AUTOMATED DIAGNOSTIC OF TECHNOLOGICAL PROCESSES BY METHODS OF HIERARCHICAL MODELING AND DIAGNOSTIC PROCEDURES

The main aspects of the implementation of diagnostic systems using hierarchical modeling and diagnostic procedures are considered. Further directions of work for the construction of an effective diagnostic system are outlined. The basic idea of diagnostic models is based on components, where a system is defined as a set of components and relationships between them. Diagnostics of such a component system is carried out in two stages: detection of malfunctions and localization of problems. A large number of approaches and models are used to analyze malfunctions in automated systems. Most often, systems that have one defined model that describes the process well are used to implement this process. It is also possible to use expert logic graphs to formalize the process. However, if the system is large and complex, the model becomes very cumbersome and cannot always correctly describe the process. Therefore, the authors propose the use of a hierarchical model for building a fault analysis system, where a general diagnostic procedure with localization of an incorrect component will be carried out at the top level, followed by the application of a specific diagnostic model to the localized area. A diagnostic procedure may refer to a certain level of component representation. The system to be diagnosed is structured in a hierarchy of components with respect to their structure and functionality. This approach allows you to break down a complex system into simpler ones and apply your own specific analysis algorithm to each subsystem. That is, when analyzing the system, a general diagnostic procedure is carried out, which localizes the level at which a malfunction is possible. This approach will make it possible to quickly analyze the system at a general level and, after identifying a discrepancy, conduct one local analysis procedure. According to the authors, this will make it possible to speed up the work of the diagnostic system for complex systems.