Prediction of Surface Roughness in Drilling of Polymers using a Geometrical Model and Artificial Neural Networks

Abstract

Polymeric materials are synthetic macromolecular products, of which, by mechanical or thermal processing, objects of various shapes can be obtained, with wide uses in industry and commerce. This paper deals with the roughness of surfaces obtained during drilling of three polymeric materials: polyamide - PA6, polyacetal - POM-C and high density polyamide - HDPE 1000. In the experimental research was used a EMCO MILL 55 milling machine numerical controlled and HS steel helical drills with two straight cutting edges with the diameter of �8 mm and �10 mm, respectively. Experimental determinations consisted in drilling of the polymeric materials by modifying some parameters of the cutting regime, and determining the roughness of the surface of the holes machined, using the Mitutoyo Surftest SJ-210 rough meter. The purpose of the paper is to predict the roughness of the machined surfaces as one of the important surface quality indicators by using a geometrical model and an artificial neural network (ANN) methodology.

Evaluation of the Effect of Machining Technologies on the Surface Texture Analysis of Ertacetal C Polymer

“…The existence of micro-uniformities on the surface of the part results in worse functional conditions and causes a number of disadvantages. Based on the results, we can state that visually at a scale of 500 μm, the POM-C and HDPE materials have a betterdefined surface state compared to PA 6, where exfoliation of the material with the effect of plastic deformation on the generated surface can be observed [12].…”

“…This article [12] deals with the roughness of surfaces obtained during drilling of three polymeric materials: polyamide -PA6, polyacetal -POM-C and high-density polyamide -HDPE 1000. The existence of micro-uniformities on the surface of the part results in worse functional conditions and causes a number of disadvantages.…”

"Predicting Bankruptcy in Romania Using Artificial Neural Network "

“…Due to the severity of the bankruptcy, a multitude of models have been developed to anticipate it, using artificial intelligence. There are numerous studies that have addressed this topic, and the best results, from the perspective of accuracy, were those presented in [6] and [7].…”

“…The best accuracy presented in this article is 95% for an algorithm using support vector machine. In [7], several algorithms were compared, the best value of accuracy was 100% using a four-layer neural network and the dropout rate equal to 0.5. The next best value of accuracy was 98.67%, for an algorithm using support vector machine.…”

“…The linear calculation part takes the input variables and executes the function f (X) = W (X) + b, where the vector X (x0, x1, ..., xm) retains the input values, W represents the weights associated with them and b is a real number called bias. The nonlinear part receives the result of the function f (X) and applies a nonlinear function, called the activation function [7]. The learning is done as follows: from the input you go through all the layers and nodes of the network, the output of a layer being the input of its successor layer.…”