Abstract:

Industry 4.0, also known as the fourth industrial revolution, introduces advanced automation and robotization of manufacturing processes. The aim of this change is to support human work and optimize job positions to increase production efficiency. Within this framework, Machine Learning is a key tool that allows machines to improve their performance based on previously collected experience. Various industries, such as waste management, food production, automotive, and aerospace, require precise sorting and categorization of products and waste materials. Efficient sorting is particularly important in the era of automated production lines. Products, semi-finished goods, and waste can be differentiated based on various categories, such as color, specific mass, density, consistency, shape, dimensions, and chemical composition. There are advanced but costly methods of distinguishing products with different dimensions and shapes using sensors, scanners, cameras, or sets of sieves that allow only desired products to pass through. On the other hand, for products with uniform shapes and/or dimensions, or for unique products like crushed PET bottles in distinct colors, optical product differentiation is recommended, for example, by detecting the desired color.
This article describes an example of applying machine learning processes using a constructed prototype of a sorting device. The document presents innovative methods used in the industry (PET recycling sector), outlines product differentiation methods, and identifies industries in which the prototype developed by the article's author would find application. The author describes the technology of product differentiation using colorful metal labels as an example. The article presents machine learning technology, identification, transportation, and sorting. In the summary, the author presents directions for development to commercialize the prototype project.