Штучний інтелект в задачах управління

• Дата: 2024
• Автори: Voronin, Albert, Savchenko, Alina
• Формат: Стаття
• Мова: Ukrainian
• Опубліковано: V.M. Glushkov Institute of Cybernetics of NAS of Ukraine 2024
• Теми: багатокритеріальні задачі; формалізація; прийняття рішень; штучний інтелект; задачі управління; обмеження; компромісна схема; нейронні мережі
• Онлайн доступ: https://jais.net.ua/index.php/files/article/view/240
• Назва журналу: Problems of Control and Informatics

The problems of optimization of a controlled object pursuing several goals are considered. A model of multi-criteria optimization has been obtained, which allows the controlled object to realize all the goals set in the entire range of possible situations without the direct participation of a person. A systematic approach to the problem of vector optimization made it possible to combine models of individual trade-off schemes into a single integral structure that adapts to the situation of making a multi-criteria decision. The advantage of the concept of a non-linear trade-off scheme is the possibility of making a multi-criteria decision formally, which is a hallmark of artificial intelligence. The apparatus of the nonlinear trade-off scheme, developed as a formalized tool for studying management systems with conflicting criteria, allows the artificial intelligence system to solve practically multi-criteria problems of a wide class. Artificial intelligence systems are created in order to replace a person as a decision maker in this or that situation. AI systems such as robots, decision support systems, neural networks, etc. operate in conditions that a person considers unfavorable for himself. Thus, a demining robot operates in an environment that is dangerous for a sapper. Decision support systems are usually used in conditions of time pressure or in aggressive environments. Neural network classifiers process volumes of information that exceed the capabilities of a human operator, etc. Replacing a person with an AI system requires the formalization of both the formulation and the process of solving the problem. Subjective factors should be excluded from the solution algorithm. A special place among such systems is occupied by those which functioning is evaluated by a set of conflicting quality criteria. When solving a specific problem of vector optimization, the decision maker creates his own model of the objective function (utility function) in accordance with his preferences.