Title :
A self-validating inferential sensor for emission monitoring
Author :
Qin, S.Joe ; Yue, Hongyu ; Dunia, Ricardo
Author_Institution :
Dept. of Chem. Eng., Texas Univ., Austin, TX, USA
Abstract :
Proposes a self-validating inferential sensor approach based on principal component analysis (PCA). The input sensors are validated using a fault identification and reconstruction approach proposed in Dunia et al. (1996). A principal component model is built for the input sensor validation. The validated principal components are used to predict output variables using linear regression or neural networks. If a sensor fails, the sensor is identified and reconstructed with the best estimate from the PCA model. The principal components are also reconstructed accordingly for prediction. The self-validating soft sensor approach is applied to air emission monitoring
Keywords :
air pollution measurement; environmental science computing; fault location; inference mechanisms; neural nets; sensor fusion; statistical analysis; PCA; air emission monitoring; fault identification; fault reconstruction; input sensor validation; linear regression; neural networks; principal component analysis; self-validating inferential sensor; self-validating soft sensor; Chemical engineering; Chemical sensors; Electrical equipment industry; Input variables; Matrix decomposition; Monitoring; Neural networks; Predictive models; Principal component analysis; Vectors;
Conference_Titel :
American Control Conference, 1997. Proceedings of the 1997
Conference_Location :
Albuquerque, NM
Print_ISBN :
0-7803-3832-4
DOI :
10.1109/ACC.1997.611844
