기계학습 알고리즘을 이용한 스마트 온실 내부온도 예측 모델 개발 및 검증 Development and Verification of Smart Greenhouse Internal Temperature Prediction Model Using Machine Learning Algorithm원문보기
본 연구는 데이터를 기반으로 한 인공지능 기계학습 기법을 활용하여 온실 내부온도 예측 시뮬레이션 모델을 개발을 수행하였다. 온실 시스템의 내부온도 예측을 위해서 다양한 방법이 연구됐지만, 가외 변인으로 인하여 기존 시뮬레이션 분석방법은 낮은 정밀도의 문제점을 지니고 있다. 이러한 한계점을 극복하기 위하여 최근 개발되고 있는 데이터 기반의 기계학습을 활용하여 온실 내부온도 예측 모델 개발을 수행하였다. 기계학습모델은 데이터 수집, 특성 분석, 학습을 통하여 개발되며 매개변수와 학습방법에 따라 모델의 정확도가 크게 변화된다. 따라서 데이터 특성에 따른 최적의 모델 도출방법이 필요하다. 모델 개발 결과 숨은층 증가에 따라 모델 정확도가 상승하였으며 최종적으로 GRU알고리즘과 숨은층6에서 r2 0.9848과 RMSE 0.5857℃로 최적 모델이 도출되었다. 본 연구를 통하여 온실 외부 데이터를 활용하여 온실 내부온도 예측 모델 개발이 가능함을 검증하였으며, 추후 다양한 온실데이터에 적용 및 비교분석이 수행되어야 한다. 이후 한 단계 더 나아가 기계학습모델 예측(predicted) 결과를 예보(forecasting)단계로 개선하기 위해서 데이터 시간 길이(sequence length)에 따른 특성 분석 및 계절별 기후변화와 작물에 따른 사례별로 개발 모델을 관리하는 등의 다양한 추가 연구가 수행되어야 한다.
본 연구는 데이터를 기반으로 한 인공지능 기계학습 기법을 활용하여 온실 내부온도 예측 시뮬레이션 모델을 개발을 수행하였다. 온실 시스템의 내부온도 예측을 위해서 다양한 방법이 연구됐지만, 가외 변인으로 인하여 기존 시뮬레이션 분석방법은 낮은 정밀도의 문제점을 지니고 있다. 이러한 한계점을 극복하기 위하여 최근 개발되고 있는 데이터 기반의 기계학습을 활용하여 온실 내부온도 예측 모델 개발을 수행하였다. 기계학습모델은 데이터 수집, 특성 분석, 학습을 통하여 개발되며 매개변수와 학습방법에 따라 모델의 정확도가 크게 변화된다. 따라서 데이터 특성에 따른 최적의 모델 도출방법이 필요하다. 모델 개발 결과 숨은층 증가에 따라 모델 정확도가 상승하였으며 최종적으로 GRU 알고리즘과 숨은층6에서 r2 0.9848과 RMSE 0.5857℃로 최적 모델이 도출되었다. 본 연구를 통하여 온실 외부 데이터를 활용하여 온실 내부온도 예측 모델 개발이 가능함을 검증하였으며, 추후 다양한 온실데이터에 적용 및 비교분석이 수행되어야 한다. 이후 한 단계 더 나아가 기계학습모델 예측(predicted) 결과를 예보(forecasting)단계로 개선하기 위해서 데이터 시간 길이(sequence length)에 따른 특성 분석 및 계절별 기후변화와 작물에 따른 사례별로 개발 모델을 관리하는 등의 다양한 추가 연구가 수행되어야 한다.
This study developed simulation model for predicting the greenhouse interior environment using artificial intelligence machine learning techniques. Various methods have been studied to predict the internal environment of the greenhouse system. But the traditional simulation analysis method has a pro...
This study developed simulation model for predicting the greenhouse interior environment using artificial intelligence machine learning techniques. Various methods have been studied to predict the internal environment of the greenhouse system. But the traditional simulation analysis method has a problem of low precision due to extraneous variables. In order to solve this problem, we developed a model for predicting the temperature inside the greenhouse using machine learning. Machine learning models are developed through data collection, characteristic analysis, and learning, and the accuracy of the model varies greatly depending on parameters and learning methods. Therefore, an optimal model derivation method according to data characteristics is required. As a result of the model development, the model accuracy increased as the parameters of the hidden unit increased. Optimal model was derived from the GRU algorithm and hidden unit 6 (r2 = 0.9848 and RMSE = 0.5857℃). Through this study, it was confirmed that it is possible to develop a predictive model for the temperature inside the greenhouse using data outside the greenhouse. In addition, it was confirmed that application and comparative analysis were necessary for various greenhouse data. It is necessary that research for development environmental control system by improving the developed model to the forecasting stage.
This study developed simulation model for predicting the greenhouse interior environment using artificial intelligence machine learning techniques. Various methods have been studied to predict the internal environment of the greenhouse system. But the traditional simulation analysis method has a problem of low precision due to extraneous variables. In order to solve this problem, we developed a model for predicting the temperature inside the greenhouse using machine learning. Machine learning models are developed through data collection, characteristic analysis, and learning, and the accuracy of the model varies greatly depending on parameters and learning methods. Therefore, an optimal model derivation method according to data characteristics is required. As a result of the model development, the model accuracy increased as the parameters of the hidden unit increased. Optimal model was derived from the GRU algorithm and hidden unit 6 (r2 = 0.9848 and RMSE = 0.5857℃). Through this study, it was confirmed that it is possible to develop a predictive model for the temperature inside the greenhouse using data outside the greenhouse. In addition, it was confirmed that application and comparative analysis were necessary for various greenhouse data. It is necessary that research for development environmental control system by improving the developed model to the forecasting stage.
Ahn W.Y., and H.C. Lee 2016, Automatic control system for cultivation environment of crops. J Korea Inst Inf Commun Eng 20:2167-2171. (in Korean) doi:10.6109/jkiice.2016.20.11.2167
Ariga M., S. Nakayama, and D. Nishibayasi 2018, Machine learning at work. O'Reilly Media, CA, USA, pp 137-140.
Chang Z., Y. Zhang, and W. Chen, 2019, Electricity price prediction based on hybrid model of adam optimized LSTM neural network and wavelet transform. Energy 187:115804. doi:10.1016/j.energy.2019.07.134
Charu C.A. 2018, Neural networks and deep learning: a Textbook. Springer, Heidelberg, Germany, pp 123-127.
Cho K., B. van Merrienboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio 2014, Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078. doi:10.48550/arXiv.1406.1078
Cho K.J., K.Y. Kim, and W.M. Yang 2015, Survey of ICT apply to plastic greenhouse, rack.pinion adaption to single span and CFD analysis. Protected Hort Plant Fac 24:308-316. (in Korean) doi:10.12791/KSBEC.2015.24.4.308
Choi H.Y., T.W. Moon, D.H. Jung, and J.E. Son 2019, Prediction of air temperature and relative humidity in greenhouse via a multilayer perceptron using environmental factors. Protected Hort Plant Fac 28:95-103. (in Korean) doi:10.12791/KSBEC.2019.28.2.95
Choi Y.S., H.J. Lee, and S.T. Joung 2012, A design and implementation of web-based green house automation system. J Korea Inst Electron Commun Sci 1519-1527. (in Korean) doi:10.13067/JKIECS.2012.7.6.1519
Fatnassi H., C. Poncet, M.M. Bazzano, R. Brun, and N. Bertin 2015, A numerical simulation of the photovoltaic greenhouse microclimate. Solar Energy 120:575-584. doi:10.1016/j.solener.2015.07.019
Francois C. 2017, Deep learning with Python. Manning Publications Company, NY, USA, pp 79-92.
Gabriel K.R. 1971, The biplot graphic display of matrices with application to principal component analysis. Biometrika 58:453-467. doi:10.1093/biomet/58.3.453
Hong S.W., and I.B. Lee 2014, Predictive model of microenvironment in a naturally ventilated greenhouse for a modelbased control approach. Protected Hort Plant Fac 23:181-191. (in Korean) doi:10.12791/KSBEC.2014.23.3.181
Hwang I.C., H. Noh, D. Yang, and M. Kim 2021, Prediction of paprika yield using multiple linear regression. J Korean Inst Commun 46:21-11. (in Korean) doi:10.7840/kics.2021.46.11.2048
Kim D.H., B.M. Jenkins, T.R. Rumsey, M.W. Yore, and N.J. Kim 2007, Simulation and model validation of a horizontal shallow basin solar concentrator. Solar Energy 81(4):463-475. doi:10.1016/j.solener.2006.08.007
Kim H.S. 2001, Prediction of cooling effect for fog cooling system in greenhouse by CFD simulation. Master Diss., Seoul National University, Seoul, Korea, pp 1-45. (in Korean)
Kim S.Y., and Y.J. Jung 2017, First learning machine learning. Hanbit Media, Seoul, Korea, pp 137-140. (in Korean)
Kwon H.W., K.C. Oh, Y. Choi, Y.G. Chung, and J. Kim 2021, Development and application of machine learning-based prediction model for distillation column. Int J Intell 36:1970-1997. doi:10.1002/int.22368
Lee I.B., and T.H. Short 1999, Analysis of the efficiency of natural ventilation in multi-span greenhouse using CFD simulation. J Bio-Env Con 8:9-18. (in Korean)
Lee I.B., N.K. Yun, T. Boulard, J.C. Roy, S.H. Lee, G.W. Kim, S.K. Lee, and S.H. Kwon 2006a, Development of an aerodynamic simulation for studying microclimate of plantcanopy in greenhouse: (1) Study on aerodynamic resistance of tomato canopy through wind tunnel experiment. J Bio-Env Con 15:289-295. (in Korean)
Lee I.B., N.K. Yun, T. Boulard, J.C. Roy, S.H. Lee, G.W. Kim, S.W. Hong, and S.H. Sung 2006b, Development of an aerodynamic simulation for studying microclimate of plantcanopy in greenhouse: (2) Development of CFD model to study the effect of tomato plants on internal climate of greenhouse. J Bio-Env Con 15:296-305. (in Korean)
Lee J.K., J.W. Oh, Y.J. Cho, and D.H. Lee 2020, A research about time domain estimation method for greenhouse environmental factors based on artificial intelligence. Protected Hort Plant Fac 3:277-284. (in Korean) doi:10.12791/KSBEC.2020.29.3.277
Muller A.C., and S. Guido 2017, Introduction to machine learning with Python: a guide for data scientists. O'Reilly Media, CA, USA, pp 27-31.
Na M.H, Y. Pack, and W. Cho 2017, A study on optimal environmental factors of tomato using smart farm data. J Korean Data Inf Sci Soc 28:1427-1435 doi:10.7465/jkdi.2017.28.6.1427
Oh K.C., H.W. Kwon, J.W. Roh, Y.Y. Cho, H.D. Park, H.T. Cho, and J.H. Kim 2020, Development of machine learning-based platform for distillation column. Korean Chem Eng Res 58:565-572. (in Korean) doi:10.9713/kcer.2020.58.4.565
Park Y.M., S.M. Gang, J.H. Chae, and J.J. Lee 2018, Classification method of plant leaf using DenseNet. J Korea Multimedia Soc 21:571-582. doi:10.9717/kmms.2018.21.5.571
Song Y.E., A.Y. Moon, S.Y. An, and H.Y. Jung 2019, Prediction of smart greenhouse temperature-humidity based on multidimensional LSTMs. J Korean Soc Precis Eng 36(3):239-246. (in Korean) doi:10.7736/KSPE.2019.36.3.239
Tadj N., T. Bartzanas, D. Fidaros, B. Draoui, and C. Kittas 2010, Influence of heating system on greenhouse microclimate distribution. Trans ASABE 53:225-238. doi:10.13031/2013.29498
Yu I.H., N.K. Yun, M.W. Cho, H.R. Ryu, and D.G. Moon 2014, Development of CFD model for analyzing the air flow and temperature distribution in greenhouse with air-circulation fans. Korean J Agric Sci 41:461-472. (in Korean) doi:10.7744/cnujas.2014.41.4.461
※ AI-Helper는 부적절한 답변을 할 수 있습니다.