Impurity removal amount prediction method in chemical process

An impurity removal amount prediction method in chemical process comprising:

• training neural network models using data from a chemical process;
• predicting removal amounts of impurities removed in the chemical process using the trained neural network models;
• and
• performing the chemical process using operating conditions from the trained neural network models,
• wherein the impurities are included in the feed supplied to reactors of the chemical process and are removed by reacting with catalysts disposed in the reactors,
• wherein the reactors include a first reactor and a second reactor arranged in parallel,
• wherein the neural network models include a first neural network model applied to the first reactor and a second neural network model applied to the second reactor,
• wherein an objective function of the neural network models includes a penalty term for correcting a difference between output data of the first neural network model and output data of the second neural network model, and
• wherein the neural network models learn in the direction to minimize the difference between the output data of the first neural network model and the second neural network model.