Rock slag classification algorithm based on convolutional neural network

• Main Authors: QIAO FEI, ZHANG TIANQI, CHEN CHANGCHUAN, WANG XINLI, DAI SHAOSHENG, LIU KAI
• Format: Patent
• Language: Chinese; English
• Published: 10.05.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention relates to a rock slag classification algorithm based on a convolutional neural network, rock slag serves as a main product in the tunneling process and contains rich information, and research and engineering practice show that the working condition of a cutterhead can be speculated in real time by observing the category of the rock slag. The purpose of indirectly detecting the cutter head is achieved by identifying the types of the rock slag through images, so that on-site constructors are guided to check and replace cutters in time. The camera collects images above the conveying belt, the severe production environment is avoided, meanwhile, the advantages of being simple in equipment, low in loss, low in cost, long in monitoring time and the like are achieved, and the rock slag classification algorithm based on the convolutional neural network is provided by taking the algorithm as a motivation. In order to extract rock slag image features, firstly, learning parameters are migrated according t