环境模型参数识别与不确定性分析

在对水文模型实例的参数不确定性分析基础上,分别采用传统灵敏度分析方法、HSY算法、线性回归等方法对模型参数特性进行了识别与比较研究.结果表明参数优化算法与传统灵敏度分析方法不能解释模型结构复杂性特征,采用不确定性分析方法对环境模型参数进行识别提供了深入分析与理解模型系统的有效途径.     

Forecasting China’s primary energy demand based on an improved AI model

An improved energy demand forecasting model is built based on the autoregressive distributed lag (ARDL) bounds testing approach and an adaptive genetic algorithm (AGA) to obtain credible energy demand forecasting results. The ARDL bounds analysis is first employed to select the appropriate input variables of the energy demand model. After the existence of a cointegration relationship in the model is confirmed, the AGA is then employed to optimize the coefficients of both linear and quadratic forms with gross domestic product, economic structure, urbanization, and technological progress as the input variables. On the basis of historical annual data from 1985 to 2015, the simulation results indicate that the proposed model has greater accuracy and reliability than conventional optimization methods. The predicted results of the proposed model also demonstrate that China will demand approximately 4.9, 5.6, and 6.1 billion standard tons of coal equivalent in 2020, 2025, and 2030, respectively.     

AHP与GA-SVM耦合模型在滑坡预警中的应用*

为了减少滑坡造成的损失，提高滑坡预测的准确性，通过搭建灾害模拟平台获得滑坡的实验数据，在获得多组模拟实验数据后，分析各变量的特性。首先，通过层次分析(Analytic Hierarchy Process，AHP)算法，对滑坡进行危险度划分；然后，通过支持向量机(Support Vector Machine，SVM)建立模型，遗传算法(Genetic Algorithm,GA)再优化SVM参数，提出1种层次分析法与GA-SVM相耦合的模型。研究结果表明:AHP方法划分后的数据，通过GA与SVM结合建立的模型精度较好，实验预测结果与实际结果较为吻合，与单一SVM相比，精度更高，结果更好，更加适用于多变量的复杂非线性滑坡预警。     

Failure mode and effect analysis using regret theory and PROMETHEE under linguistic neutrosophic context

Failure mode and effect analysis (FMEA), which aims to identify and assess potential failure modes in a system, has been widely utilized in diverse areas for improving and enhancing the performance of systems due to it is a powerful and useful risk and reliability assessment instrument. However, the conventional FMEA approach has been suffered several criticisms for it has some shortcomings, such as unable to handle ambiguous and uncertain information, neglect the relative weights of risk criteria, and without considering the psychological behaviors of decision-makers. To ameliorate these limitations, this paper aims at establishing a hybrid risk ranking model of FMEA via combing linguistic neutrosophic numbers, regret theory, and PROMETHEE (Preference ranking organization method for enrichment evaluation) approach. In the presented model, linguistic neutrosophic numbers are adopted to capture decision-makers’ evaluation regarding the failure modes on each risk criterion. A modified PROMETHEE approach based on regret theory is presented to obtain the risk priority of failure modes considering the psychological behaviors of decision-makers. Moreover, a maximizing deviation model and TOPSIS (Technique for order preference similar to ideal solution) are separately applied to derive the weights of risk criteria and decision-makers. Finally, a numerical example relating to the supercritical water gasification system is employed to implement the presented method, and the effectiveness and feasibility of the proposed model are validated by the results derived from a sensitivity and comparison analysis.     

Optimizing mixture properties of biodiesel production using genetic algorithm-based evolutionary support vector machine

Nowadays, biodiesel is used as one of the alternative renewable energy due to the increasing energy demand. However, optimum production of biodiesel still requires a huge number of expensive and time-consuming laboratory tests. To address the problem, this research develops a novel Genetic Algorithm-based Evolutionary Support Vector Machine (GA-ESIM). The GA-ESIM is an Artificial Intelligence (AI)-based tool that combines K-means Chaotic Genetic Algorithm (KCGA) and Evolutionary Support Vector Machine Inference Model (ESIM). The ESIM is utilized as a supervised learning technique to establish a highly accurate prediction model between the input--output of biodiesel mixture properties; and the KCGA is used to perform the simulation to obtain the optimum mixture properties based on the prediction model. A real biodiesel experimental data is provided to validate the GA-ESIM performance. Our simulation results demonstrate that the GA-ESIM establishes a prediction model with better accuracy than other AI-based tool and thus obtains the mixture properties with the biodiesel yield of 99.9%, higher than the best experimental data record, 97.4%.     

Factors associated with driving under the influence of alcohol

Objective: This study examined the risk factors of driving under the influence of alcohol (DUI) among drivers of specific vehicle categories (DSC). On the basis of this research, the variables related to DUI and involvement in traffic crashes were defined. The analysis was conducted for car drivers, bicyclists, motorcyclists, bus drivers, and truck drivers.

Method: The research sample included drivers involved in traffic crashes on the territory of Serbia in 2016 (60,666). Two types of analyses were conducted in this study. Logistic regression established the correlation between DUI and DSC and the The Technique for Order of Preference by Similarity to Ideal Solution (Multi-criteria decision making) method was applied to consider the scoring and explore the potential for the prevalence of DUI on the basis of 2 data sets (DUI and non DUI).

Results: The study results showed that driver error and male drivers were the 2 most significant risk factors for DUI, with the highest scores and potential for prevalence. The nonuse of restraint systems, driver experience, and driver age are the factors with a significant prediction of involvement in an accident and an insignificant prediction of DUI.

Conclusions: Following the development of the logistic prediction models for DUI drivers, testing of the model was conducted for 3 control driver groups: Car, motorcycle, and bicycle. The prediction model with a probability greater than 50% showed that 77% of car drivers were under the influence of alcohol. Similarly, the prediction percentage for motorcyclists and bicyclists amounted to 71 and 67%, respectively. The recommendation of the study is that drivers whose DUI probability is above 50% should be potentially suspected of DUI. The results of this study can help to understand the problem of DUI among specific driver categories and detect DUI drivers, with the aim of creating successful traffic safety policy.     

基于分布型电力系统的 PSO 优化设计

优化了传统粒子群算法，运用了混沌算法对粒子做初始化，优化了传统粒子群算法的收敛特性，并在算法的优化过程中，增加了混沌干扰元素对整体最优化极值做混沌干扰，将符合杂交几率的优化粒子做杂交处理，提高了粒子群的种类，增强了粒子群算法的搜寻水平。并通过IEEE33节点的分布型电力系统做无功优化仿真验证，通过比较，验证了优化算法的优越性与准确性。     

基于改进TOPSIS的受灾点需求紧迫性分级研究

地震发生初期,各受灾点对物资需求的紧迫性存在差异。在应急资源有限的情况下,为提高救援效率,应急资源需要按照受灾点需求紧迫性优先级进行分配和调度。首先,构建了受灾点需求紧迫性评价指标体系,并采用博弈论方法将熵权法和层次分析法相结合,确定权重组合系数及各评价指标综合权重。其次,利用马氏距离和灰色关联分析改进TOPSIS方法,建立了受灾点应急物资需求紧迫性分级模型。最后,将模型应用于受灾点应急物资需求紧迫性分级研究,并将该评价结果与传统TOPSIS法的评价结果进行比较,结果表明,该评价方法可以科学、客观地确定权重组合系数,消除指标间相关性,使评价结果符合实际情况,表明该评价方法科学、可行、有效,能为应急救援物资配送提供有效支持和决策。     

基于GPR-TOPSIS方法的充填配比多目标多属性优化

为获得某金矿尾砂胶结充填材料最优配比,基于试验结果,以海水比例、灰砂比和料浆质量浓度为输入参数,以充填体强度、塌落度及泌水率为输出参数,建立了充填配比与其响应量的高斯过程回归模型,分析了不同因素对充填性能的影响程度;采用遗传算法对高斯过程回归模型进行多目标参数优化,获得了Pareto非劣解,在此基础上,引入多属性决策的TOPSIS法对Pareto非劣解进行方案优选,确定了充填最优配比。研究结果表明:高斯过程回归模型相对误差值均小于6%,可靠性高;灰砂比及料浆质量浓度对充填性能影响较为显著,采用海水作为充填水源将降低充填体的强度;经优化后的充填配比与试验结果相符。     

公路隧道火灾发生位置与人群疏散通道仿真研究

利用EXODUS建立隧道的仿真场景,确定疏散人群仿真参数,并将出口工效OPS作为评价疏散效率的指标,分析不同火灾发生位置对疏散时间的影响。采用K-means算法分别对火灾发生位置和人群疏散通道位置进行聚类,并建立基于两者影响下的出口工效模型,通过对该模型求偏导,得出隧道火灾发生位置和人群疏散通道选择之间的关系。研究结果表明:火灾发生位置越接近人行横通道,疏散时间波动越大,人行横通道和隧道入口的疏散时间随人群疏散区域分界线变化,当火灾发生距人行横通道20~110 m时,变化明显,当距140~350 m时,变化平稳;出口工效OPS总体呈现不稳定的阶梯状变化趋势;火灾发生位置和人群疏散通道的最优位置呈线性递减关系。研究结果可应用于隧道应急指挥中心管理人员制定有效疏散路径和采取诱导分流人群措施。