The vibration signals of machinery with various faults often show clear nonlinear characteristics.Currently,fractal dimension analysis as the common useful method for nonlinear signal analysis,is a kind of single fractal form,which only reflects the overall irregularity of signals,but cannot describe its local scaling properties.For comprehensive revealing of internal properties,a combinatorial method based on band-phase-randomized(BPR) surrogate data and multifractal is introduced.BPR surrogate data method is effective to eliminate nonlinearity in specified frequency band for a fault signal,which can be utilized to detect nonlinear degree in whole fault signal by nonlinear titration method,and the overall nonlinear distribution of fault signal is displayed in nonlinear characteristic curve that can be used to analyze the fault signal qualitatively.Then multifractal theory as a quantitative analysis method is used to describe geometrical characteristics and local scaling properties,and asymmetry coefficient of multifractal spectrum and multifractal entropy for fault signals are extracted as new criterions to diagnose machinery faults.Several typical faults include rotor misalignment,transversal crack,and static-dynamic rubbing fault are analyzed,and the results indicate that those faults can be distinguished by the proposed method effectively,which provides a qualitative and quantitative analysis way in the field of machinery fault diagnosis. The vibration signals of machinery often variously shown clear nonlinear characteristics. Currently, fractal dimension analysis as the common useful method for nonlinear signal analysis, is a kind of single fractal form, which only reflects the overall irregularity of signals, but can not describe its its local scaling properties. For comprehensive revealing of internal properties, a combinatorial method based on band-phase-randomized (BPR) surrogate data and multifractal is introduced. BPR surrogate data method is effective to eliminate nonlinearity in specified frequency band for a fault signal, which can be utilized to detect the nonlinear degree in whole fault signal by nonlinear titration method, and the overall nonlinear distribution of fault signal displayed in nonlinear characteristic curve that can be used to analyze the fault signal qualitatively. Ten multifractal theory as a quantitative analysis method is used to describe geometrical characteristics and local scaling properties, and asymmetry coefficient of multifractal spectrum and multifractal entropy for fault signals are extracted as new criterions to diagnose machinery faults. Several typical faults include rotor misalignment, transversal crack, and static-dynamic rubbing fault are analyzed, and the results said that those faults can be distinguished by the proposed method effectively, which provides a qualitative and quantitative analysis way in the field of machinery fault diagnosis.