Rolling Bearing Fault Diagnosis Based on Stacked Autoencoder Network with Dynamic Learning Rate

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Network structure</td><td class="align_center">Accuracy (%)</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">800-400-400-400-10</td><td class="align_center">95.73</td></tr><tr><td class="align_left">800-400-300-100-10</td><td class="align_center">97.86</td></tr><tr><td class="align_left">800-600-250-100-10</td><td class="align_center">96.99</td></tr><tr><td class="align_left">800-400-200-100-10</td><td class="align_center">98.97</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of accuracy of different grid structures.</div>

Advances in Materials Science and Engineering

tab2

Table 2

Table 2: Rolling Bearing Fault Diagnosis Based on Stacked Autoencoder Network with Dynamic Learning Rate 