Home > Publications database > Experimental design and analysis |
Book | FZJ-2021-02173 |
; ;
1993
Forschungszentrum Jülich GmbH Zentralbibliothek, Verlag
Jülich
ISBN: 3-89336-124-3
Please use a persistent id in citations: http://hdl.handle.net/2128/28497
Abstract: Many experiments in chemistry and chemical engineering belong to the extreme problemtype. e.g. determination of the optimum conditions of a process, finding of the optimum constituents of a compound, etc. In such cases effectively to tackle the problem a specific designof an experiment is selected depending on the goals to beachieved in experimentation and the features of the object being investigated. The investigation scheme is usually broken down into some individual steps to evaluate the strategy for further experimentation by using theexperimental results obtained from each previous step. Thus the experimenter is able to conduct the experiment in an optimum way. With a designed experiment, it is possible to vary all factors simultaneously and obtain quantitative estimates of the mail leffects and factor interactions. Thedesigned experiment ensures a less error in determining the effects of interest than any classical method could afford. When the experimenter plans his experiments, he achieves desirable results in a much more economical manner. The design of experiments is concerned with answering the following questions:- What factors should be included? - How many levels of each factor should be included? - How should the levels of the factors be spaced? - How should the experimental units be selected? - How many experimental units should be selected for each treatment combination?- What steps should be taken to control experimental error? - What criterion measures should be used to evaluate the effects of the treatment factors? -Can the effects of primary interest be estimated adequately from the experimental data that will be obtained?
The record appears in these collections: |