Development of a smart control system for a hybrid ground source heat pump based on artificial intelligence (AI)

Name: Siwakorn Chuensiri

LCSH: Kasetsart University -- Theses. M.Eng. (Mechanical Engineering) 2023

Classification :.LCCS: TH7417.5

LCSH: Kasetsart University. -- Department of Mechanical Engineering -- Theses

LCSH: Ground source heat pump systems

LCSH: Hybrid power systems

LCSH: Heat pumps

LCSH: Artificial intelligence

Abstract: This paper provided the development of an Adaptive Network-based Fuzzy Inference System (ANFIS) for a Hybrid Ground Source Heat Pump system (HGSHP) used for air conditioning the building. The HGSHP is installed with a supplementary heat sink composter to compost organic solid waste (OSW) utilizing the excess hot air from the condensing unit to aerate and accelerate the composting process. The effects of the composter operation drastically reduce the overall system efficiency. The Fuzzy Logic Inference system (FLC) was created based on the system data collected by the sensors installed in the system to control the HGSHP system water flow rate with Variable Speed Drive (VSD) aims to improve the system performance. The ANFIS was created and trained in MATLAB software using the system data after the FLC implementation and then implemented on a Raspberry Pi nano-computer with Python code. This paper compares the performance of ANFIS with 2 different cases: the ANFIS with Triangular Membership Function (TriMF) and the ANFIS with Gaussian Membership Function (GaussMF). After implementing the ANFIS with TriMF the average COP during the composter operation and the system cooling are increased to 3.16 and 3.75 respectively. In the GaussMF case, the average COP during the composter operation and the system cooling are also increased to 2.95 and 3.31 respectively. The system power consumption of the original HGSHP system is around 3,124.089 kWh/year but after the implementation with the TriMF and GaussMF, the power consumption was reduced to 2,888.505 kWh and 3089.719 kWh, respectively. Moreover, the ANFIS also benefits in the composting process as evidenced in the composter operation time changes of the TriMF and the GaussMF cases are around +12.5% to +63.64% and -28.57% to +36.36%, respectively. Also, the system cooling time changes of the TriMF and GaussMF cases are around - 14.28% to -60% and -2.86 to -40%, respectively. In conclusion, the ANFIS can improve the HGSHP system performance in both the TriMF case and the GaussMF case, but the TriMF case shows a significant improvement in the HGSHP system performance compared to the GaussMF case.

Kasetsart University. Office of the University Library

Address: Bangkok

Email: tdckulib@ku.ac.th

Name: Kanet Katchasuwanmanee

Role: Thesis Advisor

Created: 2023

Modified: 2025-07-23

Issued: 2025-07-23

วิทยานิพนธ์/Thesis

application/pdf

URL: https://www.lib.ku.ac.th/KUthesis/2566/siwakorn-chu-all.pdf

CallNumber: TH7417.5 .S59

eng

DegreeName: Master of Engineering

Level: Master's Degree

Descipline: Mechanical Engineering

Grantor: Kasetsart University

©copyrights Kasetsart University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	siwakorn-chu-all.pdf	3.36 MB	1	2025-09-08 10:31:47

ใช้เวลา

0.023827 วินาที