相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Engineering, Civil
Jordan J. Pannell et al.
Summary: This paper presents a novel application of transfer learning for predicting peak specific impulse in blast engineering. The study demonstrates that previous knowledge learned for modeling spherical charges can be transferred to improve the performance in modeling cylindrical charges. Results show that the model with transfer learning consistently outperforms the model without transfer learning, especially when a higher proportion of data is removed.
INTERNATIONAL JOURNAL OF PROTECTIVE STRUCTURES
(2023)
Article
Engineering, Civil
Dain G. Farrimond et al.
Summary: A significant amount of scientific effort has been dedicated to measuring and understanding the effects of explosions, leading to the development of semi-empirical methods for rapid prediction of blast load parameters. However, there is still no general consensus on the accuracy and validity of these methods, and the deterministic or intrinsic variability of blast loading. This article critically reviews historic and contemporary blast experiments to demonstrate the accuracy of blast load parameter prediction using semi-empirical approaches.
INTERNATIONAL JOURNAL OF PROTECTIVE STRUCTURES
(2023)
Article
Engineering, Environmental
Qilin Li et al.
Summary: In this study, a novel machine learning approach based on Transformer neural networks is developed for predicting BLEVE loads on structures. Through extensive experiments and rigorous evaluation, it is shown that Transformer can effectively model the structure-wave interaction, yielding accurate pressure and impulse predictions with less than 14% relative errors, outperforming the widely used MLP significantly. The developed Transformer model is capable of predicting critical parameters of BLEVE loads and providing a comprehensive characterization of the pressure-time history.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2023)
Article
Engineering, Industrial
Hoang Nguyen et al.
Summary: This study develops three intelligent models, SpaSO-ELM, MFO-ELM, and SalSO-ELM, based on metaheuristic algorithms and ELM model, to predict the ground vibration intensity in mine blasting. These models demonstrate high reliability and accuracy in predicting peak particle velocity (PPV) and can ensure the safety of the surroundings in open-pit mines.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Civil
Qilin Li et al.
Summary: In this paper, a comparative study is conducted to identify the most effective machine learning model for blast loading prediction. The results show that the Transformer model achieves the best performance in BLEVE pressure prediction, with a relative error of 3.5% and R2 value of 0.997, outperforming the existing MLP approach (relative error 6.0%, R2 value 0.985). This study demonstrates that the Transformer network is an effective tool for predicting blast loading from BLEVE and other explosion sources.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Adam A. Dennis et al.
Summary: This article introduces a novel Artificial Neural Network (ANN) called "Direction-encoded Neural Network" (DeNN) for predicting blast loading in obstructed environments. The DeNN is able to learn the underlying physics of the problem and accurately predict peak overpressures in unseen, complex domains. It can also be used for predicting human injury levels and has potential applications in probabilistic risk analysis.
INTERNATIONAL JOURNAL OF PROTECTIVE STRUCTURES
(2023)
Article
Engineering, Environmental
Yang Wang et al.
Summary: In this study, numerical simulations were used to accurately predict BLEVE loads on structures by modeling 1300 sets of BLEVE cases. The open space BLEVE pressure and reflected pressure waves were simulated, and the corresponding impulses were calculated. A reflection coefficient chart was developed to predict the reflected BLEVE overpressure on rigid structures. The results can be used along with the open space BLEVE pressure predictions from a previous study to predict BLEVE loads on structures.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2023)
Article
Computer Science, Software Engineering
Zijie Li et al.
Summary: We propose a data-driven model for fluid simulation under Lagrangian representation, using graphs to represent the fluid field. Our model decomposes the simulation scheme and utilizes graph neural networks to make predictions, achieving accurate and stable results while retaining important physical properties and computational efficiency.
COMPUTERS & GRAPHICS-UK
(2022)
Article
Engineering, Industrial
Alessandro Tugnolr et al.
Summary: This study proposes a step-by-step approach for assessing domino risk indices due to fragment projection, building on existing sub-models for quantitative assessment and supporting quantification and automation of escalation risk triggered by fragment impact.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Mechanical
Monjee K. Almustafa et al.
Summary: This study introduces a machine learning model to predict the maximum displacement of reinforced concrete columns subjected to blast loading using thirteen relevant features. The model achieves high prediction performance and demonstrates its ability to identify influential parameters and their correlations with the response.
INTERNATIONAL JOURNAL OF IMPACT ENGINEERING
(2022)
Article
Engineering, Industrial
Long Ding et al.
Summary: A novel vulnerability model called the fire and explosion synergistic effect model (FESEM) is proposed to estimate time to failure and escalation probability of equipment under spatial-temporal synergistic of heat radiation and overpressure. The study demonstrates significant synergistic effects and discusses parameters influencing time to failure and escalation probability, serving as an essential guide for preventing and controlling domino effects.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Industrial
Meng Lan et al.
Summary: This paper addresses the issue of domino effects in process clusters and proposes a simulation and evaluation tool that considers the uncertainty of primary accidents triggered by natural hazards. It also develops a network-based model to analyze the NaTech-related domino effects. The results demonstrate that the proposed method can be applied to large-scale process clusters and accurately describe the role of each unit at different levels.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Civil
Jordan J. Pannell et al.
Summary: This paper introduces a novel application of a physics-guided regularisation procedure that enhances the generalisation ability of a neural network for blast load prediction. The proposed methodology can improve the accuracy and physical consistency of machine learning approaches in this field.
INTERNATIONAL JOURNAL OF PROTECTIVE STRUCTURES
(2022)
Article
Engineering, Civil
Mona Zahedi et al.
Summary: Current design manuals for blast loading analysis are limited to simple building configurations, while complex geometries require computational fluid dynamics solvers which are computationally expensive. This study evaluates machine learning algorithms for predicting peak overpressure and impulse on protruded structures exposed to blast loading, showing that gradient boosting models outperform neural networks.
INTERNATIONAL JOURNAL OF PROTECTIVE STRUCTURES
(2022)
Article
Engineering, Industrial
Jinkun Men et al.
Summary: This study proposes a systematic analytical framework to study the evolution mechanism of domino effects caused by natural hazards in chemical industrial parks. By developing an event-driven disaster chain evolution system and a system dynamic risk model, we can identify critical stages and intervals of the entire evolution process, providing support for the prevention and mitigation of such catastrophic chain events.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Civil
Chunfeng Zhao et al.
Summary: In this study, a machine learning model was used to predict the maximum displacement of reinforced concrete slabs under blast loads. The results show that the machine learning algorithms have high prediction performance, with the Gaussian process regression algorithm performing the best. The study also analyzed the influence of different input parameters on the output results, increasing the reliability of the model.
ENGINEERING STRUCTURES
(2022)
Article
Engineering, Environmental
Jingde Li et al.
Summary: This article investigates the interaction of blast waves with structures in obstructed environments, studying BLEVE peak pressure prediction and proposing simulation-based pressure prediction correlations. The results can be utilized for better assessment of explosion loads on structures.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Engineering, Industrial
Hao Qin et al.
Summary: This study developed a simulation-based approach to assess individual casualty risks from primary fragments generated by detonation of high-explosive munitions. The results showed that individual fatality and injury risks decrease with increasing stand-off distance, with a safety distance obtained of 97 m.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Engineering, Industrial
Chao Chen et al.
Summary: The study developed a dynamic methodology called Dynamic Graph Monte Carlo (DGMC) to model the evolution of multi-hazard accident scenarios, showing that risk may be underestimated if the spatial-temporal evolution of multi-hazard scenarios is neglected. Vapor cloud explosion (VCEs) may result in more severe damage than fire, and safety distances based solely on fire hazards are insufficient to prevent VCEs damage.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Engineering, Environmental
Jingde Li et al.
Summary: BLEVEs are extreme explosions driven by nonlinear physical processes, which can cause severe damage to structures and people. Prediction of blast loading using physics-based CFD methods is time-consuming but effective. The developed ANN model can efficiently predict the results of CFD models with high accuracy.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2021)
Article
Engineering, Industrial
Nicholas A. Marks et al.
Summary: This paper used Viper::Blast CFD software to probabilistically model explosive blast loads in urban environments, finding that the mean fatality risk for individuals exposed in the street when a 450 kg homemade ANFO explosive device is detonated at a road T-intersection is 16%. Placing bollards 10 m from the main street reduces fatality risk for individuals in the main street by over 90%. Additionally, deterministic analysis yielded fatality risks 10-60% higher than probabilistic analysis, leading to an overly conservative assessment of safety risks.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Engineering, Civil
Adam A. Dennis et al.
Summary: The study shows that artificial neural networks are highly suited to modeling blast loading in a confined internal environment, with significant improvements in accuracy achievable if a robust, well-distributed training dataset is used with a network structure that is tailored to the problem being solved.
INTERNATIONAL JOURNAL OF PROTECTIVE STRUCTURES
(2021)
Article
Engineering, Environmental
Shuai Yuan et al.
JOURNAL OF HAZARDOUS MATERIALS
(2020)
Article
Physics, Multidisciplinary
Or Sharir et al.
PHYSICAL REVIEW LETTERS
(2020)
Article
Engineering, Chemical
Jingde Li et al.
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES
(2020)
Article
Engineering, Civil
M. K. Almustafa et al.
ENGINEERING STRUCTURES
(2020)
Article
Engineering, Environmental
Jingde Li et al.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2019)
Article
Engineering, Mechanical
Chao Huang et al.
INTERNATIONAL JOURNAL OF IMPACT ENGINEERING
(2019)
Article
Engineering, Chemical
Jihao Shi et al.
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES
(2019)
Article
Mechanics
Y. Sugiyama et al.
Article
Engineering, Chemical
Ankit Dasgotra et al.
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES
(2018)
Article
Engineering, Marine
Jihao Shi et al.
Article
Engineering, Civil
Mark G. Stewart
Review
Construction & Building Technology
Hong Hao et al.
ADVANCES IN STRUCTURAL ENGINEERING
(2016)
Article
Biochemistry & Molecular Biology
Steven Kearnes et al.
JOURNAL OF COMPUTER-AIDED MOLECULAR DESIGN
(2016)
Review
Multidisciplinary Sciences
Yann LeCun et al.
Article
Engineering, Industrial
Margreet Spoelstra et al.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2015)
Article
Engineering, Industrial
Behrouz Hemmatian et al.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2015)
Article
Computer Science, Artificial Intelligence
Franco Scarselli et al.
IEEE TRANSACTIONS ON NEURAL NETWORKS
(2009)
Article
Engineering, Mechanical
Alex M. Remennikov et al.
INTERNATIONAL JOURNAL OF IMPACT ENGINEERING
(2007)
Article
Engineering, Chemical
A. M. Birk et al.
JOURNAL OF LOSS PREVENTION IN THE PROCESS INDUSTRIES
(2007)
Review
Engineering, Environmental
Tasneem Abbasi et al.
JOURNAL OF HAZARDOUS MATERIALS
(2007)
Review
Physics, Multidisciplinary
S. Boccaletti et al.
PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS
(2006)
Article
Computer Science, Artificial Intelligence
L Breiman
Article
Statistics & Probability
JH Friedman
ANNALS OF STATISTICS
(2001)
