The tokamak is currently the principal experimental system for research into the magnetic confinement approach to controlled fusion. Hydrogen gas is raised to very high temperatures inside a toroidal vacuum vessel, and the resulting plasma is confined by a complex system of magnetic fields. Measurements of the electron density inside a tokamak can be made using laser interferometry, which gives line-integral information along chords through the plasma. Extraction of spatially local information from this line integral data represents an ill-posed inverse problem. In this paper we describe a novel approach to the solution of this problem, based on feedforward networks, and we show that it leads to improved accuracy of reconstruction compared with conventional techniques. A software implementation of the trained network has been installed at JET and will be used on a routine basis for profile reconstruction.<\/p>\n","protected":false},"excerpt":{"rendered":"
The tokamak is currently the principal experimental system for research into the magnetic confinement approach to controlled fusion. Hydrogen gas is raised to very high temperatures inside a toroidal vacuum vessel, and the resulting plasma is confined by a complex system of magnetic fields. Measurements of the electron density inside a tokamak can be made […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193721],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-233197","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_publishername":"","msr_edition":"Aleksander, I. and Taylor, J. G. (Eds.), Artificial Neural Networks, Proceedings ICANN'92, Brighton, U.K.","msr_affiliation":"","msr_published_date":"1992-10-02","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"Aleksander, I. and Taylor, J. G. (Eds.), Artificial Neural Networks, Proceedings ICANN'92, Brighton, U.K.","msr_pages_string":"1207\u20131210","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"2","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"https:\/\/books.google.com\/books?id=jLajBQAAQBAJ&pg=PA1207&lpg=PA1207&dq=Reconstruction+of+Tokamak+Density+Profiles+Using+Feed-forward+Networks&source=bl&ots=kK9DlSwQJH&sig=w_G69bCpwVQUabhqDpgs1nb-TUc&hl=en&sa=X&ved=0ahUKEwicsIzgi_PNAhXCJsAKHa4-AWUQ6AEILDAC#v=onepage&q=Reconstruction%20of%20Tokamak%20Density%20Profiles%20Using%20Feed-forward%20Networks&f=false","msr_doi":"","msr_publication_uploader":[{"type":"url","title":"https:\/\/books.google.com\/books?id=jLajBQAAQBAJ&pg=PA1207&lpg=PA1207&dq=Reconstruction+of+Tokamak+Density+Profiles+Using+Feed-forward+Networks&source=bl&ots=kK9DlSwQJH&sig=w_G69bCpwVQUabhqDpgs1nb-TUc&hl=en&sa=X&ved=0ahUKEwicsIzgi_PNAhXCJsAKHa4-AWUQ6AEILDAC#v=onepage&q=Reconstruction%20of%20Tokamak%20Density%20Profiles%20Using%20Feed-forward%20Networks&f=false","viewUrl":false,"id":false,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"https:\/\/books.google.com\/books?id=jLajBQAAQBAJ&pg=PA1207&lpg=PA1207&dq=Reconstruction+of+Tokamak+Density+Profiles+Using+Feed-forward+Networks&source=bl&ots=kK9DlSwQJH&sig=w_G69bCpwVQUabhqDpgs1nb-TUc&hl=en&sa=X&ved=0ahUKEwicsIzgi_PNAhXCJsAKHa4-AWUQ6AEILDAC#v=onepage&q=Reconstruction%20of%20Tokamak%20Density%20Profiles%20Using%20Feed-forward%20Networks&f=false"}],"msr-author-ordering":[{"type":"user_nicename","value":"cmbishop","user_id":31452,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=cmbishop"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inbook","related_content":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/233197"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/233197\/revisions"}],"predecessor-version":[{"id":404837,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/233197\/revisions\/404837"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=233197"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=233197"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=233197"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=233197"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=233197"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=233197"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=233197"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=233197"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=233197"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=233197"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=233197"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=233197"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=233197"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=233197"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=233197"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=233197"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}