Process Analytical Technology (PAT) is a system for designing, analysing and controlling processes by measuring the critical process parameters and quality attributes of raw and processed materials to improve product quality, increase efficiency and reduce costs. Although the food industry could benefit from the implementation of PAT, complex production processes, strict legislation regarding operating conditions and the high CAPEX of sensors makes PAT applications technically difficult, time consuming and expensive to adopt.

YOGUSENSE aims to address these problems and mainstream the application of PAT among small and medium-sized food producers by demonstrating in a fermentation-based process the commercial feasibility and economic and environmental benefits of a PAT platform, merging data from sensors and analysers to create optimisation models for in-process and real-time quality control.

Six-month progress report
The main focus of the first six months was the design, development and purchase of the equipment and the lab validation and implementation of the solution. The design was revised twice to overcome issues with placing sensors in the yoghurt mix tank and ensuring accurate pH readings. At dairy company MANDREKAS, the project has prompted an overall rethink of the yoghurt production setup.

One key consideration is that the plant is currently not fully automated, which means the operators need to perform a manual task at key processing steps. The final AI-based model will aim to support operators in these tasks by (a) predicting when the next step will occur, based on historical data, training and current sensor measurements and (b) providing timely visual and aural cues so operators can react accordingly.

For MANDREKAS, the primary goal is to identify when the optimal pH is achieved during fermentation to ensure the final yoghurt has the required quality. By doing so, the company aims to reduce product rejects, extend shelf life and optimise resource efficiency overall.

Over the next months, the partners will explore opportunities to publish results about the use of AI modelling to improve yoghurt production in well-respected journals.

Final report summary
YOGUSENSE has achieved low-cost, end-to-end digitalisation of yogurt production, enabling the producer to achieve tighter quality control and continuous process optimisation. By maximising resource efficiency, the YOGUSENSE platform reduces the environmental impact of yogurt production and increases competitiveness.

• Reduced consumption of energy and water and lower CO2 emissions.
• Better utilisation of raw materials due to fewer rejected batches and less product waste.
• Reduced wastewater due to reduced cleaning requirements.
• Additional CO2 savings are expected due to extended product shelf-life and reduced waste through logistics.