The aim of the course is providing the basic techniques for both the analysis of industrial data through machine learning techniques and the design and analysis of experiments in an industrial environment.
In particular, for what concerns the analysis of industrial data the objective is the knowledge of the most important methodologies for exploratory data analysis, process understanding and troubleshooting, product quality improvement, and process monitoring. For what concerns the design and the analysis of experiment the student will acquire competences on how to plan a set of experiments and manage them with scarce resources in an industrial/laboratory environment. Furthermore, the student will learn how to carry out the analysis of experiments to optimize an experimental campaign.
At the end of the course, the student will be able to: analyze (uni- and multi-variate industrial/laboratory data to evaluate the quality of a product and/or the status of a process; improve process understanding from data and aid process and product optimization; monitor a product/process to identify and diagnose anomalies, malfunctions and faults; evaluate the available resources, organize and manage an experimental campaign in an industrial/laboratory environment; extract the most meaningful information from the experimentation and identify the optimal conditions to run a process.
In particular, for what concerns the analysis of industrial data the objective is the knowledge of the most important methodologies for exploratory data analysis, process understanding and troubleshooting, product quality improvement, and process monitoring. For what concerns the design and the analysis of experiment the student will acquire competences on how to plan a set of experiments and manage them with scarce resources in an industrial/laboratory environment. Furthermore, the student will learn how to carry out the analysis of experiments to optimize an experimental campaign.
At the end of the course, the student will be able to: analyze (uni- and multi-variate industrial/laboratory data to evaluate the quality of a product and/or the status of a process; improve process understanding from data and aid process and product optimization; monitor a product/process to identify and diagnose anomalies, malfunctions and faults; evaluate the available resources, organize and manage an experimental campaign in an industrial/laboratory environment; extract the most meaningful information from the experimentation and identify the optimal conditions to run a process.
- Docente: Pierantonio Facco