Determination of Boiling Range of Xylene Mixed in PX Device Using Artificial Neural Networks

摘要

Determination of boiling range of xylene mixed in PX device is currently acrucial topic in the practical applications because of the recent disputes ofPX project in China. In our study, instead of determining the boiling range ofxylene mixed by traditional approach in laboratory or industry, we successfullyestablished two Artificial Neural Networks (ANNs) models to determine theinitial boiling point and final boiling point respectively. Results show thatthe Multilayer Feedforward Neural Networks (MLFN) model with 7 nodes (MLFN-7)is the best model to determine the initial boiling point of xylene mixed, withthe RMS error 0.18; while the MLFN model with 4 nodes (MLFN-4) is the bestmodel to determine the final boiling point of xylene mixed, with the RMS error0.75. The training and testing processes both indicate that the models wedeveloped are robust and precise. Our research can effectively avoid the damageof the PX device to human body and environment.