A Data-Driven Semi-Supervised Soft-Sensor Method: Application on an Industrial Cracking Furnace

Abstract

The cracking furnace is the key equipment of the ethylene unit. Coking in furnace tubes results from the generation of coke during cracking, which will compromise the heat transfer efficiency and lead to shape change of tubes. In order to keep the cracking furnace operating economically and safely, the engineers need to decoke according to the surface temperature of the furnace tube. However, the surface temperature of the furnace tube is difficult to obtain in practice. Due to redundant instrumentation and the high level of process control in cracking furnaces, a large number of operation data have been collected, which makes it possible to predict the surface temperature of furnace tubes based on autocorrelation and cross correlation within and among variables. Traditional prediction methods rely on labeled data samples for training, ignoring the process information contained in a vast amount of unlabeled data. In this work, a data-driven semi-supervised soft-sensor method is proposed. Considering the nonlinear and dynamic relationship among variables, long short-term memory network (LSTM) autoencoder (AE), a deep neural network suitable for the feature extraction of long-term nonlinear series, is used for pre-training to extract process data features from unlabeled and labeled data. Then, principal component analysis (PCA) and mutual information (MI) are applied to remove feature correlation and select features related to target variables, respectively. Finally, the selected data features are utilized to establish a soft-sensor model based on artificial neural network (ANN). Data from an industrial cracking furnace of an ethylene unit is considered to validate the performance of the proposed method. The results show that the prediction error of furnace tube surface temperature is about 1% and successfully aid engineers in determining the optimal time for decoking.