Article
Computer Science, Information Systems
Shanqing Jiang, Lin Yang, Guang Cheng, Xianming Gao, Tao Feng, Yuyang Zhou
Summary: This paper proposes a quantitative framework for evaluating network's multi-stage resilience using the Dynamic Bayesian Network. The framework defines five core resilience capabilities of the network and quantifies network resilience based on these capabilities. The proposed method achieves more accurate and comprehensive evaluation of network resilience.
COMPUTER COMMUNICATIONS
(2022)
Article
Engineering, Industrial
Vishwas Dohale, Milind Akarte, Angappa Gunasekaran, Priyanka Verma
Summary: This study aims to explore the role of artificial intelligence in building production resilience during the COVID-19 pandemic. By reviewing literature and developing a decision support system, key success factors are determined and influential factors are predicted for production resilience.
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
(2022)
Article
Engineering, Industrial
Xing-lin Chen, Long-xing Yu, Wei-dong Lin, Fu-qiang Yang, Yi-ping Li, Jing Tao, Shuo Cheng
Summary: Pursuing high-quality urbanisation and improving urban system reliability are the current goals of urban development. Urban resilience is crucial in coping with disturbances, and thus assessing urban resilience can quantify urban system reliability. This study developed an assessment indicator system and a dynamic urban resilience assessment model that incorporates time varying factors. By applying the model to Fujian Province, vulnerabilities in urban resilience were identified, providing valuable insights for practitioners and researchers in optimizing urban resilience, improving urban system reliability, and formulating urban development strategies.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Green & Sustainable Science & Technology
Hengrui Chen, Ruiyu Zhou, Hong Chen, Albert Lau
Summary: This paper proposes a framework to evaluate the static and dynamic resilience of urban transportation systems and applies Bayesian network model and percolation theory for assessment. The results show a continuous growth trend of transportation resilience in Xi'an over the past decade, with the need to improve the system's restorative capacity, adaptive capacity, and resourcefulness.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Engineering, Industrial
Nanxi Wang, Min Wu, Kum Fai Yuen
Summary: This paper aims to develop measures to enhance port resilience to cope with risks and uncertainties. The major disturbances affecting ports are summarized and classified, and a port resilience assessment model is proposed. The results show that natural disasters are the major disruptors plaguing ports, and automated terminals have higher overall resilience than non-automated terminals.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Jiateng Yin, Xianliang Ren, Ronghui Liu, Tao Tang, Shuai Su
Summary: This study proposes a hybrid knowledge-based and data-driven approach for quantitative analysis of resilience in urban rail systems. It models the causal relationships to quantify the importance of different disruptions to overall resilience criteria. The method is applied to historical data from Beijing Metro, and the results demonstrate the quantitative relationships between system resilience and different types of events.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Green & Sustainable Science & Technology
Mrinal Kanti Sen, Subhrajit Dutta, Golam Kabir
Summary: This study quantifies the time-varying resilience of housing infrastructure against flood hazards using a dynamic Bayesian network (DBN). It develops a framework and implements it in a real case-study area. The study compares vulnerability, robustness, and recovery scenarios to provide resilience-based decisions for public authorities.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Computer Science, Artificial Intelligence
Auwal Haruna, Pingyu Jiang
Summary: The rapid development of Additive Manufacturing (AM) has brought many advantages to manufacturing end-use products and components, but it also faces limitations that need to be addressed through the concept of design for AM (DFAM) to reform it as a mainstream manufacturing method. This paper proposes a framework based on the Fuzzy Bayesian Network (FBN) for DFAM decision-making and investigates the potential adaptability of DFAM using 20 impact factors.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Food Science & Technology
Jan Mei Soon, Ikarastika Rahayu Abdul Wahab
Summary: This study developed a Bayesian network model to predict food fraud type and point of adulteration. The findings revealed that mislabelling, artificial enhancement, and substitution were the most commonly reported types of fraud, while beverages, dairy, and meat received the highest number of fraud notifications. Chemicals and cheaper, expired or rotten ingredients were frequently used as adulterants.
Article
Engineering, Industrial
Altyngul Zinetullina, Ming Yang, Nima Khakzad, Boris Golman, Xinhong Li
Summary: The study highlights the importance of resilience as a crucial property of chemical process systems under uncertain and unpredictable circumstances due to technical-human-organizational interactions. Resilience assessment is essential for identifying root causes of accidents and developing specific resilience attributes to withstand disruptions. The integration of Functional Resonance Analysis Method and dynamic Bayesian Network provides a useful tool for rigorous quantitative resilience analysis of complex process systems.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Geosciences, Multidisciplinary
Abdullah M. Braik, Maria Koliou
Summary: This paper proposes a digital twin framework for infrastructure systems in the face of disasters, combining physics-based and data-driven models and utilizing a dynamic Bayesian network (DBN). The results, validated using historical data, demonstrate that the digital twin model can produce detailed and highly accurate estimations for decision-making.
INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION
(2023)
Article
Green & Sustainable Science & Technology
Taiyba Tasmen, Mrinal Kanti Sen, Niamat Ullah Ibne Hossain, Golam Kabir
Summary: This study uses Dynamic Bayesian Network (DBN) to quantify the time-varying seismic resilience of urban housing infrastructure. It applies the methodology to real-world case studies in Tokyo and Kyoto, Japan, and highlights the dynamic nature of resilience and the impact of geographic location on resilience planning.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Computer Science, Artificial Intelligence
Kaiyang Chu, Rui Liu, Guijiang Duan
Summary: Fault source diagnosis methodology is crucial for quality control and assurance in multi-source and multi-stage manufacturing processes, particularly in small sample manufacturing systems. This study proposes a Bayesian network-based methodology by analyzing existing research on fault source diagnosis methods. The use of gray correlation theory and mechanism analysis in the construction of the Bayesian network model reduces the reliance on sample data size for structure learning in complex product manufacturing with small samples. Additionally, two fault source diagnosis methods based on manufacturing principle analysis and reverse Bayesian network are introduced, along with a strategy for their combined use in real manufacturing scenarios.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Geosciences, Multidisciplinary
Yuchun Tang, Wei Bi, Liz Varga, Tom Dolan, Qiming Li
Summary: This study proposed the concept of fire resilience based on system resilience theory for metro station systems (MSS), and combined disaster scene analysis, TOSE approach, and modified TOPSIS method to identify fire resilience indexes. A Bayesian network was developed to assess fire resilience and reveal critical causal chains in fire scenes. Sensitivity analysis and dynamic Bayesian network with critical importance analysis were used to formulate optimization strategies for different periods of operating life. The framework was applied to Nanjing MSS and provided practical tools for long-term resilient operation against fires.
INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION
(2022)
Article
Engineering, Industrial
Xu An, Zhiming Yin, Qi Tong, Yiping Fang, Ming Yang, Qiaoqiao Yang, Huixing Meng
Summary: This paper proposes a methodology that integrates the multi-stage STAMP with a dynamic Bayesian network (DBN) to assess the resilience of emergency response systems. By viewing emergency response systems as multi-step operations, STAMP is used to analyze the hierarchical control and feedback structures, and the output of multi-stage STAMP is applied to develop a DBN for resilience assessment. The combination of socio-technical factors and external disasters is used to evaluate system performance, and the resilience of emergency response systems is obtained from the performance curves.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Xiaoliang Yan, Reed Williams, Elena Arvanitis, Shreyes Melkote
Summary: This paper extends prior work by developing a semantic segmentation approach for machinable volume decomposition using pre-trained generative process capability models, providing manufacturability feedback and labels of candidate machining operations for query 3D parts.
JOURNAL OF MANUFACTURING SYSTEMS
(2024)
Article
Engineering, Industrial
Jing Huang, Zhifen Zhang, Rui Qin, Yanlong Yu, Guangrui Wen, Wei Cheng, Xuefeng Chen
Summary: In this study, a deep learning framework that combines interpretability and feature fusion is proposed for real-time monitoring of pipeline leaks. The proposed method extracts abstract feature details of leak acoustic emission signals through multi-level dynamic receptive fields and optimizes the learning process of the network using a feature fusion module. Experimental results show that the proposed method can effectively extract distinguishing features of leak acoustic emission signals, achieving higher recognition accuracy compared to typical deep learning methods. Additionally, feature map visualization demonstrates the physical interpretability of the proposed method in abstract feature extraction.
JOURNAL OF MANUFACTURING SYSTEMS
(2024)
