Masters Theses
Abstract
The combination of high pressure and controlled heat plays a critical role in ensuring the uniform curing of composite materials, leading to parts with superior mechanical properties. In this study, three composite samples of IM7/CYCOM 5320-1, each cut into 12x12-inch squares, were placed in an autoclave at three different locations, spaced 6 inches apart. Sixteen thermocouples were randomly distributed across the setup to monitor the curing process as the autoclave temperature was systematically ramped up and down while maintaining constant pressure, creating a fully controlled curing environment. The primary objective was to optimize the curing locations to reduce machine runtime and operational costs while ensuring uniform curing. This optimization is crucial, as uneven curing can introduce defects into the material, thereby reducing its strength, durability, and performance.
The experimental dataset was used to train a Long Short-Term Memory (LSTM) model to predict temperature variations over time. The model achieved an impressive accuracy of 98.3%, supported by key evaluation metrics such as Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-squared (R²). The R² score of 0.987 demonstrated that the model captured 98.7% of the variance in the temperature data, confirming its high predictive accuracy. The low MSE and RMSE values indicated minimal prediction errors, ensuring close alignment between predicted and actual temperature values. Positions such as PTC1, PTC2, PTC3, PTC5, and PTC7 exhibited minimal deviations, showcasing the model's ability to learn and generalize underlying patterns effectively.
Advisor(s)
Corns, Steven
Committee Member(s)
Chandrashekhara, K.
Allada, Venkat
Department(s)
Engineering Management and Systems Engineering
Degree Name
M.S. in Engineering Management
Publisher
Missouri University of Science and Technology
Publication Date
Summer 2025
Journal article titles appearing in thesis/dissertation
Paper found on pages 3-41 is intended for submission to International Journal of Advanced Manufacturing Technology.
Pagination
ix, 44 pages
Rights
© 2025 Sourav P Bolar , All Rights Reserved
Document Type
Thesis - Open Access
File Type
text
Language
English
Thesis Number
T 12504
Recommended Citation
Bolar, Sourav P., "Long Short-Term Memory (LSTM) -Based Neural Network Model for Optimizing Composite Manufacturing Process using Autoclave" (2025). Masters Theses. 8244.
https://scholarsmine.mst.edu/masters_theses/8244
