DigiFoods - Digital Food Quality

DigiFoods develops smart sensors for measuring and digitizing food quality directly on the production line. This information can be used to optimize both processes and value chains for increased profitability and reduced food waste. The quality of raw materials in the food industry varies greatly. Measuring this quality in process is challenging due to the large biological variation. The solutions being developed are based on a fundamental understanding of food quality, processing, and modern optical instrumentation, and will make it possible to measure and manage raw material variations in real-time. We also introduce robotics to enable automatic measurements in challenging processes and in the field. We study and develop concepts for how large-scale measurements can be used to 1) improve primary production and 2) differentiate products of varying quality for different consumer segments to reduce waste also at the consumer level. DigiFoods, with its 23 partners, functions as an innovation center for the food industry, technology providers, and scientific communities. Fourier-transform infrared spectroscopy (FTIR) is promising for measuring protein composition, and there is currently no industrial solution for such measurements. We have shown that FTIR can measure relevant variations in peptide sizes and collagen content in industrial peptide mixtures from enzymatic hydrolysis, two important quality indicators. A portable FTIR instrument has been built and tested with good results. This enables rapid measurements in the industry and facilitates better understanding and control of such bioprocesses. IR technology can be miniaturized and based on new types of LEDs (light-emitting diodes) that produce radiation in the mid-IR region. This enables small handheld sensor systems that can be used to measure a variety of chemical properties in foods. Semiconductor lasers (QCL, quantum cascade lasers) also generate light in the IR range and are suitable for low-cost measurement systems. Prototypes have been developed based on each of the two technologies and are being tested on various food applications. Raman spectroscopy can measure a variety of quality characteristics in food during processing. We have determined that the method can be used to measure the proportion of bone fragments, fat, protein, and collagen in ground poultry by-products. The method has been successfully tested in an industrial process. Raman is also suitable for measuring EPA and DHA in whole salmon fillets in motion on a conveyor belt. In-line measurement on salmon fillets with Raman may require robotic control that includes machine vision and algorithms that optimally handle the measurement probe. A preliminary demonstrator of such a system has been developed and tested at the center. Agricultural robots can use sensors in the field, and automatic measurement of sweetness in strawberries using a new NIR sensor is under development. An important activity at the center is to conduct measurements in industrial processes, and we have worked on the following cases: in-line measurement of dry matter in potatoes before frying, measurement of dry matter in cheese, measurement of core temperature in fish cakes after heat treatment, fat content in sausages, fat, protein, and bone in by-products of chicken and salmon, quality characteristics of salmon fillets. All these methods are new, and some have already contributed to significant process improvements that result in less waste and more consistent final quality. We develop data analytical solutions that utilize measurements of food quality to reduce waste and increase profitability in food production. We work with three strategies to manage variation in food quality: 1) Collect large datasets where we compile food quality with other available farm or production data to identify risk factors and understand the underlying causes of variation. 2) Use in-line measurements of food quality to monitor and adjust processes in real-time to ensure that quality remains stable. 3) Product differentiation, developing and marketing products of varying quality to different consumer groups. Some highlights from the past year: - We have developed a new NIR sensor for rapid and non-contact measurement of sweetness in strawberries and tomatoes. This has been tested on an autonomous robot and for measurements directly in process lines. The NIR sensor has great potential also in the seafood and meat industries. - A newly developed portable dry-film FTIR instrument has been tested with good results, enabling for the first time the characterization of protein hydrolysate quality at-line in the process. A PhD was recently completed on the topic - In cheese production, a partner has established in-line measurements of dry matter in every cheese, ending the practice of time-consuming spot checks. They now have better control over the process, contributing to increased profitability and better utilization of incoming milk.

The goal of SFI Digital Food Quality (DigiFoods) is to develop inline smart, sensor-driven solutions that deliver the essential food quality information required for successful process optimisation and digitalization of the food industry. Food processes are extremely complex and challenging to measure due to the inherent high level of biological variation in raw materials. The development of advanced solutions that are built on a fundamental understanding of food science, will allow the food industry to effectively measure and handle these variations, enabling a ground-breaking digital transformation of the industry. Effective strategies for real-time analysis and utilization of industrial data at a large scale will optimise processes and reduce waste throughout the value chain. New levels of information flow will also significantly increase productivity. DigiFoods will innovatively combine applied and basic research to generate new basic knowledge, evaluate prototype solutions, and create results for innovation in the following core areas 1) novel sensor systems and food application development, 2) robot and sensor integration, 3) integrated inline sensor solutions, and 4) analysis and utilisation of large-scale process and value chain data. A multi-disciplinary team comprising food companies, technology providers and research institutions is highly motivated to collaborate towards this common goal. The industrial partners will participate in all research tasks, committing essential in-kind contributions to the project. A critical element of this centre is that much of the experimental work will be done in the industrial process lines, which the end-users will make available for research. The centre will educate 9 PhD students and 3 post docs. DigiFoods will be governed by a board with an industrial majority, ensuring relevant research that will build the foundation for a future food industry 4.0.