Strain Performance Prediction in Bio-Ethanol Fermentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Predicting the performance of microbial strains in bio-ethanol production is challenging due to the complexity of metabolic processes and the variability of biomass feedstocks, leading to unpredictable results and high costs associated with trial-and-error methods in industrial-scale production.

Innovation Solution

A computer-implemented method that receives and analyzes process data sets from different sites to determine correlations, allowing for the reconstruction of missing data and the creation of a predictive model to forecast the performance of strains in new locations, thereby reducing costs and improving predictability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If trial-and-error methods are used to test strain performance in new plants, then actual performance data can be obtained, but production costs and time are significantly increased

Engineering Contradiction:
Improvestrain performance prediction accuracyVSAvoidtime for strain testing
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by predicting strain performance in new plants before actual production begins. It uses process data from existing plants to calculate predicted performance metrics (ethanol production, sugar consumption, pH changes) in advance, allowing stakeholders to evaluate strain suitability without committing to expensive trial runs in new facilities.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a virtual copy of the actual plant process by using process data from existing plants as training data. This virtual model replicates the metabolic processes and allows simulation of strain performance in new plants without physical experimentation, effectively copying real-world outcomes in a computational environment.

Inventive Principle:
Principle #26Copying

2Measurement precision

If trial-and-error methods are used to test strain performance in new plants, then actual performance data can be obtained, but production costs are significantly increased

Engineering Contradiction:
Improvestrain performance prediction accuracyVSAvoidproduction cost
Core Design Contradiction:
Measurement precisionVSLoss of energy

Solution Approach 1:

The system performs preliminary actions by predicting strain performance in new plants before actual production begins. It uses process data from existing plants to calculate predicted performance metrics (ethanol production, sugar consumption, pH changes) in advance, allowing stakeholders to evaluate strain suitability without committing to expensive trial runs in new facilities.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a virtual copy of the actual plant process by using process data from existing plants as training data. This virtual model replicates the metabolic processes and allows simulation of strain performance in new plants without physical experimentation, effectively copying real-world outcomes in a computational environment.

Inventive Principle:
Principle #26Copying

3Measurement precision

If microbial fermentation processes are modeled complexity, then prediction accuracy may improve, but the model becomes too complicated to understand or use

Engineering Contradiction:
Improveprediction accuracyVSAvoidmodel complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system creates a virtual copy of the actual plant process by using process data from existing plants as training data. This virtual model replicates the metabolic processes and allows simulation of strain performance in new plants without physical experimentation, effectively copying real-world outcomes in a computational environment.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system transforms complex biological metabolic processes into simplified mathematical parameters and equations. It converts biological data (substrate consumption, product formation, pH changes) into quantifiable model parameters that can be processed computationally, reducing the complexity barrier while maintaining predictive accuracy.

Inventive Principle:
Principle #35Parameter changes

4Measurement precision

If correlations between process data sets from different sites are determined, then prediction capability is improved, but data processing complexity increases

Engineering Contradiction:
Improveprediction capabilityVSAvoiddata processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the data processing task by analyzing process data from different sites independently before integrating them through correlation analysis. It processes each site's data (substrate consumption, product formation, pH, temperature) separately to identify patterns, then combines these segmented analyses to create predictive models for new sites.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces process data from existing plants as an intermediary element to bridge the gap between known and unknown sites. This intermediary data serves as training material that enables the system to infer relationships between process parameters across different locations without direct measurement at each new site.

Inventive Principle:
Principle #24Intermediary (Mediator)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enables more accurate and efficient prediction of strain performance in new plants, optimizing process conditions and reducing initial production costs by leveraging correlations between data sets from different sites, thus enhancing the scalability and efficiency of bio-ethanol production.

Implementation Method 1

The invention relates to a method, system and computer program for predicting a performance of a strain in a bio-ethanol producing process, by fermentation of biomass

Methodology Applied
Scientific EffectFermentation: Fermentation

Data Source

PatentEP4077693B1Method and system for prediction of a performance of a strain in a plant
Publication Date: 2023.12.06 DSM IP ASSETS BV
  • EP4077693B1 patent drawingFigure 1
  • EP4077693B1 patent drawingFigure 2
  • EP4077693B1 patent drawingFigure 3

AI summary

A method and system for predicting performance of strains in processes, the strains being capable of fermentation of biomass for production of at least bio-ethanol, the method including the steps of: receiving a first process data set related to a performance of a first strain in a first process for producing bio-ethanol at a first site, receiving a second process data set related to a performance of a second strain in the first process for producing bio-ethanol at the first site, receiving a third process data set related to a performance of the first strain in a second process for producing bio-ethanol at a second site, the second site being different from the first site, and wherein the first, second and third process data sets each include one or more process profiles and/or process responses, determining a first correlation between the first process data set and the second process data set, and determining a second correlation between the first process data and the third process data, and reconstructing a fourth process data set related to a performance of the second strain in the second process for producing bio-ethanol at the second site by missing data imputation, wherein the fourth process data set is estimated based on the first correlation and the second correlation.