Chemical engineers frequently try to describe the physical and chemical behavior of processes using mathematical models. These models frequently contain unknown coefficients called parameters. Often these models, due to either phenomenological considerations or heuristic reasoning (such as artificial neural networks), are nonlinear in the unknown parameters. Model complexities are increasing as computer and measurement technologies advance, allowing scientists and engineers to measure and analyze simultaneously several physical quantities (called responses) that share parameter dependencies.Parameters are typically estimated from experimental data by the minimization of a criterion called the objective finction. For complex models, the objective functions are very elaborate, and estimation of model parameters can be a very time-consuming step in model development.Least squares is one of the most, if not the most, widely used objective functions for parameter estimation. However, when observations on several response variables (characteristics of process performance) are taken for the same set of experimental conditions (runs), two critical error term assumptions required by least squares may not be true (Box et al., 1973). These are constant variances and independence between responses. For multiresponse data of this type, the multiresponse model described by Box and Draper (1965) is not limited by these two assumptions. It should be noted that weighted least squares, which minimizes a weighted sums of squares, can be used to account for differences in error variances. However, no version of least squares addresses correlation among response variables in the sense of statistical inference (Ziegel and Gorman, 1980). Despite the advantages of multiresponse modeling over least squares, multiresponse estimation (ME) has not gained wide acceptance and use. Historically, this inconsistency can Correspondence concerning this article should be addressed to D. K. Rollins. AIChE JournalOctober 1995 be attributed to the lack of "special-purpose algorithms" to minimize the objective function (Bates and Watts, 1985) as well as to a lack of understanding of the advantages over least squares just described. Not too long ago, Stewart et al. (1992) discussed in detail some theoretical issues of ME, various properties of four ME algorithms, used an example from chemical kinetics to demonstrate estimation strategy using their algorithm, and reviewed ME applications to several other chemical engineering problems that have appeared in the literature since the late 1960s. The main purposes of this article are to extend the review of Stewart et al. (1992) by comparing the performance of two algorithms, DMRCVG (Bates and Watts, 1984) and GREG (Sorensen, 1982;Caracotsios, 1986;Stewart et al., 1992), and to demonstrate model assessment in this context using residual plots.In order to accomplish these objectives a suitable process and model had to be selected. We chose the three-response, fractionation (wetted wall column), model of Tung e...
Walker, Jennifer Jane, "Development of an empirical model of human sweating and a semi-empirical model of human thermoregulation " (1999). Retrospective Theses and Dissertations. 12180. https://lib.dr.iastate.edu/rtd/12180 INFORMATION TO USERSThis manuscript has been reproduced from the miaofilm master. UMI films the text directly from the original or copy submitted. Thus, some thesis and dissertation copies are In typewriter face, while others may be from any type of computer printer.The quality of this reproduction is dependent upon the quality of the copy submitted. Broken or indistinct print, colored or poor quality illustrations and photographs, print bleedthrough, substandard margins, and improper alignment can adversely affect reproduction.In the unlikely event that the author did not send UMI a complete manuscript and there are missing pages, these will be noted. Also, if unauthorized copyright material had to be removed, a note will indicate the deletion.Oversize materials (e.g., maps, drawings, charts) are reproduced by sectioning the original, beginning at the upper left-hand comer and continuing from left to right in equal sections with small overlaps. Each original is also photographed in one exposure and is included in reduced form at the back of the book.
PACOM lessons learned are applicable to other Geographic Combatant Commands developing a JTTS during Phase Zero operations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.