Discover our suite of Artificial Intelligence tools that enable the optimization of time and processes in formulating multiple products such as margarines, shortenings, and emulgeles while maintaining high standards of quality and sustainability.
Designed to uncover the intricate relationship between triglycerides and the fatty acids they comprise with the physical characteristics of fats and oils.
The first bar margarine designed by Jul-ia.
In this process, the AI selected an optimal combination of different fatty bases and predicted their physical properties to mimic those of a market bar.
Lipid-based products such as margarines and shortenings are essential components of the food industry.
However, changing consumer preferences necessitate the adoption of innovative approaches.
Machine learning and deep learning algorithms are pivotal in addressing the intricate challenges associated with lipid-based product formulations.
Our deep learning neural network designs exhibit exceptional proficiency in predicting solid fat profiles for margarines and shortenings with remarkable precision.
Allows the use of sustainable palm and replaces palm for sustainability goals compliance.
Quantum computing-based system that significantly reduces error and minimizes prediction times for new blends of fats and oils.
Anthon/e facilitated the formulation of a new margarine in just a few seconds. Utilizing quantum computers, we implemented our own algorithms for optimizing the fat blend of this margarine.
Computer-aided design system for obtaining formulations of gelled emulsions that could mimic the functional rheological characteristics of shortenings and margarines with lower levels of saturated fats and calories.
To address the need for liquid margarines, we utilized James.ify In this application, the AI provided a design for an emulgel that mimics the rheology and sensory properties of market liquid margarines.
Evolutionary algorithm for the design of Emulsions with high nutritional impact fulfilling consumer expectations
To achieve desired textures and stability in lipid-based products, emulsions are commonly used, often employing hydrocolloids.
Predictive models of viscosity flow curves have been developed, focusing on the interaction between these hydrocolloids and lipids. These models utilize flow equations and interpolation techniques to enhance our understanding of concentration-dependent behaviors in lipid emulsions.
The results have shown relatively low errors, and the emulsions exhibit exceptional stability and performance when replacing butters and liquid margarines.