Health monitoring of a shaft transmission system via hybrid models of PCR and PLS

Prediction of motor shaft misalignment is essential for the development of effective coupling and rotating equipment maintenance information systems. It can be stated as a multivariate regression problem with ill-posed data. In this paper, hybrid models of principal components regression (PCR) and partial least squares regression (PLS) have been proposed for this problem. The basic idea of hybrid models is to combine the merits of PCR and PLS to develop more accurate prediction techniques. Both the principal components defined in PCR and the latent variables in PLS are involved in a hybrid model. The experimental results show that an optimal hybrid model can outperform PCR and PLS, especially when the number of predictor variables increases. It suggests that the proposed approach may be particularly useful for complex prediction tasks that need more predictor variables. Discussions for future research are also presented.