Control device and method for controlling personal environmental comfort
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ventilation systems in buildings lack the ability to dynamically and recurrently optimize environmental comfort for multiple users, often requiring manual intervention to deviate from predefined rules, which can lead to suboptimal comfort and energy consumption.
Innovation Solution
A control device that utilizes machine learning to analyze sensor, operational, and external data to generate personalized comfort preferences and predictive models, adjusting comfort system settings to optimize environmental conditions based on user preferences and anticipated needs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If rule-based control with predefined settings is used, then system simplicity is maintained, but adaptability to individual user preferences deteriorates
Solution Approach 1:
The system automatically learns and adapts to user preferences through machine learning algorithms without requiring manual programming or complex configuration. The control device autonomously analyzes sensor data, operational data, and external data to generate personalized comfort profiles, enabling the system to serve itself in terms of adaptation while maintaining operational simplicity for users.
Solution Approach 2:
The system dynamically adjusts operational parameters of comfort system apparatuses based on learned user preferences and predictive models. By changing parameters such as temperature, ventilation rates, and timing schedules according to individual user profiles and predicted needs, the system achieves high adaptability without requiring users to manually configure complex settings.
2Ease of operation
If manual intervention is required to deviate from predefined rules, then system simplicity is maintained, but ease of operation deteriorates
Solution Approach 1:
The system eliminates the need for manual intervention by automatically learning user preferences and making adjustments autonomously. Users simply interact with the system through natural feedback mechanisms, and the machine learning algorithms handle the complexity of deviation from predefined rules, making operation effortless while maintaining system simplicity.
Solution Approach 2:
The system incorporates continuous feedback loops where sensor data from the environment and operational data from apparatuses are analyzed to automatically adjust settings. This feedback mechanism enables users to easily deviate from predefined rules by simply providing feedback through their natural interactions, while the system handles the complex control adjustments automatically.
3Adaptability or versatility
If ventilation systems are configured with fixed set values, then system simplicity is maintained, but adaptability to dynamic conditions deteriorates
Solution Approach 1:
The system transitions from static fixed set values to dynamic adaptive configuration through machine learning. The control device continuously learns from sensor data, operational data, and external data to dynamically adjust ventilation settings according to changing conditions and user preferences, enabling the system to adapt to dynamic conditions while the learning process automatically manages configuration complexity.
Solution Approach 2:
The system uses predictive models to anticipate future conditions and pre-adjust ventilation settings before changes occur. By analyzing patterns in sensor data, operational data, and external data, the system performs preliminary actions to optimize comfort in advance, enabling adaptability to dynamic conditions while maintaining operational simplicity through automated prediction and preparation.
4Reliability
If personalized control for multiple users is implemented, then environmental comfort is improved, but device complexity increases
Solution Approach 1:
The system segments user profiles and preferences into distinct personalized configurations for multiple users. Each user receives customized environmental control based on their individual preferences learned from their specific interaction patterns and sensor data, while the underlying machine learning framework manages the complexity of handling multiple segments through unified algorithms.
Solution Approach 2:
The control device implements a universal machine learning framework that handles multiple users and various comfort parameters through a single integrated system. This multi-functional approach allows the system to manage personalized control for multiple users simultaneously while avoiding the complexity of separate control systems, as the same learning algorithms adapt to different users and conditions.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A control device (100) for recurrently controlling the personal environmental comfort in a building with one or more rooms equipped with a comfort system (120), comprising: - interfaces (101, 102, 103) for obtaining sensor data, operational data and external data;- a database (105) for storing these data; - a first machine learning module (106) trained using the stored data in order to generate personal preferred settings (108) per person; - a second machine learning module (107) trained using the stored data in order to generate predictive models (109) per room and/or per room type; and- a control unit (110) that, on the basis of the preferred settings (108) for one or more persons and/or the predictive models (109), adjusts settings of one or more apparatuses (122) in the comfort system (120) in order to improve the personal environmental comfort for users of the building.