Figure 1:
Performance difference between GWO and PSO. GWO, grey wolf optimizer; PSO, particle swarm optimization.
Figure 2:
Hierarchy of grey wolves.
Figure 3:
Quantitative damage identification method for wire rope core conveyor belts based on GWO-BP. BPs, backpropagations; GWO, grey wolf optimizer.
Figure 4:
Optimization flowchart based on GWO-BP. BP, backpropagation; GWO, grey wolf optimizer.
Figure 5:
Detection platform for internal damage in wire rope core conveyor belts.
Table 1:
Experimental instruments and main parameters
| Serial number | Experiment instrument | Quantity | Model | Rated voltage |
|---|---|---|---|---|
| 1 | Excitation device | 2 | RC300 | / |
| 2 | Speed sensor | 1 | GS10 (A) | DC12V |
| 3 | Injury detection sensors | 2 | GTSC300 | DC5V |
| 4 | Digital mining conversion workstation | 1 | TCK.W-AI-E9 | AC220V |
| 5 | Terminal master control unit | 1 | TCK.W-ZK1200-D | AC127V |
Figure 6:
Samples of wire breakage damage.
Figure 7:
Schematic diagram of feature values for steel cord damage signals.
Figure 8:
Local feature values of broken wires in the wire rope.
Figure 9:
Regression results of the dataset.
Figure 10:
Classification errors of two prediction models. BP, backpropagation; GWO, grey wolf optimizer.
Figure 11:
Classification and recognition performance of two neural network prediction models.
Figure 12:
Recognition accuracy of two prediction models under different numbers of broken threads. BP, backpropagation; GWO, grey wolf optimizer.
Figure 13:
Comparison of damage quantification identification between two prediction models. BP, backpropagation; GWO, grey wolf optimizer.