New project film

The project's objective has been to develop novel concepts and methods for flexible and sustainable food processing in Norway. Watch the film and see what we have achieved.

Kunstig intelligens og interaktiv læring vil forme arbeidslivet

Vil roboter i nær fremtid klare å utføre kompleks bearbeiding av råstoff som i dag kun utføres av mennesker? Hvordan kan dette bidra til en mer bærekraftig matproduksjon i Norge? Den 4. februar ble den nasjonale konferansen TechFood arrangert av SINTEF Ocean i Trondheim. Konferansen handlet om digitalisering, kunstig intelligens og robotisert automasjon. Marianne Barland

Program og påmelding til TechFood og sluttmøte i iProcess

TechFood Vil roboter i nær fremtid klare å utføre kompleks bearbeiding av råstoff som i dag kun utføres av mennesker? Hvordan kan dette bidra til en mer bærekraftig matproduksjon i Norge? Hva kan robotene gjøre for oss i dag og i morgen? Kan de gjøre kompleks bearbeiding av råstoff som bare mennesker klarer i dag? Hvordan kan det bidra til en mer bærekraftig

Raman spectroscopy for quality differentiation of pork

Raman spectroscopy can be used for analysis of important quality indicators in meat, feasibly leading to on-line applications of the technique in the future.   Overall meat eating quality is very important for consumer confidence, willingness to pay and repeat purchase of fresh meat. Intramuscular fat (IMF) content, pH, water-holding capacity (WHC) and color are the best indicators

5 points to consider before setting sails in data science projects in the food industry

In the slipstream of the digitalization of modern food industry, part of Industry 4.0, a paramount need to handle larger and larger amounts of data has called for new developments in both the analytical toolbox and in digital infrastructure. It has expanded the possibilities of the creation of value from data.   Terms like Data Science, Big

Tracking non-rigid objects using depth camera

Surface of non-rigid objects, such as leafy vegetables, meats and fishes can be completely and accurately tracked using a depth camera with the approach proposed in this article. This is exceptionally useful while interacting with these objects using a robot.   Automating the handling of meats, vegetables, seafoods and other delicate and irregularly shaped consumables has

Raman spectroscopy for estimation of residual bone minerals in mechanically deboned chicken meat

Residual bone, measured as %calcium or %ash, is a strictly controlled quality parameter of mechanically deboned chicken meat (MDCM). Raman spectroscopy was developed as a rapid tool for estimation of this important parameter.  Mechanical deboning is a process where protein-reach mince is optimally recovered from animal carcasses. This process typically involves grinding of carcasses to

Porosity maps give an ‘airy’ image of fruit and vegetables

See the internal structure of your product through 3D X-ray based porosity mapping.   The porosity of a fruit or vegetable quantifies the amount of air spaces inside the product. The porosity strongly determines to what extent and how it dries out, or how well the product responses to modified or controlled atmopshere conditions.   A horticultural product transports

Managing supply uncertainty in operational production planning – A whitefish case study

Managing supply uncertainty by a formal stochastic programming approach demonstrates how expected profit may be increased due to more robust production plans.   Production planning Operational production planning deals with establishing optimal production plans. A production plan determines which production lines to utilize, which products to produce and allocation of resources such as personnel and machines.

Intermediary Real-Time Trajectory Interpolating with Cubic Hermite Splines

Real-time trajectory interpolation allows a Python-based sensor-integrating application to real-time control a Franka Emika robot. Application development in Python is much faster and easier than in C++.   When robot motion generation for a processing task is dependent on real-time sensor feed-back from the processing tool, the motion must be, by it’s nature, generated at the temporal micro to meso level in real-time. Some open robot controllers allow real-time trajectory feeding at the micro level. These are obvious candidates for such real-time sensor-based motion applications.   If a given application only requires real-time trajectory generation at the meso level, interpolation may be utilized for alleviating the application from the micro real-time requirement of the robot controller. This, in turn, opens for freedom of choice of the