<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04165856</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-10T20:43:34+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="fr">A federated learning approach for rolling bearing fault diagnosis on data sources with imbalanced class distribution</title>
            <author role="aut">
              <persName>
                <forename type="first">Fabrizio</forename>
                <surname>de Fabritiis</surname>
              </persName>
              <email type="md5">b3ecd3bc2144555b70b7c3581c8b8470</email>
              <email type="domain">kuleuven.be</email>
              <idno type="idhal" notation="numeric">1271314</idno>
              <idno type="halauthorid" notation="string">2864139-1271314</idno>
              <affiliation ref="#struct-565244"/>
              <affiliation ref="#struct-230193"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Konstantinos</forename>
                <surname>Gryllias</surname>
              </persName>
              <idno type="halauthorid">1206463-0</idno>
              <affiliation ref="#struct-565244"/>
              <affiliation ref="#struct-230193"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>CCSD</forename>
                <surname>Sciencesconf.org</surname>
              </persName>
              <email type="md5">2dac992f64ee924a7ad555e53daad36f</email>
              <email type="domain">sciencesconf.org</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-07-19 13:29:12</date>
              <date type="whenModified">2023-11-23 10:48:07</date>
              <date type="whenReleased">2023-07-19 13:35:11</date>
              <date type="whenProduced">2023-07-10</date>
              <date type="whenEndEmbargoed">2023-07-19</date>
              <ref type="file" target="https://hal.science/hal-04165856v1/document">
                <date notBefore="2023-07-19"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04165856v1/file/SURVISHNO_full_paper_F_De_Fabritiis_K_Gryllias.pdf" id="file-4165856-3627736">
                <date notBefore="2023-07-19"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="167428">
                <persName>
                  <forename>CCSD</forename>
                  <surname>Sciencesconf.org</surname>
                </persName>
                <email type="md5">2dac992f64ee924a7ad555e53daad36f</email>
                <email type="domain">sciencesconf.org</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04165856</idno>
            <idno type="halUri">https://hal.science/hal-04165856</idno>
            <idno type="halBibtex">defabritiis:hal-04165856</idno>
            <idno type="halRefHtml">&lt;i&gt;Surveillance, Vibrations, Shock and Noise&lt;/i&gt;, Institut Supérieur de l'Aéronautique et de l'Espace [ISAE-SUPAERO], Jul 2023, Toulouse, France</idno>
            <idno type="halRef">Surveillance, Vibrations, Shock and Noise, Institut Supérieur de l'Aéronautique et de l'Espace [ISAE-SUPAERO], Jul 2023, Toulouse, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4165856-3627736"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SURVISHNO2023">Surveillance, Vibrations, Shock and Noise</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="fr">A federated learning approach for rolling bearing fault diagnosis on data sources with imbalanced class distribution</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Fabrizio</forename>
                    <surname>de Fabritiis</surname>
                  </persName>
                  <email type="md5">b3ecd3bc2144555b70b7c3581c8b8470</email>
                  <email type="domain">kuleuven.be</email>
                  <idno type="idhal" notation="numeric">1271314</idno>
                  <idno type="halauthorid" notation="string">2864139-1271314</idno>
                  <affiliation ref="#struct-565244"/>
                  <affiliation ref="#struct-230193"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Konstantinos</forename>
                    <surname>Gryllias</surname>
                  </persName>
                  <idno type="halauthorid">1206463-0</idno>
                  <affiliation ref="#struct-565244"/>
                  <affiliation ref="#struct-230193"/>
                </author>
              </analytic>
              <monogr>
                <idno type="localRef">78235</idno>
                <meeting>
                  <title>Surveillance, Vibrations, Shock and Noise</title>
                  <date type="start">2023-07-10</date>
                  <date type="end">2023-07-13</date>
                  <settlement>Toulouse</settlement>
                  <country key="FR">France</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>Institut Supérieur de l'Aéronautique et de l'Espace [ISAE-SUPAERO]</name>
                </respStmt>
                <imprint/>
              </monogr>
              <ref target="https://survishno2023.sciencesconf.org/453694" type="seeAlso"/>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="fr">French</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="spi">Engineering Sciences [physics]</classCode>
              <classCode scheme="halDomain" n="spi.acou">Engineering Sciences [physics]/Acoustics [physics.class-ph]</classCode>
              <classCode scheme="halDomain" n="spi.meca.vibr">Engineering Sciences [physics]/Mechanics [physics.med-ph]/Vibrations [physics.class-ph]</classCode>
              <classCode scheme="halDomain" n="spi.signal">Engineering Sciences [physics]/Signal and Image processing</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Rotating machinery fault diagnosis is a field of intensive research, attracting the last years a particular interestfor data-driven methodologies such as Machine Learning and Deep Learning. In order to build such models,the general assumption is that a sufficient number of healthy and fault samples, collected under various workingconditions, are available for model training. This assumption is often not realistic in real industry. This limi-tation could be avoided by exploiting data sets collected at multiple industrial partners, but this is in practicenot easily feasible since companies prefer not to share their data for privacy reasons. Federated Learning (FL)is an emerging machine learning approach proposed to train a global model without sharing data among users.In this context an FL methodology for fault classification based on Convolutional Neural Networks (CNN) isproposed in this paper. Local models are trained on local data sets, each one owned by a single client, i.e. anindustrial participant, and are then aggregated at a server level. In the baseline Federated Learning approach,local models optimization fails to increase global accuracy with model aggregation in case there is significantstatistical heterogeneity in the data distributions among clients. Thus the aim of this paper is the proposal of anenhanced strategy that accounts for adaptive local updates and the comparison of its performance with state-of-the-art techniques. Each participant computes the local stochastic gradients within an adaptive interval, set bythe server at the aggregation step, when the models are loaded by the participants at the end of each communi-cation round. The improved method is applied for bearing fault diagnosis and its effectiveness and accuracy areevaluated in the case of imbalanced class distribution in rolling bearing fault local data sets, i.e. considering ascenario where fault types are non-independent and identically distributed (non-i.i.d.) among clients. This caseis addressed in literature to be one of the main challenges in FL and is of practical interest since skewed datasets are common in real-world factories.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-565244" status="VALID">
          <orgName>Flanders Make</orgName>
          <desc>
            <address>
              <country key="BE"/>
            </address>
            <ref type="url">https://www.flandersmake.be/en</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-230193" status="VALID">
          <orgName>Department of Mechanical Engineering [Leuven]</orgName>
          <desc>
            <address>
              <addrLine>Celestijnenlaan 300B, box 2420, 3001 Heverlee</addrLine>
              <country key="BE"/>
            </address>
            <ref type="url">http://www.mech.kuleuven.be/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300656" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300656" status="VALID">
          <idno type="ROR">https://ror.org/05f950310</idno>
          <orgName>Catholic University of Leuven = Katholieke Universiteit Leuven</orgName>
          <orgName type="acronym">KU Leuven</orgName>
          <desc>
            <address>
              <addrLine>Oude Markt 13 - bus 5005, 3000 Leuven</addrLine>
              <country key="BE"/>
            </address>
            <ref type="url">http://www.kuleuven.be/english/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>