Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification
Thesis (MEng)--Stelllenbosch University, 2016.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | en_ZA |
| Published: |
Stellenbosch : Stellenbosch University
2016
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614052580065280 |
|---|---|
| access_status_str | Open Access |
| author | Myburgh, Travis Louis |
| author2 | Auret, Lidia |
| author_browse | Auret, Lidia Myburgh, Travis Louis |
| author_facet | Auret, Lidia Myburgh, Travis Louis |
| author_sort | Myburgh, Travis Louis |
| collection | Thesis |
| dc_rights_str_mv | Stellenbosch University |
| description | Thesis (MEng)--Stelllenbosch University, 2016. |
| format | Thesis |
| id | oai:scholar.sun.ac.za:10019.1/100263 |
| institution | Stellenbosch University (South Africa) |
| language | en_ZA |
| last_indexed | 2026-06-10T12:45:54.519Z |
| license_str | Other — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from SUNScholar — Stellenbosch University Repository |
| publishDate | 2016 |
| publishDateRange | 2016 |
| publishDateSort | 2016 |
| publisher | Stellenbosch : Stellenbosch University |
| publisherStr | Stellenbosch : Stellenbosch University |
| record_format | dspace |
| source_str | SUNScholar — Stellenbosch University Repository |
| spelling | oai:scholar.sun.ac.za:10019.1/100263 On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification Myburgh, Travis Louis Auret, Lidia Burger, A. J. Stellenbosch University. Faculty of Engineering. Dept. of Process Engineering. Fault location (Engineering) UCTD Fault-tolerant computing SR (Computer program language) Thesis (MEng)--Stelllenbosch University, 2016. ENGLISH ABSTRACT: Batch processes are transient processes, which present a unique monitoring challenge. Whereas the expected output variables of a continuous process centre on specific target values that represent some steady state, batch process variables inherently change from an initial state to a final state. Abnormal events, or faults, that occur in batch processes can be identified with an appropriate monitoring scheme. Bilinear statistical modelling based on latent methods, such as Partial Least Squares (PLS), have been shown by Nomikos and MacGregor (1995) to be an effective way to detect faults and predict the end-of-batch quality. A batch process monitoring toolbox has previously been developed, which supports off-line modelling and monitoring of batch processes. The limitation of off-line monitoring is that product end-of-batch quality and fault detection can only be assessed once the batch has been completed. On-line fault detection and end-of-batch quality prediction in near-real time endeavors to address this limitation. The aim of this project was to implement an on-line monitoring platform which can detect faults and predict end-of-batch quality in a timely manner. Synchronization of the batch trajectories is a computationally expensive step in off-line monitoring, and the ability of the on-line platform to produce computationally efficient results comparable to off-line synchronization was assessed. The Relaxed Greedy Time Warping (RGTW) approach (González-Martínez et al., 2011) was used to synchronise the trajectories in an on-line fashion. The approach was able to produce comparable results in a computationally efficient way, but some inaccuracies were observed during flat regions of the batch trajectories. The nature of phases for accurate modelling of batch data was also investigated. Models were built for batch data partitioned in three ways: no partitions, partitions based on known process stages and partitions based on linear correlation structure between the variables and the end-of-batch quality prediction accuracy was compared. The multiphase partial least squares (MPPLS) algorithm (Camacho, et al., 2007) was used to find the changes in linear correlation among the process variables and partition the data accordingly. Partitioning the data using the MPPLS algorithm showed comparable or statistically significant reductions in the overall end-of-batch prediction error compared with the other two data partitioning methods. The models were applied on-line to two case studies using the on-line monitoring platform and the fault detection and end-of-batch quality prediction accuracy were assessed for the three data partioning methods. The end-of-batch predictions made using the MPPLS algorithm provided the most accurate end-of-batch predictions. Improper on-line synchronisation caused false alarms in certain areas of the batch trajectory, but faults were detected with relative accuracy. AFRIKAANSE OPSOMMING: Enkelladingprosesse is oorgangsprosesse, wat ’n unieke moniteringsuitdaging bied. Terwyl die verwagte uitsetveranderlikes van ’n gestadigde proses gevestig is op spesifieke teikenwaardes wat een of ander ewewigstoestand verteenwoordig, verander enkelladingprosesveranderlikes inherent vanaf ’n aanvanklike toestand na ’n finale toestand. Abnormale gebeure, of foute, kan in enkelladingprosesse geïdentifiseer word met behulp van ’n toepaslike moniteringskema. Bi-lineêre statistiese modellering gebaseer op latente metodes, soos parsiële kleinste kwadrate (PKK), is deur Nomikos en MacGregor (1995) aangetoon om ’n doeltreffende wyse te wees om foute op te spoor en die kwaliteit met enkellading-einde te voorspel. ’n Enkelladingprosesmonitering-gereedskapkas, wat aflyn modellering en monitering van enkelladingprosesse steun, is reeds ontwikkel. Die beperking van aflyn monitering is dat die produk se enkellading-einde-kwaliteit en foutopsporing slegs geassesseer kan word nadat die enkellading proses voltooi is. Aanlyn foutopsporing en enkellading-einde-kwaliteitvoorspelling in ’n bykans intydse sin poog om hierdie beperking aan te spreek. Die doel van hierdie projek was om ’n aanlyn moniteringsplatform te implementeer wat foute kan opspoor en kwaliteit met enkellading-einde op ’n tydige wyse kan voorspel. Sinkronisasie van die enkellading-trajekte is ’n rekenaarmatig duur stap in aflyn monitering, en die vermoë van die aanlyn platform om rekenaarmatig doeltreffende resultate te lewer, in vergelyking met aflyn sinkronisasie, is geassesseer. Die ontspanne-gierige-tydkromtrekking-benadering (OGTB-benadering) (González-Martínez et al., 2011) is gebruik om die trajekte op ’n aanlyn wyse te sinkroniseer. Die benadering was in staat om vergelykbare resultate in ’n rekenaarmatig doeltreffende wyse te genereer, maar enkele onakkuraathede is in plat areas van die enkellading-trajekte waargeneem. Die aard van fases vir akkurate modellering van enkelladingdata is ook ondersoek. Modelle vir enkelladingdata is gebou en op drie maniere verdeel: geen verdelings nie, verdelings gebaseer op bekendeprosesfases, en verdelings gebaseer op lineêrekorrelasiestruktuur tussen die veranderlikes en die enkellading-einde-gehaltevoorspellingsakkuraatheid is vergelyk. Die multifase- parsiëlekleinste- kwadrate-algoritme (MFPKK-algoritme) (Camacho, et al., 2007) is gebruik om die veranderinge in lineêre korrelasie onder die prosesveranderlikes op te spoor, en die data dienooreenkomstig te verdeel. Verdeling van die data, deur gebruik te maak van die MFPKKalgoritme, het vergelykbare of statisties beduidende verminderings in die algehele enkelladingeinde- voorspellingsfout getoon wanneer dit met die ander twee dataverdelingsmetodes vergelyk word. Die modelle is aanlyn toegepas in twee gevallestudies deur die aanlyn moniteringsplatform, en die foutopsporing en akkuraatheid van enkellading-einde-kwaliteitvoorspelling is geassesseer vir die drie dataverdelingsmetodes. Die enkellading-einde-voorspellings wat met behulp van die MFPKKalgoritme gemaak is, het die akkuraatste enkellading-einde-voorspellings verskaf. Ongepaste aanlyn sinkronisasie het valse alarms in sekere areas van die enkellading-trajekte veroorsaak, maar foute is met relatiewe akkuraatheid opspoor. Masters 2016-12-22T13:33:31Z 2016-12-22T13:33:31Z 2016-12 Thesis http://hdl.handle.net/10019.1/100263 en_ZA Stellenbosch University 223 pages : illustrations application/pdf Stellenbosch : Stellenbosch University |
| spellingShingle | Fault location (Engineering) UCTD Fault-tolerant computing SR (Computer program language) Myburgh, Travis Louis On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification |
| title | On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification |
| title_full | On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification |
| title_fullStr | On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification |
| title_full_unstemmed | On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification |
| title_short | On-line fault detection and end-of-batch quality prediction for batch processes incorporating on-line synchronisation and phase identification |
| title_sort | on line fault detection and end of batch quality prediction for batch processes incorporating on line synchronisation and phase identification |
| topic | Fault location (Engineering) UCTD Fault-tolerant computing SR (Computer program language) |
| url | http://hdl.handle.net/10019.1/100263 |
| work_keys_str_mv | AT myburghtravislouis onlinefaultdetectionandendofbatchqualitypredictionforbatchprocessesincorporatingonlinesynchronisationandphaseidentification |