The failure of a fluid catalysis and cracking unit (FCCU) in a Chinese refinery was investigated by using nondestructive detection methods, fracture surface examination, hardness measurement, chemical composition and...The failure of a fluid catalysis and cracking unit (FCCU) in a Chinese refinery was investigated by using nondestructive detection methods, fracture surface examination, hardness measurement, chemical composition and corrosion products analysis. The results showed that the failure was caused by the dew point nitrate stress corrosion cracking. For a long operation period, the wall temperature of the regenerator in the FCCU was below the fume dew point. As a result, an acid fume NOx-SOx-H2O medium present- ed on the surface, resulting in stress corrosion cracking of the component with high residual stress. In order to confirm the relative conclusion, simulated testing was conducted in laboratory, and the results showed similar cracking characteristics. Finally, some sug- gestions have been made to prevent the stress corrosion cracking of an FCCU from re-occurring in the future.展开更多
The principal component analysis (PCA) algorithm is widely applied in a diverse range of fields for performance assessment, fault detection, and diagnosis. However, in the presence of noise and gross errors, the non...The principal component analysis (PCA) algorithm is widely applied in a diverse range of fields for performance assessment, fault detection, and diagnosis. However, in the presence of noise and gross errors, the nonlinear PCA (NLPCA) using autoassociative bottle-neck neural networks is so sensitive that the obtained model differs significantly from the underlying system. In this paper, a robust version of NLPCA is introduced by replacing the generally used error criterion mean squared error with a mean log squared error. This is followed by a concise analysis of the corresponding training method. A novel multivariate statistical process monitoring (MSPM) scheme incorporating the proposed robust NLPCA technique is then investigated and its efficiency is assessed through application to an industrial fluidized catalytic cracking plant. The results demonstrate that, compared with NLPCA, the proposed approach can effectively reduce the number of false alarms and is, hence, expected to better monitor real-world processes.展开更多
基金This work was financially supported by the Major State Basic Research Development Program of China (973 ProgramNo.19990970) and Petrochemical Company of China.
文摘The failure of a fluid catalysis and cracking unit (FCCU) in a Chinese refinery was investigated by using nondestructive detection methods, fracture surface examination, hardness measurement, chemical composition and corrosion products analysis. The results showed that the failure was caused by the dew point nitrate stress corrosion cracking. For a long operation period, the wall temperature of the regenerator in the FCCU was below the fume dew point. As a result, an acid fume NOx-SOx-H2O medium present- ed on the surface, resulting in stress corrosion cracking of the component with high residual stress. In order to confirm the relative conclusion, simulated testing was conducted in laboratory, and the results showed similar cracking characteristics. Finally, some sug- gestions have been made to prevent the stress corrosion cracking of an FCCU from re-occurring in the future.
基金Supported by the National High-Tech Research and Development (863) Program of China (No. 2001AA413320)
文摘The principal component analysis (PCA) algorithm is widely applied in a diverse range of fields for performance assessment, fault detection, and diagnosis. However, in the presence of noise and gross errors, the nonlinear PCA (NLPCA) using autoassociative bottle-neck neural networks is so sensitive that the obtained model differs significantly from the underlying system. In this paper, a robust version of NLPCA is introduced by replacing the generally used error criterion mean squared error with a mean log squared error. This is followed by a concise analysis of the corresponding training method. A novel multivariate statistical process monitoring (MSPM) scheme incorporating the proposed robust NLPCA technique is then investigated and its efficiency is assessed through application to an industrial fluidized catalytic cracking plant. The results demonstrate that, compared with NLPCA, the proposed approach can effectively reduce the number of false alarms and is, hence, expected to better monitor real-world processes.