|
|
基于模糊PID控制的家居照明环境智能调节方法
|
Abstract:
本研究融合了神经网络和模糊推理技术，提出了一种家居照明智能调节方案。该方法以家庭各区域的活动时间为输入变量，根据活动时间长短来识别不同的生活场景，并以此为规则推导出目标场景的特征值。灯具控制模型采用三层前馈型BP神经网络，包括输入层、一个隐含层(13个神经元)和输出层，利用正向传播和误差逆向传播优化模型参数。此外，引入了模糊PID控制技术实现了对灯具更精确的调光控制。经仿真验证，BP神经网络模型拟合优度好、泛化能力强，其预测得到的调光值可直接用于灯具调控。而模糊PID控制算法与传统PID控制相比，能够实现更加精确和稳定的控制效果，与其他主流控制方法相比更适用于家居照明。
In this paper, an intelligent adjustment scheme for home lighting is proposed by combining neural network and fuzzy reasoning technology. The method takes the activity time of each area of the family as the input variable, identifies different life scenes according to the activity time, and de-duces the characteristic value of the target scene according to the rule. The lamp control model adopts three-layer feedforward BP neural network, including input layer, a hidden layer (13 neu-rons) and output layer. Forward propagation and error reverse propagation are used to optimize the model parameters. In addition, the fuzzy PID control technology is introduced to achieve more accurate dimming control of the luminaire. The simulation results show that BP neural network model has good fit and generalization ability, and the dimming value predicted by BP neural net-work model can be directly used for luminaire control. Compared with traditional PID control, fuzzy PID control algorithm can achieve more accurate and stable control effect, and is more suitable for home lighting compared with other mainstream control methods.
| [1] | 杨萌. 智能照明控制系统的应用现状及发展趋势[J]. 设备管理与维修, 2021(3): 147-148. |
| [2] | 孙瑜, 胡从川. 基于ZigBee技术的照明设备亮度自适应节能控制优化方法[J]. 自动化与仪表, 2023, 38(6): 14-17, 22. |
| [3] | Athienitis, A.K. and Tzempelikos, A. (2002) A Methodology for Simulation of Daylight Room Illuminance Distribution and Light Dimming for a Room with a Controlled Shading Device. Solar Energy, 72, 271-281. https://doi.org/10.1016/S0038-092X(02)00016-6 |
| [4] | Li, L., Wang, J., Yang, S., et al. (2021) Binocular Stereo Vision Based Illuminance Measurement Used for Intelligent Lighting with LED. Optik, 237, Article ID: 166651. https://doi.org/10.1016/j.ijleo.2021.166651 |
| [5] | Li, D.H.W. and Lam, J.C. (2003) An Investigation of Daylighting Performance and Energy Saving in a Daylit Corridor. Energy and Buildings, 35, 365-373. https://doi.org/10.1016/S0378-7788(02)00107-X |
| [6] | Wang, B. and Wang, F. (2021) Research on Intelligent Lighting Distributed Control Algorithm Based on Sensor Network Technology. Microprocessors and Microsystems, 81, Article ID: 103729. https://doi.org/10.1016/j.micpro.2020.103729 |
| [7] | Trobec Lah, M., Zupan？i？, B., Peternelj, J., et al. (2006) Daylight Illuminance Control with Fuzzy Logic. Solar Energy, 80, 307-321. https://doi.org/10.1016/j.solener.2005.02.002 |
| [8] | Liao, H., Sheng, X. and Yang, D. (2018) Design of Adaptive Lighting System Based on Fuzzy PID. 2018 Chinese Control and Decision Conference (CCDC), Shenyang, 9-11 June 2018, 1543-1547. https://doi.org/10.1109/CCDC.2018.8407372 |
| [9] | Zhang, S. and Birru, D. (2012) An Open-Loop Venetian Blind Control to Avoid Direct Sunlight and Enhance Daylight Utilization. Solar Energy, 86, 860-866. https://doi.org/10.1016/j.solener.2011.12.015 |
| [10] | Yuan, X., Yang, C., Yin, Z., et al. (2018) Power Saving LED Luminance Fuzzy Control with IOT Network. 2018 2ND International Conference on Artificial Intelligence Applications and Technologies (AIAAT 2018). IOP Conference Series: Materials Science and Engineering, 435, Article ID: 011001. https://doi.org/10.1088/1757-899X/435/1/011001 |
| [11] | Xiaogang, Y., Wang, W. and Fenna, L. (2020) Design and Simulation of Intelligent Dimmer Based on Fuzzy PID. 2020 International Conference on Intelligent Design (ICID), Xi’an, 11-13 December 2020, 86-89. https://doi.org/10.1109/ICID52250.2020.00025 |
| [12] | Seyedolhosseini, A., Masoumi, N., Modarressi, M., et al. (2018) Zone Based Control Methodology of Smart Indoor Lighting Systems Using Feedforward Neural Networks. 2018 9th International Symposium on Telecommunications (IST), Tehran, 17-19 December 2018, 201-206. https://doi.org/10.1109/ISTEL.2018.8661118 |
| [13] | 刘畅, 付保川, 吴征天, 等. 道路智能照明动态模型研究及其应用[J]. 照明工程学报, 2020, 31(3): 44-49. |
| [14] | 郭敬, 张玉杰. 基于遗传模拟退火算法的室内照明节能控制方法研究[J]. 应用光学, 2022, 43(5): 879-885. |
| [15] | 邓心, 那俊, 张瀚铎, 等. 基于深度强化学习的智能灯个性化调节方法[J]. 计算机工程与应用, 2022, 58(6): 264-270. |
| [16] | 张玉杰, 王帆. 基于改进麻雀搜索算法的照明控制优化[J]. 计算机应用, 2023, 43(3): 835-841. |
| [17] | 朱思峰, 杨诚瑞, 柴争义. 基于神经网络的智能家居管控方案[J]. 南开大学学报(自然科学版), 2023, 56(5): 1-8. |
| [18] | 孙家辉, 吴涛. 基于模糊控制的智能家居控制系统研究与设计[J]. 现代电子技术, 2022, 45(16): 161-164. |
| [19] | 李文洁. 基于神经网络的智能家居照明控制系统的研究[D]: [硕士学位论文]. 北京: 北京交通大学, 2022. |
| [20] | Zhang, X., Yin, F., Zhang, Y., et al. (2018) Drawing and Recognizing Chinese Characters with Recurrent Neural Network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 849-862. https://doi.org/10.1109/TPAMI.2017.2695539 |
| [21] | Hecht-Nielsen, R. (1992) III.3—Theory of The Backpropagation Neural Network. In: Wechsl, H., Ed., Neural Networks for Perception, Academic Press, Cambridge, 65-93. https://doi.org/10.1016/B978-0-12-741252-8.50010-8 |
| [22] | 王晓辉, 刘静蕾, 边会娟, 等. 基于改进BP神经网络的室内环境热舒适度预测与分析[J]. 控制工程, 2021, 28(7): 1437-1445. |
| [23] | 戴玉宽, 喻昕. 基于BP神经网络的智能家居系统建模与分析[J]. 新型工业化, 2022, 12(7): 240-244. |
| [24] | 兰胜坤. 遗传算法优化BP神经网络的说话人识别系统[J]. 重庆理工大学学报(自然科学), 2013, 27(10): 91-95. |
| [25] | 李娟. 基于蚁群算法的太阳能LED路灯智能照明控制方法[J]. 照明工程学报, 2023, 34(3): 52-57. |
| [26] | 杜冠峰, 秦会斌. 基于车辆感知和模糊PID的隧道照明控制系统[J]. 传感器与微系统, 2021, 40(2): 95-97, 101. |
| [27] | 王加安, 杨鸿基, 张家祺. 基于遗传算法的室内照度光场分布及性能分析[J]. 照明工程学报, 2021, 32(4): 113-120. |
| [28] | 孙握瑜. 基于模糊神经网络算法的智能控制技术[J]. 河北北方学院学报(自然科学版), 2022, 38(5): 1-5. |
| [29] | De Keyser, R. and Ionescu, C. (2010) Modelling and Simulation of a Lighting Control System. Simulation Modelling Practice and Theory, 18, 165-176. https://doi.org/10.1016/j.simpat.2009.10.003 |
| [30] | 苗荣霞, 张洋, 李洁馨, 等. 基于交通流预测的隧道照明控制方法研究[J]. 微处理机, 2023, 44(6): 55-58. |
