Design of Composite Joints using Machine Learning Approaches

Author

Natalie RichardsFollow

College

Buchtel College of Arts and Sciences

Date of Last Revision

2023-05-05 06:32:53

Major

Mechanical Engineering

Honors Course

4600 461 - 012

Number of Credits

2

Degree Name

Bachelor of Science

Date of Expected Graduation

Spring 2022

Abstract

Adhesively bonded joints have an advantage in joining dissimilar engineering materials due to their high structural efficiency and being lightweight. These joints are either between two opposite laminates or between a composite laminate and a metal structure. The aerospace and automotive industries have seen an increase in utilizing these adhesive joints in their engineering applications. Joint strength along with the failure mode (adhesive, delamination, etc.) is the most important parameter to evaluate when understanding the capability of the adhesive joint. In this paper, a regression and a classification machine learning (ML) model are utilized to predict the failure load and the failure mode of single lap adhesive joints. This work compiled 103 single lap joint samples with different geometric and material parameters. An Artificial Neural Network (ANN) model and a Random Forest (RF) model were developed to accurately predict the joint’s failure load and failure mode. These models allow us to explore the complex, mathematical relationship between the input parameters and the overall joint strength.

Research Sponsor

KT Tan

First Reader

Alper Buldum

Second Reader

Manigandan Kannan

Honors Faculty Advisor

Scott Sawyer

Recommended Citation

Richards, Natalie, "Design of Composite Joints using Machine Learning Approaches" (2022). Williams Honors College, Honors Research Projects. 1558.
https://ideaexchange.uakron.edu/honors_research_projects/1558