Weighted regularized extreme learning machine to model the discharge coefficient of side slots

In the current research, a modern learning machine algorithm named “Weighted Regularized Extreme Learning Machine (WRELM)" is implemented for the first time for the simulation of the coefficient of discharge of side slots. For this purpose, an effective variable on the coefficient of discharge of side slots is firstly introduced, then five distinctive WRELM models are produced by it for the estimation of the coefficient. In the next stage, a database is created for verification of WRELM results. it should be mentioned that 70% of the data are utilized for training the WRELM models, while the rest (i.e. 30%) for testing them. After that, the optimal number of hidden layer neurons as well as the best activation function of the WRELM algorithm are chosen. In addition, the best regularization parameter and also the weight function of the WRELM are achieved. By conducting a sensitivity analysis, the most effective variable for the simulation of the coefficient of discharge along with the WRELM superior model is introduced. The WRELM superior model estimates values of the coefficient of discharge with the maximum exactness and the highest correlation. For instance, the estimations of the correlation coefficient and scatter index for this model are computed to be 0.930 and 0.051, respectively. The sensitivity analysis shows that the ratio of the side slot crest height to its length and the Froude number should be considered as the most important input variables. A comparison between the WRELM with the ELM displays that the former works much better. Furthermore, an uncertainty analysis is executed for both models. Eventually, an equation is suggested for the estimation of the coefficient of discharge and a partial derivative sensitivity analysis is performed on it.     

甘肃省陇东地区极端降水的时空特征

为阐明甘肃省陇东地区极端降水的变化规律,利用该地区13个气象台站1961~2015年的逐日降水资料,应用超门限峰值法、反距离加权法、线性倾向估计法、滑动平均法、Mann-Kendall突变分析法、复值Morlet小波分析法研究极端降水的时空变化特征。结果表明,陇东地区各站第95百分位极端降水阈值在27.8mm附近变化,即可以大雨事件作为极端降水事件进行监测;极端降水指数主要表现为从南向北递减的趋势,极端降水事件对环县和崆峒的影响较小;极端降水事件虽然在总量、强度上表现为减小趋势,但其发生频次及对总降水的贡献率逐渐增强;极端降水总量和极端降水强度周期变化均在21年左右能量最强,而极端降水频次和极端降水贡献率周期变化分别在28、5年左右能量最强。     

Ground robotics in tunnels: Keys and lessons learned after 10 years of research and experiments

The work reported in this article describes the research advances and the lessons learned by the Robotics, Perception and Real‐Time group over a decade of research in the field of ground robotics in confined environments. This study has primarily focused on localization, navigation, and communications in tunnel‐like environments. As will be discussed, this type of environment presents several special characteristics that often make well‐established techniques fail. The aim is to share, in an open way, the experience, errors, and successes of this group with the robotics community so that those that work in such environments can avoid (some of) the errors made. At the very least, these findings can be readily taken into account when designing a solution, without needing to sift through the technical details found in the papers cited within this text.     

Efficient estimation of extreme quantiles using adaptive kriging and importance sampling

This study considers an efficient method for the estimation of quantiles associated to very small levels of probability (up to O(10⁻⁹)), where the scalar performance function J is complex (eg, output of an expensive-to-run finite element model), under a probability measure that can be recast as a multivariate standard Gaussian law using an isoprobabilistic transformation. A surrogate-based approach (Gaussian Processes) combined with adaptive experimental designs allows to iteratively increase the accuracy of the surrogate while keeping the overall number of J evaluations low. Direct use of Monte-Carlo simulation even on the surrogate model being too expensive, the key idea consists in using an importance sampling method based on an isotropic-centered Gaussian with large standard deviation permitting a cheap estimation of small quantiles based on the surrogate model. Similar to AK-MCS as presented in the work of Schöbi et al., (2016), the surrogate is adaptively refined using a parallel infill criterion of an algorithm suitable for very small failure probability estimation. Additionally, a multi-quantile selection approach is developed, allowing to further exploit high-performance computing architectures. We illustrate the performances of the proposed method on several two to eight-dimensional cases. Accurate results are obtained with less than 100 evaluations of J on the considered benchmark cases.     

Simulation of performance of intermediate fluid vaporizer under wide operation conditions

The intermediate fluid vaporizer (IFV) is a typical vaporizer of liquefied natural gas (LNG), which in general consists of three shell-and-tube heat exchangers (an evaporator, a condenser, and a thermolator). LNG is heated by seawater and the intermediate fluid in these heat exchangers. A one-dimensional heat transfer model for IFV is established in this paper in order to investigate the influences of structure and operation parameters on the heat transfer performance. In the rated condition, it is suggested to reduce tube diameters appropriately to get a large total heat transfer coefficient and increase the tube number to ensure the sufficient heat transfer area. According to simulation results, although the IFV capacity is much larger than the simplified-IFV (SIFV) capacity, the mode of SIFV could be recommended in some low-load cases as well. In some cases at high loads exceeding the capacity of a single IFV, it is better to add an AAV or an SCV operating to the IFV than just to increase the mass flow rate of seawater in the IFV in LNG receiving terminals.     

Lubricating and physico-chemical properties of CI- 4 plus engine oil dispersed with surface modified multi-walled carbon nanotubes

This paper studies the effect of surface modification of multiwall carbon nanotubes (MWCNTs) prior to dispersion in engine oil to improve the tribological properties. The MWCNTs are stabilised in the lubricant with two different surfactants cetrimonium bromide (CTAB) and sorbitan monooleate (SPAN 80) and the effect of surfactants on the tribological properties has been studied. Pristine and surface modified MWCNTs in weight per cent range of 0·5% are dispersed in CI4 plus diesel engine oil. The foaming tendency and other physico-chemical properties of test lubricant have been studied to investigate the effect of nano materials and surfactants. The anti-wear and anti-friction properties are tested on a four ball wear tester and the comparison is made to assess the relative performance of pristine MWCNTs over surface modified MWCNTs. A strong influence of the surface modification technique is found on lubricating and physico-chemical properties. Both CTAB and SPAN 80 could keep the MWCNTs stable in the lubricant without compromising the foaming tendency of lubricant and other physico-chemical properties. The friction and wear characteristics of lubricants have improved with the dispersion of surface modified MWCNTs while there is no improvement in the properties of lubricant dispersed with pristine MWCNTs.     

Modeling and optimization of biodiesel engine performance using kernel-based extreme learning machine and cuckoo search

This study presents the optimization of biodiesel engine performance that can achieve the goal of fewer emissions, low fuel cost and wide engine operating range. A new biodiesel engine modeling and optimization framework based on extreme learning machine (ELM) is proposed. As an accurate model is required for effective optimization result, kernel-based ELM (K-ELM) is used instead of basic ELM because K-ELM can provide better generalization performance, and the randomness of basic ELM does not occur in K-ELM. By using K-ELM, a biodiesel engine model is first created based on experimental data. Logarithmic transformation of dependent variables is used to alleviate the problems of data scarcity and data exponentiality simultaneously. With the K-ELM engine model, cuckoo search (CS) is then employed to determine the optimal biodiesel ratio. A flexible objective function is designed so that various user-defined constraints can be applied. As an illustrative study, the fuel price in Macau is used to perform the optimization. To verify the modeling and optimization framework, the K-ELM model is compared with a least-squares support vector machine (LS-SVM) model, and the CS optimization result is compared with particle swarm optimization and experimental results. The evaluation result shows that K-ELM can achieve comparable performance to LS-SVM, resulting in a reliable prediction result for optimization. It also shows that the optimization results based on CS is effective.     

Adaptation options for wheat in Europe will be limited by increased adverse weather events under climate change

Ways of increasing the production of wheat, the most widely grown cereal crop, will need to be found to meet the increasing demand caused by human population growth in the coming decades. This increase must occur despite the decrease in yield gains now being reported in some regions, increased price volatility and the expected increase in the frequency of adverse weather events that can reduce yields. However, if and how the frequency of adverse weather events will change over Europe, the most important wheat-growing area, has not yet been analysed. Here, we show that the accumulated probability of 11 adverse weather events with the potential to significantly reduce yield will increase markedly across all of Europe. We found that by the end of the century, the exposure of the key European wheat-growing areas, where most wheat production is currently concentrated, may increase more than twofold. However, if we consider the entire arable land area of Europe, a greater than threefold increase in risk was predicted. Therefore, shifting wheat production to new producing regions to reduce the risk might not be possible as the risk of adverse events beyond the key wheat-growing areas increases even more. Furthermore, we found a marked increase in wheat exposure to high temperatures, severe droughts and field inaccessibility compared with other types of adverse events. Our results also showed the limitations of some of the presently debated adaptation options and demonstrated the need for development of region-specific strategies. Other regions of the world could be affected by adverse weather events in the future in a way different from that considered here for Europe. This observation emphasizes the importance of conducting similar analyses for other major wheat regions.     

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.