成败型产品验收试验方案研究

在可靠性定型试验的基础上，利用多层贝叶斯方法确定批产品可靠性指标的先验分布，从而制定出成败型产品可靠性验收试验的一种贝叶斯方案，给出利用定型试验信息确定产品可靠性指标先验分布的方法，这种验收方法充分利用了产品定型试验中的先验信息，在确保有较好验收效果的前提下，与传统的验收试验相比，可以大大减少试验量，从而得到可观的经济效益。     

基于模板的前视红外图像建筑物分割方法

针对前视红外地面建筑物图像目标分割问题,在传统方法的基础上提出了一种基于模板制备的改进C-V模型分割方法.首先通过DSM数据制备目标二维形状模板;然后对图像进行高斯滤波去噪,并采用模板尺度相关的结构元素对图像进行灰度形态学增强;最后引入模板形状先验信息的概念,利用水平集方法表达轮廓先验信息,在C-V模型的基础上增加目标轮廓先验信息能量项,使分割曲线进化同时受到图像数据与形状先验信息驱动,实现目标分割.实测数据显示该方法能在复杂背景条件下精确分割前视红外建筑物目标.     

一种综合评价中确定专家权重的方法

研究综合评价(CE)问题中个体评价专家权重的确定方法,提出专家权重由先验权重和后验权重构成,建立了先验权重评价指标体系和后验权重的度量准则并给出专家判断信息为模糊判断矩阵时计算后验权重的方法,通过先验、后验权重的组合实现专家群判断信息合成时对专家的赋权,最后用算例予以说明.     

具有先验信息的线性模型参数估计精度影响的度量

从广义方差比，协方差迹之经以及均方误差这三个不同的度量指标刻划了用最小二乘估计代替具有先验信息的线性模型的混合估计后对估计精度的影响问题。     

群稀疏高斯洛伦兹混合先验超分辨率重建

为了得到置信度更高的超分辨率先验模型,实现重建结果在噪声和细节之间的平衡,建立了基于混合稀疏表达框架下的高斯— 洛伦兹混合先验模型.研究了该先验模型在超分算法中的应用优势和具体的应用方案.首先,根据先验信息的类型介绍了一些超分辨率算法的优势和问题.接着,提出对图像不同分量的统计特点进行单独建模的应用方法.然后,在分析了混合稀疏框架、高斯吉布斯先验和洛伦兹先验的基础上,说明了基于群稀疏框架下的高斯— 洛伦兹混合先验的超分辨率算法.最后,介绍了具体实现环节和最终迭代方案.实验结果表明,本文基本完成了在重建过程中保持细节的同时抑制噪声的改进目标,可以用于更多复杂环境的超分辨率重建要求.     

基于正态-逆Wishart先验分布的贝叶斯分类识别方法研究

研究了各总体服从正态分布、分布参数的先验分布均为正态-逆Wishart共轭先验时，如何利用待判样品的预报密度函数，构造后验概率比和分类判别规则，并据此对样品进行分类识别；该方法的特点是充分利用了参数分布的信息，结论简单、直观，并且也不需要假设各总体的协方差阵相同。     

无信息先验下几种不同Bayes估计的比较

讨论了在二项分布场合关于成功率的不同无信息先验分布下的Bayes估计，并从Bayse风险的角度对它们进行了比较。     

基于贝叶斯理论的钢筋混凝土柱受剪承载力计算

现行混凝土结构设计规范中钢筋混凝土柱的受剪承载力公式为半经验半理论计算公式,由于试验数据的有限性和钢筋混凝土材料离散性较大的本质特性,规范建议公式缺乏明确的理论模型。该文以贝叶斯动态信息更新思路,根据主观经验信息选定现行规范中钢筋混凝土柱受剪承载力计算公式作为贝叶斯先验模型,通过已完成试验研究的柱受剪承载力数据,应用贝叶斯方法综合这两类信息进行推断,建立钢筋混凝土柱在反复荷载作用下受剪承载力的概率模型,对未知参数进行估计,修正先验模型并建立后验模型,以达到对先验模型的更新。通过先验模型计算值、后验模型计算值及试验值相互间的对比分析可知:贝叶斯方法继承了先验信息的完备性和大量试验数据的准确性,能够更准确地预测钢筋混凝土柱的受剪承载力。     

基于最大熵与贝叶斯的动态不确定度滚动更新模型

基于最大熵原理,对现有贝叶斯先验分布确定方法做出了改进,特别给出了更加符合客观实际的无信息先验分布确定方法.运用最大熵原理与贝叶斯估计推断建立动态不确定度滚动更新模型,较好的体现新的测量数据对不确定度的影响,解决了动态不确定度的滚动更新问题.     

融入频域先验信息压缩感知方法的主动声呐回波信号处理

针对弱信噪比时的水下主动声呐回波信号处理问题,从主动声呐入射信号和目标回波信号的先验信息出发,与压缩感知理论相结合,提出了融入频域先验信息的压缩感知方法（Compressed Sensing based on Fequency Prior Information,CSFPI）。针对主动声呐入射信号,获取其频域先验信息,将其作为“原子”融入信号的稀疏分解过程,构建完备频域先验稀疏矩阵。主动声呐回波信号可以等效为携带目标信息入射信号的线性叠加,将该特性与传统正交匹配追踪（Orthogonal Matching Pursuit,OMP）算法结合,形成基于“块”的正交匹配信号重构算法。采用CSFPI方法处理仿真信号来验证理论方法的正确性。进一步,通过主动声呐发射接收装置获取湖上实测数据,用CSFPI方法进行处理。当压缩比为50%、信噪比低至-5 dB时,重构信号的匹配率高于70%。实验结果表明了CSFPI算法在处理低信噪比声呐信号时的有效性。     

Theory and implementation of NDT data fusion

Scientific measurements from single or multiple sensors are usually incomplete and uncertain. A process making use of the concept of data fusion has been developed to try to encompass this problem by combining information from multiple sensors. The objective to synergistic use of information from multiple sources is to reduce uncertainty and increase the confidence level of a measurand. The implementation of data fusion to the field of NDT is relatively new. This paper summarizes the achievements of current research on data fusion applied to NDT. A theoretical data fusion strategy is described and experimental results generated from weld inspection are presented.     

基于改进加权D-S信息融合的结构多损伤位置识别

将信息融合技术中的D-S证据融合理论应用于结构的多损伤定位问题,为了解决证据融合理论中的不同证据应具有不同的重要性的问题,提出了一种新的加权证据调整的方法。这种方法利用加权平均值和优先权的证据分布形态对证据进行了加权调整,调整后的证据保证了加权平均值不变以及优先权证据分布形态的稳定。仿真结果表明,采用了证据融合方法的多损伤定位,可以产生比单一信息源更精确、更完全的估计和判决,而基于改进加权证据融合技术具有更好的对多损伤定位的识别,优于基本D-S证据组合方法以及其它加权证据组合方法。     

Theory and Implementation of NDT Data Fusion

Abstract

Scientific measurements from single or multiple sensors are usually incomplete and uncertain. A process making use of the concept of data fusion has been developed to try to encompass this problem by combining information from multiple sensors. The objective to synergistic use of information from multiple sources is to reduce uncertainty and increase the confidence level of a measurand. The implementation of data fusion to the field of NDT is relatively new. This paper summarizes the achievements of current research on data fusion applied to NDT. A theoretical data fusion strategy is described and experimental results generated from weld inspection are presented.     

An information fusion reliability allocation method considering limited sample size circumstances

As an essential part in product reliability design procedure, reliability allocation can connect the reliability index between the overall product and its multiple subsystems. To obtain a reasonable reliability allocation scheme, especially for limited sample size circumstances commonly encountered in aeronautic and astronautic fields, an information fusion allocation method is constructed in the current study. Grey relational analysis (GRA) is incorporated to analyze objective data, while analytic hierarchy process (AHP) is introduced to implement subjective data analysis. Then a final allocation scheme is derived by fusion of the binary information sources. A real application regarding an aeronautic product reliability allocation is given. The sensitivity of allocation result to limited life information circumstances and comparative analysis with reference methods are implemented to demonstrate the reasonability and effectiveness.     

Bayesian reliability: Combining information

ABSTRACT

One of the most powerful features of Bayesian analyses is the ability to combine multiple sources of information in a principled way to perform inference. This feature can be particularly valuable in assessing the reliability of systems where testing is limited. At their most basic, Bayesian methods for reliability develop informative prior distributions using expert judgment or similar systems. Appropriate models allow the incorporation of many other sources of information, including historical data, information from similar systems, and computer models. We introduce the Bayesian approach to reliability using several examples and point to open problems and areas for future work.     

不同信息融合方法在结构损伤识别上的应用和分析

在工程结构的损伤探测领域,不同的信息融合方法和方式对结构的损伤敏感程度以及计算的复杂程度往往不同,而且适用条件也不同。为了解决以上问题,描述了基于结构损伤识别的功能信息融合模型,并在此基础之上采用了多种融合方法进行了数值仿真和分析。数值仿真结果表明,采用了信息融合技术的结构多损伤位置识别,可以产生比单一信息源更精确、更完全的估计和判决,而且不同的信息融合算法的应用往往取决于研究对象和实际条件的要求。     

Effects of a priori parameter selection in minimum relative entropy method on inverse electrocardiography problem

The goal in inverse electrocardiography (ECG) is to reconstruct cardiac electrical sources from body surface measurements and a mathematical model of torso–heart geometry that relates the sources to the measurements. This problem is ill-posed due to attenuation and smoothing that occur inside the thorax, and small errors in the measurements yield large reconstruction errors. To overcome this, ill-posedness, traditional regularization methods such as Tikhonov regularization and truncated singular value decomposition and statistical approaches such as Bayesian Maximum A Posteriori estimation and Kalman filter have been applied. Statistical methods have yielded accurate inverse solutions; however, they require knowledge of a good a priori probability density function, or state transition definition. Minimum relative entropy (MRE) is an approach for inferring probability density function from a set of constraints and prior information, and may be an alternative to those statistical methods since it operates with more simple prior information definitions. However, success of the MRE method also depends on good choice of prior parameters in the form of upper and lower bound values, expected uncertainty in the model and the prior mean. In this paper, we explore the effects of each of these parameters on the solution of inverse ECG problem and discuss the limitations of the method. Our results show that the prior expected value is the most influential of the three MRE parameters.     

Reliability assessment of small sample based on multiple source information fusion and fuzzy fault tree

Aiming at the problems that was difficult to describe the relationship between events by the Boolean logic of conventional fault tree analysis (FTA), and the insufficient of getting reliability data in the practical application, a new polymorphic system reliability assessment method using small sample based on multiple source information fusion method and T-S fuzzy faulty tree was proposed. Based on T-S fuzzy fault tree, correlation multiple source information fusion method was applied to the confirmation of the basic event reliability. Meanwhile, in order to avoid the influence of unusable data, t-test was proposed to check the compatibility between prior information and sample information, which solved the problem that the reliability of the bottom event was difficult to be determined in the small sample system, and the prediction accuracy was improved. The proposed method was validated by using main hoisting mechanism of ladle crane. The results demonstrate that the proposed method can be applied to hoisting mechanism reliability assessment of ladle crane commendably, and the technique provides support and reference to improve the reliability of hoisting mechanism.     

Medical image fusion based on improved sum‐modified‐Laplacian

Sum‐modified‐Laplacian (SML) plays an important role in medical image fusion. However, fused rules based on larger SML always lead to fusion image distortion in transform domain image fusion or image information loss in spatial domain image fusion. Combined with average filter and median filter, a new medical image fusion method based on improved SML (ISML) is proposed. First, a basic fused image is gained by ISML, which is used for evaluation of the selection map of medical images. Second, difference images can be obtained by subtracting average image of all sources of medical images. Finally, basic fused image can be refined by difference images. The algorithm can both preserve the information of the source images well and suppress pixel distortion. Experimental results demonstrate that the proposed method outperforms the state‐of‐the‐art medical image fusion methods. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 206–212, 2015     

Fusion of MRI and CT images using guided image filter and image statistics

In medical imaging using different modalities such as MRI and CT, complementary information of a targeted organ will be captured. All the necessary information from these two modalities has to be integrated into a single image for better diagnosis and treatment of a patient. Image fusion is a process of combining useful or complementary information from multiple images into a single image. In this article, we present a new weighted average fusion algorithm to fuse MRI and CT images of a brain based on guided image filter and the image statistics. The proposed algorithm is as follows: detail layers are extracted from each source image by using guided image filter. Weights corresponding to each source image are calculated from the detail layers with help of image statistics. Then a weighted average fusion strategy is implemented to integrate source image information into a single image. Fusion performance is assessed both qualitatively and quantitatively. Proposed method is compared with the traditional and recent image fusion methods. Results showed that our algorithm yields superior performance.