HVAC Model Predictive Control with Automatic Fault Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
HVAC control systems face challenges in achieving optimal control due to sensor and actuator faults, leading to incorrect feedback measurements and reduced energy efficiency.
Innovation Solution
A method for automatically adapting a predictive model in HVAC systems by detecting faults, determining their impact, and adjusting parameters to generate a fault-adapted model, which allows for optimal control actions despite faults, using a neural network for fault detection and model adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional HVAC control systems are used, then the system structure is simple, but the control performance deteriorates due to sensor and actuator faults
Solution Approach 1:
The system performs preliminary fault detection and impact assessment before executing control actions. The predictive model is updated in advance based on detected faults, allowing the control system to proactively compensate for potential performance degradation rather than reacting after faults occur.
Solution Approach 2:
The predictive model parameters are dynamically adjusted based on detected faults and their assessed impacts. The system transitions from a static control model to a dynamic fault-adapted model that continuously evolves its parameters to maintain optimal control performance under varying fault conditions.
2Reliability
If fault detection and model adaptation are implemented, then control robustness improves, but computational complexity increases
Solution Approach 1:
The predictive model performs self-adjustment by automatically updating its parameters based on detected faults and their assessed impacts. This self-service mechanism eliminates the need for complex external fault compensation algorithms, reducing overall computational complexity while maintaining control robustness.
Solution Approach 2:
The system achieves enhanced robustness through parameter changes in the predictive model rather than through complex structural modifications. By adjusting model parameters based on fault conditions, the system maintains simplicity in overall architecture while improving control reliability.
3Loss of energy
If predictive model parameters are adjusted based on fault impact, then energy efficiency improves, but model complexity increases
Solution Approach 1:
The system optimizes energy efficiency by changing parameters of the existing predictive model based on fault conditions. Rather than creating complex new models, the approach modifies parameters of the current model to account for fault impacts, achieving energy savings without proportionally increasing model complexity.
Solution Approach 2:
The predictive model continuously adapts its parameters to maintain optimal energy efficiency despite faults. This continuous adaptation ensures that energy optimization actions remain effective throughout the system's operation, preventing energy losses that would occur with static models under fault conditions.
Data Source
AI summary
A method for automatically adapting a predictive model used to control a heating, ventilation, or air conditioning (HVAC) system in a building to compensate for a detected fault in the HVAC system is shown. The method includes obtaining an indication of the detected fault in the HVAC system or a zone in the building. The method further includes determining a predicted impact of the detected fault on an operational performance of the HVAC system. The method further includes adjusting one or more parameters of the predictive model based on the predicted impact of the detected fault to generate a fault-adapted predictive model. The method further includes operating the HVAC system to control an environmental condition of the building using the fault-adapted predictive model.