Showing papers on "Orthogonal array published in 1987"

Mixed orthogonal arrays for variance estimation with unequal numbers of primary selections per stratum

Abstract: SUMMARY For estimating the variance of nonlinear statistics in large-scale complex surveys, the method of balanced repeated replications has received special attention. The method at present is useful in stratified clustered designs with equal number of primary selections from each stratum. This paper extends the method to general sample designs with arbitrary number of selections from each stratum. It is shown that mixed orthogonal arrays of strength two, or equivalently, equal frequency orthogonal main-effect plans for asymmetrical factorials give a set of balanced subsamples useful in variance estimation.

Off-Line Quality Control In Integrated Circuit Fabrication Using Experimental Design

Abstract: Off-line quality control is a systematic method of optimizing production processes and product designs. It is widely used in Japan to produce high quality products at low cost. The method was introduced to us by Professor Genichi Taguchi who is a Deming-award winner and a former Director of the Japanese Academy of Quality. In this paper we will i) describe the off-line quality control method, and ii) document our efforts to optimize the process for forming contact windows in 3.5 Aim CMOS circuits fabricated in the Murray Hill Integrated Circuit Design Capability Laboratory. In the fabrication of integrated circuits it is critically important to produce contact windows of size very near the target dimension. Windows which are too small or too large lead to loss of yield. The off-line quality control method has improved both the process quality and productivity. The variance of the window size has been reduced by a factor of four. Also, processing time for window photolithography has been substantially reduced. The key steps of off-line quality control are: i) Identify important manipulatable process factors and their potential working levels. ii) Perform fractional factorial experiments on the process using orthogonal array designs. iii) Analyze the resulting data to determine the optimum operating levels of the factors. Both the process mean and the process variance are considered in this analysis. iv) Conduct an additional experiment to verify that the new factor levels indeed give an improvement.

On the inadequacy of the customary orthogonal arrays in quality control and general scientific experimentation, and the need of probing designs of higher revealing power ∗

Abstract: This paper breaks new ground concerning the general problem of factorial experimentation, namely, the identification and estimation of nonnegligible factorial effects (with minimal number of runs), without making the usual unrealistic and artificial assumptions concerning the negligibility of higher order interactions. (In other words, we consider the general factor screening problem when interactions may be present.) Through an example, it is shown that the customary orthogonal arrays fall short of the need. New principles for sieving the set of factorial effects to determine the large ones, are introduced. The concept of ‘revealing power’of designs, i.e. of their ability to help identify nonnegligible parameters is developed, and the usefulness in this direction of balanced arrays of full strength is studied.

A statistical analysis tool for variation simulation modeling

Abstract: The analysis of an assembly process in the discrete part manufacturing industry usually involves a large number of dimensions. Each dimension tolerance plays a different role with respect to the dimension variation of the final product, which is the so-called “quality”(dimension precision). Furthermore, there are many random factors (noises) present during the assembly operations (tool wear, loose fixture, etc.). Few mathematical models can represent the assembly process. Therefore, computer simulation has been employed. Variation Simulation Modeling uses the Monte Carlo sampling technique to simulate the assembly process. By applying a geometric standard and simulating the physical operations, the statistics of the final product dimensions can be predicted. With the simulation results, statistical analysis is essential to identifying the critical factors (component dimensions). The traditional experimental designs, such as full factorial design, however, are not practical since the number of factors is too large. Taguchi method, which explores a special subset of factor combinations (called the orthogonal array) is able to examine a large number of factors (and interactions) in a much smaller number of experiments. The analysis of variance is performed to ensure the proper selection of significant factors. With this proposed unified tool, engineering understanding and judgement become more effective in making appropriate decisions regarding the product and process designs.

Pairwise Balanced Designs with Prime Power Block Sizes Exceeding 7

Abstract: In this paper, we construct pairwise balanced designs (PBDs) having block sizes which are prime powers exceeding 7. If we denote by P * the set of all prime powers exceeding 7 and by B ( P * ) the set of orders of PBDs of index unity having block sizes from P * , then it is shown that v ∈ .B ( P * ) for all v > 2206 and for many orders less than this value. We also give some applications to the construction of other types of combinatorial designs, such as conjugate orthogonal Latin squares and sets of mutually orthogonal Latin squares (MOLS). For example, it is proved that the spectrum of idempotent Latin squares with distinct and pair-wise orthogonal conjugates contains all orders v mentioned above, and some of the PBDs constructed in this paper can be used to obtain more MOLS of certain orders than previously known.

Analysis of factorial experiments and least squares polynomial fitting by the method of orthogonal polynomials for any spacing of the levels of the independent variables

Abstract: (1987). Analysis of factorial experiments and least squares polynomial fitting by the method of orthogonal polynomials for any spacing of the levels of the independent variables. Journal of Applied Statistics: Vol. 14, No. 1, pp. 83-89.

Filled Image Guide for Millimeter-Wave Circuits

Abstract: In this paper the method of optimal design is dealt with for six parameters selected by the Orthogonal Array Table (OAT). A lot of sets of parameters are presented, by which the filled image guides have optimal propagation properties. The guiding ability is strengthened greatly as the hollow core is filled with another dielectric material.

Group orthogonal arrays for elimination of multiple-time-around echos in radars

Abstract: Sets of group-complementary code arrays which have the property of being ually orthogonal over a subinterval of their total cross-correlation function have been identified. These group-orthogonal arrays are generated by a multiplication operation upon a given group-complementary array using a matrix which has diagonal elements from vectors which are orthogonal. Composite code arrays are synthesized by interleaving rows from the group-orthogonal set of arrays, and applying the resulting rows of codes to bi-phase modulate pulses in bursts. The resulting composite waveform has the desirable property of temporal (zero-Doppler) sidelobe cancellation in the maximum unambiguous range interval and response cancellation over one or more multiple-time-around range intervals of an equivalent uncoded pulse sequence. The waveforms also have the property of maximizing the receiver response in one of the multiple-time-around range intervals, while achieving response cancellation in the maximum unambiguous range interval of an equivalent uncoded pulse sequence.