Please use this identifier to cite or link to this item:
http://hdl.handle.net/2080/4267
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Mahapatra, Sourav Kumar | - |
dc.contributor.author | Satapathy, Alok | - |
dc.date.accessioned | 2024-01-09T04:58:25Z | - |
dc.date.available | 2024-01-09T04:58:25Z | - |
dc.date.issued | 2023-12 | - |
dc.identifier.citation | 9th International and 30th All India Manufacturing Technology Design and Research Conference (AIMTDR), IIT BHU, Varanasi, 08-10 December 2023 | en_US |
dc.identifier.uri | http://hdl.handle.net/2080/4267 | - |
dc.description | Copyright belongs to proceeding publisher | en_US |
dc.description.abstract | The present investigation reports on the application of machine learning techniques and statistical methods to analyze and predict the erosion wear performance of ramie fiber reinforced epoxy based composites filled with different proportions of titania (TiO2) particles for wear resistant applications. These hybrid composites are fabricated using conventional hand lay-up technique and subjected to solid particle erosion tests following the design-of-experiments as per Taguchi’s L16 orthogonal array. The effects of filler content and other control factors on the erosion wear rate of these composites are studied. It reveals that filler content, followed by impact velocity and impingement angle have significant effect on the erosion wear rate. The analysis of variance (ANOVA) also confirms the same. The data generated from experimentation are further processed to predict the erosion performance of the composites with a machine learning (ML) approach following support vector machine (SVM) algorithm with different kernel functions (SVM_LIN, SVM_POLY, SVM_RBF, SVM_SIGMOID) and to analyze the absurdity among obtained experimental results and predicted response. It is found that the support vector machine with polynomial kernel function (SVM_POLY) outperforms other models with a R2 value as high as 0.9814 and has thus emerged as the best performing prediction model. | en_US |
dc.subject | Erosion wear rate | en_US |
dc.subject | machine learning | en_US |
dc.subject | ANOVA | en_US |
dc.subject | regression model | en_US |
dc.subject | support vector machine | en_US |
dc.title | Machine Learning Based Erosion Response Analysis of Hybrid FRP Composites | en_US |
dc.type | Article | en_US |
Appears in Collections: | Conference Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
2023_AIMTDR_SKMohapatra_Machine.pdf | 1.28 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.