NOUFERROUS METALLURGICAL EQUIPMENT

The main steam parameters of waste heat boiler in waste incineration power plant play an important role in the economic benefits, operation stability and safety of the incineration plant. The combustion process in incinerator is a multiple inputs and multiple outputs nonlinear physical and chemical process, and the influence of various factors must be considered. In this paper, the appropriate modeling variables are selected from the operation data of the incineration system, and a LSTM neural network model with multiple inputs and multiple outputs is established to train and test the prediction accuracy of the model. The model can be dynamically updated and optimized according to real-time data. It can accurately predict the main steam parameters and provide theoretical guidance for field personnel to adjust the control strategy, so as to improve the stability and economy of production and operation.