Kappa Number Prediction of Pulp Digester Using LSTM Neural Network

A digester, one of the major units of Kraft process, has a function for conversion of wood into wood pulp. It is controlled by monitoring Kappa number with nonlinear reaction and has a long resident time. This paper aims to present the prediction of kappa number in pulp digester in advance for 1-3 hours by using Long Short-Term Memory (LSTM) neural network. The structures of LSTM inputs consists of effective alkali, temperature, and outlet lignin content. The prediction has been developed with nonlinear simulations of digester reactions. The results reveal that a kappa prediction can be predicted in advance for 1, 2 and 3 hours with percentages of error 1.1, 1.9 and 2.9 respectively. It could be beneficial for an operator to decide on feedforward compensation before it is out of control.