Method and system for determining filling information of a dishwasher and for preparing a dishwasher washing cycle
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current dishwasher control interfaces lack the ability to adapt washing programs effectively to the specific load situation, leading to suboptimal washing quality, risk of damaging fragile items, and inefficient energy use due to the wide range of possible load conditions and variables such as item types, materials, and distribution within the dishwasher.
Innovation Solution
A method using digital color image processing and artificial intelligence/machine learning to determine the filling information of dishwasher racks, including volume, item types, material types, and item positions, providing users with optimized washing program recommendations and load balancing suggestions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If generic washing programs are used based on limited control interface options, then the operation is simple, but the washing quality is suboptimal and fragile items may be damaged
Solution Approach 1:
The system uses automated image recognition and AI algorithms to automatically analyze the dishwasher load and recommend appropriate washing programs, eliminating the need for users to manually assess and select programs. The system serves itself by capturing images, processing them through machine learning models, and generating personalized washing recommendations without requiring user expertise or complex manual input.
2Device complexity
If the control interface offers limited program options, then the device complexity is low, but the adaptability to different load conditions is insufficient
Solution Approach 1:
The patent replaces the traditional mechanical control interface (physical buttons and program selectors) with an electronic vision-based system. Instead of requiring users to interact with complex physical controls, the system uses digital image capture, computer vision algorithms, and machine learning to automatically detect load characteristics and provide personalized washing program recommendations through a digital interface.
3Device complexity
If manual program selection is used, then the device complexity is low, but the energy efficiency is suboptimal
Solution Approach 1:
The system implements a feedback loop where images of the actual load are captured, analyzed by AI algorithms to determine load characteristics (volume, item types, material types, distribution), and this information feeds back to generate optimized washing program recommendations. This closed-loop approach ensures that each washing cycle is tailored to the actual load conditions, maximizing energy efficiency by avoiding both under-washing and over-washing scenarios.
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
The method comprises the steps of acquiring a digital color image of at least one rack (21, 22) of the dishwasher (2) containing items to be washed in a given use condition; therefore, determining at least one rack filling information, according to the features of the digital color image acquired; and then providing a user, by means of a graphical interface (32), with at least one determined rack filling information. The at least one rack filling information comprises a filling level, expressed in terms of volume, or percentage of volume, occupied in the rack, and/or one or more of the following load condition information: volume, or percentage of volume, occupied in the rack, partitioned by item types belonging to a predefined set of item types; and/or volume, or percentage of volume, occupied in the rack, partitioned by material types belonging to a predefined set of material types which the items to be washed are made of; and/or area or percentage of area occupied in the rack; and/or number of items to be washed, present in the rack; and/or number of items to be washed, present in the rack, partitioned by type of items belonging to a predefined set of item types; and/or; and/or position occupied in the rack by each item present in the rack, according to a granularity defined by a predefined set of rack sub-areas; and/or position of the cutlery rack, according to a granularity defined by a predefined set of rack sub-areas. Methods and systems for preparing a dishwasher washing cycle, based on the results of the method for determining information relating to the filling are also described.