An intelligent SVM modeling process for crude oil properties prediction based on a hybrid GA-PSO method

Properties prediction of crude oil remains an essential issue for refineries. In this communication, an exhaustive and extendable support vector machine(SVM) intelligent prediction process has been proposed to solve this problem. A novel hybrid genetic algorithm-particle swarm optimization(GA-PSO)method was applied to optimize the SVM model. The optimization process and result demonstrated that the newly proposed GA-PSO-SVM method was more accurate and time-saving than the classical GA or PSO method. Compared with the classical Grid-search SVM, the combined GA-PSO-SVM model appeared to be more applicable for the properties prediction task. The TBP distillation curve fitting was exampled to evaluate the performance of the developed model. The regression result demonstrated the high accuracy and efficiency of the proposed process. The model can be applied in the Industrial Internet as a plugin, and the adaptability and flexibility is demonstrated by the implement of crude oil molecular reconstruction employing the intelligent prediction process.

GA-PSO混合算法的工作臂铰点优化设计

现有施工装置中离不开挖掘机工作臂,但在工作过程中因承载和振动,造成铰接点销轴破裂。为了提高工作的可靠性,通过SolidWorks软件建立模型,分析由铲斗、斗杆、动臂及其油缸构成平面连杆机构工作原理;建立动臂动力学模型,借助齐次矩阵方法分析各部件的铰点位置参数,得到各铰点受到外力和力矩;以动臂各铰点受力为优化目标,以各铰点坐标参数作为设计变量,以动臂油缸所做功为约束条件,实现目标函数模型建立。借助GA-PSO混合算法,进行选择、变异和交叉操作,提高工作臂的优化设计参数精确度;结合ADAMS软件,得到优化后和优化前铰点受力曲线,实现了优化后铰点受力小于优化前。同时,为相关农业机械的研究提供理论研究基础。

基于GPR代理模型和GA-APSO混合优化算法的软基水闸底板脱空反演

软基水闸底板脱空是水闸在长期服役期间受水流侵蚀等环境因素影响所产生的一种危害极大且难以察觉的病害。由于其病害部位于水下,传统方法难以检测,该研究提出一种基于高斯过程回归(Gaussian process regression,GPR)代理模型和遗传-自适应惯性权重粒子群(genetic algorithm-adaptive particle swarm optimization,GA-APSO)混合优化算法的水闸底板脱空动力学反演方法,用于检测软基水闸底板脱空。首先,构建表征软基水闸底板脱空参数和水闸结构模态参数之间非线性关系的GPR代理模型;其次,基于GPR代理模型与水闸实测模态参数建立脱空反演的最优化数学模型,将反演问题转化为目标函数最优化求解问题;最后,为提高算法寻优计算的精度,提出一种GA-APSO混合优化算法对目标函数进行脱空反演计算,并提出一种更合理判断反演脱空区域面积和实际脱空区域面积相对误差的指标—面积不重合度。为验证所提方法性能,以一室内软基水闸物理模型为例,对两种不同脱空工况开展研究分析,结果表明,反演脱空区域面积和模型实际设置脱空区域面积的相对误差分别为8.47%和10.77%,相对误差值较小,证明所提方法能有效反演出水闸底板脱空情况,可成为软基水闸底板脱空反演检测的一种新方法。

Preparation of polythiophene/WO_3 organic-inorganic hybrids and their gas sensing properties for NO_2 detection at low temperature

Polythiophene/WO3（PTP/WO3）organic-inorganic hybrids were synthesized by an in situ chemical oxidative polymerization method,and char- acterized by X-ray diffraction（XRD）,transmission electron microscopy（TEM）and thermo-gravimetric analysis（TGA）.The Polythiophene/ WO3 hybrids have higher thermal stability than pure polythiophene,which is beneficial to potential application as chemical sensors.Gas sensing measurements demonstrate that the gas sensor based on the Polythiophene/WO3 hybrids has high response and good selectivity for de- tecting NO2 of ppm level at low temperature.Both the operating temperature and PTP contents have an influence on the response of PTP/WO3 hybrids to NO2.The 10 wt%PTP/WO3 hybrid showed the highest response at low operating temperature of 70-C.It is expected that the PTP/WO3 hybrids can be potentially used as gas sensor material for detecting the low concentration of NO2 at low temperature.

Room temperature NO_2 gas sensing of Au-loaded tungsten oxide nanowires/porous silicon hybrid structure

In this work, we report an enhanced nitrogen dioxide（NO_2） gas sensor based on tungsten oxide（WO_3）nanowires/porous silicon（PS） decorated with gold（Au） nanoparticles. Au-loaded WO_3 nanowires with diameters of 10 nm–25 nm and lengths of 300 nm–500 nm are fabricated by the sputtering method on a porous silicon substrate. The high-resolution transmission electron microscopy（HRTEM） micrographs show that Au nanoparticles are uniformly distributed on the surfaces of WO_3 nanowires. The effect of the Au nanoparticles on the NO_2-sensing performance of WO_3 nanowires/porous silicon is investigated over a low concentration range of 0.2 ppm–5 ppm of NO_2 at room temperature（25℃）. It is found that the 10-？ Au-loaded WO_3 nanowires/porous silicon-based sensor possesses the highest gas response characteristic. The underlying mechanism of the enhanced sensing properties of the Au-loaded WO_3 nanowires/porous silicon is also discussed.

Energy-absorption forecast of thin-walled structure by GA-BP hybrid algorithm

In order to analyze the influence rule of experimental parameters on the energy-absorption characteristics and effectively forecast energy-absorption characteristic of thin-walled structure, the forecast model of GA-BP hybrid algorithm was presented by unifing respective applicability of back-propagation artificial neural network (BP-ANN) and genetic algorithm (GA). The detailed process was as follows. Firstly, the GA trained the best weights and thresholds as the initial values of BP-ANN to initialize the neural network. Then, the BP-ANN after initialization was trained until the errors converged to the required precision. Finally, the network model, which met the requirements after being examined by the test samples, was applied to energy-absorption forecast of thin-walled cylindrical structure impacting. After example analysis, the GA-BP network model was trained until getting the desired network error only by 46 steps, while the single BP-ANN model achieved the same network error by 992 steps, which obviously shows that the GA-BP hybrid algorithm has faster convergence rate. The average relative forecast error (A RE ) of the S EA predictive results obtained by GA-BP hybrid algorithm is 1.543%, while the A RE of the S EA predictive results obtained by BP-ANN is 2.950%, which clearly indicates that the forecast precision of the GA-BP hybrid algorithm is higher than that of the BP-ANN.

Gaseous and Particulate Exhaust Emissions of Hybrid and Conventional Cars over Legislative and Real Driving Cycles

Road transport exhaust emissions represent the main sources of atmospheric pollution in urban areas, due to the growing number of circulating vehicles and travelled distances. In order to reduce this pollution source, stricter emission standards are periodically set by governments through- out the world. Consequently, the concentrations of gaseous pollutants and particulate mass to be measured during type-approval tests of new vehicles are becoming progressively lower;moreover from 2011, diesel cars have to comply with particle number limit. In order to assess emission levels of different technology vehicles and investigate the use of a particulate number measurement technique at the exhaust of very low-emitting vehicles, an experimental activity was carried out on three in-use vehicles: a diesel car equipped with a particulate trap (DPF), a hybrid gasoline-elec- tric car and a bi-fuel passenger car fuelled with compressed natural gas (CNG). Cold and hot gaseous and particulate emission factors and fuel consumption were measured during the execution of real and regulatory driving cycles on a chassis dynamometer. Particulate was characterized in terms of mass only for the diesel car and of particle number for all vehicles. The emissions measured over the NEDC show that all three vehicles comply with their standard limits, except CO for CNG passenger car and NOx for diesel car. Cold start influences CO and HC emissions and fuel consumption for all the tested vehicles and in particular for the hybrid car. The real driving cycle is the most critical pattern for the emissions of almost all pollutants. During constant speed tests, the emissions of particles of hybrid car are an order of magnitude lower than those of the CNG car.

Novel Gas-liquid Hybrid Discharge Reactor for 4-CP Containing Wastewater Treatment

In order to improve 4-CP degradation efficiency, a novel gas-liquid hybrid discharge （liD） reactor was developed. Removal of 4-CP with spark-spark discharge （SSD） was higher than that with spark-corona discharge （SCD）. Amount of H2O2 and O3 produced with SSD were larger than that with SCD. OH formation was increased by the combination of H2O2 and O3. The contribution of ·OH （38 % formed by O3 conversion） oxidation on removal of 4-CP accounted for nearly 60 %. The other effects of ultraviolet radiation, intense shock waves and pyrolysis, played partial roles in about 40 % of removal rate.

GA and PSO culled hybrid technique for economic dispatch problem with prohibited operating zones

This paper presents an efficient and reliable genetic algorithm (GA) based particle swarm optimization (PSO) tech- nique (hybrid GAPSO) for solving the economic dispatch (ED) problem in power systems. The non-linear characteristics of the generators, such as prohibited operating zones, ramp rate limits and non-smooth cost functions of the practical generator operation are considered. The proposed hybrid algorithm is demonstrated for three different systems and the performance is compared with the GA and PSO in terms of solution quality and computation efficiency. Comparison of results proved that the proposed algo- rithm can obtain higher quality solutions efficiently in ED problems. A comprehensive software package is developed using MATLAB.

Synthesis and room-temperature NO_2 gas sensing properties of a WO_3 nanowires/porous silicon hybrid structure

We report on the fabrication and performance of a room-temperature NO2 gas sensor based on a WO3 nanowires/porous silicon hybrid structure. The W18O49 nanowires are synthesized directly from a sputtered tungsten film on a porous silicon （PS） layer under heating in an argon atmosphere. After a carefully controlled annealing treatment, WO3 nanowires are obtained on the PS layer without losing the morphology. The morphology, phase structure, and crystallinity of the nanowires are investigated by using field emission scanning electron microscopy （FESEM）, X-ray diffractometer （XRD）, and high-resolution transmission electron microscopy （HRTEM）. Comparative gas sensing results indicate that the sensor based on the WO3 nanowires exhibits a much higher sensitivity than that based on the PS and pure WO3 nanowires in detecting NO2 gas at room temperature. The mechanism of the WO3 nanowires/PS hybrid structure in the NO2 sensing is explained in detail.

纳米黏土与二氧化硅协同改性聚乳酸研究

以聚乳酸(PLA)为树脂基体,研究不同含量纳米黏土与2份SiO2协同填充,对PLA复合材料结构与性能的影响。结果表明,协同填充有效改善了PLA材料的结晶行为、熔体加工性、力学韧性和气体阻隔性能。当2份的SiO2和4份黏土杂化填充时,填料分散良好,获得的PLA复合材料展示了明显的韧性断裂和气体阻隔性能。相比没有填充PLA,拉伸断裂伸长率和冲击强度分别增加151%和74.1%,氧气和水蒸气透气系数分别下降67.4%和65.0%。过量黏土填充不利于材料韧性改善,对气体阻隔性能提高不明显。

螺旋槽小孔节流动静压气体轴承稳态承载力分析

为研究空气轴承在动静压下的稳态承载性能,使用三维建模工具建立动静压气体轴承模型,从连续方程、可压缩流体润滑方程、气体状态方程出发,得到等温条件下稳态气体润滑Reynolds方程,并计算轴承稳态承载力。对螺旋槽小孔节流空气轴承结构建立三维模型,借助Fluent仿真软件对整个流体域进行仿真分析,探讨螺旋角、偏心率、槽宽比、槽深比、槽长比等参数对气体轴承承载性能的影响。结果表明:气源压力一定时,气膜承载力随着偏心率的增加呈现非线性上升趋势,随着槽宽比的增加呈现下降趋势,槽宽比越大,这种下降趋势更加明显;随着槽深比和槽长比的增加,气膜承载力呈现先增加后降低的趋势。对轴承结构进行优化,优化后的轴承承载性能更优。

基于混合核函数GA-SVR的动车组制动闸片寿命预测

制动闸片是基础制动装置中的执行机构,对其使用寿命的精确预测直接关乎动车组的安全运行问题。为解决传统的SVR模型在寿命预测时存在着不能兼顾各类核函数优良性能的问题,进一步提高动车组制动闸片剩余寿命预测精度,提出一种基于遗传算法优化且集合了不同核函数优点的混合核SVR回归模型。首先分别采用具有优良泛化能力的多项式核函数和突出学习能力的RBF核函数构建2个单个核函数SVR回归模型。随后利用遗传算法以交叉验证方式下模型预测产生的均方误差和作为适应度函数,对2个单一核SVR回归模型的惩罚因子c和函数带宽g进行寻优求解,得到2个性能最佳的单核SVR回归模型。然后以均方误差最低为目标调整混合因数,将2个核矩阵融合为一个仍满足Mercer条件的混合核矩阵,作为新的GA-SVR模型核函数矩阵。最后基于得到的模型对动车组制动闸片剩余寿命进行评估。结果表明:混合核模型在各个时段预测时产生的累积相对误差均低于单一核模型,且在方上差也更为平稳。直接体现了所建立的模型在学习能力与泛化能力上都较单一核GA-SVR模型有了提高,有效提高了动车组制动闸片寿命预测的精度,更出色的泛化能力也表明了该模型具有一定的工程实用价值与普适性。

松属GAs相关EST-SSR标记与火炬松×洪都拉斯加勒比松苗高相关性分析

以火炬松×洪都拉斯加勒比松F1代群体为研究对象,从松树PGI(松类基因索引)数据中筛选出13个与赤霉素(GAs)代谢有关的序列。设计了这13条序列的EST-SSR引物对,并筛选出4对引物作为F1代检测的较好的标记。4对引物PCR分析显示在2个亲本和39个子代中共扩增出1014个多态性位点,其中,杂种F1代扩增出的位点数中有50.19%与父本相同,52.17%与母本相同,这表明母本(火炬松)和父本(加勒比松)杂交能够得到获得双亲遗传物质的新杂种。4个引物检测的26个等位基因位点中有6个与苗龄6个月的苗高有显著或极显著的相关性,有5个位点与苗龄9个月的苗高有显著或极显著相关性。这为早期选择提供了较好的分子标记。

真空与气体一体化串联机械开关及其直流快速转移应用

为提升中压混合式直流断路器的自然换流性能,该文提出一种真空与气体一体化串联机械开关,分析真空与气体一体化串联用于电流转移性能的工作原理。并基于此设计了双超程联动的真空与气体一体化串联开关实验样机,研究了气体类型、气压、触头结构、触头材料等参数对电弧电压特性的影响规律,确定了W70Cu桥式两触点结构,采用H2和N2体积比为2:3、气压为0.3 MPa的氢氮混合气体,弧压可由20 V提升到120 V,电流转移时间由1 900μs缩短至300μs。同时测试了静态瞬态开断电压(TIV)分布特性,真空间隙承担主要电压(55%),串联整机耐压水平为20 kV。验证了真空与气体一体化串联开关应用于中压混合式直流断路器的可行性和有效性。

基于GA-PSO的目标分配问题研究

防空作战中的目标分配问题属于NP完全问题,在综合考虑火力单元作战效能和防御效能的基础上,引入火力单元综合有利度,建立了一种用于大规模多火力单元对抗多轮次目标的静态目标分配模型,给出了基于GA因子的改进PSO算法,并将算法应用于目标分配模型的求解,通过VC 6.0编程和计算机仿真验证了模型的可行性和算法的有效性。

一种改进的遗传算法:GA-EO算法

针对基本遗传算法(GA)有局部搜索能力差、计算量大、对较大搜索空间适应能力差和易收敛于局部极小值等问题,采用将极值优化(EO)算法与传统遗传算法相结合的方式,对基本遗传算法进行改进,提出了一种新的算法:GA-EO算法,并用实验证明了新算法的有效性。