| KEYWORD |
Machine Learning Techniques for Process Control in Mechanical Manufacturing
keywords DEEP NEURAL NETWORKS, INDUSTRY 4.0, MACHINE LEARNING, NEURAL NETWORKS, PREDICTIVE MAINTENANCE, PROCESS CONTROL, SMART MANUFACTURING
Reference persons DANIELE JAHIER PAGLIARI
External reference persons Nicola Zaquini, Balance Systems S.r. l.
Research Groups GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA
Thesis type IMPLEMENTATION, INDUSTRIAL, RESEARCH
Description Design and software implementation of a manufacturing process control system using Machine/Deep Learning methods.
The thesis will be carried out in collaboration with Balance Systems S.r.l.
In the context of mechanical manufacturing, the goal is to develop a manufacturing process control and predictive maintenance system using data gathered from sensors mounted on industrial machines. Specifically, the work will focus on acceleration and vibration sensors. The data will be analyzed using machine/deep learning techniques, with the goal of predicting malfunctionings or faults.
The student will implement and compare different Machine Learning techniques, with the goal of identifying the best solution in terms of both prediciton accuracy and computational complexity.
Required skills I candidati devono avere buone abilità di programmazione ed essere interessati al machine/deep learning ed alle sue applicazioni.
Avere esperienza con Python e C++ ed avere già delle nozioni base di machine/deep learning è sicuramente preferibile ma non necessario.
Deadline 14/11/2020
PROPONI LA TUA CANDIDATURA