Predictions for hydrogel fracture experiment: synthesis of hydrogel, fracture test of hydrogel, and data processing (B)

• Main Author: Cao, XuBin
• Other Authors: Li Hua
• Format: Final Year Project
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering; Hydrogel
• Online Access: https://hdl.handle.net/10356/177187
• Institution: Nanyang Technological University

Hydrogels are versatile materials with applications ranging from biomedical engineering to material and environmental science. Understanding their fracture properties is crucial for optimizing their performance in various applications. This report investigates the prediction of fracture properties and behaviour of hydrogels through a combination of experimental techniques and machine learning algorithms. The synthesis of hydrogel samples, followed by fracture testing and data analysis, formed the basis of the research. The experimental focus of this report involved the synthesis of Polyacrylamide (PAAm) hydrogel samples followed by fracture testing using established protocols. Fracture tests were conducted to measure parameters such as stress and stretch indicative of fracture resistance. Varied compositions of PAAm hydrogel samples were tested and evaluated to obtain an optimal sample as datasets for predictions. Experimental data, and sample characteristics, were collected, and processed for further analysis. The experimental analysis involved compiling and organizing experimental results into a graphical format suitable for further understanding. Collaborative efforts with our machine learning team led to possible predictions of hydrogel fracture behaviour and an understanding of fracture properties through leveraging experimental parameters. This underscores the potential of machine learning in hydrogel analysis and likewise expands the available real-world datasets for training algorithms. In summary, this report lays the groundwork for deeper insights into hydrogel fracture mechanics and recommendations for future work for the expansion of experimental and machine-learning techniques for hydrogels.