Virtual Bulk Density Sensing for Real-Time Food Extrusion Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High volume food production faces challenges in maintaining quality control due to lag times in product sample testing, which can lead to poor product quality and sub-optimal bag fill.
Innovation Solution
A system comprising a food product processing device, a bulk density evaluation system using image analysis, and a control system with a machine learning model that determines real-time control parameters based on bulk density values to govern the operation of the processing device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sample testing methods are used for quality control, then measurement accuracy can be maintained, but response time increases due to lag times
Solution Approach 1:
The patent replaces traditional mechanical bulk density measurement devices with a vision-based system using cameras and machine learning algorithms. This substitution enables real-time measurement of bulk density from images of food products, eliminating the time lag associated with physical sampling and mechanical measurement while maintaining measurement accuracy through computational analysis.
Solution Approach 2:
The system creates a virtual copy of the bulk density measurement process by capturing images of food products and using machine learning models to infer bulk density properties from visual data. This copying approach allows simultaneous measurement of multiple products without physical contact, providing real-time feedback for quality control.
2Loss of time
If real-time control is implemented using vision systems and machine learning, then response time is reduced, but device complexity increases
Solution Approach 1:
The vision system serves multiple functions: it captures images for quality inspection, determines bulk density values, and provides input for machine learning-based control decisions. This multi-functionality consolidates what would otherwise require separate measurement and control systems, reducing overall complexity despite the advanced capabilities.
Solution Approach 2:
The machine learning model automatically processes image data to determine bulk density and generates control parameter adjustments without requiring manual intervention or complex external control logic. The system self-corrects by continuously learning from measurement data, reducing the need for complex programmed control algorithms.
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 real-time or near-real-time bulk density evaluation and control, improving food production quality by continuously adjusting processing parameters, thus reducing the risk of poor quality products and improper bagging.
Implementation Method 1
a bulk density evaluation system for analyzing image information of at least one of food material and food product to determine a bulk density value
Data Source
AI summary
Devices, systems, and methods for real-time food production are disclosed. Extrusion can include including evaluating and controlling one or more production devices to produce desirable food products. Evaluation can be performed by an evaluation system including a convolutional neural network to determine a bulk density value. Control can be performed by a machine learning model on the basis of the bulk density value. Control can include determination of real-time settings for production device parameters.