This paper aims to combine neural network modelling with model-based fault detection. An accurate and robust model is critical in model-based fault detection. However, the development of such a model is the most difficult task especially when a non-linear system is involved. The problem comes not only from the lack of concerned information about model parameters, but also from the inevitable linearization. In order to solve this problem, neural networks are introduced in this paper. Instead of using conventional neural network modelling, the neural network is only used to approximate the non-linear part of the system, leaving the linear part to be represented by a mathematical model. This new scheme of integration between neural network and mathematical model (NNMM) allows the compensation of the error from conventional modelling methods. Simultaneously, it keeps the residual signatures physically interpretable.

This content is only available via PDF.
You do not currently have access to this content.