Please use this identifier to cite or link to this item:
標題: 模糊粒子群演算法在微環境控制之應用
Micro-environment Control by Using Fuzzy-PSO Method
作者: 林柏諺
Po-Yen Lin
關鍵字: 微環境控制;模糊理論;模糊粒子群控制;Microenvironment control;Fuzzy rule;Fuzzy-PSO algorithm
引用: [1] 行政院農委會。2007。玫瑰栽培地區及生理特性。網址:。上網日期:2018年8月3日。 [2] 陳怡君。2017。日本植物工廠之發展與現況分析-對台灣的啟示-。碩士論文。台中:國立臺中科技大學應用日語系。 [3] 方煒。2001。自動化植物工廠。台北:國立台灣大學。網址: 。上網日期:2017 年10月 25日。 [4] 康昇苑。2016。小型植物工廠之創業規劃。碩士論文。台北:國立臺北科技大學管理學院工業工程與管理EMBA專班。 [5] 邱庭毅。2015。模糊理論在微環境控制之應用。碩士論文。台中:國立中興大學生物產業機電工程學系。 [6] 陳加忠。2009。蘭花與精緻農業:自遮蔭網至植物工場。台中:國立中興大學。網址: new_page_361.htm。上網日期:2017年11月7日。 [7] 邱煒勛。2016。以數值模擬分析並優化植物工廠模型內流場環境。碩士論文。宜蘭:國立宜蘭大學生物機電工程學系。 [8] 蘇木春、張孝德。2016。機器學習:類神經網路、模糊系統以及基因演算法則。第四版。新北市:全華圖書股份有限公司。 [9] 林昇甫、徐永吉。2009。遺傳演算法及其應用。初版。台北市:五南圖書出版股份有限公司。 [10] 周鵬程。2017。遺傳演算法原理與應用-活用MATLAB。第五版。新北市:全華圖書股份有限公司。 [11] 何岳勳。2009。粒子群最佳化之模糊控制器應用於衛星追蹤系統。碩士論文。高雄:國立高雄應用科技大學。 [12] D. N. Gerasimov and M. V. Lyzlova, 'Adaptive control of microclimate in greenhouses,"Journal of Computer and Systems Sciences International, vol. 53, no. 6, pp. 896–907, Nov. 2014. [13] Y. P. Su, L. H. Xu and D. W. Li, 'Adaptive fuzzy control of a cass of MIMO nonlinear system with actuator saturation for greenhouse climate control problem,"IEEE Transactions on Automation Science and Engineering, vol. 13, no. 2, pp. 772–788, Apr. 2016. [14] R. Ganesan, T. K. Das and K. M. Ramachandran, 'A multiresolution Analysis-assisted reinforcement learning approach to Run-by-Run control,"IEEE Transactions on Automation Science and Engineering, vol. 4, no. 2, pp. 182–193, Apr. 2007. [15] G. Nicolosi, R. Volpe and A. Messineo, 'An innovative adaptive control system to regulate microclimatic conditions in a greenhouse,"Energies, vol. 10, no. 5, pp. 1–14, May. 2017. [16] M. Taki, Y. Ajabshirchi, S. F. Ranjbar, A. Rohani and M. Matloobi, 'Heat transfer and MLP neural network models to predict inside environment variables and energy lost in a semi-solar greenhouse,"Energy and Buildings, vol. 110, pp. 314–329, Jan. 2016. [17] Y. Q. Jiang, T. Li, M. Zhang, S. Sha and Y. H. Ji, 'WSN-based control system of CO2 concentration in greenhouse,"Intelligent Automation & Soft Computing, vol. 21, no. 3, pp. 285–294, Jun. 2015. [18] B. Khoshnevisan, S. Rafiee, J. Iqbal, S. Shamshirband, M. Omid, N. B. Anuar and A. W. Abdul Wahab, 'A comparative study between artificial neural networks and adaptive Neuro-fuzzy inference systems for modeling energy consumption in greenhouse tomato production: A case study in Isfahan Province,"Journal of Agricultural Science and Technology, vol. 17, no. 1, pp. 49–62, Jan. 2015. [19] M. L. Jin and M. C. Ho, 'LabVIEW-based fuzzy controller design of a lighting control system,"Journal of Marine Science and Technology, vol. 17, no. 2, pp. 116-121, Apr. 2009. [20] P. C. Chen, C. W. Chen, W. L. Chiang and D. C. Lo, ' GA-based modified adaptive fuzzy sliding mode controller for nonlinear systems,"Expert Systems with Applications, vol. 36, no. 3, pp. 5872-5879, Apr. 2009. [21] J. Kennedy and R. Eberhart, 'Particle Swarm Optimization,"IEEE International Conference on Neural Networks, vol. 4, pp. 1942-1948, Dec. 1995. [22] Y. Shi and R. C. Eberhart, 'Parameter Selection in Particle Swarm Optimization,' Proceedings of the Seventh Annual Conference on Evolutionary Programming, vol. 1447, pp. 591–600, 1998. [23] H. Yoshida, K. Kawata, Y. Fukuyama, S. Takayama and Y. Nakanishi, 'A particle swarm optimization for reactive power and voltage control considering voltage security assessment,"IEEE Transactions on Power Systems, vol. 15, pp. 1232-1239, Nov. 2000. [24] D. Zhu, Y. Yang, M. Yan, 'Path panning algorithm for AUV bsed on a Fuzzy-PSO in dynamic environments,"Eighth International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp. 525-530, Sep. 2011. [25] T. Zhou, 'Temperature control method for water-coal-mixture gasifier system based on fuzzy control rules optimized by PSO algorithm, "in Proceedings of the IEEE Conference on Measurement, Information and Control, vol. 38, pp. 793-796, Aug. 2013.
微環境控制近年來發展蓬勃,受到學術界及業界的重視,世界各地紛紛投入資源,爭相開發微環境系統,用以改變農業生產模式,提高農作生產效率與能力,並同步將農村人力不足與地球環境變遷的影響降至最低。本論文運用微環境控制箱搭配模糊粒子群演算法(Particle swarm optimization, PSO)建置微環境的控制模式與能力,兼顧能源應用效率,創造出最有利於作物生長與管理的人造環境。
本研究使用非色散式紅外線溫濕二氧化碳感測器監測微環境控制箱環境數據,並將資料回傳至由MATLAB軟體所建構之即時監看人機介面,再透過模糊控制(Fuzzy Control)、模糊粒子群控制器(Fuzzy-PSO Control)兩種模式來操縱Arduino微控制器進行溫度、濕度輸出的參數比較與調控。

The establishment of microenvironment is flourished recently. Since the microenvironment is a hot topic for academia and industry, many efforts and resources have been dedicated to realization all over the world. A perfect created and controlled microenvironment not only can reconstruct a new farming model but also improve productivity and capability. The problems about labor-lack and influence from the global climate change can also be minimized with such systems simultaneously. This thesis will employ MATLAB codes, a Arduino micro-controller and the fuzzy particle swarm optimization theory algorithm to establish a micro-environment control scheme in which a NDIR CO2 meter will detect the microenvironment status inside the plant growth chamber. Then, status signs are conducted into the user interface that was coded by MATLAB as the input reference. It will be a convenient real-time surveillance system for user. The Fuzzy theory and PSO (Particle swarm optimization) algorithm compose the Fuzzy-PSO controller with which the microenvironment parameters including the temperature and humidity inside the plant growth chamber will be implemented and defined. To verify the effectiveness, five different scenarios were set to manipulate. In humidity control, the Fuzzy-PSO controller was superior to the Fuzzy controller. In temperature control, for the scenario of temperature and humidity decreased at the same time, the performance of Fuzzy-PSO controller was not as good as using Fuzzy controller only. After the heat pump worked for a relative long time, the heater had to be turned on to increase temperature. As this procedure worked near sampling time, it would resulted in the unstable status and a distinct errors. Except for the scenario above, all results conducted by the Fuzzy-PSO controller were more excellent than the Fuzzy one on temperature control. As the range of the ideal environment for roses grow is 21 to 29℃ during the daytime, 15 to 18℃ at night and the range of humidity is 50 to 60%. This thesis validates the effectiveness and practicality of the Fuzzy-PSO controller in temperature and humidity for micro-environmental control since temperature errors were controlled within 1℃, and humidity errors were controlled within 5%.
Rights: 同意授權瀏覽/列印電子全文服務,2021-08-23起公開。
Appears in Collections:生物產業機電工程學系

Files in This Item:
File SizeFormat Existing users please Login
nchu-107-7105040406-1.pdf3.22 MBAdobe PDFThis file is only available in the university internal network    Request a copy
Show full item record
TAIR Related Article

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.