Deep Learning for Estimating the Fill-Level of Industrial Waste Containers of Metal Scrap: A Case Study of a Copper Tube Plant

Advanced digital solutions are increasingly introduced into manufacturing systems to make them more intelligent. Intelligent Waste Management Systems in industries allow for data collection and analysis better-informed decisions, monitor manage processes remotely, improve waste management. In many industries, scrap is collected large containers located on the factory floor, usually close its source. most cases, monitoring of containers’ fill levels either manually performed by visual inspection operators working proximity or employing intrusive mechanical such as weight sensors. This work presents a computer vision system that uses Deep Learning (DL) Convolutional Neural Network (CNN) automated estimation level industrial metal scrap. The training method parameters well classification performance VGG16 CNN was retrained upon images field, presented detail. proposed has been validated an case study from copper tube production industry which two estimated. A total 9772 were captured first container 11,234 second container. model achieved accuracy 77.5% 95% testing dataset. demonstrates sufficient classifying allows development management applications environments.