A control system and method for a machine for preparing and dispensing hot beverages by controlled infusion of a precursor substance in granular or powder form, based on the recognition and classification of a dose unit inserted in the machine

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing machines struggle to accurately recognize and classify coffee tablets or other precursor substances in granular or powder form due to deterioration from storage conditions, environmental factors, and image acquisition issues, leading to misclassification.

Innovation Solution

A control system using machine-learning techniques, specifically a neural network, classifies dose units based on graphic recognition markings and synthetic images, correcting for image alterations through data augmentation and dynamic comparison thresholds, ensuring robust classification despite environmental changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a dose unit is inserted into the machine, then the beverage preparation process is initiated, but the system cannot reliably determine the type or characteristics of the dose unit, leading to incorrect preparation parameters

Engineering Contradiction:
Improvedose unit recognition accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies color recognition technology to identify dose unit types. The system uses optical sensors to detect the color of the dose unit container, which encodes information about the beverage type or preparation parameters. This allows the system to automatically adjust preparation settings based on the detected color, achieving reliable dose unit recognition without complex mechanical or electronic identification mechanisms.

Inventive Principle:
Principle #32Color changes

2Adaptability or versatility

If the system uses simple insertion detection, then the device remains simple, but it cannot classify different dose unit types or characteristics for proper beverage preparation

Engineering Contradiction:
Improvedose unit classification capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system uses color as an encoding mechanism for dose unit classification. Different colors represent different beverage types, concentrations, or preparation parameters. The optical detection system reads the color information and automatically selects the appropriate preparation protocol, enabling versatile dose unit classification while maintaining relatively simple system architecture.

Inventive Principle:
Principle #32Color changes

3Manufacturing precision

If the system manually verifies each dose unit parameter, then preparation accuracy is ensured, but the operation time and user effort increase significantly

Engineering Contradiction:
Improvebeverage preparation precisionVSAvoidpreparation time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The dose units are pre-coded with color information that encodes their type and preparation parameters. This preliminary encoding allows the system to automatically retrieve the correct preparation settings without requiring manual verification or user input during the preparation process, thus ensuring precision while minimizing time loss.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements automatic feedback loops where the detected color information immediately triggers the corresponding preparation parameters. The system continuously monitors the preparation process and adjusts parameters based on the initial color-based identification, ensuring precision through automated feedback control without manual intervention.

Inventive Principle:
Principle #23Feedback

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

The system provides accurate and adaptable classification of dose units, independent of machine and environmental conditions, suitable for cost-effective household machines, maintaining precision over the machine's lifespan.

Implementation Method 1

the system uses an optical sensor to detect the color of the inserted dose unit

Methodology Applied
Scientific EffectColor detection: Absorption Spectroscopy

Data Source

PatentEP4558019B1A control system and method for a machine for preparing and dispensing hot beverages by controlled infusion of a precursor substance in granular or powder form, based on the recognition and classification of a dose unit inserted in the machine
Publication Date: 2026.04.29 LUIGI LAVAZZA SPA
  • EP4558019B1 patent drawingFigure 1
  • EP4558019B1 patent drawingFigure 2a~4
  • EP4558019B1 patent drawingFigure 3

AI summary

A control system and method for a machine (1) for preparing and dispensing hot beverages by controlled infusion of a precursor substance in granular or powder form, based on the recognition and classification of a dose unit (8) inserted in the machine (1). A control system and method are described for a machine (1) for preparing and dispensing hot beverages by controlled infusion of a precursor substance in granular or powder form arranged in a dose unit (8), wherein an automatic image recognition and processing unit (84), of the machine-learning type, is arranged to classify a dose unit (8) received by the machine into one of a plurality of predetermined classes of dose units on the basis of a set of training images of dose units taken in a learning step. The set of training images of dose units comprises at least a plurality of primary images of dose units (8) including predetermined graphic recognition markings (70, 72) on a reference surface of the dose unit (8), indicative of corresponding classes of dose units, and a plurality of synthetic images obtained by alteration of the plurality of primary images.