The predictive models using Bayesian regularization neural network and grey model are established for the H+ concentration in the HPO, two kinds of model are compared and associated to establish model and to predict.

This paper compares the results by standard BP algorithm with that of Bayesian regularization together with LM algorithm.

The BPNN model of Bayesian regularization method was adopted to create the adaptivity and generalization of BPNN.

The Bayes regularization method is employed to get a well generalized neural networks, the redundant and irrelevant attributes can be deleted from the prime attributes set by pruning the input node of the networks.

This paper establishes dynamic forward feedback correction model with the method of combining Bayes regularization and BP neural network.

Based on nonlinear prediction ideas of reconstructing phase space, this paper presents a time delay BP neural network model, whose generalization is improved utilizing Bayes regularization.

The Levenberg-Marquart(L-M) Bayesian regularization algorithm is combined with the back-propagation(BP) neural network to make the BP network achieve better generalization,faster speed of convergence and higher learning accuracy.