Machine Learning Based Flow Regime Identification using Ultrasonic Doppler Data and Feature Relevance Determination

•An objective flow regime classifier was constructed from the discrete wavelet transform of ultrasonic data.•Anisotropic Kernel PCA feature extraction was optimized with genetic algorithm.•Explainability is improved by revealing the most significant input features and visualizing results as virtual...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Digital Chemical Engineering Ročník 3; s. 100024
Hlavní autoři:	Roxas  II, Ricardo, Evangelista, Matthew Angelo, Sombillo, Jalen Aeron, Nnabuife, Somtochukwu Godfrey, Pilario, Karl Ezra
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.06.2022 Elsevier
Témata:	Clustering Discrete Wavelet Transform Feature Relevance Genetic Algorithm Kernel PCA Virtual Flow Regime Map Virtual Flow Regime Map Kernel PCA Clustering Discrete Wavelet Transform Feature Relevance Genetic Algorithm
ISSN:	2772-5081, 2772-5081
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•An objective flow regime classifier was constructed from the discrete wavelet transform of ultrasonic data.•Anisotropic Kernel PCA feature extraction was optimized with genetic algorithm.•Explainability is improved by revealing the most significant input features and visualizing results as virtual flow regime maps.•Clustering of visualized 2-D features were evaluated using the global silhouette index.•Six different cross-validated machine learning methods were compared for flow regime classification. [Display omitted] Machine learning approaches are now being used in the process industries to objectively classify two-phase flow regimes in pipes such as into bubbly, slugging, churning, or annular flow. However, they lack explainability, which makes the results difficult to be trusted by plant operators in the field. This paper presents a complete machine learning workflow for flow regime identification with improved explainability through the use of virtual flow regime maps and feature relevance determination. The workflow was applied on an S-shape riser fitted with a non-intrusive ultrasonic Doppler sensor. Statistical features were first extracted via discrete wavelet transform (DWT). An improved virtual flow regime map was then constructed by projecting the DWT features onto 2-D space using kernel principal components analysis (KPCA). Within KPCA, anisotropic kernels are proposed in this study (referred to as Aniso-KPCA) to reveal which input DWT features have the best flow-distinguishing power. Kernel parameters in Aniso-KPCA were searched by maximizing the goodness of 2-D clustering of data points using the genetic algorithm. Finally, the support vector machine (SVM) emerged as the recommended classifier of flow regimes on the basis of repeatability and accuracy, as compared to other models such as neural networks, naive Bayes, k-nearest neighbors, and ensembled trees. Overall, the proposed workflow is a step towards improving the explainability of future machine learning based flow regime classifiers.
ISSN:	2772-5081 2772-5081
DOI:	10.1016/j.dche.2022.100024