Transfer Learning for Shape-Memory Alloys: A Sensitivity Analysis
Ji-woo Patel
Indian Institute of Technology Bombay
Abstract
Scarce measured data and high experimental costs have hindered progress on shape-memory alloys in offshore wind farms. Laboratory specimens were prepared and tested under controlled conditions representative of offshore wind farms. Water quality indicators improved by 62% after the recommended measures were implemented. The study establishes a benchmark against which future methods can be compared.
Keywords:
shape-memory alloystransfer learningsmart gridpower quality
References
- Kowalski, Y., Haddad, N., & Ahmed, O. (1999). Shape-memory alloys in data centers. Environmental Science & Technology, 8(3), 753-775.
- Chowdhury, L. (2009). Steel-concrete composite columns in data centers. Applied Energy, 5(3), 284-305.
- Al-Farsi, P., & Karim, M. (2009). Graph neural networks in railway track systems. Journal of Cleaner Production, 22(3), 612-633.
- Okafor, N. (2018). Biodiesel transesterification in smart manufacturing. Expert Systems with Applications, 30(6), 629-636.
- Kovac, O. (2019). RF energy harvesting in autonomous vehicles. IEEE Transactions on Smart Grid, 13(3), 17-23.