Dynamic kriging based fault detection and diagnosis approach for nonlinear noisy dynamic processes

- A New Fault Detection and Diagnosis (FDD) method combines metamodeling and Pattern Recognition Techniques (PRTs).
- The method addresses nonlinear noisy dynamic processes operating under time-varying inputs.
- Results show significant and consistent performance enhancements (accuracy and flexibility) for different PRTs types.
- The performance is preserved in different dynamic operating conditions, faulty scenarios, fault severities and fault types.
- The method successfully exploits the residuals generated by an efficient multivariate dynamic kriging-based predictor.

This paper presents a hybrid approach to improve data-based Fault Detection and Diagnosis (FDD). It is applicable to nonlinear dynamic noisy processes, operated under time-varying inputs. The method is based on the combination of kriging models and Pattern Recognition Techniques. A set of Multivariate Dynamic Kriging-based predictors (MDKs) is built and used to estimate the process dynamic behavior, while static kriging models are used to smooth the eventually noisy process outputs. The estimated and the actual smoothed outputs are compared, taking advantage of the higher capacity of the residual patterns generated in this way to characterize the process state. The performance of the method is illustrated through its application to a well-known benchmark case study, for which the FDD performance has been significantly improved. This improvement is consistently maintained in different dynamic operating conditions and faulty situations, including scenarios with modified fault severities and fault styles.