{"id":{"repo_id":"msu","oai_identifier":"oai:d.lib.msu.edu:etd_48069"},"canonical_url":"https://search.ndltd.org/etd/msu/oai:d.lib.msu.edu:etd_48069","repository":{"repo_id":"msu","name":"Michigan State University","base_url":"https://d.lib.msu.edu/oai"},"display":{"title":"Deep learning techniques for magnetic flux leakage inspection with uncertainty quantification","abstract":"Pipelines are primary infrastructure to transport oil and natural gas with low cost. Magnetic flux leakage (MFL), one of the most popular electromagnetic nondestructive evaluation (NDE) methods, is a crucial inspection technique of pipeline safety to prevent long-term failures. The important problems in MFL inspection is to detect and characterize defects in terms of shape and size. In industry, the collected MFL data amount is quite large, Convolutional neural networks (CNNs), one of the main categories in deep learning applying to images classification problems, are considered as good approaches to make the classification. In solving the inverse problem to characterize the metal loss defects, the collected MFL signals are represented by three-axis signals in terms of three groups of matrics which are consistent in the form of images. Therefore, this M.S thesis proposed a novel CNN model to estimate the size and shape of defects fed by simulated MFL signals. Some comparative results of the proposed model prove that the method is robust for distortion and variances of input MFL signals and can be applied in other NDE problems with high classification accuracy. Besides, the prediction results are correlated and affected by the systematic and random uncertainties in the MFL inspection process. The proposed CNN is then combined with a Bayesian inference method to analyze the final classification results and make uncertainty estimation on defect identification in MFL inspection. The influences of data and model variation on aleatoric and epistemic uncertainties are addressed in my work. Further, the relationship between the classification accuracy and the uncertainties are described, which provide more hints to further research in MFL inspection.","abstract_html":"Pipelines are primary infrastructure to transport oil and natural gas with low cost. Magnetic flux leakage (MFL), one of the most popular electromagnetic nondestructive evaluation (NDE) methods, is a crucial inspection technique of pipeline safety to prevent long-term failures. The important problems in MFL inspection is to detect and characterize defects in terms of shape and size. In industry, the collected MFL data amount is quite large, Convolutional neural networks (CNNs), one of the main categories in deep learning applying to images classification problems, are considered as good approaches to make the classification. In solving the inverse problem to characterize the metal loss defects, the collected MFL signals are represented by three-axis signals in terms of three groups of matrics which are consistent in the form of images. Therefore, this M.S thesis proposed a novel CNN model to estimate the size and shape of defects fed by simulated MFL signals. Some comparative results of the proposed model prove that the method is robust for distortion and variances of input MFL signals and can be applied in other NDE problems with high classification accuracy. Besides, the prediction results are correlated and affected by the systematic and random uncertainties in the MFL inspection process. The proposed CNN is then combined with a Bayesian inference method to analyze the final classification results and make uncertainty estimation on defect identification in MFL inspection. The influences of data and model variation on aleatoric and epistemic uncertainties are addressed in my work. Further, the relationship between the classification accuracy and the uncertainties are described, which provide more hints to further research in MFL inspection.","abstract_has_math":false,"creators":["Li, Zi (Graduate of Michigan State University)"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Deng, Yiming","Udpa, Lalita","Zhang, Mi"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019","date_published":"2019","updated_at":"2026-11-18T18:53:16Z","subjects":["Magnetic flux--Measurement","Gas leakage--Testing","Petroleum pipeline failures","Petroleum pipelines","Nondestructive testing"],"languages":["English"],"rights":["In Copyright"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:48069","isbn:9781085679657","isbn:1085679659","oclc:1138555628","umi:22615692","local:LI_grad.msu_0128N_17031"],"render_values":[{"text":"etd:48069","href":null,"code":true},{"text":"isbn:9781085679657","href":null,"code":true},{"text":"isbn:1085679659","href":null,"code":true},{"text":"oclc:1138555628","href":null,"code":true},{"text":"umi:22615692","href":null,"code":true},{"text":"local:LI_grad.msu_0128N_17031","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/doi:10.25335/mchp-yw18","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/doi:10.25335/mchp-yw18","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://d.lib.msu.edu/oai?verb=GetRecord&metadataPrefix=oai_dc&identifier=oai%3Ad.lib.msu.edu%3Aetd_48069","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Deng, Yiming","Udpa, Lalita","Zhang, Mi"]},{"key":"dc:creator","label":"Author","values":["Li, Zi (Graduate of Michigan State University)"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019"]},{"key":"dc:relation","label":"Dc Relation","values":["Electronic Theses & Dissertations"]},{"key":"dc:type","label":"Dc Type","values":["Text","Theses"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Magnetic flux--Measurement","Gas leakage--Testing","Petroleum pipeline failures","Petroleum pipelines","Nondestructive testing"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["etd:48069","isbn:9781085679657","isbn:1085679659","oclc:1138555628","umi:22615692","local:LI_grad.msu_0128N_17031","https://doi.org/doi:10.25335/mchp-yw18"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Pipelines are primary infrastructure to transport oil and natural gas with low cost. Magnetic flux leakage (MFL), one of the most popular electromagnetic nondestructive evaluation (NDE) methods, is a crucial inspection technique of pipeline safety to prevent long-term failures. The important problems in MFL inspection is to detect and characterize defects in terms of shape and size. In industry, the collected MFL data amount is quite large, Convolutional neural networks (CNNs), one of the main categories in deep learning applying to images classification problems, are considered as good approaches to make the classification. In solving the inverse problem to characterize the metal loss defects, the collected MFL signals are represented by three-axis signals in terms of three groups of matrics which are consistent in the form of images. Therefore, this M.S thesis proposed a novel CNN model to estimate the size and shape of defects fed by simulated MFL signals. Some comparative results of the proposed model prove that the method is robust for distortion and variances of input MFL signals and can be applied in other NDE problems with high classification accuracy. Besides, the prediction results are correlated and affected by the systematic and random uncertainties in the MFL inspection process. The proposed CNN is then combined with a Bayesian inference method to analyze the final classification results and make uncertainty estimation on defect identification in MFL inspection. The influences of data and model variation on aleatoric and epistemic uncertainties are addressed in my work. Further, the relationship between the classification accuracy and the uncertainties are described, which provide more hints to further research in MFL inspection.","Thesis (M.S.)--Michigan State University. Electrical Engineering, 2019","Includes bibliographical references (pages 61-75)"]},{"key":"dc:format","label":"Dc Format","values":["vii, 75 pages","application/pdf"]},{"key":"dc:title","label":"Title","values":["Deep learning techniques for magnetic flux leakage inspection with uncertainty quantification"]}]}],"canonical_facts":{"dc:contributor":["Deng, Yiming","Udpa, Lalita","Zhang, Mi"],"dc:creator":["Li, Zi (Graduate of Michigan State University)"],"dc:date":["2019"],"dc:description":["Pipelines are primary infrastructure to transport oil and natural gas with low cost. Magnetic flux leakage (MFL), one of the most popular electromagnetic nondestructive evaluation (NDE) methods, is a crucial inspection technique of pipeline safety to prevent long-term failures. The important problems in MFL inspection is to detect and characterize defects in terms of shape and size. In industry, the collected MFL data amount is quite large, Convolutional neural networks (CNNs), one of the main categories in deep learning applying to images classification problems, are considered as good approaches to make the classification. In solving the inverse problem to characterize the metal loss defects, the collected MFL signals are represented by three-axis signals in terms of three groups of matrics which are consistent in the form of images. Therefore, this M.S thesis proposed a novel CNN model to estimate the size and shape of defects fed by simulated MFL signals. Some comparative results of the proposed model prove that the method is robust for distortion and variances of input MFL signals and can be applied in other NDE problems with high classification accuracy. Besides, the prediction results are correlated and affected by the systematic and random uncertainties in the MFL inspection process. The proposed CNN is then combined with a Bayesian inference method to analyze the final classification results and make uncertainty estimation on defect identification in MFL inspection. The influences of data and model variation on aleatoric and epistemic uncertainties are addressed in my work. Further, the relationship between the classification accuracy and the uncertainties are described, which provide more hints to further research in MFL inspection.","Thesis (M.S.)--Michigan State University. Electrical Engineering, 2019","Includes bibliographical references (pages 61-75)"],"dc:format":["vii, 75 pages","application/pdf"],"dc:identifier":["etd:48069","isbn:9781085679657","isbn:1085679659","oclc:1138555628","umi:22615692","local:LI_grad.msu_0128N_17031","https://doi.org/doi:10.25335/mchp-yw18"],"dc:language":["English"],"dc:relation":["Electronic Theses & Dissertations"],"dc:rights":["In Copyright"],"dc:subject":["Magnetic flux--Measurement","Gas leakage--Testing","Petroleum pipeline failures","Petroleum pipelines","Nondestructive testing"],"dc:title":["Deep learning techniques for magnetic flux leakage inspection with uncertainty quantification"],"dc:type":["Text","Theses"]},"updated_at":"2026-11-18T18:53:16Z"}