Hybrid artificial neural network based on BP-PLSR and its application in development of soft sensors

A novel hybrid artificial neural network (HANN) integrating error back propagation algorithm (BP) with partial least square regression (PLSR) was proposed to overcome two main flaws of artificial neural network (ANN), i.e. tendency to overfitting and difficulty to determine the optimal number of the hidden nodes. Firstly, single-hidden-layer network consisting of an input layer, a single hidden layer and an output layer is selected by HANN. The number of the hidden-layer neurons is determined according to the number of the modeling samples and the number of the neural network parameters. Secondly, BP is employed to train ANN, and then the hidden layer is applied to carry out the nonlinear transformation for independent variables. Thirdly, the inverse function of the output-layer node activation function is applied to calculate the expectation of the output-layer node input, and PLSR is employed to identify PLS components from the nonlinear transformed variables, remove the correlation among the nonlinear transformed variables and obtain the optimal relationship model of the nonlinear transformed variables with the expectation of the output-layer node input. Thus, the HANN model is developed. Further, HANN was employed to develop naphtha dry point soft sensor and the most important intermediate product concentration (i.e. 4-carboxybenzaldehyde concentration) soft sensor in p-xylene (PX) oxidation reaction due to the fact that there exist many factors having nonlinear effect on them and significant correlation among their factors. The results of two HANN applications show that HANN overcomes overfitting and has the robust character. And, the predicted squared relative errors of two optimal HANN models are all lower than those of two optimal ANN models and the mean predicted squared relative errors of HANN are lower than those of ANN in two applications.

[1]  Luigi Fortuna,et al.  Soft sensors for product quality monitoring in debutanizer distillation columns , 2005 .

[2]  Alaa Eleyan,et al.  Face Recognition System Based on PCA and Feedforward Neural Networks , 2005, IWANN.

[3]  Hengkun Xie,et al.  Combined use of partial least-squares regression and neural network for residual life estimation of large generator stator insulation , 2007 .

[4]  A. Zilouchian,et al.  Prediction of products quality parameters of a crude fractionation section of an oil refinery using neural networks , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[5]  Mikko Lehtokangas.  Modelling with constructive backpropagation , 1999, Neural Networks.

[6]  Graham C. Goodwin,et al.  Predicting the performance of soft sensors as a route to low cost automation , 2000 .

[7]  Feng Qian,et al.  Development of a kinetic model for industrial oxidation of p‐xylene by RBF‐PLS and CCA , 2004 .

[8]  Gustavo Deco,et al.  Two Strategies to Avoid Overfitting in Feedforward Networks , 1997, Neural Networks.

[9]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[10]  Qian Feng,et al.  Development of naphtha dry point soft sensor by adaptive partial least square regression , 2005 .

[11]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[12]  Sebastian Engell,et al.  Model Predictive Control Using Neural Networks [25 Years Ago] , 1995, IEEE Control Systems.

[13]  Russell Reed,et al.  Pruning algorithms-a survey , 1993, IEEE Trans. Neural Networks.

[14]  Di Wu,et al.  BP Neural Networks Combined with PLS Applied to Pattern Recognition of Vis/NIRs , 2006, IDEAL.

[15]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[16]  Rubens Maciel Filho,et al.  Soft sensors development for on-line bioreactor state estimation , 2000 .

[17]  A. Höskuldsson.  PLS regression methods , 1988 .

[18]  Ru-Qin Yu,et al.  Multivariate nonlinear modelling of fluorescence data by neural network with hidden node pruning algorithm , 1997 .

[19]  Latifa Oukhellou,et al.  Combined use of partial least squares regression and neural network for diagnosis tasks , 2004, ICPR 2004.

[20]  Y. Jiang,et al.  Comparison of two methods of adding jitter to artificial neural network training , 2004, CARS.

[21]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[22]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[23]  Ali Zilouchian,et al.  Intelligent Control Systems Using Soft Computing Methodologies , 2000 .

[24]  Hussein A. Abbass,et al.  Stopping criteria for ensemble of evolutionary artificial neural networks , 2005, Appl. Soft Comput..