It makes complexity increasing with exponent to fault separation and diagnosis, called "Curse of Dimension" [1,2].
Finally, we give an actual fault separation problem in classical chemical process Tennessee Eastman (TE) to further study.
In fault separation problem presented above, it equals to screen original process variables related to certain faults as most as possible.
To fault separation problem with nonlinear redundancy process/control variables, an approach is proposed in Figure 2.
Fault Separation of Tennessee Eastman with Redundancy Variables
Nonlinear Fault Separation of Redundancy Variables.
With the above variable sets, the accuracy of fault separation between Fault9 and Fault11 is successivelytested.