The objective of this WP is to develop dynamic multi factorial process control strategies using machine learning architectures paired with microcontrollers and single-board computers to produce premium quality dried animal and plant based and further processed (extracts and powders) products.
This WP includes four targets:
1. Development of data management system (DMS), with infrastructural support by ENEA, Italy. All project data will be saved in the DMS based on available open source solutions.
2. Development and integration of smart monitoring and control systems (MCS), based on a "Quality by Design strategy", for smart monitoring and controlling of the specific process parameters to achieve the desired product quality with larger allowance in raw material variability and to minimize energy consumption and environmental impact.
3. Development of machine learning models to non-destructively predict changes in chemical and physicochemical characteristics of food during the process.
4. Setup transferability tests on existing process units with the aim of making new cost-effective and plug-and-play smart control strategies for industrial applications.
|Functional and final version of the smart MCS
|Report on setup transferability