[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82686-en":3,"doc-seo-82686-105":28,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":13,"seo_description":14,"update_tm":26,"read_time":27},82686,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Physics-Informed Dynamic State Estimation for Current Transformers Using Graph Neural Networks","Current transformers are vital for power system protection and measurement, yet transient core saturation can strongly distort secondary currents and reduce measurement accuracy. Existing dynamic state estimation approaches often use discretization and iterative solvers with cold-start initialisation that ignores the physical dependency structure, limiting robustness in noisy conditions. A physics-informed warm-start framework is proposed using COMTRADE measurements and Jacobian-structure-based graph neural networks. Benchmarks across discretizations and solvers identify strong baselines and show 25% and 38% average improvements in distance and objective value across tested SNR levels.","Physics-Informed Dynamic State Estimation for Current Transformers Using Graph Neural Networks  \nMichael A. Boateng∗ , Gabriel Gauderman∗ , Nathalie Uwamahoro†  \n∗ School of Electrical and Computer Engineering, Georgia Institute of Technology  \nAtlanta, Georgia, USA, {mboateng6, [ggauderman3}@gatech.edu](ggauderman3}@gatech.edu)  \n† Department of Electrical Engineering and Computer Science, Syracuse University  \nSyracuse, New York, USA, [nuwamaho@syr.edu](nuwamaho@syr.edu)  \narXiv :2607 .02679v1 [ ee ss . SY] 2 Jul 2026  \nAbstract—Current transformers are fundamental to power system protection and measurement, yet transient core saturation can severely distort the secondary current and degrade measurement accuracy. Existing dynamic state estimation methods rely mainly on numerical discretisation and iterative solvers, but their initialisation is not informed by the physical dependency structure of the estimation problem, which limits robustness under noisy conditions. This paper presents a physics-informed enhancement for current transformer dynamic state estimation using COMTRADE measurements generated in WinIGS-T. A structured benchmark of four discretisation schemes and three iterative solvers identifies Gauss-Newton with Quadratic discretisation as the strongest baseline. To address the limitation of conventional cold-start initialisation, a graph neural network is constructed from the Jacobian sparsity pattern to generate physics-informed initial state estimates. The proposed warm-start strategy improves estimator conditioning and achieves average gains of 25% in initialisation distance and 38% in initial weighted objective value across all tested SNR levels. The results demonstrate that embedding physical structure into the initialisationstage improves the robustness of CT saturation correction and supports more reliable measurement and protection performance in modern power grids.  \nIndex Terms—Dynamic State Estimation, Current Transformer Saturation, Gauss-Newton, Levenberg-Marquardt, Numerical Integration, Graph Convolutional Neural Network.  \nNOMENCLATURE  \nA. Abbreviations  \nCT Current transformer.  \nDSE Dynamic state estimation.  \nMU Merging unit.  \nFE Forward Euler.  \nBE Backward Euler.  \nTR Trapezoidal.  \nQD Quadratic.  \nGN Gauss-Newton.  \nLM Levenberg-Marquardt.  \nSNR Signal-to-noise ratio.  \nGNN Graph neural network.  \nCOMTRADE Common format for transient data exchange.  \nB. Variables  \nn Number of samples.  \nknode Node index: k ∈ {1, 2 , 3 , 4} .  \nkbranch Branch index: k ∈ {1, 2 , 3} .  \nλb Base flux linkage for burden resistor.  \nib Base current for burden resistor.  \ngm Magnetizing conductance for CT.  \nL0 Magnetizing inductance for CT.  \nr 1 Primary winding resistance.  \nr2 , r3 Secondary winding resistances.  \nL 1 , L2 , L3 CT secondary inductances.  \nM33 Mutual inductance for CT model.  \ngs1, gs2, gs3 Conductance terms L 1–L3.  \nRs or 1/gs Burden resistor or conductance.  \nλ (t) Flux linkage (Weber) .  \ne (t) Voltage generated by the flux (V) .  \nip (t) CT primary current (A) .  \nim (t) CT magnetizing current (A) .  \nvk (t), k ∈ {1, 2 , 3 , 4} CT secondary-node voltages (V) . iLk (t), k ∈ {1, 2 , 3} Currents through L 1–L3 (A) .  \nI. INTRODUCTION  \nCurrent transformers (CTs) are important measurement devices in power system protection and monitoring, yet their accuracy degrades under high fault currents because core saturation distorts the secondary current and can lead to protection maloperation [1] . This concern is especially significant in differential protection, where saturation mismatch across multiple CTs can trigger false operations, including cases caused by inrush currents from adjacent, non-seriesconnected equipment [2] . Accurate CT error estimation is therefore critical for reliable grid operation. To address this need, the present work benchmarks DSE methods for CTerror compensation and proposes a physics-informed DSE framework that leverages graph neural networks. Fig. 1 shows the equival","cbCaip4zzXkhvkpO","https://ap.wps.com/l/cbCaip4zzXkhvkpO","pdf",2293463,1,"English","en",105,"# Abstract\n# Nomenclature\n## Abbreviations\n## Variables\n# Introduction","[{\"question\":\"Why does current transformer saturation impact protection and measurement accuracy?\",\"answer\":\"High fault currents can drive CT core saturation, which distorts the secondary current. This distortion degrades measurement accuracy and can even cause protection maloperation due to mismatch across multiple CTs.\"},{\"question\":\"How does the proposed method address the weakness of conventional dynamic state estimation initialization?\",\"answer\":\"It replaces cold-start initialization with a warm-start strategy. A graph neural network constructed from the Jacobian sparsity pattern generates physics-informed initial state estimates.\"},{\"question\":\"What performance gains are reported for the warm-start strategy?\",\"answer\":\"Across all tested SNR levels, the method reports average gains of 25% in initialisation distance and 38% in the initial weighted objective value.\"}]",1784182290,20,{"code":4,"msg":29,"data":30},"ok",{"site_id":23,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":26},"physics-informed-dynamic-state-estimation-for-current-transformers-using-graph-neural-networks","",{"@graph":34,"@context":84},[35,52,67],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/physics-informed-dynamic-state-estimation-for-current-transformers-using-graph-neural-networks/82686/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":61,"encodingFormat":59,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why does current transformer saturation impact protection and measurement accuracy?","Question",{"text":74,"@type":75},"High fault currents can drive CT core saturation, which distorts the secondary current. This distortion degrades measurement accuracy and can even cause protection maloperation due to mismatch across multiple CTs.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the proposed method address the weakness of conventional dynamic state estimation initialization?",{"text":79,"@type":75},"It replaces cold-start initialization with a warm-start strategy. A graph neural network constructed from the Jacobian sparsity pattern generates physics-informed initial state estimates.",{"name":81,"@type":72,"acceptedAnswer":82},"What performance gains are reported for the warm-start strategy?",{"text":83,"@type":75},"Across all tested SNR levels, the method reports average gains of 25% in initialisation distance and 38% in the initial weighted objective value.","https://schema.org",{"og:url":50,"og:type":86,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":88,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":44,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":44,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":44,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":44,"category_name":124,"show_sort_weight":27,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":127,"show_sort_weight":27,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":44,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":44,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]