An Australian research team used machine learning to design propellers.
Results published in Aerospace ResearchCentral, show that the prototypes produced about 15 dB less noise than commercially available propellers, confirming the design methodology developed by the team.
Lead researcher Abdulgani Mohamed noted,that impressive results were made possible by two key innovations - digital algorithms developed to design propellers and their interpretation of how the ear perceives noise.
AI turns a smart speaker into a contactless heart rate sensor
“Using our algorithms for iterations atdifferent propeller designs, we were able to optimize them for different parameters such as thrust, torque, sonic directivity and more. We have also formulated a new metric that includes how the human ear perceives sound, and we propose to use it in future designs, ”added the researchers.
They also noted that this modulation could be used as an important design parameter for future propellers.
Read more
Physicists have created an analogue of a black hole and confirmed Hawking's theory. Where it leads?
Sea slugs cut off their head to regenerate a new body
Abortion and science: what will happen to the children who will give birth