具智慧型控制之HVAC個人化控制系統

Intelligent Control For Personalized HVAC Control Systems

彭勇樺(Ynug-Hua Peng)

指導教授 ： 劉寅春

淡江大學/工學院/電機工程學系人工智慧機器人碩士班/碩士(2022年)

https://doi.org/10.6846/TKU.2022.00265

摘要

本研究以實驗室作為研究場域，針對現行之HVAC系統進行改善，本研究在HVAC系統內加入暖氣之設備，藉此使得同一區域內之不同使用者皆能得到其期望溫度。
室內熱模型建模部分，本研究採用將環境切割為無數熱模型方塊之集成，藉此貼近真實環境中空氣對流之現象與溫度交換之過程，並在環境熱模型中加入太陽、室內室外溫度及熱負載等資訊。
針對個人化部分，本研究透過在HVAC系統中加入暖氣機之設備，並建置一模糊邏輯控制器以控制暖氣機設備使得每位使用者皆能根據熱感覺得到其期望溫度。
對於實驗之成果，本研究藉由MATLAB模擬驗證控制器之可行性，並透過實際利用紙箱建立實驗室之縮小模型，藉由在紙箱內對應使用者之位置放置陶瓷加熱晶片模擬暖氣機，並在箱壁上開洞以模擬冷氣機之冷氣供應，並於對應使用者之位置周圍放置溫度感測器，透過實時監測溫度資訊以控制各使用者之暖氣機工作週期，使每位使用者區域都能穩定保持在其期望之溫度範圍內。
本研究之貢獻，包含熱模型方塊之切割、HVAC系統之改進、模糊邏輯控制器之建置。

關鍵字

熱模型方塊 ； 熱負載 ； HVAC系統 ； 模糊邏輯控制

並列摘要

In this research, the laboratory is used as the research field to improve the existing HVAC system by adding heating equipment into the HVAC system. So that every user in the same area can get their desired temperature.
In the modeling part of indoor thermal model, in order to get the phenomenon of air convection and the process of temperature exchange in the real environment, this research adopts the integration of the environment into numerous thermal model cubes, and adds sun, indoor and outdoor temperature and heat loads into the environmental thermal model.
For the personalized part, this research adds heating equipment into the HVAC system and builds a fuzzy logic controller to control the heating equipment so that each user can get his desired temperature according to the thermal sensation.
For the results of the experiment, this research uses the MATLAB simulation to verify the feasibility of the controller, and then using the carton to build the laboratory model. Placing ceramic heating chips and temperature sensors corresponding to each user's location in cartons. The holes in the carton wall are used to simulate the air conditioner. This research monitors the real-time temperature information to control the duty cycle of ceramic heating chips, so that the temperature can be stably maintained in the users’ desired temperature range.
The contribution of this research includes the cutting of thermal model cubes, the improvement of HVAC system, and the construction of fuzzy logic controller.

並列關鍵字

Thermal Cube ； Heat Load ； HVAC System ； Fuzzy Logic Control

參考文獻

[1] R. Randriatsiferana, L. Rajaoarisoa, S. Ngoho, W. Rahajandraibe and B. Ravelo, "Zonal Thermal Room Original Model With Kron’s Method," IEEE Access, vol. 8, pp. 174893 - 174909, Sept. 2020.

[2] H. Doddi, S. Talukdar, D. Deka and M. Salapaka, "Data-Driven Identification of a Thermal Network in Multi-Zone Building," 2018 IEEE Conference on Decision and Control (CDC), Dec. 2018.

[3] F. Belić, D. Slišković and Ž. Hocenski , "Detailed Thermodynamic Modeling of Multi-Zone Buildings with Resistive-Capacitive Method," Energies, vol. 14, no. 21, p. 7051, Oct. 2021.

[4] F. Belic, Z. Hocenski and D. Sliskovic, "Algorithm for defining structure of thermal model of building based on RC analogy," 2019 23rd International Conference on System Theory, Control and Computing (ICSTCC), Oct. 2019.

[5] L. Yu, Y. Sun, Z. Xu, C. Shen, D. Yue, T. Jiang and X. Guan, "Multi-Agent Deep Reinforcement Learning for HVAC Control in Commercial Buildings," IEEE Transactions on Smart Grid, vol. 12, no. 1, pp. 407 - 419, July 2020.