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%.     

Suitable error evaluation criteria selection in the wind energy assessment via the K-means clustering algorithm

In this paper, wind energy potential of four locations in Xinjiang region is assessed. The Weibull distribution as well as the Logistic and the Lognormal distributions are applied to describe the distributions of the wind speed at different heights. In determining the parameters in the Weibull distribution, four intelligent parameter optimization approaches including the differential evolutionary, the particle swarm optimization, and two other approaches derived from these two algorithms and combined advantages of these two approaches are employed. Then the optimal distribution is chosen through the Chi-square error (CSE), the Kolmogorov–Smirnov test error (KSE), and the root mean square error (RMSE) criteria. However, it is found that the variation range of some criteria is quite large, thus these criteria are analyzed and evaluated both from the anomalous values and by the K-means clustering method. Anomaly observation results have shown that the CSE is the first one should be considered to be eliminated from the consequent optimal distribution function selection. This idea is further confirmed by the K-means clustering algorithm, by which the CSE is clustered into a different group with KSE and RMSE. Therefore, only the reserved two error evaluation criteria are utilized to evaluate the wind power potential.     

基于MODIS地面温度数据的成都市热岛时空变化

研究利用2000、2005和2010年逐月的MODIS/Terra和MODIS/Aqua卫星的地表温度数据产品,通过等间距法进行分析,得出成都市建成区2000~2010年间昼夜热岛的时空变化以及相互间差异。研究结果表明:成都市昼夜热岛存在显著差异,日间热岛主要呈散点分布,夜间热岛集中在城市中心区域。日夜间热岛变化趋势有显著不同,日间热岛继续分散而夜间热岛范围则有所扩大。日间热岛分布与植被覆盖存在一定的负相关性,但道路也在一定程度上促使了地面温度的增加,夜间城市热岛范围及变化则与其下垫面组成存在关系。     

密相塔半干法烟气脱硫塔内加湿降温及其对脱硫效率的影响

为了实现密相塔半干法脱硫工艺的精确加湿进一步提高系统脱硫效率,利用推导出的传热传质计算方法,得到烟气温度降低和加水量的关系.结合3组密相塔半干法工程实际数据,发现理论计算值和实测值误差区间仅为2.9％ ～5.4％.通过选取河北某钢厂210 m2烧结烟气密相塔半干法脱硫项目实际在线检测数据,发现循环脱硫灰含湿量为3％的系统脱硫效率整体高于含湿量为5％和4％的样品,最大值达93.56％.通过粒度分析、扫描电镜、X射线衍射及差热-热重对2种不同含湿量的循环脱硫灰进行表征,结果表明,含湿量为3％的循环脱硫灰较含湿量为5％的样品粒径小、比表面积大,无团聚现象,物相分析还证实相对于含湿量为5％样品,其Ca(OH)2和结晶水含量少,几乎都是CaSO4和CaS03干态物质,因此脱硫反应进行彻底,脱硫效率较高.     

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。     

面源模式的通用算法探讨

提出了矩形面源扩散模拟计算的数值积分法和中心虚点源法,以及二者结合的综合法,并用算例进行了计算精度、计算速度和结果连续性的对比.结果表明:与传统的后置虚点源法及其改进算法——谷清经验法相比,该算法与理论真值的相对误差可从20%以上降低到3%以下,并且可以准确地反映风向和面源的形状,但在计算量上要增大十几倍到上百倍.对于任意不规则面源,提出了正方形分割算法,并对分割正方形的取舍采用简便的重心判断法,以准确方便地模拟其形状.综合运用笔者提出的适于机算的通用面源算法,对不同的计算任务权衡速度和精度采用合适的算法,可以处理各种气象条件下任意形状面源的扩散计算,并可取得理想的计算精度.      

煤矿岗前人员不安全状态智能检测系统研究——以红柳林煤矿为例

为从根本上降低煤矿从业人员实施不安全行为的概率,在充分考虑煤矿从业人员不安全个体状态是诱发其不安全行为的主要原因的基础上,设计开发一套矿工不安全状态智能检测系统。首先,对2007—2022年期间各高危行业安全事故调查报告和专家研究进行归纳,总结得出煤矿从业人员不安全状态的影响因素,构建包括生理状态、心理状态以及个体能力状态在内的3个一级指标和15个二级指标体系;其次,通过相应的表征模型对不安全状态影响因素进行深入剖析;最后,基于构建的从业人员不安全状态倾向数据库,建立煤矿岗前不安全状态智能检测系统。研究结果表明：在下井工作前对从业人员个体状态进行智能检测,能够实现矿工不安全状态“早发现、早干预”,能够有效地降低人因事故发生率,研究结果对煤炭行业安全管理具有重要的参考价值。     

Location selection of emergency supplies repositories for emergency logistics management: A variable weighted algorithm

With the development of the city, the number of establishments that are proposed or under construction is increasing year by year, and if they are industries that handle flammable, explosive, toxic, harmful, and dangerous substances, the public safety will face great threats, which will bring great challenges to emergency rescue work. Therefore, providing reasonable solutions to the problem of location selection of emergency supplies repositories are necessary for improving the emergency response efficiency in chemical industrial parks. A mathematical model for location selection of emergency supplies repositories in emergency logistics management are presented considering more actual factors. The optimization objectives of the model are to minimize total transport length and cost. And then a Variable Weighted Algorithm is designed to solve the model, where an auxiliary function was constructed with different methods of building weighting factors based on the theory and method of solving multi-objective optimization problems in operational research. Simulation results show the effectiveness and feasibility of the models and algorithms presented in this paper.     

Research based on double coverage rate and reliability of gas detector layout optimization

The gas detector layout should be highly attuned to combustible gas leakage and attain a good reliability in avoiding detector malfunction, which is an important guarantee for the normal production of the chemical industry and other related enterprises. Herein, a gas detector layout optimization method based on double coverage and reliability is proposed. The key gas leakage monitoring area is determined through layout scene field investigation. To improve the detection probability and detection system reliability, the dual coverage target and voting mechanism are set, and the gas detector layout is determined with the ray-casting algorithm according to the coverage target. Combined with FLACS software to simulate a variety of typical leakage conditions under different layout scenarios, the relationship between the leaked gas concentration detected by gas detectors in each layout scheme and time is obtained, and the gas leakage detection probability in each layout scheme, number of detectors that can trigger the alarm, shortest time to trigger the alarm and reliability are comprehensively evaluated. The decision-maker selects the final gas detector layout plan according to the evaluation results and actual site needs. The study shows that the detection probability of each layout scheme set according to the double coverage is high, and multiple detectors can trigger the alarm (up to 100%), which ensures that the alarm can be triggered within 10 s under all applicable conditions. According to the evaluation results, the decision-maker can obtain a layout scheme that not only agrees with the actual site conditions but also attains a high detection probability, short detection time and strong reliability.