To detect abnormality of rotating machines in factories and power generating plants, the vibration data of the machines are used as a guide to express abnormal phenomena. In order to improve the diagnostic accuracy of the rotating machine diagnostic system, the storage and analysis of a large amount of vibration data is important. For efficient data storage and transmission, data compression is indispensable. In this paper, with a view to reducing data storage capacity and the transmission capacity in the rotating machine diagnostic system, compression of machine vibration data is attempted. In the proposed compression system, wavelet transforms are used so that the distortion generated in compression and reconstruction have minimal effect on the diagnostics. Considering the mode of system usage, a compression system is proposed that maximizes the compression ratio at allowable distortions. In order to evaluate the overall performance of the proposed compression system, data compression by several orthogonal wavelets composed of Daubechies bases and those generated by DCT (discrete cosine transform) are compared. It is shown that the system using the wavelet with a higher-order tap has the highest compression performance and that the compression factor is about 3 to 8 in the allowable distortion range of 1 to 10%.