Neural Network Window Shading Control for Learned User Preferences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing window shading systems require manual adjustment to control sunlight and visibility, which is inefficient and lacks automation to adapt to changing environmental conditions.
Innovation Solution
A window shading system that includes sensors, a processor, and a machine-readable medium using an artificial neural network to predict and automatically adjust window shading settings based on environmental data, learning user preferences over time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If manual adjustment is used to control window shading settings, then the system structure remains simple, but the automation level and adaptability to environmental conditions deteriorate
Solution Approach 1:
The system automatically adjusts window shading settings by capturing environmental data through sensors, processing it through an artificial neural network, and applying predicted settings without requiring manual intervention. The neural network learns user preferences and environmental patterns over time, enabling the system to self-optimize shading configurations based on real-time conditions.
2Use of energy by moving object
If manual adjustment is used for window shading, then the system requires less computational resources, but the energy efficiency and comfort optimization deteriorate
Solution Approach 1:
The patent replaces manual mechanical adjustment with an automated system that uses sensors to capture environmental data and an artificial neural network to process this data. The neural network computes optimal shading settings by learning from environmental patterns and user preferences, then actuates the shading mechanism automatically, eliminating the need for manual operation while optimizing energy efficiency.
3Adaptability or versatility
If automated shading control is implemented, then the adaptability to environmental conditions improves, but the system complexity and cost increase
Solution Approach 1:
The system dynamically adapts window shading settings by continuously capturing environmental data through sensors and processing it through an artificial neural network. The neural network learns from changing environmental conditions and user preferences over time, enabling the system to dynamically adjust shading configurations to optimize for comfort and energy efficiency under varying conditions such as time of day, weather, and occupancy patterns.
Data Source
AI summary
Provided is a window shading system including a means for shading one or more windows; a means for manually controlling at least one window shading setting; one or more sensors; a processor; and a tangible, non-transitory, machine readable medium storing instructions that when executed by the processor effectuates operations including capturing, with the one or more sensors, environmental data of surroundings; predicting, with the processor, the at least one window shading setting using a learned function of an artificial neural network that relates the environmental data to the at least one window shading setting; and, applying, with the processor, the at least one window shading setting predicted to the window shading system.