Machine learning guided alloy design of high-temperature NiTiHf shape memory alloys

With the increasing use of CubeSats in space exploration, the demand for reliable high-temperature shape memory alloys (HTSMA) continues to grow. A wide range of HTSMAs has been investigated over the past decade but finding suitable alloys by means of trial-and-error experiments is cumbersome and time-consuming. The present work uses a data-driven approach to identify NiTiHf alloys suitable for actuator applications in space. Seven machine learning (ML) models were evaluated, and the best fit model was selected to identify new alloy compositions with targeted transformation temperature (Ms), thermal hysteresis, and work output. Of the studied models, the K-nearest neighbouring ML model offers more reliable and accurate prediction in developing NiTiHf alloys with balanced functional properties and aids our existing understanding on compositional dependence of transformation temperature, thermal hysteresis and work output. For instance, the transformation temperature of NiTiHf alloys is more sensitive to Ni variation with increasing Hf content. A maximum Ms reduction rate of 6.12 degrees C per 0.01 at.% Ni is attained at 30 at.% Hf, and with a Ni content between 50 and 51 at.%. [GRAPHICS] .

Automated summary

With the increasing use of CubeSats in space exploration, the demand for reliable high-temperature shape memory alloys (HTSMA) continues to grow. This study uses a data-driven approach to identify suitable NiTiHf alloys for actuator applications in space. Of the machine learning models evaluated, the K-nearest neighbouring model offers reliable and accurate prediction in developing NiTiHf alloys with balanced functional properties.