The present invention relates to a device and a method for the early detection and prediction of damage to assemblies in machine plants, in particular also to mobile machine plants. For this purpose, the structure-borne sound of the machine system is sensed by a sensor (1) and output as an acceleration signal and analyzed in a digital signal processor (DSP). In this context, in order to avoid negative influences of ambient vibrations or structure-borne sounds which are not associated with the state of the machine plant, the acceleration signal is firstly transformed into the frequency domain by means of a fast-Fourier transformation, and the data obtained in this way is then transformed again into the time domain by means of cepstrum analysis so that resonance data relating to individual shock pulses (a cepstrum) is obtained in the time domain. This cepstrum is then compared with a comparison cepstrum which is available in accordance with load signals and rotational speed signals for the present operating state in a new machine plant in a storage device. When limiting values are exceeded, the diagnostic signal, in particular information relating to the assembly which is diagnosed as damaged and its predicted remaining service life, are displayed for the user and an emergency operating mode is initiated.