Página 1 dos resultados de 7924 itens digitais encontrados em 0.412 segundos

Applying design of experiments (DOE) to flavonoid extraction from Passiflora alata and P. edulis

Noriega, Peky; Mafud, Débora de Freitas; Souza, Bruna de; Soares-Scott, Marta; Rivelli, Diogo Pineda; Barros, Silvia Berlanga de Moraes; Bacchi, Elfriede Marianne
Fonte: Sociedade Brasileira de Farmacognosia Publicador: Sociedade Brasileira de Farmacognosia
Tipo: Artigo de Revista Científica
Português
Relevância na Pesquisa
95.6%
The Passifloraceae family is extensively used in native Brazilian folk medicine to treat a wide variety of diseases. The problem of flavonoid extraction from Passiflora was treated by application of design of experiments (DOE), as an experiment with mixture including one categorical process variable. The components of the binary mixture were: ethanol (component A) and water (component B); the categorical process variable: extraction method (factor C) was varied at two levels: (+1) maceration and (-1) percolation. ANOVA suggested a cubic model for P. edulis extraction and a quadratic model for P. alata.These results indicate that the proportion of components A and B in the mixture is the main factor involved in significantly increasing flavonoid extraction. In regard to the extraction methods, no important differences were observed, which indicates that these two traditional extraction methods could be effectively used to extract flavonoids from both medicinal plants. The evaluation of antioxidant activity of the extract by ORAC method showed that P. edulis displays twice as much antioxidant activity as P. alata. Considering that maceration is a simple, rapid and environmentally friendly extraction method, in this study, the optimized conditions for flavonoid extraction from these Passiflora species is maceration with 75% ethanol for P. edulis and 50% ethanol for P. alata.

Otimização de comprimidos matriciais de liberação prolongada de teofilina aplicando o planejamento estatístico de mistura; Opitimization of controlled release matrix tablets of theophylline using design of experiments

Ojoe, Evelyn
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: Tese de Doutorado Formato: application/pdf
Publicado em 14/04/2008 Português
Relevância na Pesquisa
75.65%
Foram produzidos comprimidos de liberação prolongada de teofilina baseados em matrizes hidrofílicas de misturas de hidroxipropilmetilcelulose e etilcelulose e polietilenoglicol. O planejamento estatístico de mistura Design Expert® foi empregado na seleção da composição do sistema de controle da liberação e, numa segunda fase, para otimização das formulações de comprimidos. Foram produzidas 26 formulações por compressão direta e as características físico-químicas dos comprimidos como peso médio, friabilidade, dureza e teor de fármaco foram determinadas. A porcentagem de teofilina liberada foi avaliada conforme o método da Farmacopéia Americana 30 ed. (2007), para cápsulas de liberação prolongada (Teste 10 - pá), por um período de 8 horas. Conforme as farmacopéicas os comprimidos produzidos apresentaram características físico-químicas de acordo com as especificações, com exceção das formulações 2 e 3, para o teste de friabilidade, cujos valores foram superiores. Entretanto, quanto ao ensaio de dissolução, a formulação 13, constituída por 30% de etilcelulose, atendeu aos valores preconizados para liberação prolongada de teofilina. As respostas obtidas dos experimentos foram introduzidas no programa Design Expert® que gerou superfícies de respostas nas quais foi possível avaliar a influência da composição nos parâmetros friabilidade e porcentagem de teofilina liberada na dissolução. Dessa forma...

Formulação e otimização de uma mistura de inibidores de corrosão para aço carbono em meio de água de resfriamento industrial usando planejamento estatístico.; Obtention the optimum formulation of substances tested as corrosion inhibitors for carbon steel in water-cooling systems using design of experiments.

Bueno, Glorys Coromoto Villarroel de
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: dissertação de mestrado Formato: application/pdf
Publicado em 24/10/2008 Português
Relevância na Pesquisa
95.64%
O objetivo deste trabalho foi formular e otimizar uma mistura de quatro substâncias atóxicas como inibidores de corrosão para o aço carbono ABNT 1005 em meio de água de resfriamento industrial. As substâncias estudadas foram o molibdato de sódio, o tungstato de sódio, a ftalocianina de cobre e um tensoativo polimérico a base de silano de peso molecular 17.000 g.mol-1. As técnicas usadas neste estudo foram medidas de potencial de corrosão, espectroscopia de impedância eletroquímica e curva de polarização anódicas e catódicas. O tratamento dos resultados de espectroscopia de impedância eletroquímica foi feito por meio da modelagem com circuitos elétricos equivalentes, que permitiu quantificar parâmetros como resistência a transferência e carga (Rtc) e capacitância dupla camada elétrica, (Cdl). Para caracterizar a superfície do metal foram obtidas imagens por microscopia eletrônica de varredura, onde foi comprovada a alteração da superfície pela presença das substâncias estudadas. Pelas curvas de polarização foi verificado que todas as substâncias estudadas se comportam como inibidores de corrosão anódicos no meio estudado, isto é, diminuem a velocidade de dissolução do metal na presença de maiores concentrações. O uso de um projeto fatorial completo...

Planejamento de experimentos com várias replicações em paralelo em grades computacionais; Towards distributed simulation design of experiments on computational grids

Pereira Júnior, Lourenço Alves
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: dissertação de mestrado Formato: application/pdf
Publicado em 07/06/2010 Português
Relevância na Pesquisa
85.64%
Este trabalho de mestrado apresenta um estudo de Grades Computacionais e Simulações Distribuídas sobre a técnica MRIP. A partir deste estudo foi possível propor e implementar o protótipo de uma ferramenta para Gerenciamento de Experimento em Ambiente de Grade, denominada Grid Experiments Manager - GEM, organizada de forma modular podendo ser usada como um programa ou integrada com outro software, podendo ser expansível para vários middlewares de Grades Computacionais. Com a implementação também foi possível avaliar o desempenho de simulações sequenciais com aquelas executadas em cluster e em uma Grade Computacional de teste, sendo construído um benchmark que possibilitou repetir a mesma carga de trabalho para os sistemas sobre avaliação. Com os testes foi possível verificar um ganho alto no tempo de execução, quando comparadas as execuções sequenciais e em cluster, obteve-se eficiência em torno de 197% para simulações com tempo de execução baixo e 239% para aquelas com tempo de execução maior; na comparação das execuções em cluster e em grade, obteve-se os valores para eficiência de 98% e 105%, para simulações pequenas e grandes, respectivamente; This master's thesis presents a study of Grid Computing and Distributed Simulations using the MRIP approach. From this study was possible to design and implement the prototype of a tool for Management of Experiments in Grid Environment...

Desenvolvimento de mecanismos para automatização de planejamento e execução de experimentos em sistemas orientados a serviço; Development of mechanisms for automating the planning and execution of experiments in a service-oriented systems

Nunes, Luiz Henrique
Fonte: Biblioteca Digitais de Teses e Dissertações da USP Publicador: Biblioteca Digitais de Teses e Dissertações da USP
Tipo: dissertação de mestrado Formato: application/pdf
Publicado em 16/06/2014 Português
Relevância na Pesquisa
85.6%
O planejamento de experimentos em sistemas computacionais não é uma tarefa trivial, pois envolve diversas etapas tais como, o planejamento propriamente dito, a execução dos experimentos e a análise dos resultados. A definição e a utilização de metodologias adequadas para cada uma destas etapas facilita a obtenção dos resultados de um experimento em um sistema computacional. Neste trabalho são apresentados mecanismos para auxiliar o planejamento e execução de experimentos em sistemas orientados a serviços. O planejamento de experimento é realizado a partir de um modelo baseado nos conjuntos de entradas comuns a arquiteturas orientadas a serviço. A execução deste planejamento é feita em um ambiente colaborativo real, a qual auxilia a identificação de gargalos que não estão presentes em simulações ou modelos analíticos. Um estudo de caso aplicado na arquitetura WSARCH, possibilitou avaliar seu desempenho e identificar problemas de configuração; The design of experiments in computational systems is not a trivial task as it involves several steps such as planning and execution of the experiments and the analyse of the results. The use of appropriate methodologies for each of these steps makes it easier obtain the experiment results of a computer system. In this dissertation...

Processo de injeção de uma porca plástica : análise e otimização dos parâmetros; Injection process of a plastic nut – analysis and optimization of the parameters

Silva, Dhiego Reichak da
Tipo: trabalho de conclusão de graduação Formato: application/pdf
Português
Relevância na Pesquisa
75.64%
Este trabalho apresenta um estudo dos fatores controláveis de um processo de injeção de porca plástica, aplicando projeto de experimentos, para avaliar o comportamento da resistência à torção da peça injetada. A porca é injetada com poliamida (PA66) com 30% de fibra de vidro. Esta porca é montada em um sensor de velocidade e é responsável por fixar este sensor em alguns automóveis da FIAT. A análise contempla o estudo geral do fluxo de produção do item, buscando todos os possíveis fatores controláveis responsáveis pela alteração final da resistência à torção. Foi aplicado Projeto de Experimentos (Design Of Experiments – DOE), para verificar de uma forma simples e com base estatística quais são os fatores controláveis significativos do processo de injeção. Para isso, foram injetadas amostras para cada uma das combinações de fatores controláveis. A partir dos resultados foi realizada a análise de variância (ANOVA) para determinar os fatores significativos na resistência à torção da porca plástica injetada. Definido os fatores significativos, foram ajustados os valores dos parâmetros (ótimos) do processo para se produzir uma nova amostra e assim poder validar a nova configuração otimizada.; This paper presents a study of the controllable factors of a process of injecting plastic nut...

Planejamento estatístico de experimentos como uma ferramenta para otimização das condições de biossorção de Cu(II) em batelada utilizando-se casca de nozes pecã como biossorvente; Statistical design of experiments as a tool for optimizing the batch conditions of cu (II) biosorption using pecan nutshells as biosorbent

Brasil, Jorge de Lima; Vaghetti, Júlio César Pacheco; Royer, Betina; Santos Júnior, Araci Araújo dos; Simon, Nathália Marcolin; Pavan, Flávio André; Dias, Silvio Luis Pereira; Lima, Éder Cláudio
Tipo: Artigo de Revista Científica Formato: application/pdf
Português
Relevância na Pesquisa
95.66%
In order to reduce the total number of experiments for achieving the highest amount of adsorbed Cu2+ (qmax) using pecan nutshells (Carya illinoensis) as biosorbent, a full 24 factorial design with two central points was carried out (mass of biosorbent- m, pH, initial metallic ion concentration- C0, time of contact- t). In order to continue the optimization of the system, a central composite surface analysis design with two factors and five central points was carried out. The maximum amount of Cu2+ taken up by the pecan nutshells was 20 mg g-1. These results were confirmed by determining a Cu2+ isotherm using the best conditions attained by the statistical design of experiments.

Analysis by design of experiments of distortion potentials in drawn and induction hardened wire

Rocha, Alexandre da Silva; Nunes, Rafael Menezes; Hirsch, Thomas
Tipo: Artigo de Revista Científica Formato: application/pdf
Português
Relevância na Pesquisa
95.6%
In this investigation a DoE (Design of Experiments) analysis of distortion for a typical manufacturing process of pre-straightened, cold drawn and induction hardened AISI 1045 cylindrical steel bars was carried out. A careful characterization of the material, including residual stress states and geometrical changes, was done for the different manufacturing steps. In order to identify effects and correlations on distortion behavior, the investigated variables included the drawing process itself with two different drawing angles, a stress relief treatment, which was applied to one part of the samples, and, finally, induction hardening with two different case depths. Main and statistically significant effects on the distortion of the induction hardened samples were found to be in this order, the drawing angle, the stress relief treatment and the induction hardening depth. It was also found that the distortion potentials are transmitted from the drawing process to further manufacturing steps and, consequently, from one production site to the next.

A DOE based approach for the design of RBF artificial neural networks applied to prediction of surface roughness in AISI 52100 hardened Steel turning

Pontes, Fabrcio Jose; Silva, Messias Borges; Ferreira, Joao Roberto; de Paiva, Anderson Paulo; Balestrassi, Pedro Paulo; Schoenhorst, Gustavo Bonnard
Fonte: Abcm Brazilian Soc Mechanical Sciences & Engineering Publicador: Abcm Brazilian Soc Mechanical Sciences & Engineering
Tipo: Artigo de Revista Científica Formato: 503-510
Português
Relevância na Pesquisa
75.61%
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES); Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq); The use of artificial neural networks for prediction in hard turning has received considerable attention in literature. An often quoted drawback of ANNs is the lack of a systematic way for the design of high performance networks. This study presents a DOE based approach for the design of ANNs of Radial Basis Function (RBF) architecture applied to surface roughness prediction in turning of AISI 52100 hardened steel. Experimental factors are the number of radial units on the hidden layer, the algorithm employed to calculate the spread factor of radial units and the algorithm employed to calculate radial function centers. DOE is employed to select levels of factors that benefit network prediction skills. Experiments with data sets of distinct sizes were conducted and network configurations leading to high performance were identified. ANN models obtained proved capable to predict roughness in accurate, precise and affordable way. Results pointed significant factors for network design and revealed that interaction effects between design parameters have significant influence on network performance for the task proposed. The work concludes that the DOE methodology constitutes a better approach to the design of RBF networks for roughness prediction than the most common trial and error approach.

Application of Design of experiments on the simulation of a process in an automotive industry

Montevechi, José Arnaldo Barra; De Pinho, Alexandra Ferreira; Leal, Fabiano; Marins, Fernando Augusto Silva
Tipo: info:eu-repo/semantics/conferencepaper Formato: 1601-1609
Português
Relevância na Pesquisa
95.7%
The objective of this article is to apply the Design of experiments technique along with the Discrete Events Simulation technique in an automotive process. The benefits of the design of experiments in simulation include the possibility to improve the performance in the simulation process, avoiding trial and error to seek solutions. The methodology of the conjoint use of Design of Experiments and Computer Simulation is presented to assess the effects of the variables and its interactions involved in the process. In this paper, the efficacy of the use of process mapping and design of experiments on the phases of conception and analysis are confirmed. © 2007 IEEE.

Improving a process in a brazilian automotive plant applying process mapping, Design of Experiments and Discrete Events Simulation

Montevechi, José Arnaldo Barra; De Pinho, Alexandre Ferreira; Leal, Fabiano; Marins, Fernando Augusto Silva; Costa, Rafael Florêncio Da Silva
Tipo: info:eu-repo/semantics/conferencepaper Formato: 472-480
Português
Relevância na Pesquisa
95.71%
The objective of this article is to apply the Design of Experiments technique along with the Discrete Events Simulation technique in an automotive process. The benefits of the design of experiments in simulation include the possibility to improve the performance in the simulation process, avoiding trial and error to seek solutions. The methodology of the conjoint use of Design of Experiments and Computer Simulation is presented to assess the effects of the variables and its interactions involved in the process. In this paper, the efficacy of the use of process mapping and design of experiments on the phases of conception and analysis are confirmed.

Optimization of biogas production from Sargassum sp. using a design of experiments to assess the co-digestion with glycerol and waste frying oil

Oliveira, J. V. M.; Alves, M. M.; Costa, J. C.
Fonte: Elsevier Publicador: Elsevier
Tipo: Artigo de Revista Científica
Publicado em //2015 Português
Relevância na Pesquisa
95.6%
A Design of Experiments was adopted to assess the optimal conditions for methane production from the macroalgae Sargassum sp. co-digested with glycerol (Gly) and waste frying oil (WFO). Three variables were tested:% total solids of algae (%TSSargassumsp.), co-substrate concentration (gGly/WFO L-1); and, co-substrate type (Gly or WFO). The Biochemical Methane Potential (BMP) of Sargassum sp. was 181±1 L CH4 kg-1 COD. The co-digestion with Gly and WFO increased the BMP by 56% and 46%, respectively. The methane production rate (k), showed similar behaviour as the BMP, increasing 38% and 19% with Gly and WFO, respectively. The higher BMP (283±18 L CH4 kg-1 COD) and k (65.9±2.1 L CH4 kg-1 COD d-1) was obtained in the assay with 0.5% TS and 3.0 gGly L-1. Co-digestion with glycerol or WFO is a promising process to enhance the BMP from the macroalgae Sargassum sp.

Applying design of experiments (DOE) to flavonoid extraction from Passiflora alata and P. edulis

Noriega,Peky; Mafud,Débora de Freitas; Souza,Bruna de; Soares-Scott,Marta; Rivelli,Diogo Pineda; Barros,Silvia Berlanga de Moraes; Bacchi,Elfriede Marianne
Fonte: Sociedade Brasileira de Farmacognosia Publicador: Sociedade Brasileira de Farmacognosia
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/10/2012 Português
Relevância na Pesquisa
95.6%
The Passifloraceae family is extensively used in native Brazilian folk medicine to treat a wide variety of diseases. The problem of flavonoid extraction from Passiflora was treated by application of design of experiments (DOE), as an experiment with mixture including one categorical process variable. The components of the binary mixture were: ethanol (component A) and water (component B); the categorical process variable: extraction method (factor C) was varied at two levels: (+1) maceration and (-1) percolation. ANOVA suggested a cubic model for P. edulis extraction and a quadratic model for P. alata.These results indicate that the proportion of components A and B in the mixture is the main factor involved in significantly increasing flavonoid extraction. In regard to the extraction methods, no important differences were observed, which indicates that these two traditional extraction methods could be effectively used to extract flavonoids from both medicinal plants. The evaluation of antioxidant activity of the extract by ORAC method showed that P. edulis displays twice as much antioxidant activity as P. alata. Considering that maceration is a simple, rapid and environmentally friendly extraction method, in this study, the optimized conditions for flavonoid extraction from these Passiflora species is maceration with 75% ethanol for P. edulis and 50% ethanol for P. alata.

Applying design of experiments (DOE) to flavonoid extraction from Passiflora alata and P. edulis

Noriega,Peky; Mafud,Débora de Freitas; Souza,Bruna de; Soares-Scott,Marta; Rivelli,Diogo Pineda; Barros,Silvia Berlanga de Moraes; Bacchi,Elfriede Marianne
Fonte: Sociedade Brasileira de Farmacognosia Publicador: Sociedade Brasileira de Farmacognosia
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/10/2012 Português
Relevância na Pesquisa
95.6%
The Passifloraceae family is extensively used in native Brazilian folk medicine to treat a wide variety of diseases. The problem of flavonoid extraction from Passiflora was treated by application of design of experiments (DOE), as an experiment with mixture including one categorical process variable. The components of the binary mixture were: ethanol (component A) and water (component B); the categorical process variable: extraction method (factor C) was varied at two levels: (+1) maceration and (-1) percolation. ANOVA suggested a cubic model for P. edulis extraction and a quadratic model for P. alata.These results indicate that the proportion of components A and B in the mixture is the main factor involved in significantly increasing flavonoid extraction. In regard to the extraction methods, no important differences were observed, which indicates that these two traditional extraction methods could be effectively used to extract flavonoids from both medicinal plants. The evaluation of antioxidant activity of the extract by ORAC method showed that P. edulis displays twice as much antioxidant activity as P. alata. Considering that maceration is a simple, rapid and environmentally friendly extraction method, in this study, the optimized conditions for flavonoid extraction from these Passiflora species is maceration with 75% ethanol for P. edulis and 50% ethanol for P. alata.

Process analysis and optimization mapping through design of experiments and its application to a polymerization process

Pontes,K. V.; Wolf Maciel,M. R.; Maciel,R.; Embiruçu,M.
Fonte: Brazilian Society of Chemical Engineering Publicador: Brazilian Society of Chemical Engineering
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/03/2011 Português
Relevância na Pesquisa
85.6%
The technique of experimental design is used on an ethylene polymerization process model in order to map the feasible optimal region as preliminary information for process optimization. Through the use of this statistical tool, together with a detailed deterministic model validated with industrial data, it is possible to identify the most relevant variables to be considered as degrees of freedom for the optimization and also to acquire significant process knowledge, which is valuable not only for future explicit optimization but also for current operational practice. The responses evaluated by the experimental design approach include the objective function and the constraints of the optimization, which also consider the polymer properties. A Plackett-Burman design with 16 trials is first carried out in order to identify the most important inlet variables. This reduces the number of decision variables, hence the complexity of the optimization model. In order to carry out a deeper investigation of the process, complete factorial designs are further implemented. They provide valuable process knowledge because interaction effects, including highly non-linear interactions between the variables, are treated methodically and are easily observed.

Analysis by design of experiments of distortion potentials in drawn and induction hardened wire

Rocha,Alexandre da Silva; Nunes,Rafael Menezes; Hirsch,Thomas
Fonte: ABM, ABC, ABPol Publicador: ABM, ABC, ABPol
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/04/2012 Português
Relevância na Pesquisa
95.6%
In this investigation a DoE (Design of Experiments) analysis of distortion for a typical manufacturing process of pre-straightened, cold drawn and induction hardened AISI 1045 cylindrical steel bars was carried out. A careful characterization of the material, including residual stress states and geometrical changes, was done for the different manufacturing steps. In order to identify effects and correlations on distortion behavior, the investigated variables included the drawing process itself with two different drawing angles, a stress relief treatment, which was applied to one part of the samples, and, finally, induction hardening with two different case depths. Main and statistically significant effects on the distortion of the induction hardened samples were found to be in this order, the drawing angle, the stress relief treatment and the induction hardening depth. It was also found that the distortion potentials are transmitted from the drawing process to further manufacturing steps and, consequently, from one production site to the next.

Analysis by design of experiments of distortion potentials in drawn and induction hardened wire

Rocha,Alexandre da Silva; Nunes,Rafael Menezes; Hirsch,Thomas
Fonte: ABM, ABC, ABPol Publicador: ABM, ABC, ABPol
Tipo: Artigo de Revista Científica Formato: text/html
Publicado em 01/04/2012 Português
Relevância na Pesquisa
95.6%
In this investigation a DoE (Design of Experiments) analysis of distortion for a typical manufacturing process of pre-straightened, cold drawn and induction hardened AISI 1045 cylindrical steel bars was carried out. A careful characterization of the material, including residual stress states and geometrical changes, was done for the different manufacturing steps. In order to identify effects and correlations on distortion behavior, the investigated variables included the drawing process itself with two different drawing angles, a stress relief treatment, which was applied to one part of the samples, and, finally, induction hardening with two different case depths. Main and statistically significant effects on the distortion of the induction hardened samples were found to be in this order, the drawing angle, the stress relief treatment and the induction hardening depth. It was also found that the distortion potentials are transmitted from the drawing process to further manufacturing steps and, consequently, from one production site to the next.

Objective comparison of design of experiments strategies in design and observations in practice

Freeman, Ion Chalmers, 1968-
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: thesis Formato: 149 p.; 1152528 bytes; 1152722 bytes; application/pdf; application/pdf
Português
Relevância na Pesquisa
95.66%
Design of Experiments (DoE) strategies in robust engineering determine which prototypes and how many of each are created and tested. A better strategy is one that delivers a closer-to-optimal performance at a lower experimental cost. Prototype testers who may use statistical DoE, design-build-test, or one-at-a-time methods in a wide variety of industries were sought out and interviewed to examine the strategies used in practice and how they fit into a proposed five-layer process support model. From these interviews, we see that DoE are competently and widely practiced. Some improvements to the state of the practice may include: contracts to specify and reward quality engineering among suppliers to complex product systems and wider use in light of new computing power of system level mathematical models for experimentation on complex systems. This thesis also examines the relative value of strategies in a particular response surface using a software-based comparator. The data is modified to simulate data environments with other levels of repeatability and interactions, and the way that these variables effect the performance of strategies is examined. The concept of an optimal design of experiments strategy is developed by abstracting the characteristics of a generic strategy and letting it develop in a genetic algorithm in that comparator. The framework for the evaluation of DoE strategies is one significant output to come out of this work that may be of use in future research. Further...

System regularities in design of experiments and their applications

Li, Xiang, Ph. D. Massachusetts Institute of Technology
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: thesis Formato: 156 p.; 678639 bytes; 678045 bytes; application/pdf; application/pdf
Português
Relevância na Pesquisa
85.66%
This dissertation documents a meta-analysis of 113 data sets from published factorial experiments. The study quantifies regularities observed among main effects and multi-factor interactions. Such regularities are critical to efficient planning and analysis of experiments, and to robust design of engineering systems. Three previously observed properties are analyzed - effect sparsity, hierarchy, and heredity. A new regularity on effect synergism is introduced and shown to be statistically significant. It is shown that a preponderance of active two-factor interaction effects are synergistic, meaning that when main effects are used to increase the system response, the interactions provide an additional increase and that when main effects are used to decrease the response, the interactions generally counteract the main effects. Based on the investigation of system regularities, a new strategy is proposed for evaluating and comparing the effectiveness of robust parameter design methods. A hierarchical probability model is used to capture assumptions about robust design scenarios. A process is presented employing this model to evaluate robust design methods.; (cont.) This process is then used to explore three topics of debate in robust design: 1) the relative effectiveness of crossed versus combined arrays; 2) the comparative advantages of signal-to-noise ratios versus response modeling for analysis of crossed arrays; and 3) the use of adaptive versus "one shot" methods for robust design. For the particular scenarios studied...

Sequential optimization through adaptive design of experiments

Wang, Hungjen, 1971-
Fonte: Massachusetts Institute of Technology Publicador: Massachusetts Institute of Technology
Tipo: thesis Formato: 118 p.
Português
Relevância na Pesquisa
75.69%
This thesis considers the problem of achieving better system performance through adaptive experiments. For the case of discrete design space, I propose an adaptive One-Factor-at-A-Time (OFAT) experimental design, study its properties and compare its performance to saturated fractional factorial designs. The rationale for adopting the adaptive OFAT design scheme become clear if it is imbedded in a Bayesian framework: it becomes clear that OFAT is an efficient response to step by step accrual of sample information. The Bayesian predictive distribution for the outcome by implementing OFAT and the corresponding principal moments when a natural conjugate prior is assigned to parameters that are not known with certainty are also derived. For the case of compact design space, I expand the treatment of OFAT by the removal of two restrictions imposed on the discrete design space. The first is that the selection of input level at each iteration depends only on observed best response and does not depend on other prior information. In most real cases, domain experts possess knowledge about the process being modeled that, ideally, should be treated as sample information in its own right-and not simply ignored.; (cont.) Treating the design problem Bayesianly provides a logical scheme for incorporation of expert information. The second removed restriction is that the model is restricted to be linear with pair-wise interactions - implying that the model considers a relatively small design space. I extend the Bayesian analysis to the case of generalized normal linear regression model within the compact design space. With the concepts of c-optimum experimental design and Bayesian estimations...