor Risk Modeling of Hazardous Chemical Tanker Accidents under Severe Weather
- 12 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1135-1141
Open AccessExplainable AI-Based Human Factor Risk Modeling of Hazardous Chemical Tanker Accidents under Severe Weather
- 31 January 2025
- Published by Elsevier in Ocean Engineering
- Vol. 322
Predictive maintenance for offshore wind farms with incomplete and biased prognostic information
- 31 January 2025
- Published by Elsevier in Ocean Engineering
- Vol. 322
Predictive maintenance for offshore wind farms with incomplete and biased prognostic information
- 19 February 2024
- Published by Elsevier in Process Safety and Environmental Protection
- Vol. 184, 1131-1142
Reliability analysis of corroded pipes using MFL signals and Residual Neural Networks
- 19 February 2024
- Published by Elsevier in Process Safety and Environmental Protection
- Vol. 184, 1131-1142
Reliability analysis of corroded pipes using MFL signals and Residual Neural Networks
- 10 February 2022
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 221
Risk assessment of buried gas pipelines based on improved cloud-variable weight theory
- 10 February 2022
- Published by Elsevier in Reliability Engineering & System Safety
- Vol. 221
Risk assessment of buried gas pipelines based on improved cloud-variable weight theory
- Open Access
- 2 October 2018
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2018, 1-14
Full-Scale Experimental Verification of the Explosion Shock Wave Model of a Natural Gas Pipeline
As developments in natural gas pipelines increasingly incorporate higher grades of steel, larger diameters, and higher pressures, the consequences of an accident caused by leakage, explosion, or ignition become progressively more severe. Currently, major technical obstacles include the quantification of the impact of an explosion shock wave of a high-strength, large-diameter natural gas pipeline, and the selection of a reasonable shock wave overpressure model appropriate to the operating conditions. In this paper, six models of shock wave overpressure theories, namely, the TNT equivalent method, the TNO method, the multienergy method, the British Gas method, the Shell method, and the Lee formula, were compared and analyzed to determine their applicability. A shock wave model adapted to the characteristics of a full-scale test was proposed, and the model verification of a full-scale blasting test was conducted on pipelines with diameters of 1422 mm and 1219 mm, respectively. Subsequent results indicated that the modifications to the TNT equivalent and the test parameters correlated with changes in the suitability of the model. Henrych’s formula calculation model of the British Gas method was found to correspond strongly with the measured value, in which the absolute value of the relative error was less than 30% and the absolute error within the range of 78 m to 800 m was no more than 0.05 MPa. Thus, the Henrych formula was adopted as the primary model formula for the shock wave overpressure calculations in this study. To further correct the error of the model, the trend between the curve obtained by the Henrych formula and the fitting curve of the measured value was compared and analyzed. The positive and negative compensations of the shaded area before and after the intersection point were carried out, and the new error correction overpressure model formula was obtained by fitting, with the error controlled within 15%.
- 2 October 2018
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2018, 1-14
Open AccessFull-Scale Experimental Verification of the Explosion Shock Wave Model of a Natural Gas Pipeline
As developments in natural gas pipelines increasingly incorporate higher grades of steel, larger diameters, and higher pressures, the consequences of an accident caused by leakage, explosion, or ignition become progressively more severe. Currently, major technical obstacles include the quantification of the impact of an explosion shock wave of a high-strength, large-diameter natural gas pipeline, and the selection of a reasonable shock wave overpressure model appropriate to the operating conditions. In this paper, six models of shock wave overpressure theories, namely, the TNT equivalent method, the TNO method, the multienergy method, the British Gas method, the Shell method, and the Lee formula, were compared and analyzed to determine their applicability. A shock wave model adapted to the characteristics of a full-scale test was proposed, and the model verification of a full-scale blasting test was conducted on pipelines with diameters of 1422 mm and 1219 mm, respectively. Subsequent results indicated that the modifications to the TNT equivalent and the test parameters correlated with changes in the suitability of the model. Henrych’s formula calculation model of the British Gas method was found to correspond strongly with the measured value, in which the absolute value of the relative error was less than 30% and the absolute error within the range of 78 m to 800 m was no more than 0.05 MPa. Thus, the Henrych formula was adopted as the primary model formula for the shock wave overpressure calculations in this study. To further correct the error of the model, the trend between the curve obtained by the Henrych formula and the fitting curve of the measured value was compared and analyzed. The positive and negative compensations of the shaded area before and after the intersection point were carried out, and the new error correction overpressure model formula was obtained by fitting, with the error controlled within 15%.