AE SOURCE CHARACTERIZATION IN LATTICE-TYPE STRUCTURES USING SMART SIGNAL PROCESSING
暂无分享,去创建一个
This paper describes results of an experimental investigation of acoustic emission (AE) source characterization in terms of location and strength from strain gage signals detected on a two–dimensional frame–like structure. The signals are analyzed using two different smart signal processing algorithms. One is a feed forward neural network (FFNN) that was trained by a modified back-propagation algorithm and the second is a linear system called an auto-associative processor (AAP). The common feature of these algorithms is the use of a set of pre-processed, measured prototype signals to develop a system memory. This memory is subsequently employed to process the detected signals to determine the location and strength of the AE source.
[1] Bernard Widrow,et al. 30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.
[2] Paul J. Werbos,et al. Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.
[3] C. M. Roach,et al. Fast curve fitting using neural networks , 1992 .