Development of an Integrated Expert System for Distribution Network Diagnostics Based on Artificial Intelligence Technology

Abstract

The paper proposes implementation of the concept of integrated expert diagnostic system (IESD) of distribution network equipment based on AI technology. Complexes and modules of IESD interact with subsystems of retrospective, supplemented and updated offline information (database) and online monitoring and diagnostics of main electrical equipment. The objects of study in this work are the operating main equipment of 110/6(10) kV substation and adjacent 0.4÷6(10) kV distribution network. IESD consists of the following computational complexes: executive, which provides the system with offline and online data input; intelligent, which consists of computing and analytical modules; knowledge base (KB) - Expert system that performs requests for additional data to correct calculations in the calculation modules. The aim of the work is to integrate existing and additional subsystems of online monitoring into a unified expert diagnostic system that allows for real objects: to adequately assess the condition of the main equipment and monitor its remaining life; to evaluate the distribution network state, optimize the current mode for reliability, voltage levels and power losses; to monitor the development of equipment defects and use predictive analysis models for planning of repairs and maintenance. The significance of the work lies in the development of mathematical models of operational and predictive assessment of the state of power transformers and network equipment, as well as in the formation of key components of information and analytical support for decision-making on its operation. Scientific novelty consists in the development of methods and algorithms using combined methods and learning models.