[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119910-en":3,"doc-seo-119910-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119910,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Investigation of Gas Diffusion Layer Intrusion in PEM Fuel Cell Using Physics-informed Machine Learning - Master of Science Thesis","This thesis investigates gas diffusion layer (GDL) intrusion phenomena in proton exchange membrane (PEM) fuel cells using physics-informed machine learning. The study formulates governing equations and implements numerical simulations, then designs experiments to generate training data for multiple learning algorithms. Model performance is compared using interpretability and accuracy metrics, followed by optimization over operational and geometric parameters. Results include simulation-validation against literature and analysis of how parameters influence intrusion area, providing data-driven guidance for improving fuel-cell design.","UC Irvine  \nUC Irvine Electronic Theses and Dissertations  \nTitle  \nInvestigation of Gas Diffusion Layer Intrusion in PEM Fuel Cell Using Physics-informed Machine Learning  \nPermalink  \n[https://escholarship.org/uc/item/0fq8d3d3](https://escholarship.org/uc/item/0fq8d3d3)  \nAuthor  \nLy, Vu  \nPublication Date  \n2023  \nPeer reviewed|Thesis/dissertation  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nUNIVERSITY OF CALIFORNIA,  \nIRVINE  \nInvestigation of Gas Diffusion Layer Intrusion in PEM Fuel Cell Using Physics-informed  \nMachine Learning  \nTHESIS  \nsubmitted in partial satisfaction of the requirements for the degree of  \nMASTER OF SCIENCE  \nin Mechanical and Aerospace Engineering  \nby  \nVu Ly  \nThesis Committee: Professor Yun Wang, Chair Professor Mark Walter Professor Penghui Cao  \n© 2023 Vu Ly  \nTABLE OF CONTENTS  \nPage  \nLIST OF FIGURES iii  \nLIST OF TABLES iv  \nACKNOWLEDGMENTS v  \nABSTRACT OF THE THESIS vi  \n1 An Introduction to Fuel Cell 1  \n1.1 Introduction .......................................... 1  \n1.2 What is a Fuel Cell? ...................................... 2  \n1.3 Fuel Cell Efficiency ...................................... 4  \n1.4 Proton Exchange Membrane Fuel Cell ........................... 6  \n1.5 GDL Intrusion ......................................... 9  \n1.6 Objective ............................................ 10  \n2 Methods and Approach 12  \n2.1 Governing Equations ..................................... 12  \n2.2 Numerical Implementation ................................. 15  \n2.3 Design of Experiments .................................... 17  \n2.4 Machine Learning ....................................... 18  \n2.5 Optimization ......................................... 25  \n3 Results and Discussion 27  \n3.1 Simulations and Two-Factorial Results .......................... 27  \n3.2 Results of Different Machine Learning Algorithms .................... 33  \n3.3 Optimization Results ..................................... 38  \n4 Conclusions 41  \nLIST OF FIGURES  \nPage  \n1.1 Simple explanation of Fuel Cell ............................... 3  \n1.2 PEMFC Layout [1] ....................................... 7  \n1.3 a) SEM image of carbon cloth (E-Tek), b) SEM image of carbon paper (Toray 060) [2] 8  \n1.4 Different types of gas channel configurations for BPs: (a) straight parallel; (b) in  \nterdigitated; (c) pin-type; (d) spiral; (e) single-channel serpentine; (f ) multiple  \nchannel (triple) serpentine [3] ............................... 9  \n1.5 Fuel Cell Assembly [4] .................................... 10  \n1.6 GDL intrusion in GFC at four different pressures [5] ................... 11  \n2.1 Schematic of BP and GDL .................................. 16  \n2.2 Plot showing the performance vs. Interpretability of each machine learning algorithm [6] ............................................ 20  \n2.3 Decision Tree ......................................... 21  \n2.4 Plot explaining Support Vector Machine [7] ........................ 22  \n2.5 Plot explaining K-Nearest Neighbor with K = 3 [7] .................... 23  \n2.6 Plots demonstrating underfitting, good fit, and overfitting [6] ............. 24  \n2.7 Schematic diagram of the steps for this experiment ................... 26  \n3.1 BP and GDL model from COMSOL software ....................... 28  \n3.2 Mesh size of 2 × 10−5 m for the model ........................... 28  \n3.3 Schematic of BP and GDL .................................. 29  \n3.4 Comparison of simulation results with literature data ................. 30  \n3.5 Half the intrusion area of the GDL into the channel ................... 31  \n3.6 F andP values of the five parameters and relationship represented in a half-normal plot ............................................... 32  \n3.7 Effects of different parameters on the intrusion area .................. 34  \n3.8 Results of each model, a) Linear Regression, b) Decision Tree, c) KNN, d) SVR ... 37  \n3.9","cbCaijWzClDxNwHL","https://ap.wps.com/l/cbCaijWzClDxNwHL","pdf",11560416,1,58,"English","en",105,"# Table of Contents\n## List of Figures\n## List of Tables\n## Acknowledgments\n## Abstract of the Thesis\n## 1 An Introduction to Fuel Cell\n## 1.1 Introduction\n## 1.2 What is a Fuel Cell?\n## 1.3 Fuel Cell Efficiency\n## 1.4 Proton Exchange Membrane Fuel Cell\n## 1.5 GDL Intrusion\n## 1.6 Objective\n## 2 Methods and Approach\n## 2.1 Governing Equations\n## 2.2 Numerical Implementation\n## 2.3 Design of Experiments\n## 2.4 Machine Learning\n## 2.5 Optimization\n## 3 Results and Discussion\n## 3.1 Simulations and Two-Factorial Results\n## 3.2 Results of Different Machine Learning Algorithms\n## 3.3 Optimization Results\n## 4 Conclusions","[{\"question\":\"What problem does the thesis address in PEM fuel cells?\",\"answer\":\"It focuses on investigating gas diffusion layer (GDL) intrusion in PEM fuel cells and how intrusion develops under different conditions.\"},{\"question\":\"How are physics-informed machine learning methods used?\",\"answer\":\"The work uses machine learning models trained from simulation/experiment data guided by governing physics, then compares multiple algorithms for performance and interpretability.\"},{\"question\":\"What parameters are optimized to control GDL intrusion?\",\"answer\":\"The optimization evaluates relationships between pressure and GDL height, as well as GDL Young’s modulus and rib configuration, and also considers channel width versus GDL height and GDL height versus pressure.\"}]","Investigation of Gas Diffusion Layer Intrusion in PEM Fuel Cell Using Physics-informed Machine Learning - Master of Science Thesis | PDF",1785726962,146,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"investigation-of-gas-diffusion-layer-intrusion-in-pem-fuel-cell-using-physics-informed-machine-learning-master-of-science-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/investigation-of-gas-diffusion-layer-intrusion-in-pem-fuel-cell-using-physics-informed-machine-learning-master-of-science-thesis/119910/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address in PEM fuel cells?","Question",{"text":75,"@type":76},"It focuses on investigating gas diffusion layer (GDL) intrusion in PEM fuel cells and how intrusion develops under different conditions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are physics-informed machine learning methods used?",{"text":80,"@type":76},"The work uses machine learning models trained from simulation/experiment data guided by governing physics, then compares multiple algorithms for performance and interpretability.",{"name":82,"@type":73,"acceptedAnswer":83},"What parameters are optimized to control GDL intrusion?",{"text":84,"@type":76},"The optimization evaluates relationships between pressure and GDL height, as well as GDL Young’s modulus and rib configuration, and also considers channel width versus GDL height and GDL height versus pressure.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]