Skip to main content
zenodoopen

Dataset for Digital Twin paper

<p>Description for each folder:</p> <p>1)&nbsp;The&nbsp;&quot;raw_signal_data&quot; folder contains original sensor data. The origigital sensor data is named as &quot;ACF-x-x.xlsx&quot;. In each excel document, three directions of vibration, current and force sensor data is included.&nbsp; Naming rules is as follows: &quot;ACF-1-2.xlsx&quot; represents the orginal sensor data from first layler&#39;s second slot in. &quot;ACF-2-3.xlsx&quot; represents the orginal sensor data from second layler&#39;s third&nbsp;slot.</p> <p>2)&nbsp;The original real measured surface roughness is in the &quot;Ra.xlsx&quot;.&nbsp;The corresponding cutting parameters for every raw signal data of each slot are shown&nbsp;in &quot;Ra.xlsx&quot; document as well.&nbsp;<br> 3) The prediction results from different models are save in &quot;prediction_results&quot;. The detalies are listed below.</p> <p>&nbsp; &nbsp;&quot;BPNN_all_signal.xlsx&quot; is the prediction result from BPNN used the combination of all sensors data as the model input&nbsp;<br> &nbsp;&nbsp; &nbsp;&quot;BPNN_current_signal.xlsx&quot; is the prediction result from BPNN used only the current sensor data as the model input&nbsp;<br> &nbsp;&nbsp; &nbsp;&quot;BPNN_force_signal.xlsx&quot; is the prediction results from BPNN used only the force sensor data as the model input&nbsp;<br> &nbsp;&nbsp; &nbsp;&quot;BPNN_vibration_signal.xlsx&quot; is the prediction result from BPNN used only the vibration sensor data as the model input<br> &nbsp;&nbsp; &nbsp;&quot;ELM.xlsx&quot; is the prediction result from ELM used the combination of all sensors data as the model input&nbsp;<br> &nbsp;&nbsp; &nbsp;&quot;GPR.xlsx&quot; is the prediction result from GPR used the combination of all sensors data as the model input<br> &nbsp;&nbsp; &nbsp;&quot;LASSO.xlsx&quot; is the prediction result from LASSO used the combination of all sensors data as the model input<br> &nbsp;&nbsp; &nbsp;&quot;MLR.xlsx&quot; is the prediction result from MLR used the combination of all sensors data as the model input<br> &nbsp;&nbsp; &nbsp;&quot;SVR.xlsx&quot; is the prediction result from SVR used the combination of all sensors data as the model input<br> &nbsp;&nbsp; &nbsp;&quot;cnn_all_signal.xlsx&quot; is the prediction result from CNN used the combination of all sensors data as the model input&nbsp;<br> &nbsp;&nbsp; &nbsp;&quot;cnn_current.xlsx&quot; is the prediction result from CNN used only the current sensor data as the model input&nbsp;<br> &nbsp;&nbsp; &nbsp;&quot;cnn_force.xlsx&quot; is the prediction results from CNN used only the force sensor data as the model input&nbsp;<br> &nbsp;&nbsp; &nbsp;&quot;cnn_vibration.xlsx&quot; is the prediction result from CNN used only the vibration sensor data as the model input<br> &nbsp;&nbsp; &nbsp;&quot;real_ytest.xlsx&quot; is the real-measured surface roughness data for testing models.</p>

ShareScore

32/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
16
Reuse readiness
8
Engagement
0