摘要：The control of flue gas emission in thermal power plants has been a topic of concern. Selective catalytic reduction technology has been widely used as an effective flue gas treatment technology. However, precisely controlling the amount of ammonia injected remains a challenge. Too much ammonia not only causes secondary pollution but also corrodes the reactor equipment, while too little ammonia does not effectively reduce the NOx content. In recent years, deep reinforcement learning has achieved better results than traditional methods in decision making and control, which provides new methods for better control of selective catalytic reduction systems. The purpose of this research is to design an intelligent controller using reinforcement learning technology, which can accurately control ammonia injection, and achieve higher denitrification effect and less secondary pollution. To train the deep reinforcement learning controller, a high-precision virtual denitration environment is first constructed. In order to make the virtual environment more realistic, this virtual environment was designed as a special structure with two decoders and a unique approach was used in fitting the virtual environment. A deep deterministic policy agent is used as an intelligent controller to control the amount of injected ammonia. To make the intelligent controller more stable, the actor-critic framework and the experience pool approach were adopted. The results show that the intelligent controller can control the emissions of nitrogen oxides and ammonia at the outlet of the reactor after training in virtual environment.
