Efficient space-filling and non-collapsing sequential design strategies for simulation-based modeling

Simulated computer experiments have become a viable cost-effective alternative for controlled real-life experiments. However, the simulation of complex systems with multiple input and output parameters can be a very time-consuming process. Many of these high-fidelity simulators need minutes, hours or even days to perform one simulation. The goal of global surrogate modeling is to create an approximation model that mimics the original simulator, based on a limited number of expensive simulations, but can be evaluated much faster. The set of simulations performed to create this model is called the experimental design. Traditionally, one-shot designs such as the Latin hypercube and factorial design are used, and all simulations are performed before the first model is built. In order to reduce the number of simulations needed to achieve the desired accuracy, sequential design methods can be employed. These methods generate the samples for the experimental design one by one, without knowing the total number of samples in advance. In this paper, the authors perform an extensive study of new and state-of-the-art space-filling sequential design methods. It is shown that the new sequential methods proposed in this paper produce results comparable to the best one-shot experimental designs available right now.     

A new approach with orthogonal array for global optimization in design of experiments

In this paper, we develop an approach that determines the overall best parameter setting in design of experiments. The approach starts with successive orthogonal array experiments and ends with a full factorial experiment. The setup for the next orthogonal-array experiment is obtained from the previous one by either fixing a factor at a given level or by reducing the number of levels considered for all currently non-fixed factors. We illustrate this method using an industrial problem with seven parameters, each with three levels. In previous work, the full factorial of 3⁷ = 2,187 points was evaluated and the best point was found. With the new method, we found the same point using 3% of these evaluations. As a further comparison, we obtained the optimum using a traditional Taguchi approach, and found it corresponded to the 366th of the 2,187 possibilities when sorted by the objective function. We conclude the proposed approach would provide an accurate, fast, and economic tool for optimization using design of experiments.     

Mixed two- and eight-level fractional factorial split-plot designs containing clear effects

Fractional factorial split-plot (FFSP) designs are useful in practical experiments. When the numbers of levels of the factors are not all equal in an experiment, mixed-level design is selected. This paper investigates the conditions of a resolution III or IV FFSP design with both two-level and eight-level factors to have various clear effects, including two types of main effects and three types of two-factor interaction components.     

二维序贯均匀设计方法的拓展研究

将二维序贯均匀设计方法拓展到三维空间,扩展到三维的序贯均匀设计可用于优化的三因子试验设计问题,从而达到既减少试验次数,又提高试验精度的目的.     

Factor screening for simulation with multiple responses: Sequential bifurcation

The goal of factor screening is to find the really important inputs (factors) among the many inputs that may be changed in a realistic simulation experiment. A specific method is sequential bifurcation (SB), which is a sequential method that changes groups of inputs simultaneously. SB is most efficient and effective if the following assumptions are satisfied: (i) second-order polynomials are adequate approximations of the input/output functions implied by the simulation model; (ii) the signs of all first-order effects are known; and (iii) if two inputs have no important first-order effects, then they have no important second-order effects either (heredity property). This paper examines SB for random simulation with multiple responses (outputs), called multi-response SB (MSB). This MSB selects groups of inputs such that—within a group—all inputs have the same sign for a specific type of output, so no cancellation of first-order effects occurs. To obtain enough replicates (replications) for correctly classifying a group effect or an individual effect as being important or unimportant, MSB applies Wald’s sequential probability ratio test (SPRT). The initial number of replicates in this SPRT is also selected efficiently by MSB. Moreover, MSB includes a procedure to validate the three assumptions of MSB. The paper evaluates the performance of MSB through extensive Monte Carlo experiments that satisfy all MSB assumptions, and through a case study representing a logistic system in China; the results are very promising.     

2(n1+n2)-(k1+k2)42混合水平裂区设计包含纯净效应的条件

混水平部分因析裂区设计在各类试验中有广泛应用. 在三因子及更高阶交互作用可以忽略这一很弱的假设下, 试验者可以得到纯净主效应或者纯净两因子交互作用成分的无偏估计. 本文给出了含有两个四水平因子和若干二水平因子的混水平裂区设计包含各类纯净主效应或者纯净两因子交互作用成分的条件以及构造相应设计的方法.     

单次重复试验的三水平析因设计的分析

由于试验材料、费用和时间等条件的限制,仅有单次重复试验的三水平析因设计经常要应用在农业、工业和医学临床试验等领域。例如,在医学临床试验中,为找到影响治疗关节炎效果的重要因子和最佳治疗方案需要考虑2个三水平的因子:A(药物治疗)和B(运动治疗),由于只能找到9位病情相似的病人进行试验,故只能实施仅有单次重复试验的三水平析因设计3~2。不幸的是,交互作用A×B也可能存在,这样就没有剩余自由度用于估计误差的方差,从而通常的方差分析方法不再能用于数据分析。针对上述问题,本文提出了三个基于均方误差的检验统计量用于分析单次重复试验的三水平析因设计。通过实例表明用这些方法不仅能检验所考虑因子的主效应,而且还能同时检验交互效应。相应检验所用的一些常用临界值提供在附录中。并且,还通过大量的模拟研究对所提出的三个检验方法进行了比较。结果显示,T_~((3))检验在三个检验方法中具有最大的功效。     

A sequential algorithm and error sensitivity analysis for the inverse heat conduction problems with multiple heat sources

This paper proposes a sequential approach to determine the unknown parameters for inverse heat conduction problems which have multiple time-dependent heat sources. There are two main aims in this study, one is to derive an inverse algorithm that can estimate the unknown conditions effectively, and the other is to bring up a theoretical sensitivity analysis to discuss what causes the growth of errors. This paper has three major achievements with regard to the literature on IHCPs, as follows: (1) proposing an efficient sequential inverse algorithm that can simultaneously determine several unknown time-dependent parameters; (2) exploring why the sequential function specification method can provide a stable but inaccurate estimation when tackling problems with larger measurement errors; and (3) discussing the sensitivity problem and analyzing what factors cause the growth in error sensitivity. Three examples are applied to demonstrate the performance of the proposed method, and the numerical results show that the accurate estimations can be obtained by alleviating the error sensitivity when the measurement error is considered.     

无重复因析试验中散度效应的ML估计

在无重复因析试验中,若因子A,B的散度效应显著,则不论其交互效应AB的散度效应是否显著,其散度效应的现有估计常常是有偏的,从而导致其被错误地识别为显著效应.提出了散度效应的一种新的估计方法(称为ML估计),并给出了ML估计的方差的精确表达形式,证明了在一类模型中,交互效应AB的散度效应的ML估计是无偏的.最后,将ML估计与现有的常用估计进行了比较.     

使用SAS软件进行多因素析因试验设计——SAS/QC(6.12)软件中factex过程的使用

本文介绍了SAS/QC中的factex过程的语法 ,通过例子介绍了使用它进行析因试验设计的一些方法 ,包括完全析因试验、部分析因试验、混合水评试验、拉丁方设计等。     

Gradient Estimation Schemes for Noisy Functions

In this paper, we analyze different schemes for obtaining gradient estimates when the underlying functions are noisy. Good gradient estimation is important e.g. for nonlinear programming solvers. As error criterion, we take the norm of the difference between the real and estimated gradients. The total error can be split into a deterministic error and a stochastic error. For three finite-difference schemes and two design of experiments (DoE) schemes, we analyze both the deterministic errors and stochastic errors. We derive also optimal stepsizes for each scheme, such that the total error is minimized. Some of the schemes have the nice property that this stepsize minimizes also the variance of the error. Based on these results, we show that, to obtain good gradient estimates for noisy functions, it is worthwhile to use DoE schemes. We recommend to implement such schemes in NLP solvers.We thank our colleague Jack Kleijnen for useful remarks on an earlier version of this paper and Gül Gürkan for providing us with relevant literature. Moreover, we thank the anonymous referee for valuable remarks.     

无重复析因试验位置效应分析若干方法的比较

本文介绍了在效应稀疏性的前提下venter和Steel提出的分析无重复析因试验数据的方法,并将它们和下降Lenth方法,下降Dong方法一起作了较全面的模拟比较。     

Regularities in data from factorial experiments

This article documents a meta‐analysis of 113 data sets from published factorial experiments. The study quantifies regularities observed among factor effects and multifactor interactions. Such regularities are known to be critical to efficient planning and analysis of experiments and to robust design of engineering systems. Three previously observed properties are analyzed: effect sparsity, hierarchy, and heredity. A new regularity is introduced and shown to be statistically significant. It is shown that a preponderance of active two‐factor interaction effects are synergistic, meaning that when main effects are used to increase the system response, the interaction provides an additional increase and that when main effects are used to decrease the response, the interactions generally counteract the main effects. © 2006 Wiley Periodicals, Inc. Complexity 11: 32–45, 2006     

Optimizing the DMFC operating conditions using a response surface method

The power density of a Direct Methanol Fuel Cell (DMFC) as a function of temperature, methanol concentration, air flow rate, methanol flow rate and air relative humidity was studied using a Response Surface Methodology (RSM). For a DMFC equipped with a membrane of Nafion 112, it was observed that only the temperature, methanol concentration and air flow rate were relevant factors or operating variables. A new design of experiments was done for a narrower range of these variables and the operating values that optimise the power density were obtained using the software JMP 7.0 (SAS). The predicted power density values were in agreement with the experimental results obtained for the optimized operating conditions. Then, the RSM was applied to membranes with different thicknesses, Nafion 112, Nafion 1135 and Nafion 117, and as a function of the temperature and methanol concentration. The DMFC was characterized for the open circuit voltage (OCV), methanol crossover at the OC, power density and global efficiency. The membrane showing the best compromise between power density and efficiency was Nafion 117.     

A multi-level Taguchi-factorial two-stage stochastic programming approach for characterization of parameter uncertainties and their interactions: An application to water resources management

This paper presents a multi-level Taguchi-factorial two-stage stochastic programming (MTTSP) approach for supporting water resources management under parameter uncertainties and their interactions. MTTSP is capable of performing uncertainty analysis, policy analysis, factor screening, and interaction detection in a comprehensive and systematic way. A water resources management problem is used to demonstrate the applicability of the proposed approach. The results indicate that interval solutions can be generated for the objective function and decision variables, and a variety of decision alternatives can be obtained under different policy scenarios. The experimental data obtained from the Taguchi’s orthogonal array design are helpful in identifying the significant factors affecting the total net benefit. Then the findings from the multi-level factorial experiment reveal the latent interactions among those important factors and their curvature effects on the model response. Such a sequential strategy of experimental designs is useful in analyzing the interactions for a large number of factors in a computationally efficient manner.     

Estimation of error variance in ANOVA model and order restricted scale parameters

We consider the estimation of error variance in the analysis of experiments using two level orthogonal arrays. We address the estimator which is the minimum of all the estimators which we obtain by pooling some sums of squares for factorial effects. Under squared error loss, we discuss whether or not this estimator uniformly improves upon the best positive multiple of error sum of squares. We show that when we have two factorial effects, we obtain uniform improvement. However, we show that when we have more than two factorial effects, we cannot necessarily obtain uniform improvement. Further, the above results are applied to the problem of estimating the smallest scale parameter of chi-square distributions.     

On the maximum total sample size of a group sequential test about bivariate binomial proportions

For testing “univariate” binomial proportions, it has been proven that, under mild conditions, there exist group sequential designs which satisfy the pre-specified Type I error and power of the single-stage design while the sample size is bounded above by that of the single-stage design (Kepner and Chang, 2003). In this article, we extend this result and prove the existence of such group sequential designs for various decision rules in the space of bivariate binomial variables. We also demonstrate how to obtain the actual group sequential designs for detecting changes in bivariate binomial variables.     

混料切片试验设计

混料试验设计在众多领域中都有广泛的应用,有时试验者不仅仅需要考虑各混料成分所占比例对响应变量的影响,同时还关心其它被称为过程变量的因素.在实际中,对于这类问题通常使用的设计方案是混料设计和因子设计的组合设计.这种组合设计在过程变量的不同水平组合下,使用的是相同的设计阵,因此空间填充性较差.基于混料球体堆积设计,文章提出了一类新的混料设计,称之为混料切片设计,它的整体设计和所有子设计(过程变量的每一水平组合对应的混料设计)都具有很好的空间填充性,从而比组合设计有更好的模型稳健性.基于同余子群的陪集分解方法,针对过程变量水平组合数的不同情况提出了相应的简单快速的构造算法,文章最后的数值例子解释了算法的可行性和设计的有效性.     

无重复因析试验中一种估计散度效应的方法

自从Box和Meyer首次提出无重复因析试验中散度效应的识别和估计问题, 各种散度效应的估计方法(包括迭代和非迭代)被提出. 特别地, Brenneman 和Nair 给出了这些方法的一个综述, 并且他们验证了改进的Harvey方法优于其它的方法.本文中对于对数线性模型, 一个基于多个位置模型残差平均的非迭代的散度效应估计方法在模型选择阶段被提出. 在大多数的模拟实验模型中, 本文方法具有比MH方法更小的均方误差, 且它可以应用于MH方法不适用的0或小的绝对残差情形. 我们也考虑了这个估计的理论性质, 并进行了实例分析.     

两水平无重复因析试验散度效应BH估计的性质

本文研究了两水平无重复因析试验散度效应BH估计的性质,给出了BH估计无偏性的充分必要条件,求得了它的近似方差.并在多个模型下对BH与MH估计进行了模拟比较.