【摘要】 为提高电厂除尘设备能源利用效率，本文以干式电除尘器为研究对象，展开了对其能耗优化方法的研究。首先，基于干式电除尘器的工作原理分析了影响除尘效率的关键因素；其次，利用深度神经网络建立了典型工况下电除尘器各级电场二次电流与出口烟尘浓度的预测模型，同时，采用多项式拟合方法构建了各级电场二次电流与能耗之间的关系模型；最后，以能耗为优化目标，在出口烟尘浓度与电源参数的约束条件下，应用人工蜂群算法搜索几种典型工况下的最佳电流预设值，利用该预设值得到各出口烟尘浓度所对应的能耗优化方案。实验结果表明，在保证出口烟尘浓度符合标准的前提下，干式电除尘器总视在功率得到明显优化，表明通过所提方法可以在符合环保要求的前提下有效提高能源利用效率。更多还原

【Abstract】 To enhance the energy efficiency of dust removal equipment in power plants, this study focuses on optimizing the energy consumption of a dry electrostatic precipitator(ESP). First, the key factors affecting dust removal efficiency were analyzed based on the operating principles of the dry ESP. Next, a deep neural network was employed to develop a predictive model for secondary current and outlet dust concentration under typical operating conditions. Additionally, a polynomial fitting method was used to establish a relationship model between the secondary current and energy consumption. Finally, with energy consumption as the optimization objective and constraints on outlet dust concentration and power parameters, the artificial bee colony algorithm was applied to search for the optimal current preset values under various typical conditions. These values were then used to obtain energy consumption optimization schemes corresponding to different outlet dust concentrations. Experimental results demonstrate that the proposed method significantly optimizes the total apparent power of the dry ESP while ensuring that the outlet dust concentration meets the required standards, indicating that the method can effectively improve energy efficiency while complying with environmental regulations.更多还原