Fault detection of axial piston pumps is of great significance to improve the reliability and life of fluid power systems. However, it is difficult to detect multiple faults on key lubricating interfaces due to the liquid-solid coupling. This paper proposes a fault detection strategy of the three key lubricating interfaces based on the one against all (OAA) and spare support vector machine (SSVM). The parameter sparsity is imposed to deal with the performance degradation of OAA-SVM model as a result of the imbalanced dataset. Experimental investigations on the benchmark dataset and axial piston pumps are carried out. Results show that the OAA-SSVM model accuracies of the benchmark dataset and axial piston pump are 96.67% and 95.83%, respectively, which are better than the OAA-SVM model. The recall rates of the bearing fault 3 and pump fault 2 can decrease by 13.33% and 10.00%, respectively. And the false discovery rates of the normal bearing and normal pump can be reduced by up to 7.58% and 6.24%, respectively. Besides, the OAA-SSVM model can improve the feature sparsity. Results show that the proposed method is effective in detecting multiple faults of axial piston pumps. INDEX TERMS Axial piston pumps, multiple fault detection, one against all, spare support vector machine.
A nonparametric model is established to investigate the vibration characteristics of a motorized spindle system, where the bearing restoring force, the unbalanced magnetic pull, and the external bounded noise excitation are taken into account. Based on the Monte Carlo simulation, several numerical examples are used to study the effect of dispersion parameters from model uncertainty and strength of external bounded noise excitation on the whirl frequency and bifurcation behavior of the spindle. It is shown that the whirl frequency fluctuates due to the random uncertainty, and the fluctuation range grows wider as the dispersion parameters increase as anticipated. In the randomly uncertain case, the vibration of the spindle also exhibits periodic-dominant and bifurcation phenomena, of particular interest is the delay of bifurcation point following the increase of the rotation speed. Towards the vibration condition monitoring on the spindle system, the phase space reconstruction technique is also applied to identify the vibration signals by comparing the reconstructed deterministic phase-space orbits with those from the random uncertainty and the bounded noise excitation, and the inherent dynamical behavior can be revealed from the irregular one-dimension time series effectively.
The output flow ripple of the axial piston pump is one of the excitation sources for the hydraulic system vibration. The amplitudes of its specific harmonics must be reduced to avoid the resonance with the hydraulic pipeline. In this paper, a method on the non-uniform distribution of the pistons is put forward to adjust the flow ripple. The deflection angles of the pistons are used to describe the distribution rule. The distribution rule is imported to the Fourier expansion of the flow rate of each single-piston chamber, and then every single flow rate is superposed to obtain the Fourier coefficient of total flow rate that becomes the function of deflection angles. After this, objective optimization design is carried out to reduce the amplitudes of specific harmonics. Finally, the dynamic simulation model of the non-uniformly distributed axial piston pump is established to verify the effects of objective optimization. The results show that the amplitude of the 9th harmonic of the flow ripple can be reduced by about 40%, and the reductions are about 99% for the 18th and 27th harmonic.
A fault classification method is developed by the phase-space reconstruction technique for a rotor system with a rolling bearing fault. Based on the nonlinear time series analysis, proper choices on time delay and embedding dimension are firstly discussed to accomplish the phase-space reconstruction from an arbitrarily one-dimensional time series, then the vector angle calculation is derived for each point in the reconstructed trajectory of an illustrating artificial signal, from which the vector angles of the points are composed of 90° and non-90° ones. To perform the fault feature analysis of the rolling bearing, an experimental rig of the rotor-bearing system and dynamical model of the system are established to collect the one-dimensional acceleration signals of three types of rolling bearing faults, and the topology of the reconstructed trajectory in three-dimensional phase space is characterized. It is interesting to find that the effects of various rolling bearing faults on the reconstructed trajectories are different, and the fault features can be extracted successfully by the distribution percentage of 90° and non-90° vector angles of the points in the reconstructed trajectory in three-dimensional phase space, which cannot be identified by the traditional attractor reconstruction method. Moreover, the higher the fault frequency, the lower proportion the healthy points.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.