A novel approach to model-based diagnosis with multiple observations

Abstract

Model-based diagnosis (MBD) with multiple abnormal observations utilizes inconsistencies between actual and expected observations of systems to localize system faults. Current state-of-the-art algorithms still require solvers to consider a substantial number of suspected faulty components. To address this challenge, we introduce the Dual Principles with Decision Node (DPDN) algorithm. The first part of DPDN consists of two innovative principles: the Output Dependency Judgment Principle (ODJP) and the Deep Propagation Dependency Principle (DPDP). These principles are designed to identify and categorize a larger portion of components as ‘normal’, thereby broadening the idea of filtered nodes. By increasing the number of components classified as ‘normal’, the diagnostic process becomes more efficient as fewer components need to be diagnosed. The second part of DPDN integrates a newly defined decision node guided by its Decision Node Principle (DNP). This decision node, along with its corresponding principle, further bolsters the diagnostic process by classifying additional components as normal. With DPDN, complex real-world systems can reduce the number of components considered during the diagnostic process by eliminating those that are functioning normally, thereby decreasing the time required to obtain diagnoses. We conduct comparative experiments to evaluate the efficiency of our algorithm against other prevalent methods. Empirical results distinctly underscore DPDN’s superior performance in relation to other state-of-the-art algorithms.