No abstract

A new discrete neural networks adaptive resonance theory (ART), which allows solving problems with multiple solutions, is developed. New algorithms neural networks teaching ART to prevent degradation and reproduction classes at training noisy input data is developed. Proposed learning algorithms discrete ART networks, allowing obtaining different classification methods of input.

No abstract

The formulation and solution of the problem of optimization of the parameters of metal processing during the turning operation are shown. The task is solved taking into account the level of accumulated wear on the back surface of the tool, the level of machine efficiency that depends on the operating modes and the period of economically effective tool life. The problem was solved in a multicriterial formulation with three objective functions taken into account, the solution was obtained as a Pareto optimal solution. During the solution, an artificial neural network perceptron and the genetic algorithm FFGA were applied. This approach allows solving the problems of optimization of real production.Keywords: optimization of turning the operation parameters, the accumulated wear of the tool, cost-effective tool life, multi-objective optimization problem, the Pareto-optimal solution.

No abstract