Optimization of Boiler Scheduling Based on LSTM Model for Predicting Steam Consumption in the Cigarette Industry
In the production process of cigarettes,steam belongs to the secondary production and processing energy,which is generally produced by the power workshop according to the production demand plan and is one of the indispensable energy sources.Accurately predicting steam consumption is crucial for energy conservation,optimizing boiler scheduling,reducing costs,and improving efficiency.Traditional prediction methods often suffer from issues such as insufficient accuracy or inability to handle the complexity of time series data.This article proposes a model based on Long Short Term Memory(LSTM)to predict steam consumption in cigarette production processes,and explores how to use this model to optimize boiler scheduling.The superiority of the LSTM model and its potential application in the cigarette industry have been demonstrated through experimental verification on actual datasets.
NETL
NSTL
万方数据
