Optical Molasses Quality Prediction for Yeast Production
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining the quality of molasses used in yeast production are inefficient, requiring extensive yeast production and qualification protocols, making it difficult to anticipate and address variations in molasses quality, which can result in poor yeast quality and significant losses in industrial production.
Innovation Solution
A method using optical measurements and machine learning to build a statistical model based on reference spectra of known molasses qualities, allowing for the determination of an unknown molasses quality and its expected yeast performance, enabling the identification of suitable or unsuitable molasses and adjustment of production schemes to achieve target yeast performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional yeast production and qualification protocols are used to determine molasses quality, then yeast production can proceed, but significant time and resources are lost due to post-production quality assessment
Solution Approach 1:
The patent applies preliminary action by performing optical measurements on molasses before it is used in yeast production. The system measures optical characteristics (absorbance, reflectance, or transmittance) and uses machine learning models to predict molasses quality and expected yeast performance in advance, allowing quality assessment to occur prior to production rather than after completion.
Solution Approach 2:
The patent replaces traditional mechanical/chemical analysis methods with optical measurement technology. Instead of relying on conventional laboratory tests that require extensive processing time, the system uses optical sensors to rapidly characterize molasses properties, substituting a faster, non-contact measurement approach for the traditional slow verification process.
2Measurement precision
If extensive yeast production and qualification protocols are implemented, then accurate quality determination is achieved, but production costs and resource consumption increase
Solution Approach 1:
The patent extracts the essential quality assessment function from the entire yeast production process. By using optical measurements to directly characterize molasses properties and predict yeast performance, the system separates the quality determination step from the full production cycle, allowing assessment without requiring actual yeast production and qualification testing.
Solution Approach 2:
The patent creates a virtual copy of the molasses quality assessment through optical spectroscopy and machine learning models. Instead of physically producing yeast and conducting comprehensive quality tests, the system generates a predictive model that replicates the assessment function, allowing virtual evaluation of molasses quality and expected yeast performance.
3Reliability
If molasses quality is assessed after production, then comprehensive quality data is obtained, but the ability to anticipate and adjust production schemes is reduced
Solution Approach 1:
The patent enables preliminary assessment of molasses quality and prediction of yeast performance before production begins. The optical measurement system characterizes molasses properties in advance, and the machine learning model predicts how the yeast production will perform, allowing production schemes to be adjusted proactively rather than reactively after quality issues are discovered.
4Measurement precision
If traditional quality assessment methods are used, then comprehensive testing is performed, but the speed of molasses quality determination is slow
Solution Approach 1:
The patent replaces slow mechanical and chemical analysis methods with rapid optical measurement technology. Optical sensors can quickly measure absorbance, reflectance, or transmittance characteristics of molasses, providing fast preliminary data that feeds into machine learning predictions, dramatically increasing the speed of quality determination compared to traditional methods.
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
Enables the pre-identification of molasses quality and potential yeast performance, allowing for the discard of unsuitable molasses and adjustment of production conditions to ensure compliant yeast production, thereby reducing losses and improving yield.
Implementation Method 1
illuminating a molasses sample with a first emitted light signal interacting with the sample and collecting a second light signal, resulting from the interaction between the first light signal and the current sample
Data Source
AI summary
A method for qualifying molasses based on an optical measurement, the method may include: based on reference optical spectra of samples of distinct molasses, associated with respective known molasses qualities, building by machine learning a statistical model of molasses qualities as a function of at least one spectral characteristic of the reference spectra; and for a current optical spectrum of a sample of a current molasses, based on the statistical model, identifying the at least one spectral characteristic of the current optical spectrum and determining a quality of the current molasses, the current molasses quality relating to at least one yeast performance obtained when the yeast is fed with the current molasses.