EcoefIoT

Context

In 2021, AZTI published the FoodTure report, which highlights the need to move towards a more sustainable, healthy and innovative agrifood industry, especially after the 2020 health crisis, which demonstrated the importance of having a robust and resilient sector.

In this new scenario, digitalisation is emerging as a key element to improve the efficiency and competitiveness of the Basque agrifood sector throughout the value chain. In the Basque Country, this transformation is being promoted through various strategic initiatives and support programmes aimed at facilitating the adoption of digital technologies by companies.

However, the level of digitalisation in the sector remains limited, with shortcomings in process monitoring and information centralisation. Moreover, digitalisation is a continuous process that is accelerating with the incorporation of artificial intelligence.

In this context, AZTI has made progress in recent years in the development of low-cost IoT solutions for capturing and centralising industrial process data, validating prototypes and platforms that lay the foundations for a progressive digital transformation of the food industry.

Objectives

The overall objective of the project is to continue advancing towards an innovative and competitive Basque agrifood sector, supported by the digitalisation of value chains as a basis for value creation, modernisation and increased sector competitiveness.

To achieve this, the project focuses on the progressive digital transformation of the different links in the agrifood chain, addressing the different layers required to move towards a Food Chain 4.0. These layers include process sensorisation, the digitalisation and centralisation of information through IoT platforms, and subsequently the advanced exploitation of data, ranging from basic process control to the generation of predictive models and digital twins.

The specific objective of the project is to continue the digitalisation of pilot processes that are already partially monitored and/or whose information is not centralised. To this end, the project builds on the experience initiated in 2024, based on the standardisation of a low-cost system for capturing 4–20 mA and MODBUS signals, as well as the incorporation of new sensors to improve monitoring and advance process modelling.

To achieve this objective, the project includes the following work phases:

1. Validation of pilot monitoring of a plant unit through the AZTI-IoT platform, including process and quality parameters.
2. Generation and recording of data from equipment and quality parameters, supported by experimental analyses.
3. Process modelling and development of predictive systems, both at unit-operation and plant level.
4. Application of artificial intelligence techniques to refine and improve predictive models.
5. Generation of a digital twin of the monitored system.

Expected impact

In general, the digitalisation of the food industry enables progress towards greater production efficiency, thanks to more precise process monitoring, error reduction, and greater autonomy of production systems.

The integration of technologies such as IoT and Big Data provides a global view of the value chain, improves food traceability, inventory and process control, and strengthens food safety through early detection of deviations. Likewise, the use of Business Intelligence tools enables more informed decision-making based on real-time data.

From an environmental perspective, digital systems contribute to water and energy savings, the reduction of losses and waste, and improved continuous evaluation of environmental impact, promoting more sustainable production models aligned with the circular economy.

More specifically, this project will enable AZTI to generate the knowledge required to address the digitalisation of processes with insufficient or non-centralised monitoring, through the validation of a low-cost data acquisition interface, robust and scalable. The results will lay the foundations for its future deployment in real industrial environments and for the development of predictive models and digital twins applied to the food industry.

Funding