Optimization of Generator Based on Gaussian Process Regression Model with Conditional Likelihood Lower Bound Search

The noise that comes from finite element simulation often causes the model to fall into the local optimal solution and over fitting during optimization of generator.Thus,this paper proposes a Gaussian Process Regression(GPR)model based on Conditional Likelihood Lower Bound Search(CLLBS)to optimize the design of the generator,which can filter the noise in the data and search for global optimization by combining the Conditional Likelihood Lower Bound Search method.Taking the efficiency optimization of 15 kW Permanent Magnet Synchronous Motor as an example.Firstly,this method uses the elementary effect analysis to choose the sensitive variables,combining the evolutionary algorithm to design the super Latin cube sampling plan;Then the generator-converter system is simulated by establishing a co-simulation platform to obtain data.A Gaussian process regression model combing the method of the conditional likelihood lower bound search is established,which combined the chi-square test to optimize the accuracy of the model globally.Secondly,after the model reaches the accuracy,the Pareto frontier is obtained through the NSGA-II algorithm by considering the maximum output torque as a constraint.Last,the constrained optimization is transformed into an unconstrained optimizing problem by introducing maximum constrained improvement expectation(CEI)optimization method based on the re-interpolation model,which cross-validated the optimization results of the Gaussian process regression model.The above method increase the efficiency of generator by 0.76%and 0.5%respectively;And this method can be used for rapid modeling and multi-objective optimization of generator systems.

Finite Element Analysis and Linear Regression of Maximum Temperature for Inner Wall of Chimney Foundation

The uniform design method was adopted and the twenty-four groups of different geometric and physical pa-rameters were chosen. The finite element model was built. Comparisons between the simulation results and the test re-sults prove that the simulation results are correct. The distribution of the temperature field of the chimney foundationwas analyzed. The multivariate linear regression of the hightest tomperature was performed on the inner wall of thechimney foundation by the numerical calculated results. The fitting property of the highest temperature with six influ-ence factors was obtained. A simple method for the calculation of the temperature field of the chimney foundation wasprovided.

Regression Analysis of Nutrient Elements between Soil and Tobacco Leaves and Their Influences on Aroma Quality of Flue-cured Tobacco

This study aimed to analyze the relationship between nutrient elements K, Ca, Mg, Cu, Mn, Zn and Fe in tobacco-planting soils and tobacco leaves from six main tobacco-producing areas, and to investigate the influences of these elements on chemical composition and aroma components in tobacco leaves. Results showed that there were certain relationship between contents of nutrient elements in tobacco-planting soils and contents of corresponding elements in tobacco leaves; various elements exhibited different influences on the aroma quality of flue-cured tobacco. Based on the actual situation of nutrient contents in soils from different tobaccoproducing areas, contents of various elements in tobacco leaves should be regulated by soil fertilization and foliar spraying, thereby improving the aroma quality of flue-cured tobacco.

Predicting urbanization level by main element analysis and multiple linear regression---taking Xiantao district in Hubei Province as an example

In this paper we firstly select main factors relating to urbanization level of Xiantao District in Hubei Province by main element, then, make model of urbanization level by analysis of multiple liner regression, and lastly predict its urbanization level

Predictions of elemental composition of coal and biomass from their proximate analyses using ANFIS, ANN and MLR

The elemental composition of coal and biomass provides significant parameters used in the design of almost all energy conversion systems and projects.The laboratory tests to determine the elemental composition of coal and biomass is time-consuming and costly.However,limited research has suggested that there is a correlation between parameters obtained from elemental and proximate analyses of these materials.In this study,some predictive models of the elemental composition of coal and biomass using soft computing and regression analyses have been developed.Thirty-one samples including parameters of elemental and proximate analyses were used during the analyses to develop multiple prediction models.Dependent variables for multiple prediction models were selected as carbon,hydrogen,and oxygen.Using volatile matter,fixed carbon,moisture and ash contents as independent variables,three different prediction models were developed for each dependent parameter using ANFIS,ANN,and MLR.In addition,a routine for selecting the best predictive model was suggested in the study.The reliability of the established models was tested by using various prediction performance indices and the models were found to be satisfactory.Therefore,the developed models can be used to determine the elemental composition of coal and biomass for practical purposes.

Regression Formulations for the Stress at Hot Spot of Multiplanar Tubular DT Joints

Stress concentration analysis of multiplanar tubular DT joints plays an important role in the fatigue design of offshore platforms. A semi-analytic method for stress analysis under the condition of any loads is briefly introduced in the paper. Nineteen multiplanar tubular DT joints with one of two braces of the same dimension subjected to axial loads and out- of- plane bending moments are computed for parametric stress analysis by using the present method. The influence of geometrical parameters on the stresses of multiplanar tubular DT joints is discussed and compared with corresponding uniplanar T joints. The regression formulae for the stress at hot spot of multiplanar DT joints are found by modification of SCF of corresponding uniplanar T joints. The parametric formulae for the maximum stress by superposition. Finally, the influences of stiffening effect and load-interaction effect on the maximum stress of DT joints are discussed.

环境规制、数据要素配置水平与产业结构调整

文章基于数字经济、绿色经济发展深刻影响产业结构转型升级进程这一背景,首先在理论分析的基础上构建了数据要素配置水平综合评价指标体系;然后采用Dagum基尼系数对数据要素配置水平的空间差异及主要来源进行分解测算;最后,基于2012—2019年省级面板数据探讨了环境规制的结构调整红利及数据要素有效配置的渠道效应。研究结果显示,我国数据要素配置水平总体空间差异明显,且区域间差异为主要来源,区域内差异次之。环境规制对产业结构升级存在先促进后抑制的“倒U”型影响,数据要素配置也有显著促进作用。动态边际效应结果显示,在研究期内环境规制所带来的产业结构“调整红利”正在逐渐弱化,数据要素优化配置可充当环境规制促进产业结构升级的有效路径,且从子维度来看,数据传播共享的渠道效应最为显著。数据要素配置的网络外部性特征对环境规制和产业结构优化的调节作用在不同地区所呈现的阶段性特征不同。

一种基于脉冲方位的多普勒解要素方法

舰船发射的主动声呐脉冲信号声源级高,频带窄,信噪比高,利用这些特点,可以比较精确地测量声呐脉冲信号的方位和频率信息从而有利于目标运动要素解算。本文针对发射主动脉冲的水下目标,提出一种基于主动声呐脉冲方位的多普勒解要素方法,首先估计主动脉冲信号时间位置及频率,在此基础上利用非线性回归的方法,将每一个脉冲的时刻、方位、频率以及本平台相应时刻的速度和位置等要素组成的多维向量,视作样本空间中的一个点,根据各要素间的函数关系,进行非线性拟合,从而获得目标运动要素的估计值。实测数据验证表明,提出的频率估计方法精度满足目标运动分析的要求;仿真验证了基于非线性回归的脉冲方位-频率目标运动分析算法整体的有效性。

机车前端薄壁吸能管仿真模型模糊参数的支持向量回归反求

为了获得影响耐撞性结构有限元计算精度的准确模型参数,提高冲击仿真的准确性,提出一种基于支持向量回归(support vector regression,SVR)模型进行参数优化反求的方法。以一种机车前端防爬结构中的预压薄壁吸能圆管为研究对象建立有限元模型,进行台车冲击试验验证仿真模型准确性。通过拉丁超立方试验设计驱动有限元模型进行少量计算获得数据集,有限元模型中的模糊参数为输入变量,计算与试验载荷的差异为目标响应,通过SVR方法构建映射关系,并采用增强精英保留遗传算法(strengthen elitist genetic algorithm,SEGA)对超参数进行优化,确定SVR模型最佳配置;通过该最优SVR模型再次使用SEGA优化反求,获得最佳模糊参数组合。使用这组参数组合设置有限元模型,其仿真结果相较初始计算耐撞性指标和载荷曲线匹配程度都得到了提高。研究结果为有限元模型中模糊参数的准确设定、碰撞仿真的精度提升提供了一种新的思路。

150例腺瘤型肠息肉伴上皮内瘤变患者中医体质与证素分布规律研究

目的 探讨腺瘤型肠息肉伴上皮内瘤变不同分级患者的中医体质和证素分布特点并阐述二者之间的关系,为临床研究提供依据。方法 对2019年5月-2022年3月就诊且符合纳入标准的150例患者进行中医体质和证素测定,分别运用χ^(2)检验和Logistic回归分析方法分析二者在不同病理分级中的分布特点及相关性。结果 150例患者高级别上皮内瘤变(HGIN)69例,低级别上皮内瘤变(LGIN)81例。经采集,中医体质主要构成为痰湿质[26.00%(39/150)]、阳虚质[18.67%(28/150)]、湿热质[16.67%(25/150)],中医证素主要构成为湿[24.67%(37/150)]、阳虚[16.67%(25/150)]、气滞[(16.00%(24/150)];二者相关性分析显示,痰湿质与湿、痰呈显著正相关性,阳虚质与寒、阳虚呈显著正相关性,湿热质与火、湿呈显著正相关性。结论HGIN和LGIN患者之间,中医体质和证素分布存在一定差异性,且二者存在相关性。

数据驱动下人体面部皮肤的本构参数反演及力学特征分析

人体面部皮肤的本构参数反演及力学特性研究对皮肤病变早期诊断、皮肤仿生材料设计及计算图形学中的面部模型建立都有着至关重要的作用,机器学习与有限元仿真方法相结合能更高效、更准确地解决非入侵式皮肤组织本构参数反求问题.首先建立了面部皮肤多向拉伸下的应力松弛有限元模型,并通过多步位移控制法对皮肤的超弹性力学性能与黏弹性力学性能分离;对Gasser-Ogden-Holzapfel(GOH)与Prony series本构模型参数进行敏感性分析,揭示影响面部皮肤应力松弛实验结果的关键参数.其次,利用贝叶斯超参数优化理论搭建随机森林(RF)模型与支持向量回归(SVR)模型,结合实验数据对人体面部皮肤组织本构参数进行了反求.最后,将计算得到的有限元仿真曲线与试验获得的拉伸力响应曲线对比,并引入决定系数R2对两种模型的预测准确性进行了评估.结果表明,纤维组织分散度κ、剪切模量相关参数C10和松弛模量g1是影响皮肤应力松弛实验结果的关键参数,RF模型数值计算曲线与试验曲线的拟合优度为0.98,其在皮肤本构参数反演问题上表现出更高的准确率,机器学习可以精准高效地获取面部皮肤的本构参数,进而准确描述皮肤组织的力学性能,该方法也可进一步推广到其他生物软组织的复杂本构参数反演问题.

高山地区夏季大气PM_(2.5)中元素的污染特征、生态风险及健康风险评估——以武当山为例

为了解华中高山地区夏季大气PM_(2.5)中元素的污染特征,于2018年6月在湖北省十堰市武当山国家空气质量监测站采集PM_(2.5)样品,利用电感耦合等离子体质谱仪(ICP-MS)测定样品中18种元素(Na、K、Ca、Mg、Al、Fe、V、Cr、Mo、Cu、Zn、Mn、Ni、As、Se、Cd、Ba和Pb)的浓度,并探讨了其来源、生态风险和健康风险.结果表明,武当山PM_(2.5)的日均浓度范围为5.00—33.65μg·m^(-3),平均浓度为(16.84±7.07)μg·m^(-3);元素K、Na、Fe、Ca、Al、Mg和Zn的浓度较高,7种元素占所分析元素的97.68%以上;富集因子结果表明,Mo、Zn、Pb、Cd和Se的EF值高于100,可能受周边人为活动排放污染物的区域或长距离传输影响;主成分-多元线性回归(PCA-MLR)结果表明,PM_(2.5)中元素主要来自于燃煤和机动车(57.57%)、工业源(22.52%)和地壳(19.91%);武当山PM_(2.5)重金属的生态风险指数极高,其中Cd、Se和Mo的潜在生态危害程度极强;健康风险评估显示,综合非致癌风险(HI)在儿童和成人中分别为2.28×10-2和3.04×10-2,均在可接受水平内,综合致癌风险(CRT)在儿童和成人中分别为4.45×10-7和2.37×10-6,说明成人存在潜在的致癌风险;Cr在成人中的致癌风险为1.88×10-6,说明Cr在成人中存在潜在的致癌风险,同种金属对人体的非致癌风险和致癌风险均表现为成人>儿童.

基于Kriging模型的某高射速自动机内抽壳滑板疲劳优化

为提高抽壳滑板的疲劳寿命,进而满足射速在1500发/min左右的某10连发高射速自动机寿命达1000发的最低寿命要求,提出一种基于Kriging回归的代理模型用于抽壳滑板的疲劳优化。在与试验结果相符的有限元模型基础上,通过拉丁超立方采样设置初始样本点,构建与样本点相对应的结构模型,并计算每一组样本的理论寿命。根据初始样本点构建Kriging代理模型的同时,采用以改善期望准则为加点准则、遗传算法为子优化求解算法的代理优化算法来对目标函数进行寻优。优化后抽壳滑板的疲劳寿命提高到1193发,且经试验验证,优化结果满足自动机战术技术指标。研究结果表明,通过基于Kriging和遗传算法的代理优化算法能够快速有效地寻优得到全局最优解,适用于高射速自动机内破断零部件的疲劳优化,对工程应用具有一定的借鉴意义。

不同品种大豆矿质元素含量与品质的关系研究

通过相关性分析、逐步回归分析和通径分析研究6种大豆中的矿质元素含量与其品质指标之间的关系。结果表明:6种大豆中的低聚糖、异黄酮和脂肪酸含量受品种影响较大,而蛋白质、水溶性蛋白质、脂肪和矿质元素含量受品种影响较小;N与大豆中的蛋白质、脂肪酸、异黄酮含量呈正相关;K与脂肪含量呈正相关;Ca和Fe与低聚糖含量呈正相关;Na对低聚糖含量起正向促进作用,对异黄酮含量起负间接作用;各矿质元素含量与水溶性蛋白质含量无显著相关性。N、K、Na、Fe是影响大豆品质的主要矿质元素。

不同体系评价金属元素对卷烟常规烟气指标的影响

为综合评价金属元素对卷烟常规烟气指标的影响,采用火焰原子吸收法分别测定了10种卷烟纸、5种烟丝及其组合而成的49种卷烟样品中8种金属元素的含量,并通过统计学方法从烟灰、烟丝/卷烟纸/烟灰、烟丝/卷烟纸三个体系评价了金属元素对卷烟常规烟气指标的影响。结果表明:1)烟灰中金属元素对烟气质量的影响程度相对较低,烟丝/卷烟纸中金属元素可以较好地反映金属元素对各指标的影响;2)烟丝中金属元素对烟气质量的影响程度大于卷烟纸中的;3)影响烟气质量的金属元素主要是烟丝中的锌、锰和卷烟纸中的钙、锰、锌,同一元素对不同指标的影响趋势不同。

架空地线临界融冰电流估算方法研究

架空线路覆冰是影响电网正常运行较为严重的灾害之一,尤其地线更易出现覆冰,有必要对架空地线直流融冰电流进行计算,而现有的经验公式及应用较多的布尔斯道尔夫融冰电流计算公式较为复杂,且有些参数测量困难。因此,该文提出一种用于快速估算已知架空地线型号在不同风速、环境温度、覆冰厚度条件下临界融冰电流的方法,通过分析地线融冰物理过程,利用有限元软件搭建仿真模型,经模型计算得到数据集,然后采用多元线性回归拟合得到相关变量的函数表达式,并与计算值进行对比。

基于双脉冲LIBS结合偏最小二乘回归的稀土元素定量分析

激光诱导击穿光谱(LIBS)是一种以激光为激发源的等离子体发射光谱分析技术,已有将其用于稀土元素的定量分析研究,但由于稀土矿基体差异大、元素含量低,定量分析灵敏度和准确度仍有待提高。通过使用单激光分束构造双脉冲LIBS系统,并结合偏最小二乘回归(PLSR)算法实现对稀土矿石样品中的稀土元素La、Dy、Yb和Y的定量分析。结果表明,双脉冲LIBS结合PLSR可建立更加稳定的定标模型,与常规基本定标法相比,La、Dy、Yb和Y元素的相对均方根预测误差(RMSEP)从0.0061%、0.0037%、0.0045%、0.0280%降低至0.0044%、0.0016%、0.0029%、0.0134%,平均相对预测误差(AREP)从10.88%、15.27%、6.42%、17.20%降低至6.67%、3.62%、4.10%、7.98%。因此,双脉冲LIBS结合PLSR方法可以有效地提高LIBS对稀土矿石中稀土元素的定量分析能力。

飞机轮载作用下土质道面轮辙特征仿真分析

本文基于ABAQUS有限元软件建立了飞机轮胎-土质道面相互作用有限元模型,通过在预设土质道面上改变轮胎胎压、轮胎荷载和运行次数来分析三者对土质道面垂直应力分布和轮辙特征的影响规律,并建立在三者共同影响下的最大轮辙深度数学模型。结果表明,土质道面最大轮辙深度随轮胎胎压、轮胎荷载和运行次数的增大而增大。

Influence of confined water on the limit support pressure of tunnel face in weakly water-rich strata

In the process of shield tunneling through soft soil layers,the presence of confined water ahead poses a significant threat to the stability of the tunnel face.Therefore,it is crucial to consider the impact of confined water on the limit support pressure of the tunnel face.This study employed the finite element method(FEM)to analyze the limit support pressure of shield tunnel face instability within a pressurized water-containing layer.Subsequently,a multiple linear regression approach was applied to derive a concise solution formula for the limit support pressure,incorporating various influencing factors.The analysis yields the following conclusions:1)The influence of confined water on the instability mode of the tunnel face in soft soil layers makes the displacement response of the strata not significant when the face is unstable;2)The limit support pressure increases approximately linearly with the pressure head,shield tunnel diameter,and tunnel burial depth.And inversely proportional to the thickness of the impermeable layer,soil cohesion and internal friction angle;3)Through an engineering case study analysis,the results align well with those obtained from traditional theoretical methods,thereby validating the rationality of the equations proposed in this paper.Furthermore,the proposed equations overcome the limitation of traditional theoretical approaches considering the influence of changes in impermeable layer thickness.It can accurately depict the dynamic variation in the required limit support pressure to maintain the stability of the tunnel face during shield tunneling,thus better reflecting engineering reality.

基于压力拱理论的深埋节理岩体隧道围岩压力研究

为研究节理岩体隧道围岩压力计算方法,以隧道压力拱理论为基础,通过离散元数值模拟分析了岩体的坚硬程度、完整程度和结构面的抗剪强度对隧道压力拱的影响,应用多元线性回归拟合了多因素围岩压力公式,并结合依托工程对拟合公式进行了适用性分析。结果表明:节理岩体隧道压力拱范围为拱顶到最大主应力方向的偏转点,隧道压力拱高度随着节理间距和结构面的抗剪强度的增大而减小,岩体力学参数对压力拱高度的影响较小;与现场实测的围岩压力相比,计算误差在15%以内。所提围岩压力公式适用性良好,为节理岩体的围岩压力计算提供了新的思路。