A new method for multi-channel signal compression

This paper proposed a new method for multi-chamulti-channel vibration signalsnnel vibration signals compression, for the vibration signals with three channels which was obtained by multi-channel sensor, and each channel signal was noted by X, Y and Z which were perpendicular to each. Firstly, the multi-channel signals were mapped into Greaves space, the real part and the complex part were obtained for processing; then the real/complex matrix data was segmented several sub-matrix to be considered training data samples. In the real and complex domains, the data was sent to the designed Real and Complex GHA neural networks for training and extracted principle components which were forming the weights vectors w in the trained networks. The experimental results had indicated its effectiveness and feasibility.