Data-driven modelling and adaptive control of extrusion-based 3D printing of complex food systems

This project aims to combine sensing technologies and predictive models to develop robust adaptive control strategies for extrusion-based 3D food printing.


3D food printing is an innovative technology that enables the production of customized foods to meet specific consumer needs. Over the past decade, researchers have successfully printed a variety of food materials, including chocolate, pasta, cookies, and cheese, to demonstrate the applications of 3D food printing. This technology has shown its potential of enabling decentralized food production and personalized nutrition. However, the current printing control system has limited adaptability, which requires trial-and-error experiments when attempting to print new food materials. Improving the adaptability of the printing system will allow for precise dosing and smooth extrusion of complex food materials, resulting in greater stability and quality of the printed foods. An enhanced printing control system can improve the current 3D food printing success rate and accelerate the adoption of this technology in the mass consumer market.

Our goal

Our goal is to develop an adaptive printing control system capable of printing complex food materials with high accuracy and quality. To achieve this, we are integrating sensors such as vision cameras and near infrared sensors into the printing system. These sensors can characterize the physico-chemical properties of the food materials as well as the quality of the printed output.

Through the use of computer vision and data-driven models, we analyze sensor data to accurately predict the quality of food prints based on printing parameters and material properties. Our ultimate goal is to create a series of smart printing control strategies that can ensure high-precision and rapid printing of complex food materials. By deploying these control strategies to 3D food printers, we can make 3D food printing a more market-ready technology for personalized food production, meeting the increasing demands of consumers for customized foods.

See Demos:

Thermographic sensing of 3D food printing stability

Computer vision tracking of 3D food printing flow

Layer-wise analysis of 3D food printing accuracy

Project Publications:

Ma, Y., Potappel, J., Chauhan, A., Schutyser, M. A., Boom, R. M., & Zhang, L. (2023). Improving 3D food printing performance using computer vision and feedforward nozzle motion control.Journal of Food Engineering,339, 111277.

Ma, Y., Schutyser, M. A., Boom, R. M., & Zhang, L. (2022). Thermographic and rheological characterization of viscoelastic materials for hot-extrusion 3D food printing.Innovative Food Science & Emerging Technologies,81, 103135.

Ma, Y., Schutyser, M. A., Boom, R. M., & Zhang, L. (2021). Predicting the extrudability of complex food materials during 3D printing based on image analysis and gray-box data-driven modelling.Innovative Food Science & Emerging Technologies,73, 102764.