Causal-geometry joint dictionary embedding learning for distributed monitoring and root cause analysis

Interactions across process variables are complicated in large-scale industrial processes characterized with multiple operating units, posing significant challenges for fault detection and root cause analysis. In this work, a distributed modeling approach termed causal-geometry joint dictionary embedding learning (CGDE) is proposed to monitor large-scale industrial processes and identify the root cause. An information decomposition based block division algorithm is proposed to divide the entire process into blocks that account for unique, redundant, and synergistic information among variables. Meanwhile, a geometry similarity matrix derived by the minimum spanning tree is constructed to exploit the underlying structure of data. Furthermore, a causal consistency matrix is developed to characterize the causality among variables such that the intrinsic and stable information of industrial processes can be effectively captured. The CGDE approach provides an in-depth and faithful process analysis with consideration of causalities and geometry similarity of data, enhancing the distributed monitoring and root cause analysis performance. The effectiveness of CGDE is illustrated through a simulated platform and a real fluid catalytic cracking application.