MULTI-AGENT SYSTEM FOR AUTOMATIC PLANNING AND MANAGEMENT
OF ENGINEERING CHANGES AT A RADIOELECTRONICS ENTERPRISE 

Gamid Kh. Irzaev, Candidate of technical sciences, associate professor, associate professor of the sub-department of software, computer science and automated systems, Daghestan State Technical University (70 I. Shamil avenue, Makhachkala,
Republic of Daghestan, Russia), irzajev@mail.ru
Arina A. Adamova, Candidate of technical sciences, associate professor, associate professor of the sub-department of design and production technology of electronic equipment, Bauman Moscow State Technical University (build. 1, 5 2-ya Baumanskaya street, Moscow, Russia), arinaadamova75@gmail.com
Nikolay K. Yurkov, Doctor of technical sciences, professor, honoured worker of science of the Russian Federation, head of the sub-department of radio equipment design and production, Penza State University 40 Krasnaya street, Penza, Russia), yurkov_nk@mail.ru

Background. Modern radio-electronic enterprises have to maintain consumer interest by continuously improving their products, developing new modifications and introducing engineering changes into the design and manufacturing technology. Engineering changes require significant efforts for their planning, coordination and implementation at the enterprise and are carried out in most cases manually. This study aims to develop a multi-agent decision support system for managing engineering changes in products using the wide capabilities of artificial intelligence technologies. Materials and methods. Based on the engineering change maintenance model previously developed by the authors, an original role model of agent interactions has been formed. Agents operating in an uncertain environment and lack of complete information use cognitive data structures and deduction and induction methods to draw conclusions. Results and conclusions. The concept of a system consisting of four agents and containing cognitive data structures and methods of logical inference with training and adaptation is proposed. Local goals of agents in the system are formulated, their role and general logic of actions to support decision-making on the implementation of engineering changes in electronic products are revealed. The logical architecture of the coordinator agent is developed, which requests the optimal time and cost of implementing engineering changes and makes a schedule for their implementation at the enterprise. Architectures of the forecaster agent, optimizer agent and feedback agent are also built. The model has limitations in the form of emergency situations at the enterprise, legally significant or critical changes for the safety of the enterprise, which requires switching to manual control.

coordinator agent, feedback agent, optimizer agent, forecaster agent, engineering change, artificial intelligence, multi-agent system

Irzaev G.Kh., Adamova A.A., Yurkov N.K. Multi-agent system for automatic planning and management of engineering changes at a radioelectronics enterprise. Nadezhnost' i kachestvo slozhnykh sistem = Reliability and quality of complex systems. 2025;(3):45–53. (In Russ.). doi: 10.21685/2307-4205-2025-3-5