Detection of Blockages of the Belt Conveyor Transfer Point Using an RGB Camera and CNN Autoencoder

In the material transfer area, belt is exposed to considerable damage, energy of falling lost, and there significant dust noise. One most common causes failure chute blockage, when flow in free fall or loading zone disturbed by oversized rock parts other objects, e.g., bolts. The a single point may cause entire transport route be excluded from work associated with costly breakdowns. For this reason, those places require continuous monitoring special surveillance measures. number methods for type blockage limited. article presents research results on possibility visual operating status an object underground copper ore mine. A standard industrial RGB camera was used obtain video recorded frames were processed detection algorithm based neural network. CNN autoencoder taught reconstruct image regular conditions. data set state validation.