Application of robust machine learning methods to modeling hydrogen solubility in hydrocarbon fuels

Having accurate information about the hydrogen solubility in hydrocarbon fuels and feedstocks is very important in petroleum refineries and coal processing plants. In the present work, extreme gradient boosting (XGBoost), multi-layer perceptron (MLP) trained with Levenberg–Marquardt (LM) algorithm, adaptive boosting support vector regression (AdaBoost?SVR), and a memory-efficient gradient boosting tree system on adaptive compact distributions (LiteMORT) as four novel machine learning methods were used for estimating the hydrogen solubility in hydrocarbon fuels. To achieve this goal, a database containing 445 experimental data of hydrogen solubilities in 17 various hydrocarbon fuels/feedstocks was collected in wide-spread ranges of operating pressures and temperatures. These hydrocarbon fuels include petroleum fractions, refinery products, coal liquids, bitumen, and shale oil. Input parameters of the models are temperature and pressure along with density at 20 °C, molecular weight, and weight percentage of carbon (C) and hydrogen (H) of hydrocarbon fuels. XGBoost showed the highest accuracy compared to the other models with an overall mean absolute percent relative error of 1.41% and coefficient of determination (R²) of 0.9998. Also, seven equations of state (EOSs) were used to predict hydrogen solubilities in hydrocarbon fuels. The 2- and 3-parameter Soave-Redlich-Kwong EOS rendered the best estimates for hydrogen solubilities among the EOSs. Moreover, sensitivity analysis indicated that pressure owns the highest influence on hydrogen solubilities in hydrocarbon fuels and then temperature and hydrogen weight percent of the hydrocarbon fuels are ranked, respectively. Finally, Leverage approach results exhibited that the XGBoost model could be well trusted to estimate the hydrogen solubility in hydrocarbon fuels.     

Electromagnetic transients in the control system of output parameters of a solar power plant in Tajikistan Central Asia region

At present, as the demand for electricity increases in all sectors, there is an urgent need to introduce alternative renewable energy sources into modern energy systems. Renewable energy sources, which consist of solar (photovoltaic, PV), wind and hydro power, are key alternative sources of “green energy’’ energies, but it can also be used to produce “green” hydrogen. Thanks to scientific and technological progress, the cost of photovoltaic solar radiation converters is constantly decreasing at a high rate, which makes it possible to build solar power plants of sufficiently large capacity. In the coming decades, solar energy will become an incentive for the economic development of countries that have the maximum “solar” resource. The Republic of Tajikistan is one of these countries with a high potential for solar energy.The article presents an analysis of the resources and potential of solar energy in the Republic of Tajikistan. The study of electromagnetic transients in networks with photovoltaic solar power plants is performed. The main equations, simulation model and calculations of transients are presented, taking into account changes in voltage on DC buses. An algorithm for controlling the system of automatic control of output parameters is proposed. The analysis of dynamic and static modes in parallel operation of a solar power plant with the grid is carried out. A block diagram and computer model is constructed in the MATLAB package together with Simulink and Power System Blockset.     

内含实体对H型垂直轴风力机气动性能的影响

以H型垂直轴风力机及其内含圆柱形实体为研究对象,对NACA0018翼型的五叶片H型垂直轴风力机的气动性能进行数值模拟和实验验证。分析8种不同直径的内含圆柱体,在内含实体截面积占风轮迎风面积之比分别为21.2%、50.0%和76.9%时,风力机风能利用率的峰值分别下降8.04%、20.7%及74.3%。结果表明：随着内含实体直径的增大,风能利用率的峰值逐渐减小,开始较为缓慢,达到一定值时快速下降。小直径内含实体主要影响叶片在下风区的转矩,对风能利用率的影响较小,而大直径内含实体还会影响叶片在上风区的转矩,其风能利用率迅速减小。对于内含固定直径的实体,比如在现有建筑物外侧安装风力机时,其风轮半径的选择需综合考虑风能利用率和风力机的建造成本两方面的因素。研究结果可为建筑物与垂直轴风力机进行有效结合以提高风能的利用提供参考。     

Flash Lamps as Ignition and Initiation Sources of the VS-2 Pyrotechnic Composition

In the present work it is found that the pyrotechnic composition VS-2 can be initiated with flash lamps IFC-500 and EVIS. VS-2 pyrotechnic composition contains 90% of mercury（Ⅱ） 5-hydrazinotetrazolate perchlorate and 10% of optically transparent copolymer of 2-methyl-5-vinyltetrazole and methacrylic acid （PVMT）. We have found that the flash lamps make it possible to initiate combustion of VS-2 composition with its transition to detonation both in cylindrical charges placed in brass caps of 5 mm diameter and 2 mm high， and film charges with 10 mm×80 mm in size and surface weights of 60 mg·cm^-2 and 90 mg·cm^-2， showing ignition delay times 10 μs and 3 μs， respectively. We also measured detonation velocities for VS-2 composition film charges， which were 4375-4505 m·s^-1 （of the charge being surface mass 60 mg·cm^-2） and 4221-4281 m·s^-1 （of the charge being surface mass 90 mg·cm^-2） and their blasting action on the aluminum plate. The depths of the normal shock wave imprints at the charge-barrier interface were 0.6-0.7 mm （for surface mass of the film charges 60 mg·cm^-2） and 1.2-1.3 mm （for surface mass of the film charges 90 mg·cm^-2）.     

机器翻译译文质量估计综述

机器翻译译文质量估计(Quality Estimation,QE)是指在不需要人工参考译文的条件下,估计机器翻译系统产生的译文的质量,对机器翻译研究和应用具有很重要的价值。机器翻译译文质量估计经过最近几年的发展,取得了丰富的研究成果。该文首先介绍了机器翻译译文质量估计的背景与意义;然后详细介绍了句子级QE、单词级QE、文档级QE的具体任务目标、评价指标等内容,进一步概括了QE方法发展的三个阶段: 基于特征工程和机器学习的QE方法阶段,基于深度学习的QE方法阶段,融入预训练模型的QE方法阶段,并介绍了每一阶段中的代表性研究工作;最后分析了目前的研究现状及不足,并对未来QE方法的研究及发展方向进行了展望。     

Prediction of fish quality level with machine learning

In this study, sea bream, sea bass, anchovy and trout were captured and recorded using a digital camera during refrigerated storage for 7 days. In addition, their total viable counts (TVC) were determined on a daily basis. Based on the TVC, each fish was classified as ‘fresh’ when it was <5 log cfu per g, and as ‘not fresh’ when it was >7 log cfu per g. They were uploaded on a web-based machine learning software called Teachable Machine (TM), which was trained about the pupils and heads of the fish. In addition, images of each species from different angles were uploaded to the software in order to ensure the recognition of fish species by TM. The data of the study indicated that the TM was able to distinguish fish species with high accuracy rates and achieved over 86% success in estimating the freshness of the fish species tested.     

Vision-related quality of life with myopia management: A review

The disease of myopia has come into focus as a worldwide public health concern. Myopia has shown increasing prevalence, incidence at earlier age and progression to a higher degree. Progressive increase in degree of myopia is strongly associated with increase in axial length of the eye. Various interventions have been shown to slow axial elongation in children. These interventions have been studied to assess efficacy in slowing axial elongation and correction of vision. In addition, research into quality of vision, risk of adverse events, overall safety and impact on vision-related quality (VR-QoL) of life has been pursued. In contrast, studies have been published to demonstrate the risks of myopia, high myopia and increased axial length. This review will discuss VR-QoL assessment on the most effective and most commonly prescribed interventions to slow axial elongation and myopia progression. The patient attributes considered are VR-QoL scores from validated instruments. The development and use of validated survey instruments to assess the patient-reported outcomes is discussed. The review demonstrates that there are numerous factors that may impact VR-QoL to evaluate in the decision-making process when eye care providers consider when, how and if to prescribe myopia management (MM) for children with myopia.     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Kinetic Monte Carlo simulation of hydrogen production from photocatalytic water splitting in the presence of methanol by 1 wt% Au/TiO2

In this research, using the kinetic Monte Carlo simulation (KMC), the hydrogen production from a water-methanol mixture using Au/TiO₂ photocatalyst is investigated. A mechanism is proposed, and the rate constants of the reaction steps are specified. The reaction rate constants of different steps and the concentration of the active sites on the photocatalyst surface were determined. An excellent match between simulated and experimental data confirms the results. The electron-hole pair production, methanol adsorption on the photocatalyst surface, and electron-hole recombination steps are considered the most critical steps. To study the effects of independent variables (initial concentration of methanol, photocatalyst dosage, pH, and time of reaction) on the produced hydrogen, a combination of KMC simulation and design of experiment was employed. The concentration of photocatalysis has the highest and pH has the lowest effect on the hydrogen production. The optimal conditions for photocatalytic hydrogen production are presented.