Vehicle Air Conditioner Comfort Model for Cross-Vehicle Personalization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional air conditioner performance map-based climate controls are not adjustable to individual user preferences, requiring manual adjustment and are not transferable between users or vehicles.
Innovation Solution
A method involving a control architecture that trains an average basis model from data across all users and vehicles, creating a comfort model by superimposing sub-models to predict individualized settings for any user in any vehicle, utilizing AI for centralized training and prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional performance map-based climate control is used, then the air conditioner can be set automatically based on engine performance, but it cannot be adjusted to individual user thermal preferences
Solution Approach 1:
The climate control system segments the user population into different thermal perception groups based on physiological data (age, gender, body mass index, clothing insulation). Instead of using a single average performance map, the system creates multiple segmented models that can be automatically selected or blended based on the detected user characteristics, enabling both automatic operation and individual adaptation.
Solution Approach 2:
The system changes the parameters of the climate control model by incorporating physiological parameters (age, gender, body mass index, clothing insulation) into the thermal comfort calculations. This transforms the conventional performance map that only considers environmental parameters into an adaptive model that dynamically adjusts climate settings based on user-specific physiological parameters.
2Adaptability or versatility
If AI-supported comfort models are trained with user settings and context data, then individual user preferences can be predicted, but the model cannot be used for other users or vehicles
Solution Approach 1:
The system creates a universal comfort model that can be applied across different users and vehicles. Instead of training separate AI models for each user-vehicle combination, the system develops a single multi-functional model that incorporates physiological parameters and environmental context to predict thermal comfort for any user in any vehicle, reducing complexity while maintaining adaptability.
Solution Approach 2:
The system performs preliminary action by pre-calculating and storing comfort predictions based on physiological parameters and environmental conditions. The AI model is pre-trained with aggregated data from multiple users and vehicles, so that when a new user enters a vehicle, the system can quickly retrieve or adjust predictions based on the user's physiological profile without requiring extensive real-time data collection or model retraining.
3Adaptability or versatility
If manual adjustment is required for individual comfort, then user comfort can be optimized, but the operation becomes more complex and time-consuming
Solution Approach 1:
The climate control system performs self-service by automatically detecting user physiological parameters (age, gender, body mass index, clothing insulation) and environmental conditions, then autonomously calculating and adjusting the optimal climate settings. This eliminates the need for manual user adjustment while maintaining individual comfort optimization, as the system serves itself by making intelligent decisions based on detected parameters.
Solution Approach 2:
The system implements feedback mechanisms where user thermal comfort responses are continuously monitored and used to refine climate control decisions. The system adjusts climate parameters based on feedback from thermal sensors and user physiological data, creating a closed-loop control system that automatically optimizes comfort without requiring manual intervention.
Data Source
AI summary
A method for individualized setting of an air conditioner in a vehicle for a user using a control architecture is provided. Data relating to setting the air conditioner is acquired for all users and all vehicles and an average basis model is trained in an AI unit using the data acquired for all users and all vehicles. A comfort model is then created in the AI unit from at least the basis model and individualized settings for the air conditioner for a specific user are predicted based on the comfort model.A control architecture for executing the method is also provided.