Development of novel combustion risk index for flammable liquids based on unsupervised clustering algorithms

Current liquid flammability classification mainly relies on flash point and its risk is largely dependent on consequence and probability. However, combustions of liquefied marine fuels have their uniqueness, leading to a less consistent with the common classification. This work aims at classifying flammable liquids in compression ignition engines for further safety evaluation. Besides liquid flammability characteristics, flame propagation and aerosol formulation are considered. Two unsupervised machine learning clustering algorithms, k-means and spectral clustering, are applied to the collected liquid compounds database. To consider both cluster cohesion and separation, the global mean silhouette value is used to find the optimal number of clusters and to evaluate the clustering performance. The results show that the spectral clustering outperforms k-means on classifying the risk ratings for all proposed models, while the clustering accuracy of the optimal model has been doubled by employing spectral clustering algorithm. Moreover, principal component analysis and star coordinate diagrams are presented to visualize high dimensional data to 2-D graphs. Finally, the overall liquid safety performance is evaluated by a novel combustion risk index via the weight values determined by the information entropy approach. This index can be used to explore inherently safer fuels in the process industries.     

基于DE-BPNN模型的含腐蚀缺陷管道失效压力预测*

为提升含腐蚀缺陷管道失效压力预测精度,准确把控管道状态,建立基于DE-BPNN的含腐蚀缺陷管道失效压力预测模型,有效避免BPNN模型陷入局部最优问题,提升预测精度。基于61组管道爆破实验数据,分别用DE-BPNN与BPNN模型进行仿真计算。结果表明:DE-BPNN预测结果平均相对误差为3.26%,R²为0.985 85,预测精度较BPNN模型有明显提升。应用DE-BPNN模型预测含腐蚀缺陷的管道失效压力可为长输管道运输调配和检维修提供决策支持。     

Application of machine learning technique for optimizing roadside design to decrease barrier crash costs,a quantile regression model approach

Introduction: In-transport vehicles often leave the travel lane and encroach onto natural objects on the roadsides. These types of crashes are called run-off the road crashes (ROR). Such crashes accounts for a significant proportion of fatalities and severe crashes. Roadside barrier installation would be warranted if they could reduce the severity of these types of crashes. However, roadside barriers still account for a significant proportion of severe crashes in Wyoming. The impact of the crash severity would be higher if barriers are poorly designed, which could result in override or underride barrier crashes. Several studies have been conducted to identify optimum values of barrier height. However, limited studies have investigated the monetary benefit associated with adjusting the barrier heights to the optimal values. In addition, few studies have been conducted to model barrier crash cost. This is because the crash cost is a heavily skewed distribution, and well-known distributions such as linear or poison models are incapable of capturing the distribution. A semi-parametric distribution such as asymmetric Laplace distribution can be used to account for this type of sparse distribution. Method: Interaction between different predictors were considered in the analysis. Also, to account for exposure effects across various barriers, barrier lengths and traffic volumes were incorporated in the models. This study is conducted by using a novel machine-learning-based cost-benefit optimization to provide an efficient guideline for decision makers. This method was used for predicting barrier crash costs without barrier enhancement. Subsequently the benefit was obtained by optimizing traffic barrier height and recalculating the benefit and cost. The trained model was used for crash cost prediction on barriers with and without crashes. Results: The results of optimization clearly demonstrated the benefit of optimizing the heights of road barriers around the state. Practical Applications: The findings can be utilized by the Wyoming Department of Transportation (WYDOT) to determine the heights of which barriers should be optimized first. Other states can follow the procedure described in this paper to upgrade their roadside barriers.     

基于集成学习的改进灰色瓦斯浓度序列预测*

为有效提高煤矿瓦斯浓度动态预测精度,基于微分方程理论和最小二乘法,从灰色预测模型静态灰色作用量出发,优化灰色作用量,推导幂指数型灰色作用量的改进灰色瓦斯浓度预测算法,推导基于集成学习不同灰色作用量幂指数型灰色瓦斯预测模型,进而研究吉林八连城长期和短期瓦斯浓度监控数据预测精度。结果表明:瓦斯浓度时间序列近似线性时,基于集成学习的改进灰色瓦斯浓度预测算法优于传统灰色瓦斯浓度预测算法,使瓦斯浓度预测值和实际值的均方根误差降低,均方根差最大降低2.25%。研究结果可有效提瓦斯浓度预测精度。     

Floral odor learning within the hive affects honeybees’ foraging decisions

Honeybees learn odor cues quickly and efficiently when visiting rewarding flowers. Memorization of these cues facilitates the localization and recognition of food sources during foraging flights. Bees can also use information gained inside the hive during social interactions with successful foragers. An important information cue that can be learned during these interactions is food odor. However, little is known about how floral odors learned in the hive affect later decisions of foragers in the field. We studied the effect of food scent on foraging preferences when this learning is acquired directly inside the hive. By using in-hive feeders that were removed 24 h before the test, we showed that foragers use the odor information acquired during a 3-day stimulation period with a scented solution during a food-choice situation outside the nest. This bias in food preference is maintained even 24 h after the replacement of all the hive combs. Thus, without being previously collected outside by foragers, food odors learned within the hive can be used during short-range foraging flights. Moreover, correct landings at a dual-choice device after replacing the storing combs suggests that long-term memories formed within the colony can be retrieved while bees search for food in the field.     

基于随机森林模型的辽河高时间分辨率氮、磷浓度模拟与预测

随着环境信息获取技术的飞速发展,水质监测数据逐渐呈现出高时间分辨率的特点.针对传统方法在模拟高频检测数据时的不足,本文基于随机森林建立了河流氮、磷逐日浓度预测模型,识别了影响辽河干流马虎山断面氮、磷浓度变化的主要因素,并预测了未来不同情景下氮、磷浓度变化特征.结果表明：①马虎山断面氮、磷浓度变化的主要影响因素是上游珠尔山断面的来水水质和本断面的流量;②随机森林模型在高时间分辨率的水质指标模拟中具有误差低和拟合优度高的特点,其中,TN浓度预测模型的RMSE为0.40 mg·L^-1,R²为0.95,TP浓度预测模型的RMSE为0.01 mg·L^-1,R²为0.96;③在不同水文、污染控制和来水水质的变化情景下,未来马虎山断面氮、磷浓度变化主要取决于上游 来水水质,加强全流域营养盐控制是确保断面水质稳定达标的重要基础.     

Simultaneous adoption of integrated soil fertility management technologies in the Chinyanja Triangle,Southern Africa

Empirical scientific evidence indicates that there is still room for increasing food production by improving land productivity. This study aimed at identifying the key determinants that govern farmers’ decisions to adopt multiple components of integrated soil fertility management (ISFM) in a maize mixed cropping system of the Chinyanja Triangle, Southern Africa. Revealed preferences of ISFM components were collected from 320 randomly selected households and multivariate probit (MVP) model was used to analyse the simultaneous effects on adoption based on biophysical plot and household‐level socioeconomic attributes. The results show that farmers’ choices of a set of ISFM components are determined by a mix of factors that address the trade‐offs and synergies among them. Non‐farm income, moderate land quality perception, and education influence simultaneous technology adoption, while gender and crop loss increase the likelihood of farmers’ decisions to adopt independent options. Having other sources of income supports co‐adoption of inorganic fertilizer, residue incorporation, and crop rotation. Input/output market access, access to information, financial sources, and climate variability also play pivotal role in technology adoption. These results indicate that resource availability, learning costs, finances, and risk aversion need to be considered when designing and promoting ISFM technologies as a package.     

Streamflow Hydrology Estimate Using Machine Learning (SHEM)

Continuity and accuracy of near real‐time streamflow gauge (streamgage) data are critical for flood forecasting, assessing imminent risk, and implementing flood mitigation activities. Without these data, decision makers and first responders are limited in their ability to effectively allocate resources, implement evacuations to save lives, and reduce property losses. The Streamflow Hydrology Estimate using Machine Learning (SHEM) is a new predictive model for providing accurate and timely proxy streamflow data for inoperative streamgages. SHEM relies on machine learning (“training”) to process and interpret large volumes (“big data”) of historic complex hydrologic information. Continually updated with real‐time streamflow data, the model constructs a virtual dataset index of correlations and groups (clusters) of relationship correlations between selected streamgages in a watershed and under differing flow conditions. Using these datasets, SHEM interpolates estimated discharge and time data for any indexed streamgage that stops transmitting data. These estimates are continuously tested, scored, and revised using multiple regression analysis processes and methodologies. The SHEM model was tested in Idaho and Washington in four diverse watersheds, and the model's estimates were then compared to the actual recorded data for the same time period. Results from all watersheds revealed a high correlation, validating both the degree of accuracy and reliability of the model.     

Is Learning without teaching possible? The productive tension between network governance and reflexivity

ABSTRACT

Theories of reflexive governance are closely linked with the claim that more traditional modes of coordination have been replaced by networked structures, allowing reflexivity to emerge and reflexive learning to function as a steering mechanism in rapidly changing policy contexts. This paper explores this connection between reflexivity, governance, learning and networks in societal transitions, focusing particularly on the claim that networks will deliver reflexive learning. Using network theories from both policy networks and network governance and a case study of the Canadian agricultural biotechnology (agbiotech) policy network, it suggests that the kind of learning produced in networks will be a function of network structure. In particular, higher order reflexive learning will be compromised by the inevitability of the political struggle for nodality or central place in networks and the ensuing distribution of opportunities for bridging and bonding activities. Networks such as the Canadian agbiotech policy network that may promote learning but not necessarily reflexive learning are increasingly disadvantaged in contemporary policy settings.     

Accident data for the Semantic Web

This paper describes concerns about the documentation, dissemination and use of lessons learned from mishap investigations, impediments posed by current practices, and opportunities for improvement. Lessons are presently developed, documented and stored primarily in narrative form and relational databases, and disseminated in many forms and media, including the Internet. Current practices pose many impediments to maximized development, dissemination and use. Investigation process research and new data concepts behind the Semantic Web, exploited elsewhere, offer potential opportunities to overcome these impediments. To exploit these opportunities, formation of a working group to develop an improved Semantic Web-friendly mishap investigation lessons learning system is proposed. An example illustrating an alternative approach is described to support a reasonable expectation that an alternative lessons learning system could be developed.