Research on the Development of Light Blending Model for Smart LED Lighting
LIU Qiang1, 2, 3, WAN Xiao-xia1*, LI Jun-feng1, LIANG Jin-xing1, LI Bi-hui1, WANG Qi1
1. School of Printing and Packaging, Wuhan University, Wuhan 430079, China 2. Shenzhen Institute, Wuhan University, Shenzhen 518000, China 3. State Key Laboratory of Pulp and Paper Engineering of South China University of Technology, Guangzhou 510640, China
Abstract:The color of the LED smart light is tunable by its inner equipped micro-processing systems. Therefore, it could provide significant improvement for the smart lighting conditions, such as museum lighting and home lighting. At present, the limitation of the current lighting blending technology remarkably affects the application of smart lighting technology and people could not make full use of the adjustability of the smart luminaries. In this research, a novel light blending model was proposed based on BP neural network and active set algorithm. The models could effectively simulate the nonlinear relationship between the device control values of the smart light and the output radiance spectrum of the light. Particularly, a BP neural network-based forward model for LED light blending was firstly proposed, which could accurately calculate the spectral radiance power distribution from the device control values. Afterwards, based on forward model, an active set algorithm-based backward model was developed, which could precisely predict the device control values from the desired spectral radiance power distribution. The experimental result indicates that the proposed method could accurately achieve the light blending controlling of smart LED light, with a CIEUCS Duv value of 0.002 7, which is significantly smaller than the just noticeable difference value of human vision. The authors believe that the proposed method will provided effective support for the development of smart LED lighting in near future.
Key words:LED smart lighting;Light blending;Forward model;Backward model
刘 强1,2,3,万晓霞1*,李俊锋1,梁金星1,李必辉1,王 琪1 . LED智能光源混光呈色模型构建方法研究 [J]. 光谱学与光谱分析, 2016, 36(10): 3138-3143.
LIU Qiang1, 2, 3, WAN Xiao-xia1*, LI Jun-feng1, LIANG Jin-xing1, LI Bi-hui1, WANG Qi1 . Research on the Development of Light Blending Model for Smart LED Lighting . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(10): 3138-3143.
[1] YU Chun-yu, JIN Peng, ZHOU Qi-feng(喻春雨, 金 鹏,周奇峰). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015,35(5):39. [2] Lee A T. Power Electronics, IEEE Transactions on, 2016, 31(1): 65. [3] Nascimento S,Masuda O. Journal of the Optical Society of America A: Optics and Image Science and Vision, 2014, 31(4): 214. [4] Zukauskas A. Optics Express, 2012, 20(5): 5356. [5] Mahler E, Ezrati J, Viénot F. Color Research & Application, 2009,34(1): 8. [6] Schanda J, Csuti P,Szabó F. Leukos, 2016, 12(1-2): 71. [7] Scuello M. Color Research and Application, 2004,29(2): 121. [8] Liu A. Photonics Journal, IEEE, 2013, 5(4): 6801010. [9] Pinto D, Linhares J, Nascimento S. Journal of the Optical Society of America A: Optics and Image Science and Vision, 2008,25(3): 623. [10] Imai H, Rosen M, Berns R S. Conference on Colour in Graphics, Imaging and Vision, 2002. 492. [11] Kang H R. Computational Color Technology. Bellingham: SPIE Press, 2006. 479. [12] Schanda J. Colorimetry: Understanding the CIE System. New Jersey: Wiley, 2007. [13] Jawahar M, Kannan N, Babu C,et al. Coloration Technology, 2015, 131(1): 48. [14] Fausett L. Fundamentals of Neural Networks: Architectures, Algorithms, and Applications. Englewood Cliffs: Prentice-Hall, Inc. 1994. 91. [15] Chong K,Zak S H. An Introduction to Optimization. New York: Wiley,2013. [16] Hernández J, Romero J,Lee J. Journal of the Optical Society of America A: Optics and Image Science and Vision, 2001, 18(2): 412. [17] SUN Hui, XU Shu-yan, SUN Shou-hong,et al(孙 慧, 徐抒岩, 孙守红,等). Laser & Optoelectronics(激光与光电子学进展), 2015,52(4): 80. [18] YUAN Qiao,ZHAN Qing-xuan(袁 樵, 詹庆旋). China Illuminating Engineering Journal(照明工程学报), 2002,13(4): 55.