AI-Guided Mycelium Fermentation Quality Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing solid-state fermentation (SSF) processes for producing protein-rich food products using non-mushroom filamentous fungi are limited by long fermentation times, labor-intensive manual operations, and challenges in maintaining optimal heat and mass transfer, leading to suboptimal product quality and inefficient resource use.
Innovation Solution
The development of an AI-guided quality control system that utilizes Near-Infrared (NIR) spectroscopy and machine learning algorithms to monitor and control key parameters such as inoculum quality, substrate preparation, and fermentation conditions in real-time, enabling rapid detection of flaws and automated adjustments to ensure high-quality fungal biomass production.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If solid-state fermentation is used for producing protein-rich food products, then the environmental impact is reduced and resource usage is minimized, but the fermentation time is extended and labor-intensive manual operations are required
Solution Approach 1:
The system performs preliminary actions by pre-processing substrate materials and preparing inoculum cultures before the main fermentation process. The AI system pre-configures optimal fermentation parameters and pre-monitors critical quality attributes, enabling the fermentation process to proceed more efficiently without extending the core fermentation time.
Solution Approach 2:
The patent replaces manual mechanical operations with an automated AI-driven monitoring and control system. Near-infrared spectroscopy devices and sensors automatically monitor substrate composition, moisture content, and fungal growth without requiring manual sampling or laboratory analysis, thereby reducing labor intensity while maintaining or accelerating the process.
2Manufacturing precision
If manual quality control procedures are implemented in SSF processes, then product quality can be monitored, but the operations are labor-intensive and time-consuming
Solution Approach 1:
The system substitutes manual quality control operations with automated near-infrared spectroscopy devices and sensors that continuously monitor substrate composition, moisture content, and fungal biomass. The AI system automatically analyzes spectral data to detect quality deviations, eliminating the need for manual sampling, laboratory analysis, and subjective quality assessments.
Solution Approach 2:
The patent introduces an intermediary AI system that acts as a mediator between the fermentation process and quality control decisions. The AI system processes data from multiple sensors and instruments, integrates this information, and provides automated quality assessments and process adjustments, thereby simplifying operations while maintaining high manufacturing precision.
3Quantity of substance
If conventional SSF processes are used, then fungal biomass can be produced, but heat and mass transfer issues hinder optimum heat dissipation affecting product quality
Solution Approach 1:
The system implements feedback control by continuously monitoring temperature, humidity, and substrate composition using sensors and near-infrared spectroscopy. The AI system analyzes this real-time data and automatically adjusts aeration rates, mixing intensity, and environmental conditions to optimize heat dissipation and maintain optimal fermentation conditions throughout the substrate mass.
Solution Approach 2:
The patent applies dynamic control strategies where fermentation parameters such as aeration rate, mixing speed, and temperature are continuously adjusted based on real-time process conditions. The AI system dynamically adapts these parameters to maintain optimal heat and mass transfer conditions, preventing localized overheating and ensuring uniform fungal biomass production throughout the substrate.
4Productivity
If AI-guided quality control system is implemented, then productivity and product quality are enhanced, but device complexity increases
Solution Approach 1:
The system achieves universality by designing a multi-functional AI platform that integrates multiple monitoring functions (temperature, humidity, composition analysis via near-infrared spectroscopy), control functions (aeration, mixing), and quality assessment capabilities into a single unified system. This reduces the need for separate dedicated devices for each function, thereby managing complexity while enhancing productivity.
Solution Approach 2:
The patent implements self-service capabilities where the AI system automatically calibrates sensors, validates data quality, adjusts process parameters, and generates quality reports without requiring extensive manual intervention or complex operator training. The system performs self-diagnosis and self-optimization, reducing the operational complexity despite the advanced technology involved.
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 AI-driven system significantly enhances the efficiency and quality of fungal biomass production by minimizing downtime, optimizing resource usage, and ensuring consistent product quality, thereby addressing the limitations of traditional SSF processes.
Implementation Method 1
NIR technology, in particular, operates on the known principle of molecular vibrations associated with the X-H bond type, such as O-H, N-H, C-H and S-H, and their connection with infrared radiation. The spectral range covered by NIR is between 700 - 2500 nm.
Implementation Method 2
The fungi can be cultivated on a variety of plant-based materials in which the fermented products have better nutrition quality, bioaccessibility, and digestibility compared to the non-fermented materials. Furthermore, the fungi can synthesize vitamins, and alter the protein and lipid profile of the fermented substrate due to the fungal metabolic activities.
Data Source
Figure 1
Figure 2
AI summary
Technical field The current invention reveals the application of an artificial intelligence aided method whereby near-infrared spectroscopy is employed to model desired parameters. Machine learning is applied to create algorithms from the spectral data to monitor and control process functions during the manufacturing of mycelium-based food and feed products. The mycelium-based food and feed products are obtained through fermentation of non-mushroom filamentous fungi in a high-solid fermentation process characterized by solid loadings exceeding 50 %.