{"id":{"repo_id":"nus","oai_identifier":"oai:scholarbank.nus.edu.sg:10635/234954"},"canonical_url":"https://search.dev.ndltd.org/etd/nus/oai:scholarbank.nus.edu.sg:10635/234954","repository":{"repo_id":"nus","name":"National University of Singapore","base_url":"https://scholarbank.nus.edu.sg/oai/request"},"display":{"title":"DEVELOPMENT AND APPLICATIONS OF MACHINE/DEEP LEARNING TECHNIQUES IN FLUID DYNAMICS","abstract":"In this thesis, the machine/deep learning techniques are improved and applied in fluid flow problems. Firstly, the conventional multilayer perceptron (MLP) networks are enhanced by the Gaussian radial basis function (RBF) with trainable centers and widths. Activated by Gaussian RBFs, the proposed MLP-RBF network is more accurate and efficient in nonlinear regression problems. Secondly, in view of the network structure, RBF approximation is deployed in each hidden layer of the new network (RBF-MLP-II), which exhibits stronger predictive capability than other counterparts. Thirdly, the prevailing physics-informed neural networks (PINNs) are applied to predict the fluid flows in both global and local domains. The results show better performance in PINNs than pure MLPs, and the RBF-activated PINNs are compared with the tanh-activated ones. Last, the automatic differentiation-based PINNs are improved by the finite difference scheme, and the proposed FD-PINNs are validated using incompressible isothermal and thermal flows.","abstract_html":"In this thesis, the machine/deep learning techniques are improved and applied in fluid flow problems. Firstly, the conventional multilayer perceptron (MLP) networks are enhanced by the Gaussian radial basis function (RBF) with trainable centers and widths. Activated by Gaussian RBFs, the proposed MLP-RBF network is more accurate and efficient in nonlinear regression problems. Secondly, in view of the network structure, RBF approximation is deployed in each hidden layer of the new network (RBF-MLP-II), which exhibits stronger predictive capability than other counterparts. Thirdly, the prevailing physics-informed neural networks (PINNs) are applied to predict the fluid flows in both global and local domains. The results show better performance in PINNs than pure MLPs, and the RBF-activated PINNs are compared with the tanh-activated ones. Last, the automatic differentiation-based PINNs are improved by the finite difference scheme, and the proposed FD-PINNs are validated using incompressible isothermal and thermal flows.","abstract_has_math":false,"creators":["JIANG QINGHUA"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-08-02","date_published":"2022-08-02","updated_at":"2026-07-24T03:33:22Z","subjects":["Fluid dynamics","Radial basis function","Physics-informed neural networks","Artificial neural networks","Deep learning","Machine learning"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["JIANG QINGHUA"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2022-08-02"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://scholarbank.nus.edu.sg/handle/10635/234954"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Fluid dynamics","Radial basis function","Physics-informed neural networks","Artificial neural networks","Deep learning","Machine learning"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://scholarbank.nus.edu.sg/bitstreams/51d05201-3609-4263-a833-bf6355c5669b/download"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis, the machine/deep learning techniques are improved and applied in fluid flow problems. Firstly, the conventional multilayer perceptron (MLP) networks are enhanced by the Gaussian radial basis function (RBF) with trainable centers and widths. Activated by Gaussian RBFs, the proposed MLP-RBF network is more accurate and efficient in nonlinear regression problems. Secondly, in view of the network structure, RBF approximation is deployed in each hidden layer of the new network (RBF-MLP-II), which exhibits stronger predictive capability than other counterparts. Thirdly, the prevailing physics-informed neural networks (PINNs) are applied to predict the fluid flows in both global and local domains. The results show better performance in PINNs than pure MLPs, and the RBF-activated PINNs are compared with the tanh-activated ones. Last, the automatic differentiation-based PINNs are improved by the finite difference scheme, and the proposed FD-PINNs are validated using incompressible isothermal and thermal flows."]},{"key":"dc:format.checksum.md5","label":"Dc Format Checksum Md5","values":["e6342c40f87376eea2143ccb19036552","c910980db2ff438f9bbac7baad4f92de"]},{"key":"dc:title","label":"Title","values":["DEVELOPMENT AND APPLICATIONS OF MACHINE/DEEP LEARNING TECHNIQUES IN FLUID DYNAMICS"]}]}],"canonical_facts":{"dc:creator":["JIANG QINGHUA"],"dc:date.issued":["2022-08-02"],"dc:description.abstract":["In this thesis, the machine/deep learning techniques are improved and applied in fluid flow problems. Firstly, the conventional multilayer perceptron (MLP) networks are enhanced by the Gaussian radial basis function (RBF) with trainable centers and widths. Activated by Gaussian RBFs, the proposed MLP-RBF network is more accurate and efficient in nonlinear regression problems. Secondly, in view of the network structure, RBF approximation is deployed in each hidden layer of the new network (RBF-MLP-II), which exhibits stronger predictive capability than other counterparts. Thirdly, the prevailing physics-informed neural networks (PINNs) are applied to predict the fluid flows in both global and local domains. The results show better performance in PINNs than pure MLPs, and the RBF-activated PINNs are compared with the tanh-activated ones. Last, the automatic differentiation-based PINNs are improved by the finite difference scheme, and the proposed FD-PINNs are validated using incompressible isothermal and thermal flows."],"dc:format.checksum.md5":["e6342c40f87376eea2143ccb19036552","c910980db2ff438f9bbac7baad4f92de"],"dc:identifier.uri":["https://scholarbank.nus.edu.sg/bitstreams/51d05201-3609-4263-a833-bf6355c5669b/download"],"dc:relation.isreferencedby":["https://scholarbank.nus.edu.sg/handle/10635/234954"],"dc:subject":["Fluid dynamics","Radial basis function","Physics-informed neural networks","Artificial neural networks","Deep learning","Machine learning"],"dc:title":["DEVELOPMENT AND APPLICATIONS OF MACHINE/DEEP LEARNING TECHNIQUES IN FLUID DYNAMICS"],"dc:type":["Thesis"]},"updated_at":"2026-07-24T03:33:22Z"}