Prediction of Syngas Compositions in Texaco Coal Gasification Process Using Robust Neural Estimator

A robust inferential estimator model based on improved dynamic principal component analysis (DPCA) and multiple neural networks (MNN) was proposed. Data for building non-linear models was re-sampled using DPCA algorithm to form a number of sets of training and test data. For each data set, a neural network model was developed. To improve the robustness and accuracy of the neural networks, the MNN was obtained by stacking multiple neural networks which were developed based on the reorganization of the original data. Model robustness is shown to be significantly improved as a direct consequence of using multiple neural network representations. The implementation of the model was presented and the model was applied to Texaco coal gasification system to predict the syngas compositions. Research results show that the proposed method provides promising prediction reliability and accuracy.