A process performance monitoring methodology for mineral processing plants

Groenewald, Jacobus Willem De Villiers (2014-04)

Thesis (PhD)--Stellenbosch University, 2014.

Thesis

ENGLISH ABSTRACT: Key to remaining competitive within the mineral industry is ensuring that all processes are always being operated optimally. Process performance monitoring is an ideal initiative with which to accomplish this. Not only can it be used to ensure fault free process operation, but it can also be applied for plant performance improvement through a better understanding of the contributors to the success or failure of the process operation. Critical to the success of any proposed monitoring approach would be its ability to cater for the fact that these mineral processes are typically highly complex, dynamic and non-linear. The purpose of this study was to propose and evaluate a methodical approach to plant-wide process performance monitoring for mineral processing plants. Crucial to this approach is the concept of integrating process causality maps with data-based systems for event detection and diagnosis. To this end, process causality maps were developed to provide a means of structuring process data through the use of fundamental process knowledge. Statistical data-based fault detection techniques, being especially powerful with regards to data compression and dimensionality reduction, were employed to allow huge data sets to be analysed more easily. Change point detection techniques allowed for the identification of stationary segments of data in otherwise non-stationary data sets. Variable importance analysis was used to identify and interpret the variable(s) responsible for the event conditions. Using simulated data sets, different techniques were evaluated in order to acquire an appreciation for their effectiveness and reliability. While it was found that no single technique significantly outperformed any other, it was confirmed that for data having different structures and characteristics, none of the techniques were effective in analysing all potential event conditions. It was suggested that all available techniques be run in parallel, with expert interpretation of the results, ensuring a more comprehensive analysis to be performed. Furthermore, given that only process measurements being monitored could be used to detect events and be analysed for importance, the consequences of monitoring too few process measurements were highlighted. A generic analytical methodology for multivariate process performance monitoring was defined, ensuring the use of appropriate techniques and interpretations. The methodology was subsequently successfully applied to a mineral processing concentrator case study. The application of process causality maps was found to significantly simplify the challenge of monitoring the process, not only improving the ability of the techniques applied through a better focussed application, but also the interpretability of the results due to the reduction in complexity. Extreme learning machine, a robust and computationally inexpensive algorithm, was identified as a potential core algorithm for the data analysis techniques forming part of a process performance monitoring solution. With different drivers, at different times, having different effects on the process, visual representation of the data through canonical variate analysis biplots, combined with a sound understanding of the process under investigation, contributed significantly to a better understanding of the important variables for each event condition. From an implementation perspective, adoption of the methodology remains the biggest barrier to success, requiring the most attention in the immediate future.

AFRIKAANSE OPSOMMING: Krities tot mededingendheid in die minerale-industrie is die versekering dat alle prosesse altyd optimaal bedryf word. Proses prestasie-monitering is 'n ideale inisiatief waarmee dit bereik kan word. Nie net kan dit foutvrye proses werking verseker nie, maar dit kan ook toegepas word vir proses prestasie verbetering deur middel van 'n beter begrip van die bydraers tot die sukses of mislukking van die proses. Van kritieke belang vir die sukses van enige voorgestelde benadering tot monitering is die vermoë om voorsiening te maak vir die feit dat hierdie mineraal prosesse tipies hoogs kompleks, dinamies en nie-lineêr is. Die doel van hierdie studie was om 'n metodiese benadering tot aanlegwye proses prestasie-monitering van mineraal aanlegte voor te stel en te evalueer. Deurslaggewend tot hierdie benadering is die integrasie van proses oorsaaklikheid kaarte met data-gebaseerde stelsels vir gebeurtenis opsporing en diagnose. Proses oorsaaklikheid kaarte is ontwikkel om voorsiening te maak vir die struktureering van proses data deur die gebruik van fundamentele kennis. Statistiese foutopsporings tegnieke, wat veral kragtig is ten opsigte van data kompressie en dimensionaliteit vermindering, is ingespan om groot datastelle makliker te ontleed. Veranderpunt opsporings tegnieke het toegelaat vir die identifisering van stasionêre segmente van data in andersins nie-stasionêre datastelle. Veranderlikebelang analise is gebruik om veranderlike(s) wat verantwoordelik is vir gebeurtenisse te identifiseer en te interpreteer. Gesimuleerde datastelle is gebruik om verskillende tegnieke te evalueer ten einde 'n waardering vir hul doeltreffendheid en betroubaarheid te verkry. Alhoewel dit gevind is dat geen enkele tegniek aansienlik beter as enige ander is nie, is dit bevestig dat geen enkele tegnieke effektief in die ontleding van alle potensiële gebeurtenis was vir data met verskillende strukture en eienskappe. Daar is voorgestel dat alle beskikbare tegnieke in parallel uitgevoer word met deskundige interpretasie van die resultate om te versker data 'n meer omvattende analise uitgevoer word. Gegee dat slegs proses metings wat gemoniteer word gebruik kan word vir gebeurtenis opsporing en vir die belangrikheid ontleeding, is die nadeligheid van die monitering van te min proses metings uitgelig. 'n Generiese analitiese metodologie vir meerveranderlike proses prestasie-monitering is gevolglik omskryf om die gebruik van geskikte tegnieke en interpretasies te verseker. Hierdie metodologie is suksesvol op ‘n mineraal prosesserings aanleg gevallestudie toegepas. Dit is gevind dat die toepassing van die proses oorsaaklikheid kaarte die uitdaging van monitering aansienlik vereenvoudig, nie net as gevolg van die verbeterde vermoë van die tegnieke wat gebruik word deur 'n beter gefokusde toepassing nie, maar ook deur verberterde interpretering van resultate as gevolg van die vermindering in kompleksiteit. Uiterste leermasjiene, 'n robuust en bekostigbare berekeningsintensiewe algoritme, is geïdentifiseer as 'n potensiële kern algoritme vir die data-analise tegnieke, wat deel vorm van 'n proses prestasie-monitering oplossing. Visuele voorstellings het aansienlike bydraes gelewer tot beter begrip van belangrike veranderlikes vir elke toestand, veral deur middel van ‘n kombinasie van kanoniese veranderlike-onleding biplotte en 'n deeglike begrip van die proses wat ondersoek word. Die aanvaarding van die metodologie is tans die grootste hindernis tot sukses vanuit 'n uitvoerings perspektief en benodig dus die meeste aandag in die onmiddellike toekoms.

Please refer to this item in SUNScholar by using the following persistent URL: http://hdl.handle.net/10019.1/86759
This item appears in the following collections: