Improved correlation analysis and visualization of industrial alarm data.

The problem of multivariate alarm analysis and rationalization is complex and important in the area of smart alarm management due to the interrelationships between variables. The technique of capturing and visualizing the correlation information, especially from historical alarm data directly, is beneficial for further analysis. In this paper, the Gaussian kernel method is applied to generate pseudo continuous time series from the original binary alarm data. This can reduce the influence of missed, false, and chattering alarms. By taking into account time lags between alarm variables, a correlation color map of the transformed or pseudo data is used to show clusters of correlated variables with the alarm tags reordered to better group the correlated alarms. Thereafter correlation and redundancy information can be easily found and used to improve the alarm settings; and statistical methods such as singular value decomposition techniques can be applied within each cluster to help design multivariate alarm strategies. Industrial case studies are given to illustrate the practicality and efficacy of the proposed method. This improved method is shown to be better than the alarm similarity color map when applied in the analysis of industrial alarm data.

[1]  Bill Hollifield,et al.  The alarm management handbook : a comprehensive guide , 2010 .

[2]  Sirish L. Shah,et al.  An Introduction to Alarm Analysis and Design , 2009 .

[3]  Jan Eric Larsson,et al.  Real-time root cause analysis for complex technical systems , 2007, 2007 IEEE 8th Human Factors and Power Plants and HPRCT 13th Annual Meeting.

[4]  Sirish L. Shah,et al.  Graphical representation of industrial alarm data , 2010, IFAC HMS.

[5]  Marie-Jeanne Lesot,et al.  Similarity measures for binary and numerical data: a survey , 2008, Int. J. Knowl. Eng. Soft Data Paradigms.

[6]  Sergio Pissanetzky,et al.  Sparse Matrix Technology , 1984 .

[7]  C. Tappert,et al.  A Survey of Binary Similarity and Distance Measures , 2010 .

[8]  Sirish L. Shah,et al.  SDG (Signed Directed Graph) Based Process Description and Fault Propagation Analysis for a Tailings Pumping Process , 2010 .

[9]  Bernard W. Silverman,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[10]  Sirish L. Shah,et al.  Application of Multivariate Statistics for Efficient Alarm Generation , 2009 .

[11]  Chun-Houh Chen,et al.  GAP: A graphical environment for matrix visualization and cluster analysis , 2010, Comput. Stat. Data Anal..

[12]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[13]  Nina F. Thornhill,et al.  A practical method for identifying the propagation path of plant-wide disturbances , 2008 .

[14]  Sirish L. Shah,et al.  Signed directed graph based modeling and its validation from process knowledge and process data , 2012, Int. J. Appl. Math. Comput. Sci..

[15]  Junya Nishiguchi,et al.  IPL2 and 3 performance improvement method for process safety using event correlation analysis , 2010, Comput. Chem. Eng..

[16]  Sirish L. Shah,et al.  Effective resource utilization for Alarm Management , 2010, 49th IEEE Conference on Decision and Control (CDC).

[17]  Fan Yang,et al.  Correlation analysis of alarm data and alarm limit design for industrial processes , 2010, Proceedings of the 2010 American Control Conference.

[18]  Nina F. Thornhill,et al.  PSCMAP: A new tool for plant-wide oscillation detection , 2005 .

[19]  J. Noyes,et al.  Alarm systems: a guide to design, management and procurement , 1999 .