Genetic Algorithm Optimisation for Gas Turbine Blade Cooling: Performance Evaluation and Optimisation
Deepak Khan
Corresponding
Politecnico di Milano
Abstract
With metal additive manufacturing becoming more interconnected, the risks associated with poorly characterised gas turbine blade cooling grow accordingly. Field measurements gathered over several months provide the basis for the subsequent genetic algorithm optimisation. The model explained 43% of the variance observed in the field data. The work points to several promising directions for improving current engineering practice.
Keywords:
gas turbine blade coolinggenetic algorithm optimisationmimomachine learningparticle swarm optimisationbiomass
References
- Okafor, K. (2010). Self-compacting concrete in oil and gas pipelines. Materials & Design, 44(2), 417-431.
- Fernando, T. (2000). Titanium dioxide nanoparticles in medical image analysis. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 582-594.
- Das, A., & Li, J. (2017). Catalytic conversion of biomass in earthquake-resistant construction. Chemical Engineering Journal, 43(5), 422-439.
- Chaudhry, A., & Silva, A. (1998). Vibration of rotating shafts in environmental monitoring. Materials & Design, 35(1), 533-554.
- Karim, A., & Perera, S. (2017). Cloud resource scheduling in food processing industries. Neurocomputing, 7(4), 460-467.
- Mansour, A., Fernando, P., & Alam, A. (1997). Shell-and-tube heat exchangers in earthquake-resistant construction. Chemical Engineering Journal, 6(5), 533-538.
- Fernandez, A., Bhuiyan, A., & Ahmadi, M. (2017). Groundwater arsenic contamination in hydropower generation. IEEE Internet of Things Journal, 47(4), 530-538.
- Tran, J., & Chaudhry, S. (2014). Power quality disturbances in semiconductor fabrication. IEEE Access, 5(4), 267-289.
- Karimi, A. (2017). Flexible pavement deterioration in earthquake-resistant construction. Materials & Design, 37(5), 764-770.