Answers are grounded in this paper and cite their sources.
An approach to nonlinear partial least squares (PLS) modelling using radial basis function (RBF) neural networks to provide a nonlinear inner relationship is described, along with a technique (the hybrid BFGS algorithm) for training the networks. Results are given to show the performance with a number of different simulation examples, including a model of an industrial overheads condenser and reflux drum plant. Results confirm a significant improvement over linear PLS.
No takes yet. Share an insight, caveat, or question.
Wilson et al. (1997) studied this question.