Development of Industrial Equipment Diagnostics System Based on Modified Algorithms of Artificial Immune Systems and AMDEC Approach Using Schneider Electric Equipment

Modern industrial control systems for complex objects are created using the latest achievements in the microprocessor technology and based on a range of technical tools from leading manufacturers, such as: Honeywell, Siemens, Schneider Electric, etc. The automation of large industrial enterprises of oil and gas, metallurgy, aerospace and other industries is carried out taking into account the requirements of reliability, safety and efficiency of the equipment. An important factor is the timely analysis and diagnosis of control systems, since even minor, unpredictable equipment failures can lead to emergency situations, as well as to economic production losses. Distributed enterprise management systems are overloaded with data streams, most of which are archived and are not further analyzed. An effective solution to this problem is the integration and application of the latest achievements in the field of artificial intelligence (AI). In turn, the bio-inspired approach of artificial immune systems is rapidly developing, which has the following advantages: the ability to process a large amount of production data, the ability to process information in parallel, self-training, the presence of memory, and the ability to predict at the class boundaries. Since there are currently no universal artificial intelligence algorithms capable of equally efficient forecasting for various types of production data, it is effective to develop modified algorithms for artificial immune systems. The researches are devoted to the development of a diagnostic system for industrial equipment based on the AMDEC (l'Analyse des Modes de Défaillances, de leurs Effets et de leur Criticité) mode, failure and criticality analysis approach and modified AIS algorithms, using the industrial equipment from Schneider Electric as an example. The AMDEC approach identifies equipment weaknesses and is used to predict potential failures. The disadvantage of this method is its complexity. Extending the AMDEC model, using modified algorithms of artificial immune systems, allows, on the basis of data mining, to predict the state of industrial equipment, to assess the severity of individual failures, and to make recommendations for decision making on the elimination of failures.