Thermal System Control Mode Selection Using Learned Thermal Behavior
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing thermal systems for heating and cooling in buildings lack efficient control modes that consider dynamic thermal behavior and environmental context, leading to suboptimal energy management and operational inefficiencies, particularly in facilities with high thermal inertia like grass pitches.
Innovation Solution
A method for dynamically selecting control modes in thermal systems based on real-time monitoring of boundary conditions and environmental parameters, using learned thermal behavior data to optimize temperature control and energy efficiency, incorporating self-learning algorithms and adaptive scheduling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If dynamic building simulations are used to consider thermal inertia, then thermal storage potential can be optimized, but computation time increases and complex geometrical and physical parameters are required
Solution Approach 1:
The system pre-calculates and stores thermal behavior characteristics and environmental context parameters before actual operation. By preparing simulation data in advance and creating lookup tables of thermal responses under various conditions, the system avoids performing complex dynamic simulations in real-time, thus reducing computation time while maintaining the ability to optimize thermal storage potential
Solution Approach 2:
The patent creates simplified representations (models) of the building's thermal behavior that capture essential characteristics without requiring full complex simulations. These simplified models are trained on historical data and can quickly predict thermal responses, serving as lightweight copies that replicate the behavior of complex simulations without their computational burden
2Adaptability or versatility
If multiple independent control operations are used to achieve heating/cooling goals, then operational flexibility increases, but system complexity increases and context-appropriate selection becomes difficult
Solution Approach 1:
The system continuously monitors environmental context parameters (temperature, humidity, occupancy, weather forecasts) and uses this feedback to dynamically select the most appropriate control operation. The control system adjusts its behavior based on real-time conditions, choosing from multiple available operations the one that is currently most suitable, thus managing complexity through intelligent decision-making rather than having all operations active simultaneously
Solution Approach 2:
The control system automatically evaluates and selects the appropriate control operation based on current conditions without requiring manual intervention. It self-manages the complexity of having multiple control options by implementing an autonomous selection mechanism that chooses the optimal operation based on environmental context and thermal behavior patterns
Data Source
AI summary
A method for operating a thermal system, wherein a component of a facility or building has to be heated and/or cooled by the thermal system, includes selecting a control mode of the thermal system for bringing and/or maintaining the component to or at a definable temperature value or to or within a definable temperature value range. The control mode is dynamically selected from multiple different control modes under consideration of at least one boundary condition of the component and/or at least one environmental context parameter and under consideration of data regarding learnt/adapted thermal behavior of the component.