Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A method to determine transition time for experiments in dynamic processes
Luleå University of Technology, Department of Business Administration, Technology and Social Sciences, Business Administration and Industrial Engineering.ORCID iD: 0000-0003-1473-3670
Luleå University of Technology, Department of Engineering Sciences and Mathematics, Mathematical Science.
2009 (English)Conference paper, Oral presentation only (Other academic)
Abstract [en]

Planning, conducting, and analyzing experiments performed in dynamic processes, such as continuous processes, highlight issues that the experimenter needs to consider, for example, process dynamics (inertia) and the multitude of responses. Dynamic systems exhibit a delay (transition time) the change of an experimental factor and when the response is affected. The transition time affects the required length of each experimental run in dynamic processes and long transition times may call for restrictions of the randomization of runs. By contrast, in many processes in parts production this change is almost immediate. Knowledge about the transition time helps the experimenter to avoid experimental runs that are either too short for a new steady-state to be reached, and thus incorrect estimation of treatment effects, or unnecessarily long and costly. Furthermore, knowing the transition time is important during analysis of the experiment.Determining the transition time in a dynamic process can be difficult since the processes often are heavily instrumented with a multitude of responses. The process responses are typically correlated and react to the same underlying events. Hence, multivariate statistical tools such as principal component analysis (PCA) are often beneficial during analysis. Furthermore, the responses are often highly positively autocorrelated due to frequent sampling. We propose a method to determine the transition time between experimental runs in a dynamic process. We use PCA to summarize the systematic variation in a multivariate response space. The time series analysis techniques ‘transfer function-noise modeling' or ‘intervention analysis' are then used to model the dynamic relation between an input time series event and output time series response using the principal component scores. We illustrate the method by estimating the transition time for treatment changes in an experimental blast furnace. This knowledge provides valuable input to the planning and analysis phase of the experiments in the process.

Place, publisher, year, edition, pages
2009.
National Category
Reliability and Maintenance Probability Theory and Statistics
Research subject
Quality Technology and Management; Mathematical Statistics with special emphasis on Industrial Statistic
Identifiers
URN: urn:nbn:se:ltu:diva-29958Local ID: 399419b0-e499-11de-bae5-000ea68e967bOAI: oai:DiVA.org:ltu-29958DiVA, id: diva2:1003185
Conference
ENBIS Goteborg : 20/09/2009 - 24/09/2009
Note
Godkänd; 2009; 20091209 (andbra)Available from: 2016-09-30 Created: 2016-09-30 Last updated: 2018-03-26Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

http://www.enbis.org/events/current/81_ENBIS9_Goteborg/programmeitem/517_A_Method_to_Determine_Transition_Time_for_Experiments_in_Dynamic_Processes

Authority records BETA

Vanhatalo, ErikKvarnström, BjörnBergquist, BjarneVännman, Kerstin

Search in DiVA

By author/editor
Vanhatalo, ErikKvarnström, BjörnBergquist, BjarneVännman, Kerstin
By organisation
Business Administration and Industrial EngineeringMathematical Science
Reliability and MaintenanceProbability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 20 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf