基于偏度校正的非正态质量控制图的方法研究

将Cornish-Fisher展开理论应用于非正态质量控制图研究,建立了非正态过程质量控制图的偏度校正控制限.结合生产实际非正态过程,与基于正态假设的休哈特控制图进行比较,得出结论:偏度校正控制图充分考虑到非正态过程分布的特点,能够对非正态过程进行很好的监控,虚发报警的概率在合理的水平.     

Simulation embedded artificial intelligence search method for supplier trading portfolio decision

An electric power supplier in the deregulated environment needs to allocate its generation capacities to participate in contract and spot markets. Different trading portfolios will provide suppliers with different future revenue streams of various distributions. The classical mean?variance (MV) method is inappropriate to deal with the trading portfolios whose return distribution is non-normal. In order to consider the non-normal characteristics in electricity trading, this study proposes a new model based on expected utility theory (EUT) and employs a hybrid genetic algorithm (GA) -- Monte-Carlo simulation technique as solution approach. In the real market data-based numerical studies, the performances of the proposed method and the standard MV method are compared. It was found that the proposed method is able to obtain better portfolios than MV method when non-normal asset exists for trading. The simulation results also reveal the accumulation effect along trading period, which will improve the normality of the supplier trading portfolios. The authors believe the proposed method is a useful complement for the MV method and conditional value at risk (CVaR)-based methods in the supplier trading portfolio decision and evaluation.     

A novel statistical tolerance analysis method for assembled parts

Tolerance analysis of an assembly is an important issue for mechanical design. Among various tolerance analysis methods, statistical analysis is the most commonly employed method. However, the conventional statistical tolerance method is often based on the normal distribution. It fails to predict the resultant tolerance of an assembly of parts with non-normal distributions. In this paper, a novel method based on statistical moments is proposed. Tolerance distributions of parts are first transferred into statistical moments that are then used for computing tolerance stack-up. The computed moments, particularly the variance, the skewness and the kurtosis, are then mapped back to probability distributions in order to calculate the resultant tolerance of the assembly. The proposed method can be used to analyse the resultant tolerance specification for non-normal distributions with different skewness and kurtosis. Simulated results showed that tail coefficients of different distributions with the same kurtosis are close to each other for normalised probabilities between ?3 and 3. That is, the tail coefficients of a statistical distribution can be predicted by the coefficients of skewness and kurtosis. Two examples are illustrated in the paper to demonstrate the proposed method. The predicted resultant tolerances of the two examples are only 0.5% and 1.5% differences compared with that by the Monte Carlo simulation for 1,000,000 samples. The proposed method is much faster in computation with higher accuracy than conventional statistical tolerance methods. The merit of the proposed method is that the computation is fast and comparatively accurate for both symmetrical and unsymmetrical distributions, particularly when the required probability is between ±2σ and ±3σ.     

Probabilistic Assessment of UPV Test Result of a Degasser Unit

The novelty of this paper is to address a fundamental characteristic of ultrasonic pulse velocity (UPV) test result called distribution pattern and development of a methodology to simplify non-normal distribution patterns of UPV into normal distribution domain for easy applicability of quality assurance criteria for practicing engineers. In this paper probabilistic assessment methodology of UPV test results collected from a de-gasser structure of a refinery in India is discussed. Detailed analysis is performed to identify the distribution characteristics of UPV. No conventional distribution type including normal distribution fitted for UPV test results. A further attempt is made to derive simplified normal distributions with two different modes from the empirical cumulative distribution function of in situ test results. This creates scope for application of existing normal distribution based quality assurance criteria to non-normal domain of UPV. Criteria of characteristic strength instead of mean value is proposed as a better parameter for estimation of the quality of the material. Detailed physical interpretation and justification for the methodology is discussed with mathematical reasoning. The method is discussed in reference to existing literature. It is shown that the method is applicable to derive quality assurance criteria where simple assumption of normal distribution is not valid for UPV. Thus the method has the potential to make UPV a more useful test based on statistical reasoning for application on full scale structures.     

用Lagrange乘子法求解结构可靠指标

本文用Ｌａｇｒａｎｇｅ乘子法把求解结构可靠指标的条件极值问题转化为无条件极值问题，对目前已被应用的迭代公式给出了理论证明；同时指出，对于随机变量为一般分布情况下的结构可靠指标的计算，把原来非正态分布随机变量用当量正态分布随机变量代替时，为了保证收敛，迭代过程中当量正态分布随机变量的均值和标准差必须有足够的精度。文中的几个算例表明，采用的计算方案具有较快的收敛速度和计算精度。     

非正态过程能力指数研究中的几个问题

非正态分布条件下过程能力指数的研究是目前关于过程能力分析中的热点之一。针对该领域中存在的若干问题,分析了正态性假设的重要性,指出导致质量特性呈现非正态分布的原因及其后果,以及如何进行质量特性分布的一维和多维正态性检验。对非正态过程能力指数的估计方法进行了分析和归类,简要指出在非正态过程能力指数研究中需要继续深入的几个方向。     

A SIMPLE COST MINIMIZATION PROCEDURE FOR THE (Q,R) INVENTORY MODEL: DEVELOPMENT AND EVALUATION

This paper presents a very effective procedure for determining the optimal lot size and reorder point for the popular Hadley-Whitin continuous-review (Q,R) model. It is simpler than earlier approaches. Most importantly, the procedure handles non-normal lead-time demands very easily. Extensive test results are presented to confirm the procedure's accuracy for a wide range of parameter-values and leadt-time-demand distributions.     

基于计算智能技术的结构系统可靠性优化设计

利用随机摄动和Edgeworth级数方法,将非正态随机参数可靠性优化设计中的概率约束转化为等价的确定性约束,并运用粒子群算法迅速准确地获得结构系统可靠性优化设计的初始点。针对多失效模式的结构系统,提出了随机模拟-小波神经网络方法(MCS-WNN),有效解决了结构系统的可靠性仿真。并提出了一种便于逆映射的小波神经网络模型,实现了设计参数的可靠性优化。实验结果表明上述方法是行之有效的。     

统计过程控制中基于数据深度的非参数变点控制图

为了解决多元非正态分布情况下的过程控制问题,提出基于数据深度的变点控制图,并对构建该控制图检验统计量的具体方法及控制流程进行了详细描述。为了检验该控制图的控制效果,采用服从二元伽马分布的样本数据对其进行了验证,并设置位置参数偏移范围为0.2至1.0,变点为14、24、34,几种情况分别检验其控制效果。数据仿真的结果表明:偏移越大,检测效果越好;偏移量小于0.7时,变点越大,检测效率越高;而当变点大于0.7时变点对检测效果的影响不明显。偏移量在0.1至0.4的范围内,变点越大,检测效果越好,但是这种边际效果在减小。     

Variable screening and ranking using sampling-based sensitivity measures

This paper presents a methodology for screening insignificant random variables and ranking significant important random variables using sensitivity measures including two cumulative distribution function (CDF)-based and two mean-response based measures. The methodology features (1) using random samples to compute sensitivities and (2) using acceptance limits, derived from the test-of-hypothesis, to classify significant and insignificant random variables. Because no approximation is needed in either the form of the performance functions or the type of continuous distribution functions representing input variables, the sampling-based approach can handle highly nonlinear functions with non-normal variables. The main characteristics and effectiveness of the sampling-based sensitivity measures are investigated using both simple and complex examples. Because the number of samples needed does not depend on the number of variables, the methodology appears to be particularly suitable for problems with large, complex models that have large numbers of random variables but relatively few numbers of significant random variables.     

基于NSGA-Ⅱ算法的不完全概率信息刨头多目标模糊可靠性优化

针对滑行刨煤机能耗和载荷波动问题,讨论了随机参数服从非正态分布滑行刨煤机刨头的多目标可靠性优化,在基本随机参数的前四阶矩已知的情况下,应用随机摄动法和Edgeworth级数方法,计算刨头多目标的可靠性,并采用遗传算法NSGA\-Ⅱ算子进行模拟可靠性运算.研究结果表明：该方法计算得到的刨煤机刨头的载荷波动和比能耗显著降低,提高了刨煤机的工作可靠性,优化了刨头的结构参数．     

Introduction to Numerical Analysis

A development of the mathematical structure of nested designs is presented using, for a general case, a four-stage nested design. For the casea where the variables at each stage are normally distributed, analytical results can be obtained. This is done for the unbalanced “staggered” and “inverted” designns. Empirical estimattas of variance for the non-normal case are obtained. These are compared with the analytical solutions. Also considered is the probability of negative variance estimates. It ia interesting to note that for these alternatives to balanced nested designs, one can decrease the probabilities of negative estimates of some variances at the cost of increasing them for others.     

电铲斗杆强度分析

应用Ｓｕｐｅｒ ＳＡＰ程序对２１００ＢＬ电铲斗杆进行了强度分析，得出不同工况下的最大应力值及危险截面位置。该结果与美国Ｐ&Ｈ公司发布的维修公告一致，为进一步改进结构设计提供了依据。     

基于截尾概率分布的结构可靠性分析

基于概率分布理论,建立了截尾概率分布分析模型;为便于截尾概率分布可靠性分析,提出了计算可靠指标的新优化模型,该模型无需对概率分布进行当量正态化,也无需知道概率分布类型信息;给出了截尾概率分布在给定子区间内产生随机数的方法,使得MonteCarlo抽样成为可能。算例结果表明,截尾概率分布更符合实际情况,并且会使可靠指标提高,其影响不容忽视。     

电厂燃煤虚拟采样及发热量均值不确定度评定

电厂锅炉燃煤发热量还未能实现广泛的连续测量,在发电厂效率检测时,采用少量样品煤的实验室化验数据表示检测周期内全部燃煤的发热量,由此带来较大的测量不确定性。研究了入炉煤多次采样样品发热量平均值的不确定性,当发热量样本是正态分布,或求取平均值的样品个数大于30时,根据中心极限定理,可采用传统方法对样品均值的不确定度进行评定;当发热量样本是非正态分布,且求取平均值的样品个数小于30时,可采用挑选样抽法产生发热量的随机样本,然后利用发热量均值的虚拟样本,进行非正态分布下扩展不确定度的计算。实际应用表明,本文给出的方法结果合理,能够满足发电机组效率检测不确定度分析的需要。     

Reliability analysis of pipelines carrying H2S for risk based inspection of heavy water plants

Reliability analysis of pipelines containing corrosion defects due to H₂S is presented. The pipeline carrying H₂S is more susceptible to the internal corrosion thereby reducing the pipeline's load carrying capacity. The objective of this study is to obtain the pipelines' failure probabilities that are required in establishing a Risk Based Inspection (RBI) programme for heavy water plants. The reliability assessment of pipelines involves the estimation of failure pressure and evaluating the limit state function. Several failure pressure models were studied for this purpose and it was found that the modified B31G failure pressure model is most suitable for the pipeline failure pressure modeling. Due to the presence of non-linearity in the limit state function and non-normal variables, the first order reliability method has been employed for carrying out the reliability analysis. The uncertainty of the random variables on which the limit state function depends is modeled using normal and non-normal probabilistic distributions. The failure probabilities and the categories of the pipelines connected to the first pair of first stage of exchange towers are presented. In addition, a sensitivity analysis was carried out on random variables involved in the problem. The results of sensitivity analysis are also presented.     

Progressive delamination growth analysis using discontinuous layered element

In this paper, a fracture mechanic approach is used to analyze delamination propagation between layers of composite laminates. A finite element method based on layer-wise theory is extended for the analysis of delamination growth. In this approach, delamination is modeled by jump discontinuity conditions at the interfaces. The layer-wise finite element is developed to calculate the strain energy release rates based on the virtual crack closure technique (VCCT). A procedure is proposed to handle the progressive delamination of laminates. Finally, analyses of the edge delamination propagation for several composite laminates are performed and the corresponding failure stresses are calculated. The predicted results are compared with the available experimental and numerical results. It is shown that the predicted failure stresses using this method are comparable with those obtained using interface elements.     

A simple and accurate Ritz formulation for free vibration of thick rectangular and skew plates with general boundary conditions

The Ritz method is one of the most elegant and useful approximate methods for obtaining solutions for the natural frequencies and vibration modes of elastic plates. It is simple to use and also straightforward to implement. In conventional Ritz method, the geometric boundary conditions are only satisfied and hence the Ritz method is known as a method that can produce upper bound solution results for the natural frequencies of elastic plates. On the other hand, the accuracy of the Ritz method for the solution of differential equations with mixed natural boundary conditions at the boundary lines is not very satisfactory. To overcome this difficulty, this paper presents a simple and accurate Ritz formulation in which the natural boundary conditions are exactly implemented. The versatility, accuracy, and efficiency of the proposed method for free vibration analysis of thick rectangular and skew plates are tested against other solution procedures. It is revealed that the proposed method to handle the mixed natural boundary conditions is simple to use and can produce highly accurate solutions for the natural frequencies of thick rectangular and skew plates involving free edges.     

塑料导爆管在连接件中的起爆过程

文中通过微光照度法测定导爆管起爆段相对浓度变化，从而确定导爆管的起爆过程。实验表明：在连接中导爆管的起爆过程具有三种典型情况，即不正常起爆、正常的长诱导起源及正常加速起爆。控制导爆管轴向方向获得较强的反射冲击波可达到理想的起爆过程。     

DSC analysis of a simply supported anisotropic rectangular plate

The discrete singular convolution (DSC) algorithm is used to analyze the deflection and free vibration behavior of a simply supported anisotropic rectangular plate. A novel approach is proposed to solve the difficulty in using DSC to handle the simply supported boundary conditions with bending–twisting coupling. DSC results are presented for bending under distributed load and a center concentrated load, and natural frequencies of flexural vibrations. It is shown that the DSC with proposed method to apply the simply supported boundary conditions yields very accurate results as compared to exact solutions or results obtained by methods of differential quadrature and finite element with fine meshes. It is also verified that neglecting the bending–twisting coupling in applying the simply supported boundary conditions may result incorrect solutions, especially for the bending analysis of anisotropic plates.