風力發電市電併聯系統之類神經網路分數階PID功率控制

Neural Network FOPID Power Control for Grid-tied Wind Energy Conversion Systems

洪偉傑(Wei-Jei Hong)

指導教授 ： 邱謙松

中原大學/工學院/電機工程研究所/碩士(2014年)

https://doi.org/10.6840/cycu201400912

摘要

本論文主旨在研製一風力發電市電併聯系統，即將風力發電機的電力經由z-source 轉換器和全橋式變流器兩種電力電子轉換器併入市電。為了達到高效能的風力發電及穩定的電壓輸出，本論文提出類神經分數階PID ( Neural Network Based Fractional Order PID )進行交流變流器之輸出電流追蹤控制，進而使風力發電機達到最大功率輸出並解決最大功率追蹤( Maximum Power Point Tracking, MPPT )的問題。從本論文的模擬以及實作結果可以發現NNFOPID控制器的響應比傳統的PI控制器來的好。本論文提出的控制器可以在不同環境下自行調整內部參數，在變動風速的環境下，也可以快速收斂到最大功率點。

關鍵字

類神經分數階PID ； 市電併聯 ； 風力發電系統 ； 最大功率追蹤

並列摘要

The main purpose of thesis is to design a grid-tied wind power generating system with maximum power point tracking (MPPT) performance. To transfer the wind power to electric power access the utility grid, a two-stage power converters containing a z-source converter and a full-bridge DC/AC inverter are applied on the wind power generating system. In order to achieve high efficiency and to stabilize output power, we design a neural network based fractional-order PID (FOPID) for the output current tracking of the DC/AC inverter. The neural network based fractional order PID controller can adjust the control parameter by itself for different environment. The numerical simulation and experimental results can show the response of the NN-FOPID controller is better than PI controller. Therefore, fast convergence of the MPPT can be assured even if the wind speed is rapidly varying.

並列關鍵字

Grid Tied System ； Maximum Power Point Tracking (MPPT) ； Neural Network Based Fractional Order PID. ； Wind Power

參考文獻

[4] 王建斌，“風力發電系統最大功率追蹤方法之研究”，私立中原大學電機工程學系碩士論文，民國94年。

[1] E. Koutroulis, K. Kalaitzakis, and N. C. Voulgaris, “Development of a microcontroller-based, photovoltaic maximum power point tracking control system,” IEEE Trans. Power Electronics., vol. 16, no. 1, pp, 46-54, 2001.

[2] C. Hua, J. Lin, and C. Shen, “Implementation of a dsp-controlled photovoltaic system with peak power tracking,” IEEE Trans. Industrial Electronics, vol. 45, pp. 99-107, 1998.

[3] C. Dorofte, U. Borup, and F. Blaabjerg, “A combined two-method mppt control scheme for grid-connected photovoltaic system,” IEEE Power Electronics and Applications. Conf., pp. 1-10, 2005.

[5] H. Li, K. L. Shi, and P. G. McLaren, “Neural-Network-based sensorless maximum wind energy capture with compensated power coefficient,” IEEE Trans. on Industry Applications, Vol. 41, No. 6, pp. 1548-1556, 2005.