基于SVM回归模型的混合气体组分种类光谱识别方法

针对混合气体红外光谱分析中无法采用同一模型同时进行混合气体组分浓度的定量分析和组分种类的定性分析的问题,本文提出了基于SVM回归模型的混合气体组分种类光谱识别方法.通过详细推导,证明混合气体组分种类识别完全可以通过组分浓度分析的SVM回归模型来求解,混合气体组分种类识别是一种特殊的回归.实验结果显示,该方法的混合气体组分种类的正确识别率不小于92.5%.     

基于炉口辐射光谱支持向量机回归的转炉终点碳含量检测

转炉终点碳含量在线检测对实现炼钢终点准确控制,提高钢铁产品质量,降低能耗,减少废气排放具有重要意义。针对转炉冶炼终点控制及碳含量检测的难题,研究了一种新的基于炉口辐射光谱分析的非接触式在线碳含量检测方法。方法基于辐射光谱的支持向量机回归(SVR)实现转炉终点前过程的碳含量预测。通过远距离光谱采集系统获取炉口火焰光谱信息,基于冶炼过程炉口火焰辐射光谱变化规律的分析,分别提取了表征辐射光谱整体特征的两个参数即总谱宽和辐射峰值、以及表征发射谱的三个特征波长600,630和775 nm处的幅值作为支持向量机的输入,结合脱碳理论和实测碳值拟合重构的脱碳函数曲线作为支持向量机的输出,利用支持向量机回归方法建立光谱分布与碳含量的关系模型。通过训练样本集和测试集循环优化确定模型最佳参数。设计的仪器和优选的模型已安装在转炉生产现场长时间运行,现场实验结果表明,终点碳含量检测准确率为90.2%,测量时间小于0.3 s,可实时在线检测,能够满足生产需求,为转炉冶炼终点的精确控制提供了重要依据。     

水溶液中Cr^3＋的火焰原子吸收光谱法测试条件的优化

为优化火焰原子吸收光谱法测定水溶液中的Cr^3＋的测试条件,分别采用单因素简单比较法、正交实验设计极差分析及正交实验回归方法考察了光谱通带n,空心阴极灯电流I,燃烧器高度h以及乙炔/空气流量比P对于仪器灵敏度的影响。结果表明单因素简单比较法获得的实验条件最优。乙炔/空气流量比P对火焰原子吸收仪器灵敏度影响最大、其次是光谱通带n,燃烧器高度h和灯电流I的影响很小。测定水溶液中的Cr^3＋时仪器灵敏度最佳的实验条件为：乙炔/空气流量比P=0.4;光谱通带n=0.2nm;灯电流I=5mA;燃烧器高度h=5cm。     

混合气体红外光谱支持向量机分析的新方法

介绍了一种基于支持向量机的混合气体红外光谱组分浓度和种类分析的新方法。利用核函数将组分气体特征吸收谱线重叠严重的混合气体光谱在高维空间变换后,建立SVM回归校正模型,进行混合气体浓度分析。在利用支持向量机回归校正模型进行混合气体组分浓度分析的同时,证明支持向量机回归校正模型也可用于混合气体组分种类分析。对不同组分和不同组分浓度的混合气体红外光谱数据进行了实验,研究了谱仪扫描间隔、分析特征波长范围、核函数和惩罚因子等因素对分析结果的影响。混合气体组分浓度实验结果的最大平均绝对误差Mean AE为0.132%;混合气体组分种类识别的准确率大于94%。解决了传统的光谱分析方法中光谱特征谱线重叠、光谱数据的维数大、定性和定量分析无法使用同一方法等问题,可用于其他混合气体的红外光谱分析,具有实际应用价值。     

Acoustic detection and classification of river boats

We present a robust algorithm to detect the arrival of a boat of a certain type when other background noises are present. It is done via the analysis of its acoustic signature against an existing database of recorded and processed acoustic signals. We characterize the signals by the distribution of their energies among blocks of wavelet packet coefficients. To derive the acoustic signature of the boat of interest, we use the Best Discriminant Basis method. The decision is made by combining the answers from the Linear Discriminant Analysis (LDA) classifier and from the Classification and Regression Trees (CART) that is also accompanied with an additional unit, called Aisles, that reduces false alarms rate. The proposed algorithm is a generic solution for process control that is based on a learning phase (training) followed by an automatic real time detection while minimizing the false alarms rate.     

AB_5型储氢合金及混合稀土的ICP-AES分析

对于制备镍氢电池负极材料的 AB5型储氢合金 ,制备储氢合金的原材料混合稀土主体元素和杂质元素的分析方法进行了较为详尽的研究。利用仪器的功能软件初步选出各分析元素的多条谱线 ,通过综合考察各干扰元素对分析元素波长的干扰系数 ,确定出各元素的最佳分析波长 ,部分受干扰的元素用干扰系数校正法进行了校正。本法应用于实际产品分析 ,分析精密度为 0 .12 %— 1.32 %之间 ,回收率在94 %— 10 6%之间。     

Reflection and transmission at normal incidence onto air-saturated porous materials and direct measurements based on parametric demodulated ultrasonic waves

The present work is related to the characterization of air-saturated porous media by using parametric demodulated ultrasonic waves. One uses two different powerful ultrasonic emitters working either at 47 kHz or at 162 kHz which are electronically amplitude modulated over the 200 Hz-4 kHz or 2 kHz-40 kHz bandwidths respectively. The demodulation process takes place in air, due to its nonlinearity enabling to generate audio range acoustical waves or alternatively low frequency ultrasonic waves which can be used to characterize porous materials in the reflection configuration at normal incidence. Some appropriate theoretical calculations are introduced for three configurations of interest, i.e. a porous slab, a porous layer mounted onto a rigid plate, and a porous half space, in the case of the equivalent-fluid model. Comparisons between theoretical modeling and experimental data are provided and prospective industrial applications are discussed.     

Mixture cure models in credit scoring: If and when borrowers default

Mixture cure models were originally proposed in medical statistics to model long-term survival of cancer patients in terms of two distinct subpopulations - those that are cured of the event of interest and will never relapse, along with those that are uncured and are susceptible to the event. In the present paper, we introduce mixture cure models to the area of credit scoring, where, similarly to the medical setting, a large proportion of the dataset may not experience the event of interest during the loan term, i.e. default. We estimate a mixture cure model predicting (time to) default on a UK personal loan portfolio, and compare its performance to the Cox proportional hazards method and standard logistic regression. Results for credit scoring at an account level and prediction of the number of defaults at a portfolio level are presented; model performance is evaluated through cross validation on discrimination and calibration measures. Discrimination performance for all three approaches was found to be high and competitive. Calibration performance for the survival approaches was found to be superior to logistic regression for intermediate time intervals and useful for fixed 12 month time horizon estimates, reinforcing the flexibility of survival analysis as both a risk ranking tool and for providing robust estimates of probability of default over time. Furthermore, the mixture cure model’s ability to distinguish between two subpopulations can offer additional insights by estimating the parameters that determine susceptibility to default in addition to parameters that influence time to default of a borrower.     

Direct numerical method for an inverse problem of a parabolic partial differential equation

A coefficient inverse problem of the one-dimensional parabolic equation is solved by a high-order compact finite difference method in this paper. The problem of recovering a time-dependent coefficient in a parabolic partial differential equation has attracted considerable attention recently. While many theoretical results regarding the existence and uniqueness of the solution are obtained, the development of efficient and accurate numerical methods is still far from satisfactory. In this paper a fourth-order efficient numerical method is proposed to calculate the function u(x,t) and the unknown coefficient a(t) in a parabolic partial differential equation. Several numerical examples are presented to demonstrate the efficiency and accuracy of the numerical method.     

Atomic force microscopy enabled roughness analysis of nanostructured poly (diaminonaphthalene) doped poly (vinyl alcohol) conducting polymer thin films

The Atomic Force Microscopy (AFM) helps in evaluating parameters like amplitude or height parameters, functional or statistical parameters and spatial parameters which describe the surface topography or the roughness. In this paper, we have evaluated the roughness parameters for the native poly (vinyl alcohol) (PVA), monomer diaminonaphthalene (DAN) doped PVA, and poly (diaminonaphthalene) (PDAN) doped PVA films prepared in different solvents. In addition, distribution of heights, skewness and Kurtosis moments which describe surface asymmetry and flatness properties of a film were also determined. At the same time line profiles, 3D and 2D images of the surface structures at different scanning areas i.e. 5 × 5 μm² and 10 × 10 μm² were also investigated. From the roughness analysis and the surface skewness and coefficient of Kurtosis parameters, it was concluded that for PVA film the surface contains more peaks than valleys and the PDAN doped PVA film has more valleys than peaks. It was also found that the PDAN doped PVA film with acetonitrile solvent was used for substrate in electronics applications because the film gives less fractal morphology. Thus, the AFM analysis with different parameters suggested that the PDAN doped PVA films are smooth at the sub-nanometer scale.