Title :
Ultrasonic distance sensor improvement using a two-level neural-network
Author :
Carullo, Alessio ; Ferraris, Franco ; Graziani, Salvatore ; Grimaldi, Ugo ; Parvis, Marco
Author_Institution :
Politecnico di Torino, Italy
fDate :
4/1/1996 12:00:00 AM
Abstract :
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 an ultrasonic (US) pulse. The sensor, which embeds a correction system for the temperature effect, achieves a distance uncertainty (rms) of less than 0.5 mm over 0.5 m by using a two-level neural network to process the US echo and determine the TOF in the presence of environmental acoustic noise. The network embeds a “guard” neuron that guards against gross measurement errors, which would be possible in the presence of high environmental noise
Keywords :
computational complexity; computerised instrumentation; distance measurement; echo suppression; learning (artificial intelligence); neural nets; nonelectric sensing devices; 0.5 m; TOF; US echo; contactless distance sensor; correction system; distance uncertainty; environmental acoustic noise; environmental noise; gross measurement errors; guard neuron; industrial measurement; performance improvement; temperature effect; time of flight; two-level neural network; two-level neural-network; ultrasonic distance sensor; ultrasonic pulse; Acoustic noise; Acoustic pulses; Acoustic sensors; Neural networks; Neurons; Pulse measurements; Sensor systems; Temperature sensors; Time measurement; Ultrasonic variables measurement;
Journal_Title :
Instrumentation and Measurement, IEEE Transactions on
