Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy

Laser-induced breakdown spectroscopy(LIBS)has become a widely used atomic spectroscopic technique for rapid coal analysis.However,the vast amount of spectral information in LIBS contains signal uncertainty,which can affect its quantification performance.In this work,we propose a hybrid variable selection method to improve the performance of LIBS quantification.Important variables are first identified using Pearson's correlation coefficient,mutual information,least absolute shrinkage and selection operator(LASSO)and random forest,and then filtered and combined with empirical variables related to fingerprint elements of coal ash content.Subsequently,these variables are fed into a partial least squares regression(PLSR).Additionally,in some models,certain variables unrelated to ash content are removed manually to study the impact of variable deselection on model performance.The proposed hybrid strategy was tested on three LIBS datasets for quantitative analysis of coal ash content and compared with the corresponding data-driven baseline method.It is significantly better than the variable selection only method based on empirical knowledge and in most cases outperforms the baseline method.The results showed that on all three datasets the hybrid strategy for variable selection combining empirical knowledge and data-driven algorithms achieved the lowest root mean square error of prediction(RMSEP)values of 1.605,3.478 and 1.647,respectively,which were significantly lower than those obtained from multiple linear regression using only 12 empirical variables,which are 1.959,3.718 and 2.181,respectively.The LASSO-PLSR model with empirical support and 20 selected variables exhibited a significantly improved performance after variable deselection,with RMSEP values dropping from 1.635,3.962 and 1.647 to 1.483,3.086 and 1.567,respectively.Such results demonstrate that using empirical knowledge as a support for datadriven variable selection can be a viable approach to improve the accuracy and reliability of LIBS quantification.

The Effects of Agricultural Informatization on Agricultural Economic Growth: An Empirical Analysis Based on Regression Model

This article selects some major factors influencing the agricultural economic growth are selected,such as labor,capital input,farmland area,fertilizer input and information input.And it selects some factors to explain information input,such as the number of website ownership,types of books,magazines and newspapers published,the number of telephone ownership per 100 households,the number of home computers ownership per 100 households,farmers' spending on transportation and communication,culture,education,entertainment and services, and the total number of agricultural science and technology service personnel.Using regression model,this article conducts regression analysis of the cross-section data on 31 provinces,autonomous regions and municipalities in 2010.The results show that the building of information infrastructure,the use of means of information,the popularization and promotion of knowledge of agricultural science and technology,play an important role in promoting agricultural economic growth.

ON LINE COMPUTATION OF EMPIRICAL FORMULA BY MEANS OF ELEMENTAL ANALYSIS AND ITS PROGRAM DESIGN

On line determination of empirical formula for organic compounds with an automatic elemental analyzer and its program design method were investigated. The computational results shews that the reliability of computational results depends on the accuracy of the analytical data and the organic compound itself.

Prediction of cavity growth rate during underground coal gasification using multiple regression analysis

During underground coal gasification （UCG）, whereby coal is converted to syngas in situ, a cavity is formed in the coal seam. The cavity growth rate （CGR） or the moving rate of the gasification face is affected by controllable （operation pressure, gasification time, geometry of UCG panel） and uncontrollable （coal seam properties） factors. The CGR is usually predicted by mathematical models and laboratory experiments, which are time consuming, cumbersome and expensive. In this paper, a new simple model for CGR is developed using non-linear regression analysis, based on data from 1 l UCG field trials. The empirical model compares satisfactorily with Perkins model and can reliably predict CGR.

Empirical Likelihood Diagnosis of Modal Linear Regression Models

In this paper, we investigate the empirical likelihood diagnosis of modal linear regression models. The empirical likelihood ratio function based on modal regression estimation method for the regression coefficient is introduced. First, the estimation equation based on empirical likelihood method is established. Then, some diagnostic statistics are proposed. At last, we also examine the performance of proposed method for finite sample sizes through simulation study.

Empirical formulae for electric double-layer repulsion between two arbitrarily inclined clay particles

To understand the mesoscopic mechanism of clayey soil in view of macroscopic behavior, it is essential to quantitatively calculate the electric double-layer repulsion between arbitrarily inclined clay particles.However, suitable calculation methods with high efficiency and accuracy are still rare at present in literature. Based on a great number of numerical calculations of the repulsion between two inclined platy clay particles, explicit empirical formulae for estimating electric double-layer repulsion between clay particles are put forward. Comparison between the empirical solutions and corresponding numerical results shows that the proposed formulae have a reasonable accuracy, and application of the presented formula is easy and efficient.

EMPIRICAL STUDY ON CAPITAL STRUCTURE OF LISTED COMPANIES IN CHINESE STOCK MARKET

Capital structure decision is an important issue of corporate finance.Theories show that,the corporate debt ratio is determined by many factors.This study conducts empirical work on capital structure theories,focusing on the corporate data of Chinese listed companies,by considering the intrinsic characteristics,utilizing the principal factor analysis and the ridge regression method.Our results suggest that a firms debt ratio has a positive relationship with its size,profitability and operating risk and has a negative relationship with its growth and non debt tax shield,while the long term leverage has a positive relationship with its collateral value of assets.

Estimation of ice resistance and sensitivity analysis for an icebreaker

The Lindqvist method is adopted to estimate the ice resistance for an icebreaker.The accuracy of the method is evaluated in a comparison of the calculated results with model test results.In addition to the estimation of ice resistance,a sensitivity analysis based on the Lindqvist method is carried out.A full parametric model developed using CAESES software allows the convenient construction of many new hull lines.The primary factors relevant to ice resistance are embedded as design parameters in the full parametric model.Meanwhile,response surface methodology is adopted to give better insight into new hull lines.Results show that the ice resistance is more sensitive to the rake angle and waterline entrance angle.The aim of the present study is to improve the techniques of designing the hull forms of icebreakers.

基于回归分析法的矩形槽圆管吸能特性研究

为了研究矩形槽圆管吸能特性规律,提出了一种基于回归分析法的结构参数与吸能特性关系的拟合方法。针对轴向冲击下的圆管动态响应,首先,建立了6005A-T6材料的Cowper-Symonds本构模型,并验证了仿真模型的准确性;其次,设计了正交试验,建立了吸能特性与结构参数之间的计算模型;然后,利用多元线性与非线性回归分析方法对计算模型参数求解,并对比了两种拟合结果,得到了峰值力和吸能量的经验公式;接着,对比经验公式与有限元数值计算值表明,经验公式在研究范围内具有较高准确性,误差在8%以内;最后,引入吸能性能指标并使用遗传算法对圆管进行了结构优化,优化结果表明,在研究范围内当直径和槽端距最小、壁厚和槽宽最大、槽深最浅时,矩形槽圆管的吸能性能最优。

基于新闻情感分析和区间分解的汇率预测研究

汇率序列具有非线性和连续变化等特点,其细节波动是一系列事件和新闻综合影响的结果.然而,现有区间预测模型难以量化重大事件和公众情绪的影响,导致其缺乏广泛的适用性,且传统区间分解方法存在上下界混叠的缺陷.因此,论文从新冠疫情冲击出发,提出一种基于新闻情感分析和区间分解的汇率波动实时预测模型.首先,基于Snownlp情感词典对外汇新闻文本进行情感分析,获得相应的情感分数.另外,构建全球恐惧指数(the global fear index,简称GFI)以量化新冠疫情的影响,并将其与芝加哥期权交易所波动率(the Chicago board options exchange volatility index,简称VIX指数)相结合作为汇率的影响因素.然后,提出一种新的区间经验模态分解(interval empirical mode decomposition,简称IEMD)方法对区间汇率序列进行多尺度分解,并根据样本熵重构得到高、中、低频区间序列和残差项.其次,利用极限学习机(extreme learning machine,简称ELM)、多层感知机(multi-layer perceptron,简称MLP)、随机森林(random forest,简称RF)和二次曲面支持向量回归(quadric surface support vector regression,简称QSSVR)分别对不同特征的子序列进行组合预测,以提高预测结果的准确性和稳定性.最后,利用论文方法对美元兑人民币、澳元兑人民币和瑞士法郎兑人民币3种汇率进行实证预测分析,结果表明,论文模型适用于重大事件影响下的汇率区间波动预测,与现有方法相比具有较高的预测精度.

车桥耦合连续梁-拱组合桥冲击系数研究

为了得到连续梁-拱组合桥真实的冲击系数,以某三跨连续梁-钢管混凝土拱组合桥为依托,考虑车桥耦合振动效应,利用ANSYS建立大桥空间梁单元模型和车辆的三轴半车模型,分析桥面不平度、车速、车辆数对主梁不同部位及不同响应冲击系数的影响,并以车速和桥面不平度为自变量得到冲击系数二元回归公式,最后利用2座基频相近桥梁冲击系数的实测数据验证该公式。结果表明:桥面不平度对冲击系数影响最大,当桥面不平度达到B级以上,冲击系数超过规范值,最大可达规范值5.42倍;对于主梁,不同外部激励、不同响应和不同部位的冲击系数存在差异,部分冲击系数超出规范值;该文给出的冲击系数回归公式可用于类似结构主梁冲击系数估算。

基于CEEMD-BiLSTM-RFR的短期光伏功率预测

由于短期光伏预测中气象因素的时间尺度不同,直接分析其对光伏功率的相关性,易忽略时间尺度的影响,进而导致预测模型误差。为提高光伏功率预测精度,构建了预测模型。首先,利用互补集合经验模态分解(complementary empirical mode decomposition,CEEMD)将光伏序列进行分解,得到在不同时间尺度上的光伏分量;然后,通过Pearson相关系数分析各光伏分量与空气温度、太阳辐射度、风速、风向和空气湿度的关系,对于强相关分量建立关于气象因素的随机森林回归(random forest regression,RFR)预测模型,弱相关分量直接通过双向长短期记忆网络(bidirectional long short-term memory neural network,BiLSTM)进行预测;并将预测求和输出。通过安徽省蚌埠市光伏电站7月实测数据进行验证,实验结果表明,所提预测模型CEEMD-BiLSTM-RFR相比传统预测模型有较好的预测精度。

高强钢高效车削切削参数对切削力影响研究

D6AC高强度钢强度高、韧性好,是一种在众多领域应用广泛的难加工材料。文章从实现D6AC高强钢粗加工高效切削的角度,采用正交试验方法,研究其高效车削加工时切削用量三要素对切削力影响的显著性,根据试验结果利用极差分析和灰色关联分析获得了各个切削用量对切削力影响的显著性顺序,建立了各个切削分力及切削合力的经验公式并进行了检验,结果表明切削力经验公式具有良好的准确性。

益肾调气法治疗肾虚肝郁型抑郁障碍远期复发率的多中心前瞻性队列研究

目的:评价益肾调气法对肾虚肝郁型抑郁障碍2年复发率的影响。方法:选取2017年1月至2018年4月在全国13个分中心招募肾虚肝郁型抑郁障碍患者,按照接受的治疗方案自然形成中医组、中西医组和西医组,比较3组的复发率。并根据干预的时间,将中医组和中西医组分为低、中、高3个暴露水平,比较不同水平的复发率,评价益肾调气法降低肾虚肝郁型抑郁障碍的远期复发率的效果。结果:共纳入肾虚肝郁型抑郁障碍1314例,其中中医组385例,西医组453例,中西医组476例。中医组、西医组、中西医组的两年复发率分别是23.61%,34.97%、18.14%。中医组比西医组使复发风险降低29.2%(P<0.05),中西医组比西医组使复发风险降低45.5%(P<0.001)。中医组以低中药水平暴露时间(TCM-ET)为参照,高TCM-ET较于低TCM-ET复发风险降低81.4%(P<0.01);中西医组以低TCM-ET为参照,中TCM-ET比低TCM-ET复发风险降低46.9%(P<0.05),高TCM-ET比低TCM-ET复发风险降低65.3%(P<0.01)。结论:益肾调气法治疗肾虚肝郁型抑郁障碍能够降低远期复发率,且中医药干预的暴露水平与复发率之间具有密切的关系,较长的暴露水平显著降低了患者的复发率。

基于近场动力学的船用钢受破片冲击研究

为了研究船用钢在非接触式爆炸产生破片冲击下的相关响应模式,更好地提高舰船船体抵抗破片冲击能力,基于近场动力学方法对船用钢受立方体破片冲击的工况进行研究。首先,结合近场动力学理论改进损伤数指标,建立符合船用钢材料规范的船用钢受立方体破片冲击模型;其次,对船用钢在受到不同速度和冲击方式的立方体破片冲击的工况进行物理冲击试验和近场动力学数值模拟,结合数值模拟后的优化损伤图和物理冲击试验后的失效图分析各工况下钢板的失效模式,同时选取船用钢被贯穿失效后的应力图进行各贯穿阶段应力变化分析;最后,使用无量纲法结合线性回归法分析船用钢受破片冲击的临界贯穿速度影响规律。在破片冲击方式对船用钢影响程度方面,立方体破片以棱边对船用钢冲击的工况中钢板损伤程度比以面和尖角冲击的工况分别高出44.6%和29.9%;在破片临界贯穿速度影响规律研究方面,分别得出误差率小于4%的立方体破片以棱边、面、尖角冲击钢板的极限贯穿速度经验公式,并得出在同样条件下立方体破片以棱边对船用钢冲击所需临界贯穿速度最小。采用该近场动力学方法进行破片冲击船用钢的数值模拟研究具有高适用性和准确性,在对船用钢板强度分析时应注重研究立方体破片以棱边冲击钢板的工况。

基于连续比例Logistic回归模型的贝叶斯判别分析

针对传统贝叶斯判别分析方法处理实际问题的局限性,提出一种基于连续比例Logistic回归模型的贝叶斯判别分析方法.首先基于连续比例Logistic回归模型建立半参数密度比模型,通过经验似然法估计模型的参数,并使用贝叶斯定理计算后验概率进行分类预测.然后对比新方法与传统方法的回判正确率,统计模拟表明当总体数据符合正态分布时,2者判别能力相当,否则,提出的新方法能够更好地判别不同的数据特征.最后运用新方法分析真实的数据集,验证了新方法在分类预测中的准确性和稳健性,与传统方法相比,更适用于实际应用中多元分类问题的建模和预测.

基于灰色关联与逐步回归的黄石市区岩土参数相关性研究

为获取较为准确可靠的岩土参数值,提升岩土工程勘察效率,以黄石市区第四系全新统湖积层(Q_(4)^(l))淤泥质土和第四系上更新统残积层(Q_(3)^(el))粉质黏土为研究对象,采用灰色关联分析法分析土层各岩土参数之间的关联程度,建立逐步回归模型,得到力学参数的经验公式。研究结果表明:土体的力学参数与其物理参数存在联系,确定了黄石市区两类典型土体的力学参数与物理参数相关度;逐步回归模型得到的力学参数与物理参数之间的经验公式拟合效果较好。研究结论为岩土工程勘察相关参数的快速获取及标定提供参考。

基于船体变形数值仿真的FPSO管道应力分析

为区别于传统经验公式计算管道应力的方法,采用有限元方法计算浮式生产储卸油装置(Floating Production Storage and Offloading,FPSO)船体变形,提取具体管道支架的位移值,并利用CAESARⅡ软件进行管道应力计算。有限元预报得到的管道应力更加准确,而经验公式得到偏保守的结果。建议在对FPSO管道进行初步设计时可采用经验公式方法,在进行详细设计和局部管道应力校核时可采用数值仿真方法。

船桥撞击力的神经网络预测与经验公式研究

为了减少船舶与桥梁撞击对人身和财产安全造成的危害,研究船舶与桥梁撞击力的最大值及其与其他影响因素之间的关系具有十分重要的意义。该文首先利用ANSYS/LS-DYNA软件建立了船舶撞桥的有限元模型,计算了不同撞击速度和撞击角度下船桥撞击力的最大值,并将计算结果与各国规范进行比较;然后,利用反向传播(back propagation,BP)神经网络技术,结合仿真计算数据,在最大撞击力值、撞击速度和撞击角度这3个训练参数下,创建了船桥最大撞击力的预测模型;最后,通过分析撞击速度和角度的散点图,拟合了1个最大撞击力与撞击速度和角度关系的经验公式,并将经验公式、有限元仿真计算结果和神经网络预测结果进行比较,验证了经验公式的准确性。该研究为快速评估船桥撞击是否会导致灾难性后果提供了1种有效的方法。

旋转流体多边形自由表面形成机制研究

针对流体在约束旋转中产生多边形涡流的现象,设计了旋转圆筒实验装置,对不同旋转频率、液面高度及圆筒半径下的旋转流体行为进行了研究。基于实验现象,提出了全局复合波理论模型,该模型的计算结果与实验现象一致。根据流动相似理论,利用量纲分析法对实验数据进行分析处理;借助黑体辐射模型给出了流体参数在一定范围下的经验公式,该公式在径长比小于4的情况下与实验数据符合程度较好。本文建立的全局复合波理论模型及相关研究结论可为多边形涡流形成机制与变化规律研究提供理论参考。