Adaptive Milking Control Unit for Individual Animal Flow Profiles

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current automatic milking systems lack a fully automatic procedure for determining an individually optimal milking time that balances long-term milk yield and animal health, given the variability in milk flow characteristics among and within animals.

Innovation Solution

A control unit with processing circuitry that receives milk flow parameters from teats, using criteria such as decline phase detection and threshold slope analysis to determine the optimal take-off time for milking, adaptable to specific animal profiles and equipment, ensuring appropriate milking times based on historic and current milk-flow data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If milking is stopped based on fixed time schedules or simple flow thresholds, then the control system remains simple and easy to operate, but it cannot adapt to individual animal variations and may lead to suboptimal milk yield or animal health issues

Engineering Contradiction:
Improveadaptability to individual animal milk-flow profilesVSAvoidcomplexity of control system
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by collecting and storing milk flow data from previous milking sessions for each animal. This historical data is used to establish baseline profiles before the actual milking decision is made, allowing the system to adapt to individual animal characteristics without requiring complex real-time analysis during milking.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The control system continuously monitors milk flow during milking and compares real-time flow characteristics against historical profiles and predefined criteria. This feedback mechanism enables the system to dynamically adjust milking duration based on actual animal response, balancing adaptability with manageable complexity through rule-based decision logic.

Inventive Principle:
Principle #23Feedback

2Productivity

If milking continues until complete milk extraction, then short-term milk yield is maximized, but animal health may deteriorate due to over-milking and udder stress

Engineering Contradiction:
Improvemilk yieldVSAvoidanimal health impact from over-milking
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system applies preliminary anti-action by proactively stopping milking before complete extraction based on predictive criteria. By analyzing flow patterns and detecting the transition from plateau to decline phase, the system prevents over-milking damage while maintaining high productivity, counteracting the tendency to continue milking until empty.

Inventive Principle:
Principle #9Preliminary anti-action

Solution Approach 2:

The system changes the control parameter from fixed time or simple flow threshold to a dynamic criterion based on the rate of flow decrease. By monitoring when the milk flow decreases faster than a threshold slope during the decline phase, the system optimizes the balance between milk yield and animal health through parameter adaptation.

Inventive Principle:
Principle #35Parameter changes

3Object-affected harmful factors

If milking is stopped early to protect animal health, then animal health is maintained, but long-term milk yield is reduced

Engineering Contradiction:
Improveanimal health protectionVSAvoidlong-term milk yield
Core Design Contradiction:
Object-affected harmful factorsVSProductivity

Solution Approach 1:

The system applies dynamics by making the milking stop criterion adaptive rather than static. The threshold slope and decision parameters are adjusted based on individual animal profiles and current milking characteristics, allowing the system to optimize the health-yield balance dynamically for each animal and each milking occasion.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system enables self-service by using each animal's own historical milk flow data to determine optimal stop timing. The animal's unique profile serves as the reference for its own milking control, allowing the system to protect health while maximizing yield without requiring external intervention or standardized conservative limits.

Inventive Principle:
Principle #25Self-service

4Measurement precision

If the system uses detailed analysis of milk flow profiles and multiple criteria to determine take-off time, then individually optimal milking time is achieved, but the decision-making process becomes more complex and computationally intensive

Engineering Contradiction:
Improveprecision in determining take-off timeVSAvoidcomplexity of processing circuitry and algorithms
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies segmentation by dividing the milking process into distinct phases (rise, plateau, decline) and applying specific simplified criteria to each phase. This segmentation allows precise take-off time determination through a series of simple, manageable checks rather than one complex continuous analysis, reducing computational burden while maintaining precision.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3749087B1Control unit, method and computer program for a milking system
Publication Date: 2023.08.09 DELAVAL HLDG AB
  • EP3749087B1 patent drawingFigure 1~2
  • EP3749087B1 patent drawingFigure 3A~3B
  • EP3749087B1 patent drawingFigure 3C~5

AI summary

An automatic milking system is controlled by receiving a para- meter representing a measured flow (f(t)) of milk being extracted from at least one teat of an udder of an animal being milked via at least one teatcup. A take-off time (tTO) is determined when the milking shall be stopped based on : a first criterion indicating that the flow (f(t)) has reached a decline phase ( Phdecl), and a second criterion indicating that the flow (f(t)) decreases faster than a threshold slope (scrit1). The take-off time (t TO) is determined in response to fulfillment of the second criterion on or after a point in time (t1) when the first criterion has been fulfilled. As a result, a particular amount of milk ( Mres) is estimated to be left in the udder irrespective of an overall milking time (tM) for the animal in question.