Optical Wash Item Recognition for Adaptive Dishwasher Cycles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Commercial dishwashers often inefficiently use resources and fail to provide optimal treatment for various types of wash items due to lack of automatic differentiation in treatment programs, leading to prolonged cycles and inadequate cleaning.
Innovation Solution
An optical wash item recognition system using neural networks, such as a Single-Shot MultiBox detector (SSD) architecture, classifies wash items and adjusts treatment parameters automatically within the dishwasher, optimizing washing, rinsing, and drying processes based on item type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a fixed treatment program is used for all wash items, then the dishwasher is simple to operate, but resource efficiency deteriorates and cleaning effectiveness deteriorates
Solution Approach 1:
The dishwasher automatically detects wash item types using optical sensors and cameras, then self-adjusts treatment parameters without user intervention. The system serves itself by autonomously selecting appropriate programs based on detected items, eliminating the need for manual program selection while optimizing resource usage.
Solution Approach 2:
The system dynamically changes treatment parameters (temperature, water flow, cycle duration, chemical dosage) based on detected wash item types. Different parameters are automatically adjusted for different item categories, enabling resource-efficient treatment while maintaining simplicity for the user.
2Ease of operation
If a fixed treatment program is used for all wash items, then the dishwasher is simple to operate, but cleaning effectiveness deteriorates
Solution Approach 1:
The dishwasher automatically detects wash item types using optical sensors and cameras, then self-adjusts treatment parameters without user intervention. The system serves itself by autonomously selecting appropriate programs based on detected items, eliminating the need for manual program selection while optimizing resource usage.
Solution Approach 2:
The system dynamically changes treatment parameters (temperature, water flow, cycle duration, chemical dosage) based on detected wash item types. Different parameters are automatically adjusted for different item categories, enabling resource-efficient treatment while maintaining simplicity for the user.
3Reliability
If manual program selection is required for different wash item types, then treatment effectiveness is improved, but device complexity increases
Solution Approach 1:
The manual mechanical selection process (user choosing programs) is replaced by an optical detection and automated control system. Cameras and sensors detect wash item types, and a control system automatically selects appropriate treatment programs, replacing complex user interaction with automated optical-mechanical systems.
Solution Approach 2:
The dishwasher automatically detects wash item types using optical sensors and cameras, then self-adjusts treatment parameters without user intervention. The system serves itself by autonomously selecting appropriate programs based on detected items, eliminating the need for manual program selection while optimizing resource usage.
4Reliability
If manual pre-treatment and post-treatment are performed, then cleaning effectiveness is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary detection of wash item types before the washing cycle begins, using optical sensors to identify items and pre-select appropriate treatment parameters. This preliminary action ensures optimal treatment is applied from the start, eliminating the need for subsequent manual pre-treatment or post-treatment interventions.
Data Source
Figure 1
Figure 2
AI summary
A system for optical wash item recognition for commercial dishwashers (1) embodied in particular as conveyor dishwashers or as automatic programme dishwashers, in particular hood dishwashers, wherein the system includes an optical recognition system (51), especially a camera, for recording at least one two-dimensional image of at least some of the wash items to be treated in the dishwasher (1). The system also includes an analysis device (52) for analysing at least one recorded image in such a way that individual wash items or groups of individual wash items in the recorded image are located and classified. According to the invention, it is in particular provided that at least one neural network will be used to analyse the at least one recorded image.