Fermentation Parameter Prediction via Neural Network Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Predicting the outputs of fermentation processes is challenging due to complex microbial interactions and the difficulty in determining the appropriate fermentation parameters to achieve desired product characteristics.
Innovation Solution
A system and method using neural networks and machine learning technologies to predict fermentation parameters and product attributes, minimizing experimental work by modeling microbial interactions and metabolic pathways, and providing insights through explainability methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional methods are used to predict fermentation outputs, then physical experimentation is required, but this increases time consumption and development costs
Solution Approach 1:
The patent creates a virtual copy of the fermentation system through a computational model that replicates microbial interactions and metabolic pathways. This digital twin allows prediction of fermentation outputs without physical experimentation, significantly reducing time and cost while maintaining predictive accuracy.
Solution Approach 2:
The patent replaces the physical experimentation mechanism with a computational modeling mechanism. The system uses algorithms to simulate microbial dynamics and predict product characteristics, substituting the need for actual laboratory experiments with in silico simulations.
2Ease of manufacture
If conventional methods are used to determine fermentation parameters, then extensive physical experimentation is needed, but this increases development costs
Solution Approach 1:
The patent creates a virtual replica of the fermentation process that can be repeatedly simulated at minimal cost. This digital model allows extensive parameter exploration and optimization without the financial burden of repeated physical experiments, making parameter determination economically feasible.
Solution Approach 2:
The patent performs preliminary computational simulations to identify promising fermentation parameters and conditions before any physical experimentation occurs. This preliminary digital screening reduces the scope and cost of subsequent physical experiments by focusing resources only on the most promising scenarios.
3Measurement precision
If microbial interactions are modeled in detail, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
The patent divides the complex microbial system into discrete functional modules, each representing specific microbial species or metabolic pathways. This segmentation allows the model to handle complexity systematically by processing interactions in manageable units while maintaining overall predictive accuracy.
Solution Approach 2:
The patent dynamically adjusts model complexity by changing parameters such as the level of detail in microbial interaction representations. The system can simplify or elaborate on specific interaction mechanisms based on the predictive accuracy requirements, optimizing the balance between model complexity and prediction precision.
Data Source
AI summary
In variants, the method can include: determining a set of fermentation parameters; determining a set of features associated with the set of fermentation parameters; and determining a set of product attributes associated with the set of features. In examples, the method can optionally predict the attributes of a product manufactured using the set of fermentation parameters and/or predict the set of fermentation parameters that would create or replicate the attributes of a target product.