Evaluating alternative system configurations using simulation: A nonparametric approach

The real utility of simulation lies in comparing different alternatives that might represent competing system designs. Conventional statistical techniques are not directly applicable to the analysis of simulation output data in the evaluation of competing alternatives since the usual assumptions of normality and common variance are difficult to justify in simulation experiments. This paper revisits a known nonparametric test whose application has recently become feasible due to considerable increases in computing power:randomization tests assess the significance of the observed value of the test statistic by evaluating different permutations of the data. The procedure only requires invariance of the data under all permutations.     

Combinatorial data analysis: Confirmatory comparisons between sets of matrices

The task of assessing the similarity of pattern between the entries of two square matrices has been discussed extensively over the last decade, as a unifying strategy for approaching a variety of seemingly disparate statistical problems. As typically defined, the comparison depends on a measure of matrix correspondence, usually a normalized cross-product measure of some form, that is evaluated for relative size by the use of a reference distribution constructed through an equally likely permutation hypothesis defined at the level of the objects corresponding to the rows and columns of the two matrices. The extreme generality provided by this very simple framework subsumes a variety of different statistical problems, ranging from the study of spatial autocorrelation for variables observed over a set of geographic locations, to the topics of analysis of variance, the measurement of rank correlation, and confirmation techniques concerned with various conjectures of combinatorial structure that might be posited for an empirically determined measure of relationship between pairs of a given set of objects. The comparison strategies extant always assume that both matrices are fixed, and in those cases where one of the matrices codifies a given theoretical structure to be evaluated according to a second, this assumption can lead to substantial arbitrariness in how matrix similarity might be indexed, and thus, in how the comparison is implemented. As developed in this paper, exactly the same principles appropriate for use in the fixed comparison context can be extended to include matrices constructed through optimally weighted linear combinations of other sets of matrices. This generalization provides one mechanism for developing comparison strategies that allow assessment against very broad classes of matrices, which in turn serve to represent very general conjectures of possible combinatorial structure. This paper reviews some of these extensions in detail, with a particular emphasis on categorical and ordered categorical variables and whether they may reflect an empirically generated measure of object relationship.     

On the second law of thermodynamics

The second law of thermodynamics has two distinct aspects to its foundations. The first concerns the question of why entropy goes up in the future, and the second, of why it goes down in the past. Statistical physicists tend to be more concerned with the first question and with careful considerations of definition and mathematical detail. The second question is of quite a different nature; it leads into areas of cosmology and quantum gravity, where the mathematical and physical issues are ill understood.     

Testing Hypotheses About the Power Law Process Under Failure Truncation Using Intrinsic Bayes Factors

Conventional Bayes factors for hypotheses testing cannot typically accommodate the use of standard noninformative priors, as such priors are defined only up to arbitrary constants which affect the values of the Bayes factors. To circumvent this problem, Berger and Pericchi (1996, J. Amer. Statist. Assoc., 19, 109-122) introduced a new criterion called the Intrinsic Bayes Factor (IBF). In this paper, we use their methodology to test several hypotheses regarding the shape parameter of the power law process. Assuming that we have data from the process according to the failure-truncation sampling scheme, we derive the arithmetic and geometric IBF's using the reference priors. We deduce a set of intrinsic priors that correspond to these IBF's, as the observed number of failures tends to infinity. We then use these results to analyze an actual data set on the failures of an aircraft generator.     

Some test statistics for the structural coefficients of the multivariate linear functional relationship model

Summary For the testing problem concerning the coefficients of the multivariate linear functional relationship model, the distribution of a statistic previously proposed by A. P. Basu depends on the unknown covariance matrixV of errors, so limiting its applicability. This article proposes new test statistics with sampling distributions which are independent of the unknown parameters for the cases whereV is either unknown or known only up to a proportionality factor. The exact distributions of the test statistics are also discussed.     

Strain gage evaluation with four-point bending at moderate temperatures

This paper describes the application of the traditional four-point bending technique to conduct strain gage performance tests at moderate temperatures. The tests measure the apparent strain, linearity, drift, creep and hysteresis behavior to ascertain the reliability of strain gages to be used in the testing of experimental cylindrical vessels subjected to thermal loading. The four-point bending rig was designed to take advantage of the advances in personal computer datalogging and graphical processing software. The test rig is designed to provide a thermal barrier to minimize the heat losses and thermal isolation of the test beam while maintaining structural continuity. A low wattage and lightweight electric foil heater incorporating a precise temperature controller minimizes weight and enhances temperature stability. Gage performance data on five candidate strain gages at temperatures ranging from ambient to 215°C (419°F) are presented, and the evaluation procedure is outlined. The strain gage with the most acceptable performance was identified within the validity limits from ambient to a temperature of 215°C and from zero to a maximum strain of 1000 .     

Laboratory optimization of the soil digging process

A new idea for the optimization of digging using earth-working machinery is presented and experimentally verified. This idea is based on the conclusions derived from previous papers presented by the same authors, that the soil cutting trajectories incorporating the generated shear band as a part of them are the optimal ones. Dividing the whole excavation task into several repeatable cycles for which the soil free boundary before and after the experiment are similar the optimization of a single cycle plays a significant role in the energetic efficiency of the whole task. A single cycle of the working process is defined using several basing parameters. The influence of each parameter on the specific unit energy of the process was experimentally verified. Finally, a set of values for the discussed parameters is recommended for the particular soil and tool shape.     

Gas Flow in Porous Media With Klinkenberg Effects

Gas flow in porous media differs from liquid flow because of the large gas compressibility and pressure-dependent effective permeability. The latter effect, named after Klinkenberg, may have significant impact on gas flow behavior, especially in low permeability media, but it has been ignored in most of the previous studies because of the mathematical difficulty in handling the additional nonlinear term in the gas flow governing equation. This paper presents a set of new analytical solutions developed for analyzing steady-state and transient gas flow through porous media including Klinkenberg effects. The analytical solutions are obtained using a new form of gas flow governing equation that incorporates the Klinkenberg effect. Additional analytical solutions for one-, two- and three-dimensional gas flow in porous media could be readily derived by the following solution procedures in this paper. Furthermore, the validity of the conventional assumption used for linearizing the gas flow equation has been examined. A generally applicable procedure has been developed for accurate evaluation of the analytical solutions which use a linearized diffusivity for transient gas flow. As application examples, the new analytical solutions have been used to verify numerical solutions, and to design new laboratory and field testing techniques to determine the Klinkenberg parameters. The proposed laboratory analysis method is also used to analyze data from steady-state flow tests of three core plugs from The Geysers geothermal field. We show that this new approach and the traditional method of Klinkenberg yield similar results of Klinkenberg constants for the laboratory tests; however, the new method allows one to analyze data from both transient and steady-state tests in various flow geometries.     

Stress and Strain Analysis of Pipelines with Localized Metal Loss

This paper presents the analysis of stress and strain data acquired with the finite element method and with tests that used post-yielding strain gages bonded onto the external surface of pipes that suffered thickness metal loss and that had been loaded with internal pressure. These metal loss areas were produced by three different processes: actual internal corrosion, careful machining of external patches by spark-erosion, and milling of internal or external patches to simulate limited or extensive strip corrosion defects with depths up to 70% of the pipe’s thickness. Results show that: (1) the extensive longitudinal internal or external defect areas behave as extensive strips with a high degree of freedom to deform elastically and plastically in the circumferential and thickness directions, and (2) large restraints are offered to the longitudinal strains by the non-corroded thick walls parallel to the strip. Using the above experimental observation, a simple mathematical model was developed to predict the burst pressure of pipes with longitudinal extensive and reasonably constant depths of metal loss. This model employed thin-pipe-strength-of-material equations associated to a bulging correction factor, the material’s uniaxial ultimate strength and the von Mises criterion. The onset of plastic collapse predicted by the simple model was successfully compared with results determined from actual hydrostatic tests that were carried out with full scale pipe specimens and from finite element results generated by the use of a commercial program. The developed model was also helpful in showing that the yield and burst behaviors of new or corroded pipeline specimens under laboratory test conditions can be directly compared and extended to the yield and burst behaviors of buried pipeline in field operation.     

Effects of static electric field on the fracture behavior of piezoelectric ceramics

The paper gives an overview on experimental observations of the failure behavior of electrically insulating and conducting cracks in piezoelectric ceramics. The experiments include the indentation fracture test, the bending test on smooth samples, and the fracture test on pre-notched (or pre-cracked) compact tension samples. For electrically insulating cracks, the experimental results show a complicated fracture behavior under electrical and mechanical loading. Fracture data are much scattered when a static electric field is applied. A statistically based fracture criterion is required. For electrically conducting cracks, the experimental results demonstrate that static electric fields can fracture poled and depoled lead zirconate titanate ceramics and that the concepts of fracture mechanics can be used to measure the electrical fracture toughness. Furthermore, the electrical fracture toughness is much higher than the mechanical fracture toughness. The highly electrical fracture toughness arises from the greater energy dissipation around the conductive crack tip under purely electric loading, which is impossible under mechanical loading in the brittle ceramics. The project supported by an RGC grant from the Research Grant Council of the Hong Kong Special Administrative Region, China