State Key Laboratory of Clean Energy Utilization, State Environmental Protection Center for Coal-Fired Air Pollution Control, Zhejiang University, Hangzhou, 310027, China.
Jiaxing Research Institute, Zhejiang University, Jaixing, 314000, China.
Environ Sci Pollut Res Int. 2023 Apr;30(18):53089-53102. doi: 10.1007/s11356-023-25988-5. Epub 2023 Feb 28.
Circulating fluidized bed (CFB) boilers with wet flue gas desulfurization (WFGD) system is a popular technology for SO removal in the coal-fired thermal power plant. However, the long response time of continues emission monitoring system (CEMS) and the hardness of continuously monitoring the coal properties leads to the difficulties for controlling WFGD. It is important to build a model that is adaptable to the fluctuation of load and coal properties, which can obtain the SO concentration ahead CEMS, without relying on coal properties. In this paper, a prediction model of inlet SO concentration of WFGD considering the delay between the features and target based on long-short term memory (LSTM) network with auto regression feature is established. The SO concentration can be obtained 90 s earlier than CEMS. The model shows good adaptability to the fluctuation of SO concentration and coal properties. The root-mean-squared error (RMSE) and R squared (R) of the model are 30.11 mg/m and 0.986, respectively. Meanwhile, a real-time prediction system is built on the 220 t/h unit. A field test for long-term operation has been conducted. The prediction system is able to continuously and accurately predict the inlet SO concentration of the WFGD, which can provide the operators with an accurate reference for the control of WFGD.
循环流化床(CFB)锅炉结合湿法烟气脱硫(WFGD)系统是燃煤火力发电厂去除 SO 的一种流行技术。然而，连续排放监测系统(CEMS)的长响应时间和持续监测煤质的困难导致 WFGD 控制变得困难。建立一个能够适应负荷和煤质波动的模型非常重要，该模型可以在不依赖煤质的情况下提前获得 CEMS 之前的 SO 浓度。本文提出了一种基于长短期记忆(LSTM)网络自动回归特征的考虑特征与目标之间延迟的 WFGD 入口 SO 浓度预测模型。该模型可以提前 90s 获取 SO 浓度。该模型对 SO 浓度和煤质的波动具有良好的适应性。模型的均方根误差(RMSE)和 R 平方(R)分别为 30.11mg/m 和 0.986。同时，在 220t/h 机组上建立了实时预测系统，并进行了长期运行的现场测试。预测系统能够连续、准确地预测 WFGD 的入口 SO 浓度，为 WFGD 的控制提供了准确的参考。
