A feasibility study on non-contact liquid nitrogen level measurement in laboratory settings using machine learning-driven ultrasonic system
摘要
Accurate liquid nitrogen level measurement is crucial in cryogenics for safety and optimal storage. Industrial-grade solutions, such as optical fibers and capacitive sensors, are effective but costly and complex, while conventional dipstick methods suffer from heat transfer issues and measurement inaccuracies. This study explores the feasibility of using an ultrasonic sensor for non-contact level detection in an open-mouth laboratory storage setup. By measuring the time of flight of ultrasonic pulses and applying a machine learning model to compensate for environmental fluctuations, the proposed approach offers a non-contact, accurate, and reliable alternative for laboratory applications.