Target classification with artificial neural networks using ultrasonic phased arrays

Abstract

The problem of classifying objects from their ultrasonic signature for robotic applications is studied in this paper. The system developed utilises the spatial diversity of a four element linear array transducer to enhance classification performance. A signal pre-processing technique employing time domain envelope detection in combination with a multi-layer perceptron neural network has yielded classification success rates approaching 90% for previously unseen targets. This level of discrimination is not possible with a single sensor configuration