Milk Quality Sensor Using Neural Prediction of Inhomogeneities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting milk inhomogeneities, such as clots, in automatic milking systems are unreliable and time-consuming, leading to the risk of substandard milk entering the bulk tank without prior prediction.
Innovation Solution
A quality sensor using a trained artificial neural network that receives input variables from animal characteristics, milk characteristics, and milking process parameters to predict milk inhomogeneities, allowing diversion of suspected poor-quality milk before extraction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual visual inspection is used to detect milk quality deviations, then the milker can identify sick cows and prevent abnormal milk from entering the bulk tank, but the process is time-consuming and cannot be implemented in automatic milking systems
Solution Approach 1:
The patent replaces manual visual inspection with an automatic optical detection system using cameras and image processing algorithms. The system captures images of milk streams and automatically analyzes them for deviations such as clots, color changes, and homogeneity issues, eliminating the need for manual inspection while maintaining detection reliability in automatic milking systems
Solution Approach 2:
The system enables the milking process to self-monitor quality by integrating sensors and algorithms that automatically detect and flag quality deviations without human intervention. The computer vision system processes milk stream images in real-time, automatically identifying abnormalities and preventing contaminated milk from entering the bulk tank
2Extent of automation
If detectors are used to measure milk quality aspects in automatic milking systems, then electric conductivity and color can be measured, but other deviations such as milk clots cannot be automatically detected
Solution Approach 1:
The patent transitions from point-based sensor measurements (electric conductivity, color) to area-based visual inspection using 2D image capture. By capturing the entire milk stream cross-section and analyzing spatial patterns, the system can detect clots, foreign objects, and homogeneity issues that point sensors cannot detect, while maintaining full automation
Solution Approach 2:
The optical detection system serves multiple functions: it detects clots, measures color, assesses homogeneity, and identifies foreign objects all through a single imaging platform. This multi-functional approach replaces multiple specialized sensors and enables comprehensive quality monitoring in automatic milking systems
3Measurement precision
If milk quality is assessed during or after extraction, then deviations can be detected, but substandard milk may already have entered the bulk tank
Solution Approach 1:
The system performs preliminary quality assessment during the milking process itself, analyzing milk stream images in real-time as milk is being extracted. This allows the system to identify quality deviations early and trigger immediate responses such as alerting operators or diverting contaminated milk streams before they contaminate the bulk tank
Data Source
AI summary
A quality sensor that predicts a degree of inhomogeneities in milk extracted from an animal, by receiving a set of input variables reflecting at least one characteristic each of the animal, the extracted milk, and at least process during which milk was extracted from the animal, and by feeding the input variables into a trained artificial neural network in the quality sensor, which generates an estimate of a predicted degree of inhomogeneities in the milk of the animal.