Showing papers on "Orthogonal array published in 1990"
TL;DR: In this article, a fractional factorial orthogonal array (FELF) is used for location effects and a design projection is proposed for sequential experimentation in FIFO factorial arrays.
Abstract: @Key Words: Fractional factorial; Orthogonal array; Location effects; Dispersion effects; Design projection; Sequential experimentation.
74 citations
TL;DR: Interaction graphs are graphical aids to plan fractional factorial experiments as discussed by the authors, which can be used to generate a plan from an orthogonal array by selecting certain columns of the orthogonality and deleting the rest.
Abstract: Interaction graphs are graphical aids to plan fractional factorial experiments. A fractional factorial plan can be generated from an orthogonal array by selecting certain columns of the orthogonal array and deleting the rest. Interaction graphs are grap..
48 citations
Book•
31 Aug 1990
TL;DR: The Concept of Quality Concurrent Statistics Noise Taking Aim at Noise Building the Quality In Parameter design Tolerence Design Parameter Design Making the Experimental Effort Viable.
Abstract: The Concept of Quality Concurrent Statistics Noise Taking Aim at Noise---An Arsenal of Experimental Tools Building the Quality In---The Parameter Design Tolerence Design Parameter Design---Making the Experimental Effort Viable Special Topics Examples of Engineering Quality by Design in Action Orthogonal Array Structures for Experimental Designs
44 citations
Patent•
02 Jan 1990TL;DR: In this paper, a facility is provided for generating from a series of parameters (factors) and their respective values (levels) inputted by a user a plurality of test cases using an orthogonal array selected from a library of such arrays, in which the selection is optimized by characterizing the arrays by respective cumulative level vectors and converting the user input into a cumulative level input vector.
Abstract: A facility is provided for generating from a series of parameters (factors) and their respective values (levels) inputted by a user a plurality of test cases using an orthogonal array selected from a library of such arrays, in which the selection is optimized by characterizing the arrays by respective cumulative level vectors and converting the user input into a cumulative level input vector. The smallest array for generating the test cases is then selected on the basis that the values of the input vector are no larger than the corresponding values of the cumulative level vector characterizing the selected array.
28 citations
TL;DR: A concern expressed in the literature about Genichi Taguchi's methods for experimental design is that many such designs are not optimal in the sense that they are not the maximum resolution possible for a given number of main effects and array size.
Abstract: A concern expressed in the literature about Genichi Taguchi's methods for experimental design is that many such designs are not optimal in the sense that they are not the maximum resolution possible for a given number of main effects and array size. Thi..
25 citations
Journal Article•
TL;DR: In this paper, an extended class of geometrically orthogonal designs of linear regression models is defined and studied, which includes all well-behaved ANOVA and regressions designs.
Abstract: Tjur (1984) showed that an orthogonal (=balanced) analysis of variance (ANOVA) design may be described and analysed in terms of an associated factor structure diagram. In this paper an extended class of orthogonal designs is defined and studied, the class of geometrically orthogonal designs of linear regression models, which includes all well-behaved ANOVA and regressions designs. It is shown that such designs may be characterized and analysed most naturally in terms of the lattice structure of L, the family of regression subspaces in the design. Any such design may be extended in a natural way to a family of canonical variance component models, called a geometrically orthogonal variance component design
17 citations
01 May 1990
TL;DR: A method of yield gradient estimation is proposed, based on the orthogonal array approach to the design of experiments, which is applied to stochastic approximation based parametric yield optimization.
Abstract: A method of yield gradient estimation is proposed. It is based on the orthogonal array approach to the design of experiments. The method is related to the G. Taguchi (1987) philosophy of off-line quality control but is much more efficient. The method is applied to stochastic approximation based parametric yield optimization. Several test and circuit examples are presented. >
15 citations
01 Jul 1990
TL;DR: A systematic methodology based on Taguchi methods to determine and optimize a machine vision system's capability and the response surface plots were provided for a user to choose an alternative.
Abstract: This paper presents a systematic methodology based on Taguchi methods to determine and optimize a machine vision system's capability. Seven factors were studied in anL
27(313) orthogonal array: lens type, color of the background, distance between two objects on the target, distance between the camera and the target, filter, lighting source, and angle between the optic axis of the camera and the surface of the target. The optimal factor-level combination was determined from the experiment results, and the response surface plots were provided for a user to choose an alternative. Because this Taguchi methods-based methodology is simple and effective, it is recommended for determining and optimizing a machine vision system's capability.
10 citations
01 Jan 1990
TL;DR: The proposed theory is applied to describe a number of well known interconnection networks such as the binary m-cube and spanning-bus meshes and Multi-dimensional access (MDA) memories are shown as examples of orthogonal shared memory multi-processing systems.
Abstract: A graph theoretical representation for a class of interconnection networks is suggested. The idea is based on a definition of orthogonal binary vectors and leads to a construction rule for a class of orthogonal graphs. An orthogonal graph is first defined as a set of 2m nodes, which in turn are linked by 2m-n edges for every link mode defined in an integer set Q*. The degree and diameter of an orthogonal graph are determined in terms of the parameters n, m and the number of link modes defined in Q*. Routing in orthogonal graphs is shown to reduce to the node covering problem in bipartite graphs. The proposed theory is applied to describe a number of well known interconnection networks such as the binary m-cube and spanning-bus meshes. Multi-dimensional access (MDA) memories are shown as examples of orthogonal shared memory multi-processing systems.
5 citations
TL;DR: It is proved that there is a perpendicular array PA( n, 7) for all odd n ⩾2129, and it is shown that this condition is sufficient when the number of points is at least 2129, with at most 103 possible exceptions below this value.
TL;DR: In this article, rank tests for non-additive models in the two-way layout with n levels of each factor were developed, and the rank tests were then computed on the resulting sums.
Abstract: One of the major unresolved problems in the area of nonparametric statistics is the need for satisfactory rank-based test procedures for non-additive models in the two-way layout, especially when there is only one observation on each combination of the levels of the experimental factors. In this paper we consider an arbitrary non-additive model for the two-way layout with n levels of each factor. We utilize both alignment and ranking of the data together with basic properties of Latin squares to develop rank tests for interaction (non-additivity). Our technique involves first aligning within one of the main effects, ranking within the other main effects (columns and rows) and then adding the resulting ranks within “interaction bands” corresponding to orthogonal partitions of the interaction for the model, as denoted by the letters of an n × n Latin square. A Friedman-type statistic is then computed on the resulting sums. This is repeated for each of (n−1) mutually orthogonal Latin squares (thus accounting...
TL;DR: Through the use of mutually orthogonal frequency squares, a generalization of the original Golomb-Posner code is constructed and the minimum distance and weight distribution are determined.
Abstract: Through the use of mutually orthogonal frequency squares, a generalization of the original Golomb-Posner code is constructed. The minimum distance and weight distribution of the generalized code when it is constructed from a complete set of orthogonal squares over a finite field are also determined. >
TL;DR: With these extensions and improvements the Box-Meyer method becomes viable as a technique for interactive analysis of any orthogonal factorial design, not just small, saturated ones.
Abstract: Box and Meyer (1986) [1] proposed a Bayesian analysis for saturated orthogonal dedigns, based on the widely-used method of examining normal plots of effects estimates. Stephenson, Hulting, and Moore (1989) [5] give an algorithm for computing this analysis, but it can be quite slow for even 25 designs. In this paper we extend the technique to cover all orthogonal factorial designs, rather than just saturated ones, and we show how the computational algorithm can be greatly improved, both in terms of accuracy and speed. With these extensions and improvements the Box-Meyer method becomes viable as a technique for interactive analysis of any orthogonal factorial design, not just small, saturated ones.
01 Jan 1990
TL;DR: An algorithm for solving constrained optimization problems is presented, and for problems in which gradients would have to be estimated using finite-differences the number of function evaluations required for the optimization is significantly reduced, when compared with traditional nonlinear programming techniques.
Abstract: An algorithm for solving constrained optimization problems is presented. First, design of experiment techniques are used to survey the design space. After evaluating the objective and constraint functions, as specified by Taguchi orthogonal arrays, analytical models of these functions are generated using a least-squares regression analysis. Next, a nonlinear programming package is used to optimize the analytical model. Based on the optimization information, the design space is reduced so as to close in around the minimum, and the entire procedure is repeated until convergence. An important feature of the algorithm is that function gradients are not required; therefore, for problems in which gradients would have to be estimated using finite-differences the number of function evaluations required for the optimization is significantly reduced, when compared with traditional nonlinear programming techniques. In addition, there is no requirement that the gradients must be smooth and continuous.
05 Nov 1990
TL;DR: An extension of the Smith construction for self orthogonal array codes is presented, where the information bit array, originally two dimensional, now becomes multidimensional.
Abstract: An extension of the Smith construction for self orthogonal array codes is presented. The information bit array, originally two dimensional, now becomes multidimensional. Array codes obtained with this construction are not self orthogonal. Decoding is rather more complex, but the codes are more efficient (have higher rates) than those of the Smith construction.
TL;DR: In this paper, complete OA(n,m,s,t) with s = 2 (levels) and general t; and with t = 2, 3 and general s.