Deep Sparse Autoencoder for Feature Extraction and Diagnosis of Locomotive Adhesion Status

<table class="fixed-width table-group" id="tab1"><tr><td><table class="table"><colgroup><col style="width:10.75em"/><col style="width:15.35em"/></colgroup><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Different types of States</td><td class="align_center">State representation</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Normal</td><td class="align_center">Running with a low adhesion</td></tr><tr><td class="align_left" colspan="2"><hr/></td></tr><tr><td class="align_left">Fault symptom</td><td class="align_center">Near the peak adhesion coefficient</td></tr><tr><td class="align_left" colspan="2"><hr/></td></tr><tr><td class="align_left">Small fault</td><td class="align_center">Across the peak adhesion point</td></tr><tr><td class="align_left" colspan="2"><hr/></td></tr><tr><td class="align_left">Large fault</td><td class="align_center">Serious slip running unsafe already</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Description of adhesion state of locomotive wheel rail.</div>

Journal of Control Science and Engineering

tab1

Table 1

Table 1: Deep Sparse Autoencoder for Feature Extraction and Diagnosis of Locomotive Adhesion Status 