Fault Diagnosis of Reciprocating Compressor Based on Convolutional Neural Networks with Multisource Raw Vibration Signals

<table class="fixed-width table-group" id="tab2"><tr><td><table class="table"><colgroup><col style="width:7.93em"/><col style="width:13.42em"/><col style="width:12.69em"/><col style="width:5.41em"/></colgroup><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left"> </td><td class="align_center">power spectrum energy (+BP)</td><td class="align_center">wavelet packet energy (+BP)</td><td class="align_center">MSRCNN</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">Recognition rate</td><td class="align_center">60%</td><td class="align_center">87.27%</td><td class="align_center">100%</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of fault diagnosis results of different methods.</div>

Mathematical Problems in Engineering

tab2

Table 2

Table 2: Fault Diagnosis of Reciprocating Compressor Based on Convolutional Neural Networks with Multisource Raw Vibration Signals 