Based on a practical research test, the statistic analysis method for the experimental data in the split-split plot design was introduced in detail, especially in- troduced the significant test method of three-factor ...Based on a practical research test, the statistic analysis method for the experimental data in the split-split plot design was introduced in detail, especially in- troduced the significant test method of three-factor interaction and the calculation of test value, which solved the problem of how to make statistical analysis on the data in split-split plot design.展开更多
Fractional factorial split-plot design has been widely used in many fields due to its advantage of saving experimental cost. The general minimum lower order confounding criterion is usually used as one of the attracti...Fractional factorial split-plot design has been widely used in many fields due to its advantage of saving experimental cost. The general minimum lower order confounding criterion is usually used as one of the attractive design criterion for selecting fractional factorial split-plot design. In this paper, we are interested in the theoretical construction methods of the optimal fractional factorial split-plot designs under the general minimum lower order confounding criterion. We present the theoretical construction methods of optimal fractional factorial split-plot designs under general minimum lower order confounding criterion under several conditions.展开更多
This paper describes a novel approach to explore a multidimensional design space and guide multi-actor decision making in the design of sustainable buildings.The aim is to provide proactive and holistic guidance of th...This paper describes a novel approach to explore a multidimensional design space and guide multi-actor decision making in the design of sustainable buildings.The aim is to provide proactive and holistic guidance of the design team.We propose to perform exhaustive Monte Carlo simulations in an iterative design approach that consists of tw o steps:1) preparation by the modeler,and 2) a multi-collaborator meeting.In the preparation phase,the simulation modeler performs Morris sensitivity analysis to fixate insignificant model inputs and to identify non-linearity and interaction effects.Next,a representation of the global design space is obtained from thousands of simulations using low-discrepancysequences(LPτ) for sampling.From these simulations,the modeler constructs fast metamodels and performs quantitative sensitivity analysis.During the meeting,the design team explores the global design space by filtering the thousands of simulations.Variable filter criteria are easily applied using an interactive parallel coordinate plot w hich provide immediate feedback on requirements and design choices.Sensitivity measures and metamodels show the combined effects of changing a single input and how to remedy unw anted output changes.The proposed methodology has been developed and tested through real building cases using a normative model to assess energy demand,thermal comfort,and daylight.展开更多
This paper discussed Bayesian variable selection methods for models from split-plot mixture designs using samples from Metropolis-Hastings within the Gibbs sampling algorithm. Bayesian variable selection is easy to im...This paper discussed Bayesian variable selection methods for models from split-plot mixture designs using samples from Metropolis-Hastings within the Gibbs sampling algorithm. Bayesian variable selection is easy to implement due to the improvement in computing via MCMC sampling. We described the Bayesian methodology by introducing the Bayesian framework, and explaining Markov Chain Monte Carlo (MCMC) sampling. The Metropolis-Hastings within Gibbs sampling was used to draw dependent samples from the full conditional distributions which were explained. In mixture experiments with process variables, the response depends not only on the proportions of the mixture components but also on the effects of the process variables. In many such mixture-process variable experiments, constraints such as time or cost prohibit the selection of treatments completely at random. In these situations, restrictions on the randomisation force the level combinations of one group of factors to be fixed and the combinations of the other group of factors are run. Then a new level of the first-factor group is set and combinations of the other factors are run. We discussed the computational algorithm for the Stochastic Search Variable Selection (SSVS) in linear mixed models. We extended the computational algorithm of SSVS to fit models from split-plot mixture design by introducing the algorithm of the Stochastic Search Variable Selection for Split-plot Design (SSVS-SPD). The motivation of this extension is that we have two different levels of the experimental units, one for the whole plots and the other for subplots in the split-plot mixture design.展开更多
文摘Based on a practical research test, the statistic analysis method for the experimental data in the split-split plot design was introduced in detail, especially in- troduced the significant test method of three-factor interaction and the calculation of test value, which solved the problem of how to make statistical analysis on the data in split-split plot design.
文摘Fractional factorial split-plot design has been widely used in many fields due to its advantage of saving experimental cost. The general minimum lower order confounding criterion is usually used as one of the attractive design criterion for selecting fractional factorial split-plot design. In this paper, we are interested in the theoretical construction methods of the optimal fractional factorial split-plot designs under the general minimum lower order confounding criterion. We present the theoretical construction methods of optimal fractional factorial split-plot designs under general minimum lower order confounding criterion under several conditions.
文摘This paper describes a novel approach to explore a multidimensional design space and guide multi-actor decision making in the design of sustainable buildings.The aim is to provide proactive and holistic guidance of the design team.We propose to perform exhaustive Monte Carlo simulations in an iterative design approach that consists of tw o steps:1) preparation by the modeler,and 2) a multi-collaborator meeting.In the preparation phase,the simulation modeler performs Morris sensitivity analysis to fixate insignificant model inputs and to identify non-linearity and interaction effects.Next,a representation of the global design space is obtained from thousands of simulations using low-discrepancysequences(LPτ) for sampling.From these simulations,the modeler constructs fast metamodels and performs quantitative sensitivity analysis.During the meeting,the design team explores the global design space by filtering the thousands of simulations.Variable filter criteria are easily applied using an interactive parallel coordinate plot w hich provide immediate feedback on requirements and design choices.Sensitivity measures and metamodels show the combined effects of changing a single input and how to remedy unw anted output changes.The proposed methodology has been developed and tested through real building cases using a normative model to assess energy demand,thermal comfort,and daylight.
文摘This paper discussed Bayesian variable selection methods for models from split-plot mixture designs using samples from Metropolis-Hastings within the Gibbs sampling algorithm. Bayesian variable selection is easy to implement due to the improvement in computing via MCMC sampling. We described the Bayesian methodology by introducing the Bayesian framework, and explaining Markov Chain Monte Carlo (MCMC) sampling. The Metropolis-Hastings within Gibbs sampling was used to draw dependent samples from the full conditional distributions which were explained. In mixture experiments with process variables, the response depends not only on the proportions of the mixture components but also on the effects of the process variables. In many such mixture-process variable experiments, constraints such as time or cost prohibit the selection of treatments completely at random. In these situations, restrictions on the randomisation force the level combinations of one group of factors to be fixed and the combinations of the other group of factors are run. Then a new level of the first-factor group is set and combinations of the other factors are run. We discussed the computational algorithm for the Stochastic Search Variable Selection (SSVS) in linear mixed models. We extended the computational algorithm of SSVS to fit models from split-plot mixture design by introducing the algorithm of the Stochastic Search Variable Selection for Split-plot Design (SSVS-SPD). The motivation of this extension is that we have two different levels of the experimental units, one for the whole plots and the other for subplots in the split-plot mixture design.
