Flexible Scaling in Quality Station for Manufacturing Production

The document describes the restoration and implementation of the Vision station for the Modular Production System (MPS) laboratory, for which a Raspberry Pi 4 embedded system was used as the core, with a memory capacity 8 GB RAM, which allows performance to be more suitable for artificial vision control, and through its Ethernet port, digital pins and a WiFi module, communication with industrial protocols is facilitated. For the station to be able to recognize the machined parts from the laboratory, it was necessary to apply automatic learning supervised by the classification method, where 900 positive images of the parts and 500 negative images of the environment were used as input data, as well as A Windows program called Cascade-Trainer-Gui was designed capable of generating an xml file, in which the positive and negative images were uploaded, obtaining a file to be used in Python. In machine learning, the system was programmed in Python based on the OpenCV library, which interprets the xml file that contains the learning of the machined part, which together with identification codes, makes its operation similar to facial recognition of smartphones, adding the possibility of locating and recognizing the pieces within a controlled environment.