SUMMARY

Shape Memory Alloys (SMAs) are smart materials with desirable properties used in a wide range of applications, from aerospace, medicine, and actuation. Studying these materials has seen huge progress in identifying new SMAs with a range of compositions and properties that has resulted in a large uptick in their use in industry. However, large gaps in data still exist in the space of possible SMAs. ML approaches have shown some promise in closing these gaps as well as identifying new materials used for specific applications, but ML requires large amounts of data which presents an obstacle for the use of ML tools. This work aims to present an approach to automated DSC analysis which could allow the collection of large amounts of data in an automated lab, allowing researchers to collect and analyze data faster and cheaper than before.