一种基于多传感器测量值的变风量空调系统传感器原位校准方法
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN UNIV OF TECH
- Filing Date
- 2023-03-21
- Publication Date
- 2026-07-17
AI Technical Summary
Sensor failures are frequent and difficult to detect in a timely manner in existing variable air volume (VAV) air conditioning systems, leading to energy waste and a decline in indoor environmental quality. Existing calibration methods cannot effectively distinguish between different types of sensors, resulting in low calibration accuracy and long calibration time.
A sensor evaluation and data-driven modeling approach is adopted. By comprehensively evaluating the characteristics of sensors, the control and monitoring types of sensors are distinguished, and replacement or in-situ calibration is selected based on price and construction difficulty. A model is built by combining linear regression and backpropagation neural networks, and sensor deviation calibration is performed using Bayes' theorem and Monte Carlo Markov chain algorithm.
It improved the accuracy of sensor measurements, reduced deviations, ensured stable system operation, and ensured that the calibrated values and the true values were basically equal, improving calibration accuracy by 94%.
Smart Images
Figure CN116358616B_ABST