Degradation parameter or deviation parameter from normal to failure condition of machine part or system is needed as an object of prediction in prognostics method. This study proposes the combination between relevance vector machine (RVM) and logistic regression (LR) in order to assess the failure degradation and prediction from incipient failure until final failure occurred. LR is used to estimate failure degradation of bearing based on run-to-failure datasets and the results are then regarded as target vectors of failure probability. RVM is selected as intelligent system then trained by using run-to-failure bearing data and target vectors of failure probability estimated by LR. After the training process, RVM is employed to predict failure probability of individual units of machine component. The performance of the proposed method is validated by applying the system to predict failure time of individual bearing based on simulation and experimental data. The result shows the plausibility and effectiveness of the proposed method, which can be considered as the machine degradation assessment model. 相似文献
In this research, the performance of metal–organic frameworks (MOFs) of MIL-101(Fe) and MOF-808 as aspirin detoxification agents was evaluated. MIL-101(Fe) was successfully prepared for the first time using the electrochemical method for 30 min under room temperature and pressure. MIL-101(Fe) detoxification capacity was compared to that of MOF-808, which was synthesized by a common solvothermal method at 135 °C for 24 h. The obtained materials were fully confirmed by X-ray diffraction (XRD) with the appearance of MIL-101(Fe) characteristic peaks (at 2θ 8.5°; 9°;16.7°) and MOF-808 (at 2θ 8.3°; 8.7°; 10°; 10.9°), and also confirmed by Fourier transform infrared (FTIR) spectroscopy that shows the coordination between metal and ligand. Based on scanning electron and transmission electron microscopy (SEM and TEM), MIL-101(Fe) has a micro-spindle shape with average particles size of 649.12?±?73.32 nm, while MOF-808 showed irregular shape with average particle sizes of 169.73?±?31.87 nm. Nitrogen sorption isotherm confirmed that both materials could be classified as micro to-meso porous materials by the pore radius of 1.89 nm for each materials with BET surface areas of 131 for MIL-101(Fe), and 847 m2/g for MOF-808, respectively. Based on an in vitro test, in a gastric simulation, MIL-101(Fe) decreased 11.78% of aspirin, while MOF-808 decreased 7.99%. In the intestinal simulation, MIL-101(Fe) and MOF-808 decreased aspirin by 24.06% and 26.74%, respectively. XRD analysis of the MOFs after the detoxification test showed that MIL-101(Fe) has lower stability than MOF-808. FTIR spectra confirmed that aspirin was successfully adsorbed into the MOFs. Transmission electron microscopy showed that aspirin interacted with MIL-101(Fe) on the outer surface and with MOF-808 on the inside of the pores.
