Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems
In a heat pump system, performance is an important indicator that should be monitored for system optimization, fault diagnosis, and operational efficiency improvement. Real-time performance measurement and monitoring during heat pump operation is difficult because expensive performance measurement d...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/1/362 |
| _version_ | 1797499592194916352 |
|---|---|
| author | Ji-Hyun Shin Young-Hum Cho |
| author_facet | Ji-Hyun Shin Young-Hum Cho |
| author_sort | Ji-Hyun Shin |
| collection | DOAJ |
| description | In a heat pump system, performance is an important indicator that should be monitored for system optimization, fault diagnosis, and operational efficiency improvement. Real-time performance measurement and monitoring during heat pump operation is difficult because expensive performance measurement devices or additional installation of various monitoring sensors required for performance calculation are required. When using a data-based machine-learning model, it is possible to predict and monitor performance by finding the relationship between input and output values through an existing sensor. In this study, the performance prediction model of the air-cooled heat pump system was developed and verified using artificial neural network, support vector machine, random forest, and K-nearest neighbor model. The operation data of the heat pump system installed in the university laboratory was measured and a prediction model for each machine-learning stage was developed. The mean bias error analysis is −3.6 for artificial neural network, −5 for artificial neural network, −7.7 for random forest, and −8.3 for K-nearest neighbor. The artificial neural network model with the highest accuracy and the shortest calculation time among the developed prediction models was applied to the Building Automation System to enable real-time performance monitoring and to confirm the field applicability of the developed model. |
| first_indexed | 2024-03-10T03:49:37Z |
| format | Article |
| id | doaj.art-be774d8a39d84a49ae3cc74a6b79a886 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T03:49:37Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-be774d8a39d84a49ae3cc74a6b79a8862023-11-23T11:11:49ZengMDPI AGApplied Sciences2076-34172021-12-0112136210.3390/app12010362Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump SystemsJi-Hyun Shin0Young-Hum Cho1Department of Architectural Engineering, Graduate School of Yeungnam University, Gyeongsan 38541, Gyeongbuk-do, KoreaSchool of Architecture, Yeungnam University, Gyeongsan 38541, Gyeongbuk-do, KoreaIn a heat pump system, performance is an important indicator that should be monitored for system optimization, fault diagnosis, and operational efficiency improvement. Real-time performance measurement and monitoring during heat pump operation is difficult because expensive performance measurement devices or additional installation of various monitoring sensors required for performance calculation are required. When using a data-based machine-learning model, it is possible to predict and monitor performance by finding the relationship between input and output values through an existing sensor. In this study, the performance prediction model of the air-cooled heat pump system was developed and verified using artificial neural network, support vector machine, random forest, and K-nearest neighbor model. The operation data of the heat pump system installed in the university laboratory was measured and a prediction model for each machine-learning stage was developed. The mean bias error analysis is −3.6 for artificial neural network, −5 for artificial neural network, −7.7 for random forest, and −8.3 for K-nearest neighbor. The artificial neural network model with the highest accuracy and the shortest calculation time among the developed prediction models was applied to the Building Automation System to enable real-time performance monitoring and to confirm the field applicability of the developed model.https://www.mdpi.com/2076-3417/12/1/362machine-learningcoefficient of performanceheat pump systemprediction model |
| spellingShingle | Ji-Hyun Shin Young-Hum Cho Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems Applied Sciences machine-learning coefficient of performance heat pump system prediction model |
| title | Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems |
| title_full | Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems |
| title_fullStr | Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems |
| title_full_unstemmed | Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems |
| title_short | Machine-Learning-Based Coefficient of Performance Prediction Model for Heat Pump Systems |
| title_sort | machine learning based coefficient of performance prediction model for heat pump systems |
| topic | machine-learning coefficient of performance heat pump system prediction model |
| url | https://www.mdpi.com/2076-3417/12/1/362 |
| work_keys_str_mv | AT jihyunshin machinelearningbasedcoefficientofperformancepredictionmodelforheatpumpsystems AT younghumcho machinelearningbasedcoefficientofperformancepredictionmodelforheatpumpsystems |