计算机直接试验设计

根据试验设计的原则，直接按因素－水平的实际组合随机安排若干个试验方案，按五种优良性或均匀性准则从中选出较优者，用回归分析方法分析试验结果．     

两变量随机系数回归模型的最优设计

本文考虑两变量随机系数回归模型在单位正方形设计区域上基于A-,Ds-,I-和D-准则下的最优设计.证明了最优设计可在设计域的顶点处获得,并得到了几类最优设计的解析或数值结果.     

Model Identification for Flow Simulations in Geothermal Reservoirs: Towards Optimally Drilling Boreholes

In geothermal reservoir engineering, one is interested in determining the location of boreholes such that measurements taken therein, say temperature, will allow the estimation of unknown parameters such as porosity and permeability. We formulate such a particular borehole location problem and find its solution by techniques from optimal experimental design. More precisely, we minimize the D-optimality criterion to find an optimal location of a single borehole to estimate hydraulic permeability from temperature measurements in two boreholes. (© 2013 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Optimum ramp-stress accelerated life test for m identical repairable systems

This paper proposes optimum ramp accelerated life test (ALT) of m identical repairable systems using non-homogeneous power law process (PLP) under failure truncated case. An ALT with linearly increasing stress is a ramp test. In particular, a ramp test with two different linearly increasing stresses is a simple ramp test. The optimum ramp test with different stress rates is formulated by determining the proportions of test systems allocated to each stress rate using D-optimality criterion. D-optimality criterion minimizes the reciprocal of the determinant of the Fisher information matrix of the model parameters. The method developed is illustrated using two stress rates and three stress rates. It has been found that it takes much longer to obtain same estimated expected no. of failures at baseline condition than at stress levels.     

Quadrature Methods for Bayesian Optimal Design of Experiments With Nonnormal Prior Distributions

Many optimal experimental designs depend on one or more unknown model parameters. In such cases, it is common to use Bayesian optimal design procedures to seek designs that perform well over an entire prior distribution of the unknown model parameter(s). Generally, Bayesian optimal design procedures are viewed as computationally intensive. This is because they require numerical integration techniques to approximate the Bayesian optimality criterion at hand. The most common numerical integration technique involves pseudo Monte Carlo draws from the prior distribution(s). For a good approximation of the Bayesian optimality criterion, a large number of pseudo Monte Carlo draws is required. This results in long computation times. As an alternative to the pseudo Monte Carlo approach, we propose using computationally efficient Gaussian quadrature techniques. Since, for normal prior distributions, suitable quadrature techniques have already been used in the context of optimal experimental design, we focus on quadrature techniques for nonnormal prior distributions. Such prior distributions are appropriate for variance components, correlation coefficients, and any other parameters that are strictly positive or have upper and lower bounds. In this article, we demonstrate the added value of the quadrature techniques we advocate by means of the Bayesian D-optimality criterion in the context of split-plot experiments, but we want to stress that the techniques can be applied to other optimality criteria and other types of experimental designs as well. Supplementary materials for this article are available online.     

Notes on D-optimal designs

The purpose of this paper is to exhibit new infinite families of D-optimal (0, 1)-matrices. We show that Hadamard designs lead to D-optimal matrices of size (j, mj) and (j − 1, mj), for certain integers j ≡ 3 (mod 4) and all positive integers m. For j a power of a prime and j ≡ 1 (mod 4), supplementary difference sets lead to D-optimal matrices of size (j, 2mj) and (j − 1, 2mj), for all positive integers m. We also show that for a given j and d sufficiently large, about half of the entries in each column of a D-optimal matrix are ones. This leads to a new relationship between D-optimality for (0, 1)-matrices and for (±1)-matrices. Known results about D-optimal (±1)-matrices are then used to obtain new D-optimal (0, 1)-matrices.     

Optimum design in the presence of parametric uncertainty

A new class of optimal design problems that incorporates environmental uncertainty is formulated and related to worst-case design, minimax objective design, and game theory. A numerical solution technique is developed and applied to a weapon allocation problem, a structural design problem with an infinite family of load conditions, and a vibration isolator design problem with a band of excitation frequencies.     

无穷方差厚尾过程变点的小波估计

研究随机设计下噪声为厚尾随机变量时非参数函数中的变点估计问题.首先,通过设计变换将随机设计转化为等间距固定设计,进而利用小波方法估计变换后的变点的位置,再利用逆设计变换求得随机设计下变点位置的估计,并给出估计的收敛速度.模拟研究结果说明对于无穷方差厚尾过程中的变点估计问题小波方法是有效的.     

Airfoil design optimization using the Navier-Stokes equations

A design optimization technique is presented which couples a computationally efficient Navier-Stokes code with a numerical optimization algorithm. The design method improves the aerodynamic performance of an airfoil subject to specified design objectives and constraints. Recent advances in computers and compputational fluid dynamics have permitted the use of the Navier-Stokes equations in the design procedure to include the nonlinear, rotational, viscous physics of transonic flows. Using numerical optimization guarantees that a better design will be produced even with strict design constraints. The method is demonstrated with several examples at transonic flow conditions.     

基于APL的EWMA控制图经济统计优化设计

为了提高指数加权移动平均(EWMA)控制图监控效率评价的精确性和全面性,提出用一个质量周期内的平均产品个数替代平均抽样个数来进行控制图的经济性和统计性综合评价,建立了一种基于平均产品长度(APL)的更为精确的EWMA控制图经济统计多目标优化设计模型,并采用具体的算例说明了采用NSGA-Ш算法对该模型进行计算的步骤。最后,用该方法优化设计的EWMA控制图与已有的几种EWMA控制图优化设计进行比较,结果表明:本文提出的经济统计优化设计方法显著优于只考虑经济性能的经济设计和只考虑统计性能的统计设计方案。     

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.     

均衡随机分组设计的研究

均衡随机分组设计是一种把随机抽样设计与显著性检验相结合的试验设计方法.试验设计可以避免完全随机抽样(或完全随机分组)设计可能会造成所分组间存在较大差异的缺点,保证所分组或样本间具有均衡性,确保抽样的科学性和可比性,以增强对处理效果反应的灵敏度,提高试脸的准确度.     

A new methodology for evaluating sustainable product design performance with two-stage network data envelopment analysis

Sustainable product design has been considered as one of the most important practices for achieving sustainability. To improve the environmental performances of a product through product design, however, a firm often needs to deal with some difficult technical trade-offs between traditional and environmental attributes which require new design concepts and engineering specifications. In this paper, we propose a novel use of the two-stage network Data Envelopment Analysis (DEA) to evaluate sustainable product design performances. We conceptualize “design efficiency” as a key measurement of design performance in terms of how well multiple product specifications and attributes are combined in a product design that leads to lower environmental impacts or better environmental performances. A two-stage network DEA model is developed for sustainable design performance evaluation with an “industrial design module” and a “bio design module.” To demonstrate the applications of our DEA-based methodology, we use data of key engineering specifications, product attributes, and emissions performances in the vehicle emissions testing database published by the US EPA to evaluate the sustainable design performances of different automobile manufacturers. Our test results show that sustainable design does not need to mean compromise between traditional and environmental attributes. Through addressing the interrelatedness of subsystems in product design, a firm can find the most efficient way to combine product specifications and attributes which leads to lower environmental impacts or better environmental performances. This paper contributes to the existing literature by developing a new research framework for evaluating sustainable design performances as well as by proposing an innovative application of the two-stage network DEA for finding the most eco-efficient way to achieve better environmental performances through product design.     

Construction of uniform designs without replications

A uniform design scatters its design points evenly on the experimental domain according to some discrepancy measure. In this paper all the design points of a full factorial design can be split into two subdesigns. One is called the complementary design of the other. The complementary design theories of characterizing one design through the other under the four commonly used discrepancy measures are investigated. Based on these complementary design theories, some general rules for searching uniform designs through their complementary designs are proposed. An efficient method to check if a design has repeated points is introduced and a modified threshold-accepting algorithm is proposed to search uniform or nearly uniform designs without replications. The new algorithm is shown to be more efficient by comparing with other existing methods. Many new uniform or nearly uniform designs without replications are tabulated and compared.     

Optimal design of multi-purpose beam-columns

The paper deals with the optimal design of an elastic pinended member of given volume that is to serve as a beam for a part of its design life and as a column for the rest. The optimal design can be interpreted in two ways. Firstly, it is the design that has the maximum Euler buckling load in column action, subject to a prescribed maximum deflection as a beam. Secondly, it is the design that has the least deflection as a beam under a midspan concentrated load, subject to a minimum permissible Euler buckling load in column action. The effectiveness of the optimal design is judged by comparing it with a prismatic bar of the same volume.     

Joint optimization of product family configuration and scaling design by Stackelberg game

Product family design is generally characterized by two types of approaches: module-based and scale-based. While the former aims to enable product variety based on module configuration, the latter is to variegate product design by scaling up or down certain design parameters. The prevailing practice is to treat module configuration and scaling design as separate decisions or aggregate two design problems as a single-level, all-in-one optimization problem. In practice, optimization of scaling variables is always enacted within a specific modular platform; and meanwhile an optimal module configuration depends on how design parameters are to be scaled. The key challenge is how to deal with explicitly the coupling of these two design optimization problems.     

Optimal design of double layer scallop domes using genetic algorithm

An efficient methodology is proposed for optimal design of large-scale domes with various topologies and dimensions in plan. The major concern with the optimal design of large domes is the difficulties arising from plurality of design variables, i.e., size and shape variables. This complexity has propounded the optimal design problem of large scale domes as a great challenge over the years. Thus, in current study, extending the novel idea of using parametric mathematical functions, design variables are correlated to the geometrical properties of domes through a new point of view. Additionally, a modified sizing approach is taken up while treating with element sections. In this way, the number of design variables is decreased. Consequently, fewer numbers of these variables provides an impressive condition that considerably takes down the computational efforts needed to explore the design space for finding the solution of optimization problem. Optimization task is performed by the robust technique of genetic algorithm. The presented approach is applicable to a wide variety of enormous domes with outsized number of nodes and members. However, to show applicability as well as computational advantages of the presented algorithm, a numerical example of scallop domes is investigated.     

Approximate and Widespread Pareto Solutions in the Structure-Control Design of Mechatronic Systems

The structure-control design approach of mechatronic systems requires a different design formulation where the mechanical structure and control system are simultaneously designed. Optimization problems are commonly stated to confront the structure-control design formulation. Nevertheless, these problems are often very complex with a highly nonlinear dependence between the design variables and performance functions. This fact has made the use of evolutionary algorithms, a feasible alternative to solve the highly nonlinear optimization problem; the method to find the best solution is an open issue in the structure-control design approach. Hence, this paper presents a mechanism to exhaustively exploit the solutions in the differential evolution (DE) algorithm in order to find more non-dominated solutions with uniformly distributed Pareto front and better trade-offs in the structure-control design framework. The proposed approach adopts an external population to retain the non-dominated solutions found during the evolutionary process and includes a mechanism to mutate the individuals in their corresponding external population region. As a study case, the structure-control design of a serial-parallel manipulator with its control system is stated as a dynamic optimization problem and is solved by using the proposed approach. A comparative analysis shows that the multi-objective exhaustive exploitation differential evolution obtained a superior performance in the structure-control design framework than a DE algorithm which did not consider the proposal. Hence, the resulting designs provide better trade-offs between the structure-control performance functions.