@inproceedings{,
	author = {Jouini, Mohamed Soufiane, and Riahi, Mohamed Kamel},
	title = {Spectral Reconstruction of Magnetite Deposits in Steam Generator Tubing: An Artificial Intelligence Approach},
	year = {2022},
	journal = {Transactions of the American Nuclear Society},
	volume = {127},
	pages = {314-315},
	number={1},
	doi = {},
	url = {https://www.ans.org/pubs/transactions/article-52359/},
	document_type={Article},
	abstract={Steam Generator (SG) tubing is a crucial component in
the Pressurized Water Reactors. A variety of degradation
of the SG tubes challenge the integrity of such component
and therefore the station reliability and even safety. Cracks,
hardening, stress corrosion are serious factors that threaten
tube failure, hence the safety of the power plant. To prevent
unwelcome radioactive accident, Non-Destructive Evaluation
(NDE) techniques are heavily used, among which tomography
by Eddy-Current (EC) excitation. The latter is considered
to be among the cheapest NDE techniques. In this work we
shall present a tomography inversion technique based on the
use of Artificial Intelligence (AI) together with Finite element
solution [1] to Eddy-current problem. A variety of inversion
technique have emerged, [2,3,4,5,6] and recently [7] without
being exhaustive. These techniques suffers from large memory
demand, and ill-posedness in the sense of dependency of the
output with respect to the initial guess. The latter method [7]
constitute a way around large memory requirement, although
it produces indicator function that is diffused hence not a clear
cut toward detecting the deposition. Nonetheless, the quality-
cost ratio for the LSM makes it highly potentially good method
to approximately detect conductive deposition and cracks. In
this work we aim at introducing AI technique as an alternative
approach for the NDE.}
}

{"_id":"2eQMm7H9w7AEGg4ty","bibbaseid":"jouini-riahi-spectralreconstructionofmagnetitedepositsinsteamgeneratortubinganartificialintelligenceapproach-2022","author_short":["Jouini, M. S.","Riahi, M. K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"propositions":[],"lastnames":["Jouini"],"firstnames":["Mohamed","Soufiane"],"suffixes":[""]},{"propositions":[],"lastnames":["Riahi"],"firstnames":["Mohamed","Kamel"],"suffixes":[]}],"title":"Spectral Reconstruction of Magnetite Deposits in Steam Generator Tubing: An Artificial Intelligence Approach","year":"2022","journal":"Transactions of the American Nuclear Society","volume":"127","pages":"314-315","number":"1","doi":"","url":"https://www.ans.org/pubs/transactions/article-52359/","document_type":"Article","abstract":"Steam Generator (SG) tubing is a crucial component in the Pressurized Water Reactors. A variety of degradation of the SG tubes challenge the integrity of such component and therefore the station reliability and even safety. Cracks, hardening, stress corrosion are serious factors that threaten tube failure, hence the safety of the power plant. To prevent unwelcome radioactive accident, Non-Destructive Evaluation (NDE) techniques are heavily used, among which tomography by Eddy-Current (EC) excitation. The latter is considered to be among the cheapest NDE techniques. In this work we shall present a tomography inversion technique based on the use of Artificial Intelligence (AI) together with Finite element solution [1] to Eddy-current problem. A variety of inversion technique have emerged, [2,3,4,5,6] and recently [7] without being exhaustive. These techniques suffers from large memory demand, and ill-posedness in the sense of dependency of the output with respect to the initial guess. The latter method [7] constitute a way around large memory requirement, although it produces indicator function that is diffused hence not a clear cut toward detecting the deposition. Nonetheless, the quality- cost ratio for the LSM makes it highly potentially good method to approximately detect conductive deposition and cracks. In this work we aim at introducing AI technique as an alternative approach for the NDE.","bibtex":"@inproceedings{,\n\tauthor = {Jouini, Mohamed Soufiane, and Riahi, Mohamed Kamel},\n\ttitle = {Spectral Reconstruction of Magnetite Deposits in Steam Generator Tubing: An Artificial Intelligence Approach},\n\tyear = {2022},\n\tjournal = {Transactions of the American Nuclear Society},\n\tvolume = {127},\n\tpages = {314-315},\n\tnumber={1},\n\tdoi = {},\n\turl = {https://www.ans.org/pubs/transactions/article-52359/},\n\tdocument_type={Article},\n\tabstract={Steam Generator (SG) tubing is a crucial component in\nthe Pressurized Water Reactors. A variety of degradation\nof the SG tubes challenge the integrity of such component\nand therefore the station reliability and even safety. Cracks,\nhardening, stress corrosion are serious factors that threaten\ntube failure, hence the safety of the power plant. To prevent\nunwelcome radioactive accident, Non-Destructive Evaluation\n(NDE) techniques are heavily used, among which tomography\nby Eddy-Current (EC) excitation. The latter is considered\nto be among the cheapest NDE techniques. In this work we\nshall present a tomography inversion technique based on the\nuse of Artificial Intelligence (AI) together with Finite element\nsolution [1] to Eddy-current problem. A variety of inversion\ntechnique have emerged, [2,3,4,5,6] and recently [7] without\nbeing exhaustive. These techniques suffers from large memory\ndemand, and ill-posedness in the sense of dependency of the\noutput with respect to the initial guess. The latter method [7]\nconstitute a way around large memory requirement, although\nit produces indicator function that is diffused hence not a clear\ncut toward detecting the deposition. Nonetheless, the quality-\ncost ratio for the LSM makes it highly potentially good method\nto approximately detect conductive deposition and cracks. In\nthis work we aim at introducing AI technique as an alternative\napproach for the NDE.}\n}\n","author_short":["Jouini, M. S.","Riahi, M. K."],"key":"","id":"","bibbaseid":"jouini-riahi-spectralreconstructionofmagnetitedepositsinsteamgeneratortubinganartificialintelligenceapproach-2022","role":"author","urls":{"Paper":"https://www.ans.org/pubs/transactions/article-52359/"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://docs.google.com/uc?export=download&id=1GhoAKJBee1PlLyIx6KepRvIg2UrLVBRg","dataSources":["EebkmJjgLhgSZMFtf"],"keywords":[],"search_terms":["spectral","reconstruction","magnetite","deposits","steam","generator","tubing","artificial","intelligence","approach","jouini","riahi"],"title":"Spectral Reconstruction of Magnetite Deposits in Steam Generator Tubing: An Artificial Intelligence Approach","year":2022}