FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2943505170> ?p ?o ?g. }

• W2943505170 abstract "Fault detection and identification (FDI) framework plays an important role to ensureconsistent and reliable operation of chemical process systems. The FDI framework hastwo main tasks, namely to detect the presence of a fault and to classify the location andtype of the fault. In most cases, it is impractical to develop precise model from firstprinciples as it requires the involvement of process complex physics and the interactionsamong the different components creating the process. Therefore, data-driven FDImethods, which can make use of process data to capture their trends and dynamics,provide an attractive alternative for the quick development and deployment of FDIsolutions. One of the main objectives of this thesis is to develop a hybrid framework fordata-driven FDI in chemical process systems. This framework integrated a novel multiscaledimensional reduction method for pre-processing step and an improved datadrivenFDI framework. This thesis focuses on proposing a dimensionality reductionmethod based on multi-scale kernel Fisher discriminant analysis (multi-scale KFDA), inwhich discrete wavelet transform (DWT) was combined with kernel Fisher discriminantanalysis (KFDA) method. Initially, DWT was applied to extract the dynamics of theprocess at different scales. The wavelet coefficients obtained during the analysis werereconstructed using the inverse discrete wavelet transform (IDWT) method and then,they were fed into the KFDA to produce discriminant vectors. Finally, the discriminantvectors were used as inputs for the classification task in fault identification step. Apartfrom that, complete fault identification procedures based on adaptive neuro-fuzzyinference system (ANFIS), support vector machine (SVM), Gaussian mixture model(GMM), and k-nearest neighbor (kNN) were developed to investigate the parameters that could be optimised for better fault identification. Furthermore, this thesis extendedthe proposed multi-scale KFDA-based fault identification methods to a hybrid datadrivenFDI framework. In the hybrid FDI framework, all classification methods usedpreviously were combined into a single classification framework. Hence, a completedata-driven hybridisation FDI framework for chemical process systems was proposedand analysed. The proposed FDI frameworks were applied in three different chemicalprocesses: the simulation of Tennessee Eastman process, the fed-batch penicillinfermentation process, and a real industrial data set of semiconductor etch process.Notably, the fault detection and classification results demonstrated the effectiveness ofthe proposed methods." @default.
• W2943505170 created "2019-05-09" @default.
• W2943505170 creator A5046868139 @default.
• W2943505170 date "2018-09-01" @default.
• W2943505170 modified "2023-09-26" @default.
• W2943505170 title "A framework for data-driven fault detection and identification with multiscale kernel fisher discriminant analysis in chemical process systems / Norazwan Md Nor" @default.
• W2943505170 hasPublicationYear "2018" @default.
• W2943505170 type Work @default.
• W2943505170 sameAs 2943505170 @default.
• W2943505170 citedByCount "0" @default.
• W2943505170 crossrefType "dissertation" @default.
• W2943505170 hasAuthorship W2943505170A5046868139 @default.
• W2943505170 hasConcept C111919701 @default.
• W2943505170 hasConcept C114614502 @default.
• W2943505170 hasConcept C119857082 @default.
• W2943505170 hasConcept C121927907 @default.
• W2943505170 hasConcept C124101348 @default.
• W2943505170 hasConcept C152745839 @default.
• W2943505170 hasConcept C153180895 @default.
• W2943505170 hasConcept C154945302 @default.
• W2943505170 hasConcept C172707124 @default.
• W2943505170 hasConcept C181367576 @default.
• W2943505170 hasConcept C196216189 @default.
• W2943505170 hasConcept C31510193 @default.
• W2943505170 hasConcept C33923547 @default.
• W2943505170 hasConcept C41008148 @default.
• W2943505170 hasConcept C46286280 @default.
• W2943505170 hasConcept C47432892 @default.
• W2943505170 hasConcept C69738355 @default.
• W2943505170 hasConcept C70518039 @default.
• W2943505170 hasConcept C74193536 @default.
• W2943505170 hasConcept C98045186 @default.
• W2943505170 hasConceptScore W2943505170C111919701 @default.
• W2943505170 hasConceptScore W2943505170C114614502 @default.
• W2943505170 hasConceptScore W2943505170C119857082 @default.
• W2943505170 hasConceptScore W2943505170C121927907 @default.
• W2943505170 hasConceptScore W2943505170C124101348 @default.
• W2943505170 hasConceptScore W2943505170C152745839 @default.
• W2943505170 hasConceptScore W2943505170C153180895 @default.
• W2943505170 hasConceptScore W2943505170C154945302 @default.
• W2943505170 hasConceptScore W2943505170C172707124 @default.
• W2943505170 hasConceptScore W2943505170C181367576 @default.
• W2943505170 hasConceptScore W2943505170C196216189 @default.
• W2943505170 hasConceptScore W2943505170C31510193 @default.
• W2943505170 hasConceptScore W2943505170C33923547 @default.
• W2943505170 hasConceptScore W2943505170C41008148 @default.
• W2943505170 hasConceptScore W2943505170C46286280 @default.
• W2943505170 hasConceptScore W2943505170C47432892 @default.
• W2943505170 hasConceptScore W2943505170C69738355 @default.
• W2943505170 hasConceptScore W2943505170C70518039 @default.
• W2943505170 hasConceptScore W2943505170C74193536 @default.
• W2943505170 hasConceptScore W2943505170C98045186 @default.
• W2943505170 hasLocation W29435051701 @default.
• W2943505170 hasOpenAccess W2943505170 @default.
• W2943505170 hasPrimaryLocation W29435051701 @default.
• W2943505170 hasRelatedWork W1995702746 @default.
• W2943505170 hasRelatedWork W2013344763 @default.
• W2943505170 hasRelatedWork W2170447682 @default.
• W2943505170 hasRelatedWork W2188500676 @default.
• W2943505170 hasRelatedWork W2350488487 @default.
• W2943505170 hasRelatedWork W2377675823 @default.
• W2943505170 hasRelatedWork W2386697697 @default.
• W2943505170 hasRelatedWork W2468241156 @default.
• W2943505170 hasRelatedWork W2615805087 @default.
• W2943505170 hasRelatedWork W2734473170 @default.
• W2943505170 hasRelatedWork W2737861799 @default.
• W2943505170 hasRelatedWork W2756109228 @default.
• W2943505170 hasRelatedWork W2781808249 @default.
• W2943505170 hasRelatedWork W2836980489 @default.
• W2943505170 hasRelatedWork W2898768896 @default.
• W2943505170 hasRelatedWork W2900531880 @default.
• W2943505170 hasRelatedWork W3004397971 @default.
• W2943505170 hasRelatedWork W3037043436 @default.
• W2943505170 hasRelatedWork W3097066912 @default.
• W2943505170 hasRelatedWork W3177741117 @default.
• W2943505170 isParatext "false" @default.
• W2943505170 isRetracted "false" @default.
• W2943505170 magId "2943505170" @default.
• W2943505170 workType "dissertation" @default.