Since in practical industrial applications, soft sensors based on static models often lead to low accuracy and poor robustness, a multiple neural network (MNN) model is presented to develop dynamic soft sensors. The a...Since in practical industrial applications, soft sensors based on static models often lead to low accuracy and poor robustness, a multiple neural network (MNN) model is presented to develop dynamic soft sensors. The approach is applied to building a dynamic soft sensor estimating the production component in a simulated binary distillation unit and good results are obtained.展开更多
文摘Since in practical industrial applications, soft sensors based on static models often lead to low accuracy and poor robustness, a multiple neural network (MNN) model is presented to develop dynamic soft sensors. The approach is applied to building a dynamic soft sensor estimating the production component in a simulated binary distillation unit and good results are obtained.
