Jihao Shi- Doctor of Engineering
- Research Assistant Professor at The Hong Kong Polytechnic University
Jihao Shi
- Doctor of Engineering
- Research Assistant Professor at The Hong Kong Polytechnic University
Natural gas and hydrogen release and dispersion modeling, vapor cloud explosion modeling of offshore platform
About
77
Publications
13,142
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,307
Citations
Introduction
Current institution
Publications
Publications (77)
Complex dynamics inherent of building fire poses big challenges to firefighting and rescue, especially with limited access to critical fire-hazard information. This work proposes the novel AIoT-integrated Digital Twin for the full-scale multi-floor building to manage the dynamics fire information. This system allows for super real-time mapping of a...
In this study, the influence of porous non-metallic balls on the dynamics of detonation propagation
in hydrogen–oxygen mixtures is studied in stainless steel tubes with square cross-sections. The
effect of the length and thickness of the balls is considered in detail. Four pressure transducers are
used to record the detonation time-of-arrival, an...
Hydrogen is considered a leading clean energy carrier and versatile industrial raw material, playing a crucial role in driving down greenhouse gas emissions. Ensuring the safe utilization of hydrogen holds paramount significance. The present study investigated the variation law of the lower flammability limit of hydrogen under the influence of inhi...
The determination of the critical ventilation flow rate is significant for risk control and standard development during accidental hydrogen leakage in a confined space with hydrogen-related equipment. This paper presents an analytical model for calculating the critical ventilation flow rate through the quantification and constraint solution of the...
Efficient modeling of jet diffusion during accidental release is critical for operation and maintenance management of hydrogen facilities. Deep learning has proven effective for concentration prediction in gas jet diffusion scenarios. Nonetheless, its reliance on extensive simulations as training data and its potential disregard for physical laws l...
A reasonable natural gas explosion load model is essential to evaluate the damage to the utility tunnel. This study systematically investigates critical parameters that affect gas explosion loads in the utility tunnel by the finite volume method, including ignition point location, methane volume, methane concentration, internal obstacles, and utili...
Natural gas jet fire induced by igniting blowouts has the potential to cause critical structure damage and great casualties of offshore platforms. Real-time natural gas jet fire plume prediction is essential to support the emergency planning to mitigate subsequent damage consequence and ocean pollution. Deep learning based on a large amount of Comp...
Natural gas explosion of offshore platform is prone to cause accidental disaster such as platform collapse and casualties etc. Real-time natural gas explosion consequence reconstruction is essential to support a quick accidental emergency response planning to prevent the accidental escalation to disaster. The widely-used CFD is computationally inte...
Recent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring underwater gas leakage, but the shortcomings of huge...
The subsea wellhead (SW) system is a crucial connection between blowout preventors (BOPs) and subsea oil and gas wells. Excited by cyclical fatigue dynamic loadings, the SW is prone to fatigue failure, which would lead to the loss of well integrity and catastrophic accidents. Based on the Bayesian Regularization Artificial Neuron Network (BRANN), t...
In order to reveal the mechanism of water fog explosion suppression and research the combined effect of water fog and obstacle on hydrogen/air deflagration, multiple sets of experiments were set up. The results show that the instability of thermal diffusion under lean combustion conditions is the main influencing factor of hydrogen/air flame surfac...
Gas leaks from subsea oil and gas facilities could cause significant ocean environment damage. Such leaks can cause fire and explosion, for example, a fire on the ocean surface west of Mexico's Yucatan peninsula. Detecting a gas leak is critical in managing fire and explosion risks. This study proposes using autonomous underwater vehicles -robotic...
Natural gas release from oil and gas facilities contributes significantly to the greenhouse effect and reduces the benefit of displacing heavy fossil fuels with natural gas. Real-time concentration spatiotemporal evolution forecasting of natural gas release is essential to predetermine atmospheric carbon trajectory and devise timely strategy to mit...
Risk assessment plays an important role in facilitating the safety and sustainability of deepwater drilling. Managed pressure drilling is increasingly used as an alternative to conventional drilling techniques. This technique increases the complexity and uncertainty of drilling systems with enhancement and advancement of functions. This paper prese...
Water spray is an economical and environment-friendly alternative to mitigate gas explosion. This study conducts explosion risk analysis (ERA)-based water spray mitigation analysis of ultra-deep-water semi-submersible platform. 5000 gas explosion simulations with and without water spray are conducted by using FLACS codes. The outcome demonstrates t...
Fine water mist is one of the most well-known alternatives to mitigate the gas explosion in the chamber of maritime safety. Previous experimental researches were mainly focused on the water mist's mitigation effects upon the gas explosion on condition that the spray nozzles were distributed evenly, however, they are locally distributed actually. Th...
The drilling risers are the most critical and vulnerable connection of floating drilling platform and subsea wellhead. In order to improve the operation efficiency, the operators have attempted to suspend the drilling operations and keep the drilling risers connected to the wellhead to survive in the storm, thus the fragility of the drilling risers...
This study aims to introduce the integrated approach, namely the integration of the Faster R-CNN technique and Optical gas imaging (OGI) for real-time natural gas leak detection of offshore platforms. OGI is used to record large number of leak videos which are essential to develop the desirable Faster R-CNN model. Due to the fact that the natural g...
Computational Fluid Dynamic (CFD) has been widely used for the gas release and dispersion modeling, which however could not support real-time emergency response planning due to its high computation overhead. Surrogate models offer a potential alternative to rigorous computational approaches, however, as the point-estimation alternatives, the existi...
Some attempts have been made to predict the adverse effects of released toxic gas on individuals. However, the classification of the hazardous area considering the dynamic changes and focusing on the whole facility remains a challenging issue. This paper presents a novel approach to classify the hazardous areas on offshore facilities in toxic gas l...
High repeatability of similar information but a lack of typical fault features, in the monitoring data of distillation processes for continuous production, leads to a small proportion of data with labels. Therefore, the requirement for a large number of labeled samples in conventional deep learning models cannot be met, resulting in significant per...
Hydrogen sulfide (H2S) precipitation incidents often occur during pigging operations in crude oil pipelines, which result in the leakage of H2S with a high concentration at the site and seriously threaten the life and health of workers. To identify the main cause of H2S precipitation, this study designs a crude oil pipeline experimental system by w...
Poisoning load and explosion overpressure load pose grave threat to the offshore oil and gas industry. Many safety measures are adopted to prevent and mitigate the adverse impact due to the poisoning load and explosion overpressure load. Among them, the process protection system is a general safety barrier which has been widely used. Therefore, the...
Explosion risk analysis (ERA) is an effective method to investigate potential accidents in hydrogen production facilities. The ERA suffers from significant hydrogen dispersion-explosion scenario-related parametric uncertainty. To better understand the uncertainty in ERA results, thousands of Computational Fluid Dynamics (CFD) scenarios need to be c...
Real-time hydrocarbon leak detection is an essential part of process safety and loss prevention program. Optical gas imaging (OGI) is one of the attractive methods to monitor hydrocarbon leak in the processing system. The manual analysis of a video frame to detect a potential leak is cumbersome and error-prone. The purpose of this study is to devel...
The Fuel Cell Vehicles are going to be introduced in domestic cities of China, which will require urban Hydrogen Refueling Stations (HRS). Such urban refueling center would be a public concern given their location in the congested area and the potential hydrogen release and fire risk. Risk analysis of possible fire scenarios is an efficient approac...
Hydrogen leakage is a crucial risk for the hydrogen generation unit, which would lead to the potential fire and explosion accidents. Hydrogen leakage risk analysis is the essential alternative to ensure the safety of the hydrogen generation process. This paper presents a dynamic risk analysis methodology regarding the hydrogen leakage in the hydrog...
Drilling risers are crucial connection of subsea wellhead and floating drilling platform. Fracture failure of deepwater drilling risers is the most serious accident in offshore drilling, which would lead to disastrous consequences. This paper presents a Bayesian Network (BN) model to conduct risk analysis for fracture failure of deepwater drilling...
Recently, the Bayesian Regularization Artificial Neural Network (BRANN) approach has been used for flammable cloud estimation in a congested offshore setting. These authors observed that BRANN exhibits lower accuracy under specific release and dispersion scenarios. To improve BRANN’s accuracy and robustness, the authors have proposed the integratio...
Gas composition has a significant impact on the dispersion behavior and accumulation characteristics of blowout gas. However, few public studies has investigated the corresponding effect of gas composition. Therefore, this study firstly builds the FLACS-based numerical model about an offshore drilling platform. Then several scenarios by varying the...
The Response Surface Method (RSM)-based non-intrusive method has been widely used to reduce the computational cost for stochastic Explosion Risk Analysis (ERA) in oil and gas industry. However, the RSM, which may cause the overfitting problem, can reduce robustness and efficiency of the ERA procedure. Therefore, a more robust Bayesian Regularizatio...
This study aims to develop an integrated model - NFPA-68-BRANN model, which can be used to calculate the vent areas of cubic enclosures with obstacles. Seven experiments regarding vented explosion inside the obstructed enclosure are reviewed and applied to check the accuracy of two existing standards, i.e. the NFPA-68 2018 and the BS EN 14994:2007....
Computational Fluid Dynamics (CFD) is routinely used in Explosion Risk Analysis (ERA), as CFD-based ERA offers a good understanding of underlying physics accidental loads. Generally, simplifications were incorporated into CFD-based ERA to limit the number of simulations. Frozen Cloud Approach (FCA) is a frequently used simplification in the dispers...
Data driven models are increasingly used in engineering design and analysis. Bayesian Regularization Artificial Neural Network (BRANN) and Levenberg-Marquardt Artificial Neural Network (LMANN) are two widely used data-driven models. However, their application to study the dispersion in complex geometry is not explored.
This study aims to investigat...
This study aims to introduce the Artificial Neuron Network (ANN) technique, namely Bayesian Regularization Artificial Neuron Network (BRANN) to Explosion Risk Analysis (ERA) of floating offshore platform and eventually develop the ANN-based ERA procedure. In order to verify the feasibility of this developed procedure, a case study of floating offsh...
The complexity of a deepwater well control system makes defining appropriate safety requirements with traditional safety analysis methods difficult. Hence, there is a need for a complex systems approach for better understanding the development and prevention of accidents during deepwater drilling. Differing from traditional methods based on reliabi...
Data driven models are increasingly used in engineering design and analysis. Bayesian Regularization Artificial Neural Network (BRANN) and Levenberg-Marquardt Artificial Neural Network (LMANN) are two widely used data-driven models. However, their application to study the dispersion in complex geometry is not explored.
This study aims to investiga...
In explosion risk analysis, Frozen Cloud Approach (FCA) and Dimensionless Response Surface Method (DRSM) are both commonly used to achieve a balance between simulation workloads and accurate results. However, the drawbacks of these two approaches are obvious. FCA is not reliable for risk study of fuel-dominated regions. Whereas DRSM usually couples...
The numerical modeling is one of the key foundations for the explosion risk assessment of offshore platforms. However, there is a lack of unified modelling standards for grid size, obstruction congestion etc., and thus the prediction accuracy of the explosive overpressure is difficult to guarantee. This paper aims to propose a procedure to derive t...
In view of the insufficient ability to assess the damage of corrugated blast walls subjected to blast loads by using the SDOF model, a NLFEA (nonlinear finite element analysis model was built to analyze the dynamic response and damage mechanism of three kinds of typical corrugated blast walls on a platform. P-I diagrams and a simplified empirical e...
Pressure–impulse (P–I) diagrams are commonly used for assessment on blast resistance capacity of corrugations on offshore cabins for given blast-loading scenarios or in the early design. Current methods such as experimental models, analytical models and Nonlinear Finite Element Analysis (NLFEA) models could be used to generate the P–I diagram. Howe...
Liquefied natural gas (LNG), playing an important part in clean energy utilization at present, prompts the requirements of road tanker trucks but raises great concerns for its transportation safety. In view of this, an analysis was first made on the whole failure process from LNG leakage to fire to the overload on the tank in some real accidents of...
Questions
Questions (4)
Which is better between Radial Basis Function Neural Network and Support Vector Machine in terms of function approximation? Have some already conducted the comparisons for function approximation? Thanks
Do the GA- or PSO or ABC- based BPANN (LM or BR) perform better than the traditional BRANN in terms of function approximation? My answer is ' Not Necessarily'. How about your opinion? Any discussion would be welcome. Thax.
Hi, everyone, I would like to employ the ANN for the probability analysis. In the process, the ANN can support deterministic model when the high accuracy can be obtained. However, when less accuracy, I just view the ANN as the stochatic model. Consequently, I need to get the confident interval of prediction interval of ANN model. Then I can get the sampling from those intervals for the following probability analysis. I know how to calculate the intervals when the input data number is larger than that of parameters trained in the ANN. But how can I get those intervals when the input data number is smaller ( N-p<0)? Thax.
Hi, everyone
Who is familiar with the Explosion Risk Analysis (ERA) of offshore platform? My question focuses on the ignition model since two model are popular, i.e. UKOOA model and TDIIM model. May I use the UKOOA model for further ERA to determine the DALs.
