Fault detection for air conditioning system using machine learning
| Autor: | Noor Asyikin Sulaiman, Muhammad Noorazlan Shah Zainudin, Hayati Abdullah, Azdiana Md Yusop, Pauzi Abdullah |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Information Systems and Management
Computer science 020209 energy 0211 other engineering and technologies 02 engineering and technology Machine learning computer.software_genre Fault detection and isolation Damper Artificial Intelligence 021105 building & construction 0202 electrical engineering electronic engineering information engineering Electrical and Electronic Engineering business.industry Deep learning Supervised learning Coefficient of performance Perceptron Support vector machine Control and Systems Engineering Air conditioning Artificial intelligence business Fault detection computer Air conditioning system |
| Zdroj: | IAES International Journal of Artificial Intelligence (IJ-AI). 9:109 |
| ISSN: | 2252-8938 2089-4872 |
| Popis: | Air conditioning system is a complex system and consumes the most energy in a building. Any fault in the system operation such as cooling tower fan faulty, compressor failure, and damper stuck, etc. could lead to energy wastage and reduction in the system’s coefficient of performance (COP). Due to the complexity of the air conditioning system, detecting those faults is hard as it requires exhaustive inspections. This paper consists of two parts; i) to investigate the impact of different faults related to the air conditioning system on COP and ii) to analyse the performances of machine learning algorithms to classify those faults. Three supervised learning classifier models were developed, which were deep learning, support vector machine (SVM) and multi-layer perceptron (MLP). The performances of each classifier were investigated in terms of six different classes of faults. Results showed that different faults give different negative impacts on the COP. Also, the three supervised learning classifier models able to classify all faults for more than 94%, and MLP produced the highest accuracy and precision among all. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|