Development of machine learning models for the prediction of erosion wear of hybrid composites

Self Cite

This article reports on the implementation of artificial neural network (ANN) and statistical methods to analyze and predict the erosion performance of titania (TiO2) filled ramie‐epoxy based composites. These hybrid composites are prepared by conventional hand lay‐up route and subjected to solid particle erosion tests as per Taguchi's L27 orthogonal array. The effects of different control factors on erosion rate of these composites are studied using Taguchi method. It reveals that impact velocity and filler content have significant effect on the erosion wear rate followed by other least significant factors. The individual effect of each control factor while keeping other factors constant is ascertained by performing steady state erosion experiments. Further, a computational model based on ANN is used as a tool to effectively predict the erosion rates of the composites. The results show that the predicted values are in reasonably good agreement with the experimental ones with an accuracy of 90% and relative error lying within a range of 1%–10%. Further, the trained ANN model is validated by considering the erosion rates obtained during steady state erosion process as the input parameter. The possible mechanisms causing the wear loss are identified using electron microscopy.Highlights Successful fabrication of titanium oxide reinforced hybrid composites. Steady state erosion experiments are performed. Erosion rates are predicted using ANN and compared with the experimental data. Wear loss mechanisms are identified using electron microscopy.

Parametric appraisal and wear prediction of hybrid composites using an integrated soft computing approach

Mahapatra,

Satapathy

2024

Self Cite

A comparison of fabrication routes and property evaluation methods for bio‐particulate filled glass‐epoxy composites

Batha,

Mahapatra,

Satapathy

2024

This research work aims to investigate the effect of fabrication techniques on the physico‐mechanical properties of pistachio shell (PS) filled glass‐epoxy composites and to compare the experimental findings with numerical simulation results using finite element analysis (FEM). These hybrid composites are fabricated by vacuum‐assisted resin transfer molding (VARTM) and hand layup (HL) techniques with fixed glass fiber fraction (20 wt. %) but different PS powder loadings of 0–30 wt. %. The composites are then characterized for physical, compositional, micro‐structural and mechanical properties. The micro‐structural analysis of the filler and composites is performed using electron microscopy and stereo‐microscopy. To identify the phases present in both the raw filler and the composite, an x‐ray diffraction test is performed. The presence of functional groups is identified with the help of Fourier transform infrared spectroscopy (FTIR). It is observed that there is a reasonable improvement in the mechanical properties of the composites with increase in PS powder content, irrespective of the fabrication process used. The density and void fraction are also greatly affected by the amount of filler particles present in the composites and also on the composite fabrication technique. The FEM analysis is also carried out using ANSYS 22.0 workbench to determine the characteristic properties numerically. The comparison of experimental and numerical results yields that the properties obtained by using VARTM results are close to experimental ones with errors lying in the range of 1%–4%. These composites can possibly find potential applications in light duty structures and wear resistant applications.Highlights Development of hybrid composites using HL and VARTM techniques. Physical and mechanical properties alter with filler loading. Evaluation of mechanical properties using finite element analysis. Validating the model by comparing experimental and numerical results.

Sliding wear characteristics of epoxy composites reinforced with steel wire and flax fiber mats: An experimental and analytical study

Bhoi,

Satapathy

2024

This study evaluates the sliding wear behavior of hybrid composites made of epoxy reinforced with alternating layers of flax fiber mats and steel wire mesh. The aim is to enhance the wear resistance of flax fiber‐epoxy composites by incorporating steel wire mesh. Specifically, three composite types are produced by varying their stacking sequences using the simple hand layup technique. Dry sliding wear tests are performed on a pin‐on‐disc test rig under different conditions according to ASTM G99 standard. Taguchi analysis is performed using an L25 orthogonal array and it reveals that sliding velocity is the most critical factor, followed by normal load, in affecting the wear rate of the steel‐flax‐epoxy hybrid composite. Subsequently, a steady‐state wear analysis shows that sliding velocity and normal load increase the specific wear rate (SWR), while steel reinforcement decreases it. ANOVA results indicate that sliding velocity significantly impacts wear rates to the extent of 69.47% for flax‐epoxy composite and more than 70% for flax‐steel‐epoxy composites. Additionally, electron microscopy is used to study the worn surfaces of the composites to determine the wear mechanisms.Highlights Successful fabrication of flax‐steel wire mesh reinforced hybrid composites. Wear behavior of multi‐layer composites with different stacking sequence. Use of statistical technique for the prediction of wear rate. Wear mechanisms are identified using electron microscopy.