Implementation of Genetic Algorithms Into Development of Mechatronic Multi-Edge’s Grinder Design

Abstract

Authors of the study propose the method aiming at determination of design properties of a multi-edge grinder. This method is based on a genetic algorithm and its purpose is to optimise the geometric shape of the cutting edges. The input data include population of individuals. Each individual is represented by a set of cutting disks. Whereas the fitness function was assumed as a combination of several postulates of the mechanical design foundations. Those postulates include mechanical, design and energy metrics. Each individual constitutes a complete solution of the disk set whereas the population represents the entire class of solutions. The fitness function of an individual is calculated as the fitness average of each disk supplemented by information describing the relationship between both disks and discs. The method for calculating function values was selected to ensure its maximisation in the process of evolution. Despite promising results of the genetic algorithms operation, one can consider improvement of the method efficiency. The authors used morphological operations in order to better adjust the method to the task. Results of the simulations were verified in laboratory conditions with positive effects.

Design and stress analysis of wheeled compactor construction

“…The least yield point value of used material was used for results and so lifespan of construction also depends on features of used material. Every manufacturer of materials used for analysing has different final features by production of steel and this fact must be taken into consideration [9][10][11][12][13][14][15][16][17].…”

Optimization and design of the vulcanization press sandwich pressure plate parameters

“…• compilation of the parametric FEM model for the ADINA calculation software and related files for evaluation of the results [11], • creating an objective function in MATLAB [4,12]. The high time requirement is assumed based on the character of the optimization task, and therefore it is necessary to create models with minimal computational demands [13,14]. Therefore, when creating a FEM model, the double symmetry of construction and a few simplifications were used.…”

Predictive compensation of thermal deformations of ball screws in CNC machines using neural networks

“…The search continues for an effective, universal, simple and cheap method of compensating for the elongation of ball screw transmission systems [6][7][8][9][10][11][12][15][16][17][18][19].…”