| dc.description.abstract | The agricultural value chain in general and food processing specifically are facing challenges at multiple levels (social, ecological, financial). Within the European Union, Food and Beverage (F&B) is the biggest economic sector with more than 99 % being small and medium enterprises (SMEs). Due to the lack of financial flexibility, SMEs are generally disadvantaged for implementation and integration of process and resource efficiency, thus hindering the development of advanced processing methods and in turn the production of high quality products. Additionally, as per the Sustainable Development Goals 2 and 12, it is important to improve food and nutritional security globally, through sustainable agriculture and food production methods. Therefore, it is essential to develop innovative solutions that are not only affordable but also sustainable. Within the food processing chain, drying is one of the oldest and most frequently implemented processing method, for preserving food products, reducing post-harvest losses and increasing the food and nutritional status. As simple as it may seem, drying is rather a complex process, which, if not optimized on a system level, results in (1) significant quality degradation and (2) resource wastage. Additionally, as most food products undergo at least partial drying, optimisation of this process will evidently help improve and optimise the food processing chain. In this context, concepts such as „Smart Food Factory“ and „Industry 4.0“ recognise the need for intelligent processing methods that facilitate the production of tailored final product quality. Recently, there has been significant advancement from the information and communications technology domain due to methodologies such as Internet of things (IoT), Cloud-Computing, and Artificial Intelligence (AI), which has led to a rapid development of digitalisation in the F&B sector. Studies indicate that AI methodologies such as fuzzy logic and artificial neural networks are helpful tools to resolve problems within the drying process. Additionally, integration of machine learning models with AI methodologies can also allow for real time optimisation and control of the drying system. To that end, this study aims to conduct an in-depth review on the current state of AI applications that have been integrated within the convective drying process and provide a future outlook for the development of intelligent drying systems which simultaneously cater for improved food quality, energy and resource efficiency. | en |
