Improving the performance of causality analysis techniques for automated fault diagnosis in mineral processing plants
| dc.contributor.advisor | Auret, Lidia | en_ZA |
| dc.contributor.advisor | Bauer, Margret | en_ZA |
| dc.contributor.author | Lindner, Brian Siegfried | en_ZA |
| dc.contributor.other | Stellenbosch University. Faculty of Engineering. Dept. of Process Engineering. | en_ZA |
| dc.date.accessioned | 2019-02-27T10:37:00Z | |
| dc.date.accessioned | 2019-04-17T08:21:02Z | |
| dc.date.available | 2019-02-27T10:37:00Z | |
| dc.date.available | 2019-04-17T08:21:02Z | |
| dc.date.issued | 2019-04 | |
| dc.description | Thesis (PhD)--Stellenbosch University, 2019. | en_ZA |
| dc.description.abstract | ENGLISH ABSTRACT: Modern mineral processing companies are driven towards improving productivity by leveraging existing processes optimally. This can be achieved by improving diagnosis of faults that degrade process performance to provide insightful and actionable information to process engineers. In mineral processing plants, units and variables are connected to each other through material ow, energy ow, and information ow. Faults propagate through a process along these interconnections, and can be traced back along their propagation paths to their root causes. Techniques have been developed for extracting these causal connections from historical process data. These techniques have proven successful for fault diagnosis in chemical processes. However, they have not been widely accepted by industry due to lack of automation of the techniques, complicated implementation, and complicated interpretation. This dissertation investigated the limitations of the causality analysis procedures currently available to process engineers as fault diagnosis tools and developed improvements on them. Improvements were developed and tested using a combination of simulated case studies and real world case studies of operational faults occurring in a mineral processing plant. Objective I: was to investigate the factors that a ect performance of causality analysis techniques. The use of transfer entropy for fault diagnosis in a minerals processing concentrator plant was demonstrated. The desired performance criteria of causality analysis techniques were then de ned in terms of: general applicability; automatability; interpretability; accuracy; precision; and computational complexity. The impact of process conditions on the performance of Granger causality and transfer entropy were then investigated. An analysis of variance (ANOVA) was performed to investigate the impact of process dynamics, fault dynamics, and the parameters on the accuracy of transfer entropy. Objective II: was to design a systematic work ow for application of causality analysis for fault diagnosis. The ANOVA was used to develop a novel relationship between the optimal transfer entropy parameters and the process and fault dynamics. This relationship was then placed within a systematic work ow developed for the application of transfer entropy for oscillation diagnosis, addressing the need for clear procedures and guidelines for data selection and parameter selection. The work ow was applied to an oscillation diagnosis case study from a minerals concentrator plant, and shown to provide a systematic approach to accurately determining the fault propagation path. Objective III: was to design a tool to aid the decision of which causality analysis method to select. A comparative analysis of Granger causality and transfer entropy for fault diagnosis based on the performance criteria de ned was performed. The comparison showed that transfer entropy was more precise, generalisable, and visually interpretable. Granger causality was more automatable, less computationally expensive, and easier to interpret. Guidelines were developed from these comparisons to aid users in deciding when to use Granger causality or transfer entropy Objective IV: was to present tools for interpretation of causal maps for root cause analysis. Methods for construction of causal maps from the results of the causality analysis calculation were presented, and methods for interpretation of causal maps. The usefulness of these techniques for diagnosis of real world case studies was demonstrated. | en_ZA |
| dc.description.abstract | AFRIKAANSE OPSOMMING: Mineraalprosesseringsmaatskappye plaas hul fokus op die verhoging van produktiwiteit deur bestaande prosesse te optimeer. Dit word bereik deur op `n meer doeltreffende manier foute op te spoor wat prosesprestasie hinder en sodanig insiggewende inligting aan prosesingenieurs oor te dra. Proseseenhede en veranderlikes word verbind aan mekaar in `n mineraalproseseringsaanleg deur die vloei van material, energie en inligting. Foute word deur `n proses voortgesit deur die verbintenis van die proseseenhede aan mekaar, en die kernoorsaak van `n fout kan opgespoor word deur terug te werk deur prosesverbintenisse. Tegnieke is ontwikkel om oorsaaklike verbintenisse te onttrek vanuit historiese prosesdata. Hierdie tegnieke word as suksesvol geag vir foutdiagnose in chemiese prosesse. Hulle is egter nie in die mineraalprosesseringsbedryf aanvaar nie weens die tekort aan die moontlikheid van outomasie, die ingewikkelde implementasie daarvan, asook ingewikkelde interpretasie. Hierdie verhandeling ondersoek die beperkinge van beskikbare oorsaaklikheidsanalisemetodes as foutdiagnosegereedskap vir prosesingenieurs en ontwikkel verbeteringe op die metodes. Verbeterings is ontwikkel en getoets deur `n kombinasie van gesimuleerde gevallestudies en werklike gevallestudies van `n mineraalprosesseringsaanleg. Doel I: was om faktore te ondersoek wat die prestasie van oorsaaklikheidsanalises affekteer. Die gebruik van oordragsentropie vir foutdiagnose in `n mineraalprosesserings konsentrasie-eenheid is gedemonstreer. Die gewenste prestasiekriteria van oorsaaklikheidsanalises is toe gedefinieer in terme van: algemene toepaslikheid; outomiseerheid; interpreteerbaarheid; akkuraatheid; presisie; en berekeningkompleksiteit. Die impak van prosestoestande op die prestasie van Granger oorsaaklikheid en oordragsentropie is toe ondersoek. `n ANOVA variansieanalise is toe uitgevoer om die impak van prosesdinamika, foutdinamika, en geselekteerde parameters op die akkuraatheid van oordragsentropie te ondersoek. Doel II: was om `n systematiese werksvloei te ontwerp vir die toepassing van oorsaaklikheidsanalises op foutdiagnose. Die ANOVA was gebruik om `n nuwe verhouding te ontwikkel tussen die optimale oordragsentropieparameters en die proses- en foutdinamika. Hierdie verhouding is toe in `n sistematiese werksvloei geplaas ontwikkel vir die toepassing van oordragsentropie vir ossillasiediagnose, wat die nodigheid vir duidelike prosedures en riglyne vir data- en parameterseleksie addresseer het. Die werkvloei is toegepas op `n ossilasiediagnose gevallestudie van `n mineralekonsentrasieaanleg, en is gewys om `n systematiese benadering te verskaf om die foutvoortplantingspad akkuraat vas te stel. Doel III: was om gereedskap te ontwerp om te help besluit tussen oorsaaklikheidsanalisemetodes. `n Vergelykende analise van Granger oorsaaklikheid en oordragsentropie vir foutdiagnose gebaseer op gedefinieerde prestasiekriteria is uitgevoer. Die vergelyking het getoon dat oordragsentropie meer presies, veralgemeenbaar en visueel interpreteerbaar is. Granger oor saaklikheid is meer outomeerbaar, minder berekeningsintensief en makliker om te interpreteer. Riglyne is ontwikkel vanuit hierdie vergelykings om verbruikers te help kies tussen Granger oorsaaklikheid en oordragsentropie. Doel IV: was om gereedskap voor te stel vir die interpretasie van oorsaaklikheidskaarte vir kernoorsaakanalises. Metodes om oorsaaklikheidskaarte op te stel vanuit die resultate van oorsaaklikheidsanaliseberekeninge is voorgestel, asook metodes vir die interpretasie van oorsaaklikheidskaarte. Die nut van hierdie tegnieke vir die diagnosering van werklike gevallestudies is gedemonstreer. | af_ZA |
| dc.format.extent | 201 pages : illustrations | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/10019.1/105963 | |
| dc.language.iso | en_ZA | en_ZA |
| dc.publisher | Stellenbosch : Stellenbosch University | en_ZA |
| dc.rights.holder | Stellenbosch University | en_ZA |
| dc.subject | Granger causality | en_ZA |
| dc.subject | UCTD | |
| dc.subject | Entropy | en_ZA |
| dc.subject | Mineral processing | en_ZA |
| dc.subject | Fault location (Engineering) | en_ZA |
| dc.title | Improving the performance of causality analysis techniques for automated fault diagnosis in mineral processing plants | en_ZA |
| dc.type | Thesis | en_ZA |