Method for controlling a home appliance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing load detection methods in home appliances, such as dishwashers, are imprecise in determining the exact location and type of loads, leading to rudimentary adaptation of wash programs.
Innovation Solution
A method involving a camera on the appliance capturing load images, which are sent to a server for processing using a trained neural network and generative adversarial network (GAN) to enhance accuracy, allowing precise load segmentation and adaptation of appliance programs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If load detection is performed using sound transducers and cameras to identify material types and locations, then cleaning efficiency and program adaptation are improved, but device complexity and cost increase
Solution Approach 1:
The patent introduces an image processing system as an intermediary between the camera and the control system. The processed images provide enhanced information about load material types and locations, enabling better program adaptation without requiring complex direct sensor-appliance communication systems.
Solution Approach 2:
The patent creates processed copies of the original images that highlight specific features (material types, locations) relevant for cleaning program selection. These processed images serve as simplified representations that the control system can use without analyzing raw complex image data directly.
2Measurement precision
If precise load detection and segmentation are implemented to accurately identify material types and locations, then program adaptation precision is improved, but device complexity and computational requirements increase
Solution Approach 1:
The image processing system acts as an intermediary that performs complex segmentation and material identification algorithms, delivering precise detection results to the control system without requiring the appliance itself to contain complex processing hardware.
Solution Approach 2:
The patent applies image segmentation to divide the detected load into distinct regions based on material types and locations. This segmentation enables precise identification of different materials (plastic, metal, glass, ceramic) and their positions, allowing targeted program adaptation for each segment.
Data Source
AI summary
A method for controlling a home appliance depending on a load includes taking a load image with an appliance camera, sending the image from the appliance to the server, processing the image on the server, and generating a processing result. Control data is determined on the server for controlling the appliance based on the result and is then sent to the appliance and/or the processing result is sent to the appliance enabling the appliance to determine data for controlling the appliance based on the processing result. The control data and/or the processing result is received from the server on the appliance and based thereon appliance working programs are controlled. Image processing generating the result includes upscaling the image using a trained generative adversarial network and analyzing the load using a trained neural network. A server, home appliance and system including both are also provided.