<?xml version="1.0"?>
<article xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" dtd-version="1.4" xsi:noNamespaceSchemaLocation="https://jats.nlm.nih.gov/archiving/1.4/xsd/JATS-archivearticle1.xsd" xml:lang="ru">
  <front>
    <journal-meta>
      <journal-id journal-id-type="ojs">IE</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">&#x421;&#x422;&#x420;&#x41E;&#x418;&#x422;&#x415;&#x41B;&#x42C;&#x41D;&#x42B;&#x415; &#x418; &#x414;&#x41E;&#x420;&#x41E;&#x416;&#x41D;&#x42B;&#x415; &#x41C;&#x410;&#x428;&#x418;&#x41D;&#x42B;</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>STROITEL'NYE I DOROZHNYE MASHINY</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="ppub">0039-2391</issn>
      <publisher>
        <publisher-name>&#x418;&#x41F; &#x41F;&#x43E;&#x434;&#x43A;&#x43E;&#x43B;&#x437;&#x438;&#x43D; &#x41C;.&#x41C;.</publisher-name>
      </publisher>
      <self-uri xlink:href="https://iereview.ru/index.php/IE"/>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="publisher-id">278</article-id>
      <article-categories>
        <subj-group xml:lang="ru" subj-group-type="heading">
          <subject>&#x41C;&#x410;&#x428;&#x418;&#x41D;&#x42B; &#x418; &#x41C;&#x415;&#x425;&#x410;&#x41D;&#x418;&#x417;&#x41C;&#x42B;</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title xml:lang="ru">&#x410;&#x43D;&#x430;&#x43B;&#x438;&#x437; &#x44D;&#x444;&#x444;&#x435;&#x43A;&#x442;&#x438;&#x432;&#x43D;&#x43E;&#x441;&#x442;&#x438; &#x43C;&#x435;&#x442;&#x43E;&#x434;&#x43E;&#x432; &#x43C;&#x430;&#x448;&#x438;&#x43D;&#x43D;&#x43E;&#x433;&#x43E; &#x43E;&#x431;&#x443;&#x447;&#x435;&#x43D;&#x438;&#x44F; &#x434;&#x43B;&#x44F; &#x43A;&#x440;&#x430;&#x442;&#x43A;&#x43E;&#x441;&#x440;&#x43E;&#x447;&#x43D;&#x43E;&#x433;&#x43E; &#x43F;&#x440;&#x43E;&#x433;&#x43D;&#x43E;&#x437;&#x438;&#x440;&#x43E;&#x432;&#x430;&#x43D;&#x438;&#x44F; &#x442;&#x440;&#x443;&#x434;&#x43E;&#x435;&#x43C;&#x43A;&#x43E;&#x441;&#x442;&#x438; &#x440;&#x435;&#x43C;&#x43E;&#x43D;&#x442;&#x43E;&#x432; &#x43D;&#x430; &#x43E;&#x441;&#x43D;&#x43E;&#x432;&#x435; &#x43E;&#x433;&#x440;&#x430;&#x43D;&#x438;&#x447;&#x435;&#x43D;&#x43D;&#x44B;&#x445; &#x442;&#x435;&#x43B;&#x435;&#x43C;&#x430;&#x442;&#x438;&#x447;&#x435;&#x441;&#x43A;&#x438;&#x445; &#x434;&#x430;&#x43D;&#x43D;&#x44B;&#x445;</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>Analysis of machine learning methods efficiency for short-term forecasting of repair labor intensity based on limited telematics data</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group content-type="author">
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid" authenticated="false">https://orcid.org/0009-0001-9296-0775</contrib-id>
          <name-alternatives>
            <name name-style="western" specific-use="primary" xml:lang="ru">
              <surname>&#x41C;&#x430;&#x437;&#x43B;&#x443;&#x43C;&#x44F;&#x43D;</surname>
              <given-names>&#x413;&#x440;&#x438;&#x433;&#x43E;&#x440;&#x438;&#x439; &#x421;&#x435;&#x440;&#x433;&#x435;&#x435;&#x432;&#x438;&#x447;</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Mazlumyan</surname>
              <given-names>Grigorii S.</given-names>
            </name>
          </name-alternatives>
          <xref ref-type="aff" rid="aff-1"/>
          <email>g.mazlumyan@madi.ru</email>
        </contrib>
        <contrib contrib-type="author">
          <name-alternatives>
            <name name-style="western" specific-use="primary" xml:lang="ru">
              <surname>&#x412;&#x430;&#x43B;&#x44F;&#x435;&#x432;</surname>
              <given-names>&#x41E;&#x43B;&#x435;&#x433; &#x410;&#x43B;&#x435;&#x43A;&#x441;&#x435;&#x435;&#x432;&#x438;&#x447;</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Valyaev</surname>
              <given-names>Oleg A.</given-names>
            </name>
          </name-alternatives>
          <xref ref-type="aff" rid="aff-1"/>
          <email>o.valyaev@madi.ru</email>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid" authenticated="false">https://orcid.org/0000-0003-1685-082X</contrib-id>
          <name-alternatives>
            <name name-style="western" specific-use="primary" xml:lang="ru">
              <surname>&#x421;&#x443;&#x431;&#x431;&#x43E;&#x442;&#x438;&#x43D;</surname>
              <given-names>&#x411;&#x43E;&#x440;&#x438;&#x441; &#x421;&#x435;&#x440;&#x433;&#x435;&#x435;&#x432;&#x438;&#x447;</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Subbotin</surname>
              <given-names>Boris S.</given-names>
            </name>
          </name-alternatives>
          <xref ref-type="aff" rid="aff-1"/>
          <email>bsubbotin@mail.ru</email>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid" authenticated="false">https://orcid.org/0000-0002-9405-7248</contrib-id>
          <name-alternatives>
            <name name-style="western" specific-use="primary" xml:lang="ru">
              <surname>&#x421;&#x43C;&#x438;&#x440;&#x43D;&#x43E;&#x432;</surname>
              <given-names>&#x41F;&#x435;&#x442;&#x440; &#x418;&#x43B;&#x44C;&#x438;&#x447;</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Smirnov</surname>
              <given-names>Petr I.</given-names>
            </name>
          </name-alternatives>
          <xref ref-type="aff" rid="aff-2"/>
          <email>smirnovpi@vogu35.ru</email>
        </contrib>
        <contrib contrib-type="author">
          <name-alternatives>
            <name name-style="western" specific-use="primary" xml:lang="ru">
              <surname>&#x411;&#x43E;&#x440;&#x43E;&#x432;&#x438;&#x43D;</surname>
              <given-names>&#x42E;&#x440;&#x438;&#x439; &#x41C;&#x438;&#x445;&#x430;&#x439;&#x43B;&#x43E;&#x432;&#x438;&#x447;</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Borovin</surname>
              <given-names>Yurij M.</given-names>
            </name>
          </name-alternatives>
          <xref ref-type="aff" rid="aff-3"/>
          <email>borovin@mail.ru</email>
        </contrib>
      </contrib-group>
      <aff-alternatives id="aff-1">
        <aff xml:lang="ru">
          <institution content-type="orgname">&#x41C;&#x43E;&#x441;&#x43A;&#x43E;&#x432;&#x441;&#x43A;&#x438;&#x439; &#x430;&#x432;&#x442;&#x43E;&#x43C;&#x43E;&#x431;&#x438;&#x43B;&#x44C;&#x43D;&#x43E;-&#x434;&#x43E;&#x440;&#x43E;&#x436;&#x43D;&#x44B;&#x439; &#x433;&#x43E;&#x441;&#x443;&#x434;&#x430;&#x440;&#x441;&#x442;&#x432;&#x435;&#x43D;&#x43D;&#x44B;&#x439; &#x442;&#x435;&#x445;&#x43D;&#x438;&#x447;&#x435;&#x441;&#x43A;&#x438;&#x439; &#x443;&#x43D;&#x438;&#x432;&#x435;&#x440;&#x441;&#x438;&#x442;&#x435;&#x442; (&#x41C;&#x410;&#x414;&#x418;), 125319, &#x433;. &#x41C;&#x43E;&#x441;&#x43A;&#x432;&#x430;, &#x41B;&#x435;&#x43D;&#x438;&#x43D;&#x433;&#x440;&#x430;&#x434;&#x441;&#x43A;&#x438;&#x439; &#x43F;&#x440;&#x43E;&#x441;&#x43F;&#x435;&#x43A;&#x442;, 64</institution>
        </aff>
        <aff xml:lang="en">
          <institution content-type="orgname">Moscow Automobile and Road Construction State Technical University (MADI), 64 Leningradsky Prospekt, Moscow, 125319</institution>
        </aff>
      </aff-alternatives>
      <aff-alternatives id="aff-2">
        <aff xml:lang="ru">
          <institution content-type="orgname">&#x412;&#x43E;&#x43B;&#x43E;&#x433;&#x43E;&#x434;&#x441;&#x43A;&#x438;&#x439; &#x433;&#x43E;&#x441;&#x443;&#x434;&#x430;&#x440;&#x441;&#x442;&#x432;&#x435;&#x43D;&#x43D;&#x44B;&#x439; &#x443;&#x43D;&#x438;&#x432;&#x435;&#x440;&#x441;&#x438;&#x442;&#x435;&#x442;, 160000, &#x433;. &#x412;&#x43E;&#x43B;&#x43E;&#x433;&#x434;&#x430;, &#x443;&#x43B;. &#x41B;&#x435;&#x43D;&#x438;&#x43D;&#x430;, &#x434;. 15</institution>
        </aff>
        <aff xml:lang="en">
          <institution content-type="orgname">Vologda State University, 15 Lenina St, Vologda, 160000</institution>
        </aff>
      </aff-alternatives>
      <aff-alternatives id="aff-3">
        <aff xml:lang="ru">
          <institution content-type="orgname">&#x420;&#x43E;&#x441;&#x441;&#x438;&#x439;&#x441;&#x43A;&#x438;&#x439; &#x433;&#x43E;&#x441;&#x443;&#x434;&#x430;&#x440;&#x441;&#x442;&#x432;&#x435;&#x43D;&#x43D;&#x44B;&#x439; &#x443;&#x43D;&#x438;&#x432;&#x435;&#x440;&#x441;&#x438;&#x442;&#x435;&#x442; &#x438;&#x43C;. &#x410;.&#x41D;. &#x41A;&#x43E;&#x441;&#x44B;&#x433;&#x438;&#x43D;&#x430;, 119071, &#x433;. &#x41C;&#x43E;&#x441;&#x43A;&#x432;&#x430;, &#x443;&#x43B;. &#x41C;&#x430;&#x43B;&#x430;&#x44F; &#x41A;&#x430;&#x43B;&#x443;&#x436;&#x441;&#x43A;&#x430;&#x44F;, &#x434;. 1</institution>
        </aff>
        <aff xml:lang="en">
          <institution content-type="orgname">The Kosygin State University of Russia, 1 Malaya Kaluzhskaya St, Moscow, 119071</institution>
        </aff>
      </aff-alternatives>
      <pub-date date-type="pub" publication-format="epub">
        <day>30</day>
        <month>03</month>
        <year>2026</year>
      </pub-date>
      <volume>70</volume>
      <issue>3</issue>
      <fpage>132</fpage>
      <lpage>141</lpage>
      <permissions>
        <copyright-statement xml:lang="ru">&#xA9; 2026 &#x421;&#x422;&#x420;&#x41E;&#x418;&#x422;&#x415;&#x41B;&#x42C;&#x41D;&#x42B;&#x415; &#x418; &#x414;&#x41E;&#x420;&#x41E;&#x416;&#x41D;&#x42B;&#x415; &#x41C;&#x410;&#x428;&#x418;&#x41D;&#x42B;. &#x412;&#x441;&#x435; &#x43F;&#x440;&#x430;&#x432;&#x430; &#x437;&#x430;&#x449;&#x438;&#x449;&#x435;&#x43D;&#x44B;.</copyright-statement>
        <copyright-statement xml:lang="en">&#xA9; 2026 STROITEL'NYE I DOROZHNYE MASHINY. All rights reserved.</copyright-statement>
        <copyright-year>2026</copyright-year>
        <copyright-holder xml:lang="ru">&#x421;&#x422;&#x420;&#x41E;&#x418;&#x422;&#x415;&#x41B;&#x42C;&#x41D;&#x42B;&#x415; &#x418; &#x414;&#x41E;&#x420;&#x41E;&#x416;&#x41D;&#x42B;&#x415; &#x41C;&#x410;&#x428;&#x418;&#x41D;&#x42B;</copyright-holder>
        <copyright-holder xml:lang="en">STROITEL'NYE I DOROZHNYE MASHINY</copyright-holder>
        <license license-type="open-access" specific-use="metadata" xlink:href="https://creativecommons.org/publicdomain/zero/1.0/" xml:lang="ru">
          <license-p>&#x41C;&#x435;&#x442;&#x430;&#x434;&#x430;&#x43D;&#x43D;&#x44B;&#x435; &#x43D;&#x430;&#x441;&#x442;&#x43E;&#x44F;&#x449;&#x435;&#x439; &#x437;&#x430;&#x43F;&#x438;&#x441;&#x438; &#x440;&#x430;&#x441;&#x43F;&#x440;&#x43E;&#x441;&#x442;&#x440;&#x430;&#x43D;&#x44F;&#x44E;&#x442;&#x441;&#x44F; &#x43D;&#x430; &#x443;&#x441;&#x43B;&#x43E;&#x432;&#x438;&#x44F;&#x445; Creative Commons CC0 1.0 (&#x43F;&#x435;&#x440;&#x435;&#x434;&#x430;&#x447;&#x430; &#x432; &#x43E;&#x431;&#x449;&#x435;&#x441;&#x442;&#x432;&#x435;&#x43D;&#x43D;&#x43E;&#x435; &#x434;&#x43E;&#x441;&#x442;&#x43E;&#x44F;&#x43D;&#x438;&#x435;).</license-p>
        </license>
        <license license-type="open-access" specific-use="metadata" xlink:href="https://creativecommons.org/publicdomain/zero/1.0/" xml:lang="en">
          <license-p>The metadata of this record are distributed under the Creative Commons CC0 1.0 Universal Public Domain Dedication.</license-p>
        </license>
      </permissions>
      <self-uri xlink:href="https://iereview.ru/index.php/IE/article/view/278"/>
      <abstract xml:lang="ru">
        <p>&#x420;&#x430;&#x437;&#x440;&#x430;&#x431;&#x43E;&#x442;&#x43A;&#x430; &#x438; &#x432;&#x435;&#x440;&#x438;&#x444;&#x438;&#x43A;&#x430;&#x446;&#x438;&#x44F; &#x438;&#x442;&#x435;&#x440;&#x430;&#x442;&#x438;&#x432;&#x43D;&#x43E;&#x439; &#x43C;&#x435;&#x442;&#x43E;&#x434;&#x438;&#x43A;&#x438; &#x43A;&#x440;&#x430;&#x442;&#x43A;&#x43E;&#x441;&#x440;&#x43E;&#x447;&#x43D;&#x43E;&#x433;&#x43E; &#x43F;&#x440;&#x43E;&#x433;&#x43D;&#x43E;&#x437;&#x438;&#x440;&#x43E;&#x432;&#x430;&#x43D;&#x438;&#x44F; &#x442;&#x440;&#x443;&#x434;&#x43E;&#x435;&#x43C;&#x43A;&#x43E;&#x441;&#x442;&#x438; &#x440;&#x435;&#x43C;&#x43E;&#x43D;&#x442;&#x43E;&#x432; &#x434;&#x43B;&#x44F; &#x430;&#x434;&#x430;&#x43F;&#x442;&#x438;&#x432;&#x43D;&#x43E;&#x433;&#x43E; &#x43F;&#x43B;&#x430;&#x43D;&#x438;&#x440;&#x43E;&#x432;&#x430;&#x43D;&#x438;&#x44F; &#x442;&#x435;&#x445;&#x43D;&#x438;&#x447;&#x435;&#x441;&#x43A;&#x43E;&#x433;&#x43E; &#x43E;&#x431;&#x441;&#x43B;&#x443;&#x436;&#x438;&#x432;&#x430;&#x43D;&#x438;&#x44F; &#x43D;&#x430; &#x440;&#x430;&#x43D;&#x43D;&#x438;&#x445; &#x44D;&#x442;&#x430;&#x43F;&#x430;&#x445; &#x446;&#x438;&#x444;&#x440;&#x43E;&#x432;&#x43E;&#x439; &#x442;&#x440;&#x430;&#x43D;&#x441;&#x444;&#x43E;&#x440;&#x43C;&#x430;&#x446;&#x438;&#x438;, &#x43A;&#x43E;&#x433;&#x434;&#x430; &#x434;&#x43E;&#x441;&#x442;&#x443;&#x43F;&#x43D;&#x44B; &#x43B;&#x438;&#x448;&#x44C; &#x43E;&#x433;&#x440;&#x430;&#x43D;&#x438;&#x447;&#x435;&#x43D;&#x43D;&#x44B;&#x435; &#x434;&#x430;&#x43D;&#x43D;&#x44B;&#x435; &#x43D;&#x430;&#x447;&#x430;&#x43B;&#x44C;&#x43D;&#x43E;&#x433;&#x43E; &#x43F;&#x435;&#x440;&#x438;&#x43E;&#x434;&#x430; &#x44D;&#x43A;&#x441;&#x43F;&#x43B;&#x443;&#x430;&#x442;&#x430;&#x446;&#x438;&#x438; (&#x434;&#x43E; 160 &#x442;&#x44B;&#x441;. &#x43A;&#x43C;). &#x41D;&#x430; &#x43C;&#x430;&#x441;&#x441;&#x438;&#x432;&#x435; &#x438;&#x437; 100 &#x440;&#x435;&#x430;&#x43B;&#x44C;&#x43D;&#x44B;&#x445; &#x437;&#x430;&#x44F;&#x432;&#x43E;&#x43A; &#x43F;&#x440;&#x43E;&#x432;&#x435;&#x434;&#x435;&#x43D; &#x441;&#x440;&#x430;&#x432;&#x43D;&#x438;&#x442;&#x435;&#x43B;&#x44C;&#x43D;&#x44B;&#x439; &#x430;&#x43D;&#x430;&#x43B;&#x438;&#x437; &#x43C;&#x435;&#x442;&#x43E;&#x434;&#x43E;&#x432; &#x43C;&#x430;&#x448;&#x438;&#x43D;&#x43D;&#x43E;&#x433;&#x43E; &#x43E;&#x431;&#x443;&#x447;&#x435;&#x43D;&#x438;&#x44F;: &#x433;&#x440;&#x430;&#x434;&#x438;&#x435;&#x43D;&#x442;&#x43D;&#x43E;&#x433;&#x43E; &#x431;&#x443;&#x441;&#x442;&#x438;&#x43D;&#x433;&#x430; (XGBoost, LightGBM), &#x440;&#x435;&#x43A;&#x443;&#x440;&#x440;&#x435;&#x43D;&#x442;&#x43D;&#x44B;&#x445; &#x43D;&#x435;&#x439;&#x440;&#x43E;&#x43D;&#x43D;&#x44B;&#x445; &#x441;&#x435;&#x442;&#x435;&#x439; (LSTM, GRU) &#x438; &#x43F;&#x43E;&#x43B;&#x438;&#x43D;&#x43E;&#x43C;&#x438;&#x430;&#x43B;&#x44C;&#x43D;&#x43E;&#x439; &#x440;&#x435;&#x433;&#x440;&#x435;&#x441;&#x441;&#x438;&#x438; 5-&#x433;&#x43E; &#x43F;&#x43E;&#x440;&#x44F;&#x434;&#x43A;&#x430;. &#x41A;&#x43B;&#x44E;&#x447;&#x435;&#x432;&#x44B;&#x43C; &#x43A;&#x440;&#x438;&#x442;&#x435;&#x440;&#x438;&#x435;&#x43C; &#x44D;&#x444;&#x444;&#x435;&#x43A;&#x442;&#x438;&#x432;&#x43D;&#x43E;&#x441;&#x442;&#x438; &#x432;&#x44B;&#x431;&#x440;&#x430;&#x43D;&#x430; &#x43E;&#x448;&#x438;&#x431;&#x43A;&#x430; &#x43F;&#x440;&#x43E;&#x433;&#x43D;&#x43E;&#x437;&#x430; &#x43D;&#x430; &#x43E;&#x434;&#x438;&#x43D; &#x43F;&#x43B;&#x430;&#x43D;&#x43E;&#x432;&#x44B;&#x439; &#x43C;&#x435;&#x436;&#x441;&#x435;&#x440;&#x432;&#x438;&#x441;&#x43D;&#x44B;&#x439; &#x438;&#x43D;&#x442;&#x435;&#x440;&#x432;&#x430;&#x43B; &#x432;&#x43F;&#x435;&#x440;&#x435;&#x434; (MAE_ext). &#x410;&#x43B;&#x433;&#x43E;&#x440;&#x438;&#x442;&#x43C; XGBoost &#x43F;&#x43E;&#x43A;&#x430;&#x437;&#x430;&#x43B; &#x43D;&#x430;&#x438;&#x43B;&#x443;&#x447;&#x448;&#x438;&#x439; &#x431;&#x430;&#x43B;&#x430;&#x43D;&#x441; &#x43C;&#x435;&#x436;&#x434;&#x443; &#x442;&#x43E;&#x447;&#x43D;&#x43E;&#x441;&#x442;&#x44C;&#x44E; &#x438;&#x43D;&#x442;&#x435;&#x440;&#x43F;&#x43E;&#x43B;&#x44F;&#x446;&#x438;&#x438; (R&#xB2;=0.89) &#x438; &#x443;&#x441;&#x442;&#x43E;&#x439;&#x447;&#x438;&#x432;&#x43E;&#x441;&#x442;&#x44C;&#x44E; &#x43A; &#x43A;&#x440;&#x430;&#x442;&#x43A;&#x43E;&#x441;&#x440;&#x43E;&#x447;&#x43D;&#x43E;&#x439; &#x44D;&#x43A;&#x441;&#x442;&#x440;&#x430;&#x43F;&#x43E;&#x43B;&#x44F;&#x446;&#x438;&#x438; (MAE_ext=0.55), &#x43F;&#x440;&#x435;&#x432;&#x437;&#x43E;&#x439;&#x434;&#x44F; &#x43F;&#x43E;&#x43B;&#x438;&#x43D;&#x43E;&#x43C;&#x438;&#x430;&#x43B;&#x44C;&#x43D;&#x44B;&#x435; &#x43C;&#x43E;&#x434;&#x435;&#x43B;&#x438;. &#x41D;&#x430; &#x435;&#x433;&#x43E; &#x43E;&#x441;&#x43D;&#x43E;&#x432;&#x435; &#x43F;&#x440;&#x435;&#x434;&#x43B;&#x43E;&#x436;&#x435;&#x43D; &#x43C;&#x435;&#x442;&#x43E;&#x434;&#x43E;&#x43B;&#x43E;&#x433;&#x438;&#x447;&#x435;&#x441;&#x43A;&#x438;&#x439; &#x444;&#x440;&#x435;&#x439;&#x43C;&#x432;&#x43E;&#x440;&#x43A;, &#x43E;&#x441;&#x43D;&#x43E;&#x432;&#x430;&#x43D;&#x43D;&#x44B;&#x439; &#x43D;&#x430; &#x43F;&#x440;&#x438;&#x43D;&#x446;&#x438;&#x43F;&#x435; &#xAB;&#x441;&#x43A;&#x43E;&#x43B;&#x44C;&#x437;&#x44F;&#x449;&#x435;&#x433;&#x43E; &#x433;&#x43E;&#x440;&#x438;&#x437;&#x43E;&#x43D;&#x442;&#x430; &#x43F;&#x440;&#x43E;&#x433;&#x43D;&#x43E;&#x437;&#x438;&#x440;&#x43E;&#x432;&#x430;&#x43D;&#x438;&#x44F;&#xBB; &#x438; &#x446;&#x438;&#x43A;&#x43B;&#x438;&#x447;&#x435;&#x441;&#x43A;&#x43E;&#x43C; &#x43F;&#x435;&#x440;&#x435;&#x43E;&#x431;&#x443;&#x447;&#x435;&#x43D;&#x438;&#x438;. &#x41D;&#x43E;&#x432;&#x438;&#x437;&#x43D;&#x430; &#x440;&#x430;&#x431;&#x43E;&#x442;&#x44B; &#x437;&#x430;&#x43A;&#x43B;&#x44E;&#x447;&#x430;&#x435;&#x442;&#x441;&#x44F; &#x432; &#x430;&#x434;&#x430;&#x43F;&#x442;&#x430;&#x446;&#x438;&#x438; &#x43F;&#x430;&#x440;&#x430;&#x434;&#x438;&#x433;&#x43C;&#x44B; &#x43E;&#x43D;&#x43B;&#x430;&#x439;&#x43D;/&#x438;&#x43D;&#x43A;&#x440;&#x435;&#x43C;&#x435;&#x43D;&#x442;&#x430;&#x43B;&#x44C;&#x43D;&#x43E;&#x433;&#x43E; &#x43E;&#x431;&#x443;&#x447;&#x435;&#x43D;&#x438;&#x44F; &#x434;&#x43B;&#x44F; &#x43F;&#x440;&#x438;&#x43A;&#x43B;&#x430;&#x434;&#x43D;&#x43E;&#x439; &#x437;&#x430;&#x434;&#x430;&#x447;&#x438; &#x443;&#x43F;&#x440;&#x430;&#x432;&#x43B;&#x435;&#x43D;&#x438;&#x44F; &#x441;&#x435;&#x440;&#x432;&#x438;&#x441;&#x43E;&#x43C; &#x43F;&#x430;&#x440;&#x43A;&#x430; &#x442;&#x435;&#x445;&#x43D;&#x438;&#x43A;&#x438; &#x438; &#x438;&#x43D;&#x442;&#x435;&#x440;&#x43F;&#x440;&#x435;&#x442;&#x430;&#x446;&#x438;&#x438; &#x43F;&#x440;&#x43E;&#x433;&#x43D;&#x43E;&#x437;&#x43D;&#x44B;&#x445; &#x43A;&#x43E;&#x44D;&#x444;&#x444;&#x438;&#x446;&#x438;&#x435;&#x43D;&#x442;&#x43E;&#x432; &#x43A;&#x430;&#x43A; &#x43C;&#x435;&#x442;&#x440;&#x438;&#x43A; &#x43E;&#x43F;&#x435;&#x440;&#x430;&#x446;&#x438;&#x43E;&#x43D;&#x43D;&#x43E;&#x433;&#x43E; &#x440;&#x438;&#x441;&#x43A;&#x430;. &#x41F;&#x440;&#x430;&#x43A;&#x442;&#x438;&#x447;&#x435;&#x441;&#x43A;&#x430;&#x44F; &#x437;&#x43D;&#x430;&#x447;&#x438;&#x43C;&#x43E;&#x441;&#x442;&#x44C; &#x2013; &#x432; &#x43F;&#x440;&#x435;&#x434;&#x43B;&#x43E;&#x436;&#x435;&#x43D;&#x438;&#x438; &#x43D;&#x430;&#x443;&#x447;&#x43D;&#x43E; &#x43E;&#x431;&#x43E;&#x441;&#x43D;&#x43E;&#x432;&#x430;&#x43D;&#x43D;&#x43E;&#x433;&#x43E;, &#x43E;&#x441;&#x442;&#x43E;&#x440;&#x43E;&#x436;&#x43D;&#x43E;&#x433;&#x43E; &#x43F;&#x43E;&#x434;&#x445;&#x43E;&#x434;&#x430; &#x43A; &#x437;&#x430;&#x43F;&#x443;&#x441;&#x43A;&#x443; &#x43F;&#x440;&#x435;&#x434;&#x438;&#x43A;&#x442;&#x438;&#x432;&#x43D;&#x43E;&#x433;&#x43E; &#x43E;&#x431;&#x441;&#x43B;&#x443;&#x436;&#x438;&#x432;&#x430;&#x43D;&#x438;&#x44F;, &#x43C;&#x438;&#x43D;&#x438;&#x43C;&#x438;&#x437;&#x438;&#x440;&#x443;&#x44E;&#x449;&#x435;&#x433;&#x43E; &#x440;&#x438;&#x441;&#x43A;&#x438; &#x440;&#x435;&#x448;&#x435;&#x43D;&#x438;&#x439; &#x43D;&#x430; &#x43E;&#x441;&#x43D;&#x43E;&#x432;&#x435; &#x43D;&#x435;&#x43A;&#x43E;&#x440;&#x440;&#x435;&#x43A;&#x442;&#x43D;&#x43E;&#x439; &#x44D;&#x43A;&#x441;&#x442;&#x440;&#x430;&#x43F;&#x43E;&#x43B;&#x44F;&#x446;&#x438;&#x438;.</p>
      </abstract>
      <trans-abstract xml:lang="en">
        <p>Development and verification of an iterative methodology for short-term forecasting of repair labor intensity for adaptive maintenance planning at the early stages of digital transformation, when only limited initial operating-period data are available (up to 160 thousand km). A comparative analysis of machine learning methods was carried out on a dataset of 100 repair requests: gradient boosting (XGBoost, LightGBM), recurrent neural networks (LSTM, GRU), and fifth-degree polynomial regression. The key efficiency criterion was the forecast error for one scheduled service interval ahead (MAE_ext). The XGBoost algorithm demonstrated the best balance between interpolation accuracy (R&#xB2;=0.89) and resistance to short-term extrapolation (MAE_ext=0.55), outperforming polynomial models. On this basis, a methodological framework was proposed that relies on the rolling forecasting horizon principle and cyclic retraining. The novelty of the study consists in adapting the online/incremental learning paradigm to the applied problem of fleet service management and in interpreting forecast coefficients as operational risk metrics. The practical significance lies in proposing a scientifically grounded and cautious approach to launching predictive maintenance, minimizing the risks of decisions based on incorrect extrapolation.</p>
      </trans-abstract>
      <kwd-group xml:lang="ru">
        <kwd>&#x43F;&#x440;&#x435;&#x434;&#x438;&#x43A;&#x442;&#x438;&#x432;&#x43D;&#x43E;&#x435; &#x43E;&#x431;&#x441;&#x43B;&#x443;&#x436;&#x438;&#x432;&#x430;&#x43D;&#x438;&#x435;</kwd>
        <kwd>&#x43C;&#x430;&#x448;&#x438;&#x43D;&#x43D;&#x43E;&#x435; &#x43E;&#x431;&#x443;&#x447;&#x435;&#x43D;&#x438;&#x435;</kwd>
        <kwd>&#x433;&#x440;&#x430;&#x434;&#x438;&#x435;&#x43D;&#x442;&#x43D;&#x44B;&#x439; &#x431;&#x443;&#x441;&#x442;&#x438;&#x43D;&#x433;</kwd>
        <kwd>&#x438;&#x442;&#x435;&#x440;&#x430;&#x442;&#x438;&#x432;&#x43D;&#x43E;&#x435; &#x43E;&#x431;&#x443;&#x447;&#x435;&#x43D;&#x438;&#x435;</kwd>
        <kwd>&#x43E;&#x433;&#x440;&#x430;&#x43D;&#x438;&#x447;&#x435;&#x43D;&#x43D;&#x44B;&#x435; &#x434;&#x430;&#x43D;&#x43D;&#x44B;&#x435;</kwd>
        <kwd>&#x442;&#x435;&#x43B;&#x435;&#x43C;&#x430;&#x442;&#x438;&#x43A;&#x430;</kwd>
        <kwd>&#x43F;&#x440;&#x43E;&#x433;&#x43D;&#x43E;&#x437;&#x438;&#x440;&#x43E;&#x432;&#x430;&#x43D;&#x438;&#x435; &#x442;&#x440;&#x443;&#x434;&#x43E;&#x435;&#x43C;&#x43A;&#x43E;&#x441;&#x442;&#x438;</kwd>
        <kwd>&#x443;&#x43F;&#x440;&#x430;&#x432;&#x43B;&#x435;&#x43D;&#x438;&#x435; &#x440;&#x438;&#x441;&#x43A;&#x430;&#x43C;&#x438;</kwd>
      </kwd-group>
      <kwd-group xml:lang="en">
        <kwd>predictive maintenance</kwd>
        <kwd>machine learning</kwd>
        <kwd>gradient boosting</kwd>
        <kwd>iterative learning</kwd>
        <kwd>limited data</kwd>
        <kwd>telematics</kwd>
        <kwd>labor intensity forecasting</kwd>
        <kwd>risk management</kwd>
      </kwd-group>
      <funding-group>
        <funding-statement xml:lang="ru">&#x418;&#x441;&#x441;&#x43B;&#x435;&#x434;&#x43E;&#x432;&#x430;&#x43D;&#x438;&#x435; &#x432;&#x44B;&#x43F;&#x43E;&#x43B;&#x43D;&#x435;&#x43D;&#x43E; &#x431;&#x435;&#x437; &#x432;&#x43D;&#x435;&#x448;&#x43D;&#x435;&#x433;&#x43E; &#x444;&#x438;&#x43D;&#x430;&#x43D;&#x441;&#x438;&#x440;&#x43E;&#x432;&#x430;&#x43D;&#x438;&#x44F;.</funding-statement>
        <funding-statement xml:lang="en">The study was conducted without external funding.</funding-statement>
      </funding-group>
      <counts>
        <page-count count="10"/>
      </counts>
      <custom-meta-group>
        <custom-meta>
          <meta-name>metadata-license</meta-name>
          <meta-value>
            <ext-link ext-link-type="uri" xlink:href="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0</ext-link>
          </meta-value>
        </custom-meta>
      </custom-meta-group>
    </article-meta>
  </front>
  <back>
    <ref-list xml:lang="ru">
      <title>&#x421;&#x43F;&#x438;&#x441;&#x43E;&#x43A; &#x43B;&#x438;&#x442;&#x435;&#x440;&#x430;&#x442;&#x443;&#x440;&#x44B;</title>
      <ref id="R1">
        <mixed-citation>Abbes S., Hassine H., Amari S., Chaari R., Haddar M. Remaining useful life prediction for aircraft maintenance using machine learning // Quality and reliability engineering international. 2026.</mixed-citation>
      </ref>
      <ref id="R2">
        <mixed-citation>Ajjaj S., El Houssaini S., Hain M., El Houssaini M.-A. Incremental online machine learning for detecting malicious nodes in vehicular communications using real-time monitoring // Telecom. 2023. Vol. 4. &#x2116; 3. pp. 629-648.</mixed-citation>
      </ref>
      <ref id="R3">
        <mixed-citation>Celestin M. How predictive maintenance in logistics fleets is reducing equipment downtime and operational losses // International journal of advanced research in engineering and technology. 2023. Vol. 7. &#x2116; 10. pp. 1023-1033.</mixed-citation>
      </ref>
      <ref id="R4">
        <mixed-citation>Chen T., Guestrin C. XGBoost: a scalable tree boosting system // Proceedings of the 22nd ACM SIGKDD Inter. conf. on Knowledge Discovery and Data mining (KDD 2016). 2016. pp. 785-794.</mixed-citation>
      </ref>
      <ref id="R5">
        <mixed-citation>Huang Z., Wei Y., Cheng Y. A quantitative framework for performance-based reliability prediction for a multi-component system subject to dynamic self-reconfiguration // Reliability Engineering and System Safety. 2025. Vol. 262. Art. 111188.</mixed-citation>
      </ref>
      <ref id="R6">
        <mixed-citation>Lu Q., An K., Li J., Wang J. Network intrusion detection for modern smart grids based on adaptive online incremental learning // IEEE transactions on smart grid. 2025. Vol. 16. &#x2116; 3. pp. 2541-2553.</mixed-citation>
      </ref>
      <ref id="R7">
        <mixed-citation>Martin T., Allg&#xF6;wer F. Data-driven system analysis of nonlinear systems using polynomial approximation // arXiv:2108.11298. 2021.</mixed-citation>
      </ref>
      <ref id="R8">
        <mixed-citation>Pakdemirli M. Polynomial regression analysis based on constrained data // Journal of mathematical problems, equations and statistics. 2025. Vol. 6. &#x2116; 2. pp. 135-139.</mixed-citation>
      </ref>
      <ref id="R9">
        <mixed-citation>Prytz R., Nowaczyk S., Rognvaldsson T., Byttner S. Predicting the need for vehicle compressor repairs using maintenance records and logged vehicle data // Engineering applications of Artificial Intelligence. 2015. Vol. 41. pp. 139-150.</mixed-citation>
      </ref>
      <ref id="R10">
        <mixed-citation>Rodriguez-Ramos A., Rivera P.J., Neto S., Llanes-Santiago O. Machine learning-based condition monitoring with novel event detection and incremental learning for industrial faults and cyberattacks // Processes. 2025. Vol. 13. &#x2116; 9. Art. 2984.</mixed-citation>
      </ref>
      <ref id="R11">
        <mixed-citation>Sahdev G., Agarwal S., Bhati P. Hybrid learning models for remaining useful life prediction of lithium-ion batteries in electric vehicles // IOP conf. Series: Materials science and engineering. 2025. Vol. 1334. &#x2116; 1. Art. 012003.</mixed-citation>
      </ref>
      <ref id="R12">
        <mixed-citation>Saravanan V. Data-driven assessment of selection criteria for commercial electric scooters // REST Journal on advances in mechanical engineering. 2025. Vol. 4. &#x2116; 4. &#x440;p. 21-29.</mixed-citation>
      </ref>
      <ref id="R13">
        <mixed-citation>Theissler A., P&#xE9;rez-Vel&#x430;zquez J., Kettelgerdes M., Elger G. Predictive maintenance enabled by machine learning: use cases and challenges in the automotive industry // Reliability engineering and system safety. 2021. Vol. 215. Article 107864.</mixed-citation>
      </ref>
      <ref id="R14">
        <mixed-citation>Vashisht S. Connected aftermarket services for off-highway vehicles: enhancing fleet management through real-time data and predictive maintenance // SAE technical paper series. 2025. Vol. 1.</mixed-citation>
      </ref>
      <ref id="R15">
        <mixed-citation>Xue K., Yang J., Yang M., Wang D. An improved generic hybrid prognostic method for RUL prediction based on PF-LSTM learning // IEEE Transactions on instrumentation and measurement. 2023. Vol. 72. &#x440;p. 1-21.</mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>
