Researchers from Russia created and patented a neural network complex that can control the bucket of a mining excavator.
The hardware part of the complex consists of a pair of stereo video cameras mounted in the excavator cabin and calibrated with laser rangefinders to obtain a 3D picture of the production process.
Scientists from the Ural Mining State University collected data to train three neural networks at different times of the year – in winter and summer, in cooperation with mining enterprises in asbestos and coal mines. Various excavators were used to make the development universal.
The complex determines the exact position of the excavator bucket and the environment in which it operates. One of the neural networks estimates the distance to objects. The other is responsible for the coordinates and electrical parameters of the main drives. The third defines the current technological process – scooping, transferring a full or empty bucket, unloading. The artificial intelligence then determines the optimum dumping point, the trajectory of movement to it and gives commands to the excavator control drives.
According to the researchers’ calculations, the introduction of a new technique will increase the productivity of the machines by up to 10%. This can be done in a few months with the interest of mining companies.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
