Optimization of Product Quality Indicators in the “Producer–Consumer” System Based on Fuzzy Cognitive Maps and Genetic Algorithm

The authors propose an approach to setting and solving the problem of optimal selection of product quality indicators, taking into account the interests of both the producer and consumer. The problem is formulated in terms of mathematical programming. The optimization criterion is the maximum proximity between the product attractiveness and the desire to purchase it; the controlled variables are the levels of producer- and consumer-specific indicators; the constraints are agreements regarding the necessary levels of indicators common to the producer and the consumer. Fuzzy cognitive maps are used to construct the dependencies that appear in the objective function, and optimal solutions are found using a genetic algorithm. The approach is illustrated by the example of a robot vacuum cleaner, which is one of the best-selling household applications of artificial intelligence.