Unsupervised process fault detection with random forests

Simple item page
dc.contributor.authorAuret L.
dc.contributor.authorAldrich C.
dc.date.accessioned2011-05-15T16:01:47Z
dc.date.available2011-05-15T16:01:47Z
dc.date.issued2010
dc.description.abstractProcess monitoring technology plays a vital role in the automation of mineral processing plants, where there is an increased emphasis on safe, cost-effective, and environmentally responsible operation. Members of an important class of advanced diagnostic systems are data-driven and deal with potentially large numbers of variables at any given time by generating diagnostic sequences in lower-dimensional spaces. Despite rapid development in this field, nonlinear process systems remain challenging, and in this investigation, a novel approach to the monitoring of complex systems based on the use of random forest models is proposed. Random forest models consist of ensembles of classification and regression trees in which the model response is determined by voting committees of independent binary decision trees. In this study, a framework for diagnosing steady- and unsteady-state faults with random forests is proposed and demonstrated with simulated and real-world case studies. © 2010 American Chemical Society.
dc.description.versionArticle
dc.identifier.citationIndustrial and Engineering Chemistry Research
dc.identifier.citation49
dc.identifier.citation19
dc.identifier.issn8885885
dc.identifier.other10.1021/ie901975c
dc.identifier.urihttp://hdl.handle.net/10019.1/12150
dc.subjectAdvanced diagnostic systems
dc.subjectBinary decision trees
dc.subjectClassification and regression tree
dc.subjectComplex systems
dc.subjectData-driven
dc.subjectDimensional spaces
dc.subjectEnvironmentally responsible
dc.subjectMineral processing plants
dc.subjectModel response
dc.subjectMonitoring technologies
dc.subjectNonlinear process
dc.subjectProcess fault detection
dc.subjectRandom forests
dc.subjectRapid development
dc.subjectReal-world
dc.subjectUnsteady state
dc.subjectBinary trees
dc.subjectFault detection
dc.subjectProcess monitoring
dc.subjectDecision trees
dc.titleUnsupervised process fault detection with random forests
dc.typeArticle
Files
Collections
Stellenbosch University - Scopus Publications