Hybrid approach to casual analysis on a complex industrial system based on transfer entropy in conjunction with process connectivity information

• We present a hybrid approach to causal analysis in a complex system.
• Our approach incorporates transfer entropy analysis with a topology-based model.
• A unique search algorithm is utilized in order to facilitate the analysis.
• The analysis is successfully demonstrated on industrial board machine.
• This approach considerably reduces the computational time and improves the results.

Industrial processes often encounter disturbances that propagate through the process units and their control elements, leading to poor process performance and massive economic losses. Thus, one major concern in the chemical industry is the detection of disturbances and identification of their propagation path. Causal analysis based on process data is frequently applied to identify causal dependencies among process measurements and thereby obtain the propagation path of disturbances. One significant challenge in data-based causal analysis is investigating industrial systems with a high degree of connectivity due to multiple causal pathways. This paper proposes a new hybrid approach for detecting causality based on the transfer entropy (TE) method by incorporating process connectivity information using an explicit search algorithm. Based on the hybrid approach, initially, the TE is only calculated for pathways that are considered as direct pathways based on the process topology. Then, the direct transfer entropy (DTE) is employed to discriminate spurious and/or indirect pathways obtained by the initial TE results. To facilitate the DTE calculation, the search algorithm is invoked once again to extract the intermediate pathways. This concept is demonstrated on an industrial board machine. In particular, the propagation path of an oscillation due to valve stiction within multiple control loops in the drying section of the machine is studied. Finally, the results are discussed and evaluated.