Portal de Periódicos da CAPES

Using Neural Network for Predicting the Load of Conveyor Systems

2021; Springer International Publishing; Linguagem: Inglês

10.1007/978-3-030-85540-6_90

2367-3370

Teodor Boyadzhiev, Ivaylo Andonov, Simeon Tsvetanov,

Industrial Automation and Control Systems

Usually the purpose of a conveyor is not only to transfer the load to its destination but also to make a buffer that allows storing some number of products before the accepting side is available. Compromise between the throughput and storage density gets harder when the load varies during operation. The conveyour’s efficiency could improve if it can predict the load. Here we present a novel method for finding load distribution patterns in conveyor systems using neural network in order to predict the load and to automatically adapt the conveyor behavior. We used simulated input load and output loads for the conveyour to train a neural network. The experimental results showed that the network is able to predict the input and output loads with high accuracy.