Prediction of Selected Mechanical Properties of Polymer Composites with Alumina Modifiers

Abstract

Forecasting is one of the cognitive methods based on empirical knowledge supported by appropriate modeling methods that give information about the way the relations between factors and how the phenomenon under study will develop in the future. In this article, a selection is made of a suitable architecture for a predictive model for a set of data obtained during testing of the properties of polymer composites with a matrix in the form of epoxy resin with trade name L285 (Havel Composites) with H285 MGS hardener (Havel Composites), and with the addition of the physical modifier noble alumina with mass percentages of 5%, 10%, 15%, 20% and 25% for the following grain sizes: F220, F240, F280, F320, F360, respectively. In order to select the optimal architecture for the predictive model, the results of the study were tested on five types of predictive model architectures results were tested on five types of prediction model architectures, with five-fold validation, including the mean square error (MSE) metric and R2 determined for Young’s modulus (Et), maximum stress (σm), maximum strain (εm) and Shore D hardness (⁰Sh). Based on the values from the forecasts and the values from the empirical studies, it was found that in 63 cases the forecast should be considered very accurate (this represents 63% of the forecasts that were compared with the experimental results), while 15 forecasts can be described as accurate (15% of the forecasts that were compared with the experimental results). In 20 cases, the MPE value indicated the classification of the forecast as acceptable. As can be seen, only for two forecasts the MPE error takes values classifying them to unacceptable forecasts (2% of forecasts generated for verifiable cases based on experimental results).

Knee Joint Osteoarthritis Diagnosis Based on Selected Acoustic Signal Discriminants Using Machine Learning

“…The values of weights can be changed, which allows the network to learn and adapt to the problem being solved. ANNs find application in solving problems related to data processing and analysis, prediction and classification especially when the analyzed issues involve poorly known phenomena and processes (Badurowicz, 2022;Kosicka, Krzyzak, Dorobek & Borowiec, 2022;Rogala, 2020;Szabelski, Karpiński & Machrowska, 2022).…”

Modeling of Polymer Composite Materials Chaotically Reinforced with Spherical and Cylindrical Inclusions

“…Methods for calculating composite materials are based on solving the equations of solid medium mechanics. It can be done using analytical approaches [ 56 ], as well as using finite element methods, boundary elements, finite differences, finite volumes, and other numerical methods applicable to specific tasks [ 57 ].…”

Analysis of the Effectiveness of Removing Surface Defects by Brushing

“…Owing to the way they are manufactured, polymer composites are one example of materials that are prone to the formation of a higher number of internal defects. Improper bonding conditions of the reinforcing phase can affect the number of internal defects formed, and thus the strength of the composite material, its resistance to operating conditions, or damage to the final product [ 5 ]. There exist numerous methods for detecting both surface and internal defects.…”