Economic competitiveness of compact steam methane reforming technology for on-site hydrogen supply: A Foshan case study

On-site hydrogen production through steam-methane reforming (SMR) from city gas or natural gas is believed to be a cost-effective way for hydrogen-based infrastructure due to high cost of hydrogen transportation. In recent years, there have been a lot of on-site hydrogen fueling stations under design or construction in China. This study introduces current developments and technology prospects of skid-mounted SMR hydrogen generator. Also, technical solutions and economic analysis are discussed based on China's first on-site hydrogen fueling station project in Foshan. The cost of hydrogen product from skid-mounted SMR hydrogen generator is about 23 CNY/kg with 3.24 CNY/Nm³ natural gas. If hydrogen price is 60 CNY/kg, IRR of on-site hydrogen fueling station project reaches to 10.8%. While natural gas price fall to 2.3 CNY/Nm³, the hydrogen cost can be reduced to 18 CNY/kg, and IRR can be raised to 13.1%. The conclusion is that skid-mounted SMR technology has matured and is developing towards more compact and intelligent design, and will be a promising way for hydrogen fueling infrastructures in near future.     

Enhanced gaseous hydrogen solubility in ferritic and martensitic steels at low temperatures

Metals that are exposed to high pressure hydrogen gas may undergo detrimental failure by embrittlement. Understanding the mechanisms and driving forces of hydrogen absorption on the surface of metals is crucial for avoiding hydrogen embrittlement. In this study, the effect of stress-enhanced gaseous hydrogen uptake in bulk metals is investigated in detail. For that purpose, a generalized form of Sievert's law is derived from thermodynamic potentials considering the effect of microstructural trapping sites and multiaxial stresses. This new equation is parametrized and verified using experimental data for carbon steels, which were charged under gaseous hydrogen atmosphere at pressures up to 1000 bar. The role of microstructural trapping sites on the parameter identification is critically discussed. Finally, the parametrized equation is applied to calculate the stress-enhanced hydrogen solubility of thin-walled pipelines and thick-walled pressure vessels during service.     

Tabular data: Deep learning is not all you need

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.     

Data fusion and transfer learning empowered granular trust evaluation for Internet of Things

In the Internet of Things (IoT), a huge amount of valuable data is generated by various IoT applications. As the IoT technologies become more complex, the attack methods are more diversified and can cause serious damages. Thus, establishing a secure IoT network based on user trust evaluation to defend against security threats and ensure the reliability of data source of collected data have become urgent issues, in this paper, a Data Fusion and transfer learning empowered granular Trust Evaluation mechanism (DFTE) is proposed to address the above challenges. Specifically, to meet the granularity demands of trust evaluation, time–space empowered fine/coarse grained trust evaluation models are built utilizing deep transfer learning algorithms based on data fusion. Moreover, to prevent privacy leakage and task sabotage, a dynamic reward and punishment mechanism is developed to encourage honest users by dynamically adjusting the scale of reward or punishment and accurately evaluating users’ trusts. The extensive experiments show that: (i) the proposed DFTE achieves high accuracy of trust evaluation under different granular demands through efficient data fusion; (ii) DFTE performs excellently in participation rate and data reliability.     

Analysis of operating limits and combustion state regulation for low-calorific value gases in industrial burners

The effective and efficient utilization of low-calorific value (LCV) gases has gained increasing attention in scientific research and industrial fields. In this study, the combustion characteristics of three LCV gases in practical devices are analyzed by using a nonadiabatic perfectly stirred reactor model. The complete steady-state solution in the temperature-residence time parameter space is obtained with arc-length continuation. The stable operation region is quantified by the eigenvalue analysis. The transition of solution curves is quantified with heat loss coefficient. Five key system parameters are systematically investigated on their effects on stability limits. With the combustion performance being quantified by a combustion state index, a combustion state regulation method is proposed to find the optimal regulation path of system parameters. Active subspace method is further applied to shorten the regulation step by identifying the active direction. The proposed method and findings are useful for optimal regulation of burning LCV gases in industrial burners.     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

A data-driven digital-twin prognostics method for proton exchange membrane fuel cell remaining useful life prediction

Prognostics and health management of proton exchange membrane fuel cell (PEMFC) systems have driven increasing research attention in recent years as the durability of PEMFC stack remains as a technical barrier for its large-scale commercialization. To monitor the health state during PEMFC operation, digital twin (DT), as a smart manufacturing technique, is applied in this paper to establish an ensemble remaining useful life prediction system. A data-driven DT is constructed to integrate the physical knowledge of the system and a deep transfer learning model based on stacked denoising autoencoder is used to update the DT with online measurement. A case study with experimental PEMFC degradation data is presented where the proposed data-driven DT prognostics method has applied and reached a high prediction accuracy. Furthermore, the predicted results are proved to be less affected even with limited measurement data.     

Effect of wind condition on unintended hydrogen release in a hydrogen refueling station

Ambient condition, especially the wind condition, is an important factor to determine the behavior of hydrogen diffusion during hydrogen release. However, only few studies aim at the quantitative study of the hydrogen diffusion in a wind-exist condition. And very little researches aiming at the variable wind condition have been done. In this paper, the hydrogen diffusion in different wind condition which including the constant wind velocity and the variable wind velocity is investigated numerically. When considering the variable wind velocity, the UDF (user defined function) is compiled. Characteristics of the FGC (flammable gas cloud) and the HMF (hydrogen mass fraction) are analyzed in different wind condition and comparisons are made with the no-wind condition. Results indicate that the constant wind velocity and the variable wind velocity have totally different effect for the determination of hydrogen diffusion. Comparisons between the constant wind velocity and the variable wind velocity indicate that the variable wind velocity may cause a more dangerous situation since there has a larger FGC volume. More importantly, the wind condition has a non-negligible effect when considering the HMF along the radial direction. As the wind velocity increases, the distribution of the HMF along the radial direction is not Gaussian anymore when the distance between the release hole and the observation line exceeds to a critical value. This work can be a supplement of the research on the hydrogen release and diffusion and a valuable reference for the researchers.     

Modeling unaccounted-for gas among residential natural gas consumers using a comprehensive fuzzy cognitive map

Residential natural gas consumption depends on several factors. Available tools and methods to identify, categorize, and validate effective factors have some limitations, making consumption modeling more complex. Once a comprehensive model of effective consumption factors is developed for residential gas consumers, it can predict consumption. In addition, such a model could be used to verify the accuracy of measuring devices in order to reduce unaccounted for gas (UFG). The key factors affecting residential gas consumption were identified based on previous studies and their mutual effects were analyzed using a fuzzy cognitive mapping (FCM) method. The most significant factors and their effects on natural gas consumption in the residential sector were determined. In this study, for the first time, the expected consumption for each consumer was estimated using a consumption index. Generally, if the estimated consumption is significantly different from the amount recorded by the meter, it could suggest a potential source of UFG. The proposed method was applied to the data collected from the residential gas consumers of a small region in Iran (Dasht-e Arjan region, Fars province), and the results demonstrate the effectiveness of the proposed method.     

Preparation and electrochemical characterization of Ti-based amorphous metallic glass with high strength

Ti-based amorphous metallic glasses have excellent mechanical, physical, and chemical properties, which is an important development direction and research hotspot of metal composite reinforcement. As a stable, simple, efficient, and large-scale preparation technology of metallic powders, the gas atomization process provides an effective way of preparing amorphous metallic glasses. In this study, the controllable fabrication of a Ti-based amorphous powder, with high efficiency, has been realized by using gas atomization. The scanning electron microscope, energy-dispersive spectrometer, and X-ray diffraction are used to analyze surface morphology, element distribution, and phase structure, respectively. A microhardness tester is used to measure the mechanical property. An electrochemical workstation is used to characterize corrosion behavior. The results show that as-prepared microparticles are more uniform and exhibit good amorphous characteristics. The mechanical test shows that the hardness of amorphous powder is significantly increased as compared with that before preparation, which has the prospect of being an important part of engineering reinforced materials. Further electrochemical measurement shows that the corrosion resistance of the as-prepared sample is also significantly improved. This study has laid a solid foundation for expanding applications of Ti-based metallic glasses, especially in heavy-duty and corrosive domains.