• anomalies
• data analysis
• data engineering
• industrial
• machine learning
• vibrations

The thesis work is the result of a company internship at Extra Red and the project had the aim of designing, developing and deploy a machine learning model for an industrial winding machine.
The machine learning model will allow to predict anomalous behavior of an industrial machine and also to exploit the reasons that causes those anomalies. The problem have been addressed by following a machine learning process pipeline and data analysis techniques. The work starts with an understanding of the legacy project and then gathering and engineering the data of the production machine for a coherent dataset. Hence, with the cleaned and engineered dataset, it have been possible to train machine learning models for predicting and also to understand the vibration phenomenon in real time production of the industrial machine.