Finding the Direction of Disturbance Propagation in a Chemical Process Using Transfer Entropy

In continuous chemical processes, variations of process variables usually travel along propagation paths in the direction of the control path and process flow. This paper describes a data-driven method for identifying the direction of propagation of disturbances using historical process data. The novel concept is the application of transfer entropy, a method based on the conditional probability density functions that measures directionality of variation. It is sensitive to directionality even in the absence of an observable time delay. Its performance is studied in detail and default settings for the parameters in the algorithm are derived so that it can be applied in a large scale setting. Two industrial case studies demonstrate the method

[1]  Joydeep Bhattacharya,et al.  Effective detection of coupling in short and noisy bivariate data , 2003, IEEE Trans. Syst. Man Cybern. Part B.

[2]  Claude E. Shannon,et al.  A Mathematical Theory of Communications , 1948 .

[3]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part III: Process history based methods , 2003, Comput. Chem. Eng..

[4]  Richard D. Braatz,et al.  Fault Detection and Diagnosis in Industrial Systems , 2001 .

[5]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part II: Qualitative models and search strategies , 2003, Comput. Chem. Eng..

[6]  Carroll,et al.  Statistics for mathematical properties of maps between time series embeddings. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[7]  T. Schreiber,et al.  Information transfer in continuous processes , 2002 .

[8]  Nina F. Thornhill,et al.  Measuring Cause and Effect between Process Variables , 2005 .

[9]  Theodora Kourti,et al.  Process analysis and abnormal situation detection: from theory to practice , 2002 .

[10]  Schreiber,et al.  Measuring information transfer , 2000, Physical review letters.

[11]  James Theiler,et al.  Generalized redundancies for time series analysis , 1995 .

[12]  Leo H. Chiang,et al.  Process monitoring using causal map and multivariate statistics: fault detection and identification , 2003 .

[13]  Raghunathan Rengaswamy,et al.  A systematic framework for the development and analysis of signed digraphs for chemical processes. 2. Control loops and flowsheet analysis , 2003 .

[14]  D. W. Scott.  On optimal and data based histograms , 1979 .

[15]  L. Desborough,et al.  Increasing Customer Value of Industrial Control Performance Monitoring—Honeywell’s Experience , 2002 .

[16]  X. Rong Li.  Probability, Random Signals, and Statistics , 1999 .

[17]  Raghunathan Rengaswamy,et al.  A review of process fault detection and diagnosis: Part I: Quantitative model-based methods , 2003, Comput. Chem. Eng..

[18]  H. Kantz,et al.  Analysing the information flow between financial time series , 2002 .

[19]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[20]  Nina F. Thornhill,et al.  Specifying the directionality of fault propagation paths using transfer entropy , 2004 .

[21]  J. A. Stewart,et al.  Nonlinear Time Series Analysis , 2015 .

[22]  Vladimir Ponomarenko,et al.  Characterizing direction of coupling from experimental observations. , 2003, Chaos.

[23]  T. Schreiber,et al.  Surrogate time series , 1999, chao-dyn/9909037.

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

[25]  R. Rengaswamy,et al.  A Systematic Framework for the Development and Analysis of Signed Digraphs for Chemical Processes. 1. Algorithms and Analysis , 2003 .

[26]  Steven J Schiff,et al.  Analytical coupling detection in the presence of noise and nonlinearity. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[27]  Ute Feldmann,et al.  Predictability Improvement as an Asymmetrical Measure of Interdependence in bivariate Time Series , 2004, Int. J. Bifurc. Chaos.