M
Ming Yang
Researcher at Delft University of Technology
Publications - 89
Citations - 1839
Ming Yang is an academic researcher from Delft University of Technology. The author has contributed to research in topics: Computer science & Risk analysis. The author has an hindex of 20, co-authored 78 publications receiving 1184 citations. Previous affiliations of Ming Yang include Nazarbayev University & Memorial University of Newfoundland.
Papers
More filters
Journal ArticleDOI
Arctic shipping accident scenario analysis using Bayesian Network approach
TL;DR: In this article, the authors presented a methodology for the analysis of Arctic shipping accident scenarios using Bayesian Networks (BN) and applied it to a scenario involving a collision between a vessel and an iceberg.
Journal ArticleDOI
An operational risk analysis tool to analyze marine transportation in Arctic waters
TL;DR: An Object-Oriented Bayesian Network model is proposed to dynamically predict ship-ice collision probability based on navigational and operational system states, weather and ice conditions, and human error to predict oil tanker collision with sea ice.
Journal ArticleDOI
Precursor-based hierarchical Bayesian approach for rare event frequency estimation: A case of oil spill accidents
TL;DR: In this article, a hierarchical Bayesian approach (HBA) was used to estimate the frequency of a rare event in probabilistic risk assessment (PRA) using the BP Deepwater Horizon accident in the Gulf of Mexico.
Journal ArticleDOI
Prioritization of environmental issues in offshore oil and gas operations: A hybrid approach using fuzzy inference system and fuzzy analytic hierarchy process
TL;DR: A hybrid approach using fuzzy inference system (FIS) and fuzzy AHP which not only eliminates the above limitations but also serves as a robust tool for the prioritization of environmental issues in OOG operations is proposed.
Journal ArticleDOI
Dynamic failure analysis of process systems using neural networks
TL;DR: In this article, a multi-layer perceptron (MLP) is used to define the relationship among process variables and a probabilistic approach is proposed to estimate the likelihoods of failure to the process unit.