Method and system for controlling heating, ventilation, and air conditioning system in buildings based on adaptive model predictive control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional HVAC control methods struggle to adapt to complex and changing operating conditions, leading to inefficiencies, energy waste, and poor performance due to noise susceptibility and measurement errors, with suboptimal decision-making under uncertainty and external disturbances.
Innovation Solution
An adaptive model predictive control (MPC) system that integrates Learning Algorithm for Multivariable Data Analysis (LAMDA) and extended Kalman filtering to classify operation states, dynamically adjust control strategies, and optimize energy management by combining real-time data analysis and state estimation to improve accuracy and adaptability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional fixed control strategies are used for HVAC systems, then the control method is simple and easy to implement, but the system cannot adapt to complex operating conditions and environmental changes, resulting in low energy efficiency
Solution Approach 1:
The patent implements dynamic adaptability by continuously updating the state of charge (SOC) estimates and adjusting control strategies in real-time based on changing operating conditions. The extended Kalman filter dynamically adapts to varying system parameters and environmental changes, allowing the HVAC system to optimize energy efficiency across different operating states rather than relying on fixed control parameters.
Solution Approach 2:
The patent changes key parameters dynamically by using adaptive parameter estimation through extended Kalman filtering. The SOC estimates and related parameters are continuously updated based on real-time measurements and system behavior, allowing the control strategy to adapt to different operating conditions without requiring a completely complex redesign of the control architecture.
2Measurement precision
If conventional MPC is used in nonlinear systems, then the control structure is straightforward, but the system is susceptible to noise and measurement errors, resulting in poor state estimation accuracy
Solution Approach 1:
The patent implements feedback mechanisms through the extended Kalman filter, which continuously compares predicted SOC values with actual measurements and adjusts estimates accordingly. This feedback loop effectively filters out noise and measurement errors while maintaining accurate state estimation, improving both reliability and precision simultaneously through iterative correction based on real-time data.
Solution Approach 2:
The extended Kalman filter acts as an intermediary between raw measurements and the control system, processing and filtering measurement data before it reaches the controller. This intermediary layer reduces the impact of noise and measurement errors on state estimation accuracy while maintaining the straightforward MPC control structure.
3Productivity
If conventional control methods are used, then the system structure is simple, but optimization of control strategies lags behind rapidly changing operating conditions, making it difficult to make optimal decisions
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing SOC estimates and control parameters that can be quickly retrieved and applied when operating conditions change. The extended Kalman filter continuously prepares updated state estimates in advance, allowing the MPC controller to make optimal decisions rapidly without requiring complex real-time calculations when conditions change abruptly.
Solution Approach 2:
The patent replaces complex mechanical control adjustments with computational methods. Instead of using complex mechanical systems to adapt to changing conditions, the system uses extended Kalman filtering and adaptive algorithms to calculate and adjust control parameters computationally, achieving fast optimization speed with relatively simple system structure.
4Use of energy by moving object
If conventional HVAC control is used, then the system is easy to operate, but energy consumption is high due to lack of accuracy in adapting to changing conditions
Solution Approach 1:
The patent implements self-service by enabling the HVAC system to automatically adjust its own operation based on real-time SOC estimates and environmental conditions. The extended Kalman filter continuously monitors system state and autonomously optimizes control parameters without requiring complex external control systems, reducing energy consumption while keeping the control system relatively simple through intelligent self-adjustment capabilities.
Data Source
AI summary
A method and system for controlling a heating, ventilation, and air conditioning system (HVAC) in a building based on adaptive model predictive control (MPC) is disclosed, and belongs to the technical field of intelligent building adaptive control. The method may include: acquiring operation data of the HVAC under different working conditions, and performing preprocessing on the acquired data; calculating a marginal fitness measure (MAD) of each data point for each class based on the preprocessed data, and calculating a fitness measure of each data point for each class by combining MADs of all descriptors to obtain a global fitness measure (GAD); setting a GAD threshold, and classifying current operation states of the system according to classification rules; and adopting adaptive control strategies for different operation states since model parameters of each class are fixed after classification.