Ultrasonic distance sensor improvement using a two-level neural network

This paper discusses the performance improvement that a neural network can provide to a contactless distance sensor based on the measurement of the time of flight (TOF) of a ultrasonic (US) pulse. The sensor, which embeds a correction system for the temperature effect, achieves a distance accuracy (rms) better than 0.5 mm over 0.5 m by using a two-level neural network that processes the US echo in order to correctly determine the TOF in the presence of environmental acoustic noise