EvoPhase
EvoPhase uses evolutionary AI algorithms to autonomously design, test, and optimize industrial processes and equipment, particularly for granular materials. The technology generates and refines thousands of design iterations to improve efficiency, reduce energy consumption, and minimize waste without relying on training data. This approach accelerates R&D cycles for manufacturers in sectors like pharmaceuticals, food, and personal care.
- Artificial Intelligence
- Industrial Automation
- Manufacturing / Industry 4.0
- Software Only
Funding
Founders
Product
Problem
Traditional industrial R&D relies on slow, expensive trial-and-error methods to optimize processes and equipment designs. This is especially challenging for granular materials, which behave like solids, liquids, and gases depending on conditions, making them the most complex form of matter to process in industrial systems. The high cost and time required for optimization often create a prohibitive barrier for companies seeking efficiency improvements.
Solution
EvoPhase provides AI-driven optimization for industrial systems using evolutionary algorithms rather than deep learning. The technology autonomously generates and tests thousands of potential designs, refining them over multiple iterations to find the most efficient, high-performance solution for real-world conditions. By combining Discrete Element Method (DEM) simulations with advanced optimization algorithms, EvoPhase accelerates design improvements and reduces the need for manual trial-and-error. The approach has demonstrated results such as a 46% power reduction in attritor mill designs while maintaining grinding ball stress, and it enables companies to achieve breakthrough performance improvements without requiring deep AI expertise.
Target Audience
Primary customers are industrial companies in manufacturing, pharmaceuticals, food processing, personal care, and sustainable infrastructure that need to optimize processes involving granular materials and complex equipment designs.
Features
- Evolutionary AI algorithms that generate and test thousands of design iterations without relying on training data
- Discrete Element Method (DEM) simulation for accurate modeling of granular material behavior
- Autonomous design optimization for industrial equipment including ribbon mixers, attritor mills, fluidised beds, and high-shear mixers
- Real-time AI-led optimization that reduces energy consumption, cuts waste, and improves productivity
- Transparent, human-centred AI approach that enhances rather than replaces engineering expertise
- Applicable across manufacturing, pharmaceuticals, and sustainable infrastructure sectors