To achieve efficient and accurate remaining life prediction and effectively express the uncertainty of prediction results, this paper proposes a remaining life prediction method based on fuzzy evaluation-Gaussian process regression (FE-GPR). First, the prediction of the remaining useful life (RUL) is affected by unknown variables, such as the environment, and it is difficult to achieve accurate predictions. It is necessary to effectively express the uncertainty of such prediction results. In this paper, we have put forward a RUL prediction method based on GPR, which can realize the RUL prediction with a confidence interval. Second, combined with the characteristics of the GPR method, an observation data preprocessing method based on fuzzy evaluation is proposed. The initial fuzzy evaluation method is established based on expert knowledge. Then, the classification nodes are optimized by the gravitational search algorithm (GSA) and historical data. This method, which uses fuzzy logic combined with expert knowledge, can avoid over-fitting in the case of limited data, and effectively improves the prediction accuracy of the GPR model. Finally, we use NASA PCoE. lithium battery data for a case study. The results show that the FE-GPR method achieves a more accurate RUL prediction and effectively reflects the uncertainty of the prediction results.

In this paper, the random vibration test and finite element simulation analysis of SAC305 solder joints in BGA packaged electronic chips were carried out. A failure model for BGA solder joints was established based on the life data. And Vulnerable parts in electronic chips were analyzed. Firstly, the random vibration test was conducted. Secondly a lognormal distribution model of solder joints by means of the life data was established and analyzed based on the fracture mechanics theory. Finally, the finite element simulation model of BGA packaged electronic chip was established and discussed. Failure characteristics of solder joints at different positions in electronic chips were compared and the failure mode of the solder joint was discussed using the simulation result and the observation result with scanning electron microscope(SEM). The results show that the life of each single solder joint in BGA packaged electronic chips follows a logarithmic normal distribution under the random vibration. Solder balls located at the four outermost corners of the chip are subjected to the greatest stress, which are the weakest parts in electronic chips. Cracks in solder joints are generated near the package side and emerged from the edge of the IMC layer with the largest curvature.

Solenoid valves are important electromagnetic devices which are used widely in various fields. Considering the uncertainty of failure mechanisms in practical operation, a thermal-structure coupled model of a direct action solenoid valve is constructed by using the finite element method. The coupled model provides useful information such as temperature distribution and stress distribution for failure mechanism study of the solenoid valve. The model results predict that the failure of the solenoid valve is closely related to the thermal expansion inside the coil, which means the high temperature generated by thermal expansion melts the insulation layers. Under the combined action of high temperature and coupled stress, the shorting of coils occurs and the resistance decreases which may cause the eventual failure of the solenoid valve. To verify the prediction of the finite element model, a degradation experiment is designed. The results suggest that the failure of the solenoid valve is a gradual degradation process, and there are several mutations of coil temperature and resistance. The high temperature melts the insulation layers and causes the shorting of coils, which further decreases the resistance and increases the current. Later more heat is generated to rise coil temperature and melt insulation layers, which will short out the coils and drop the resistance. With such a relationship, as the temperature rises alternately, the resistance decreases alternately until the solenoid valve completely fails. The model provides a reference for failure mechanism study and life prolonging research of solenoid valves.

The solenoid valve is a kind of basic automation component applied widely. It’s significant to analyze and predict its degradation failure mechanism to improve the reliability of solenoid valve and do research on prolonging life. In this paper, a three-dimensional finite element analysis model of solenoid valve is established based on ANSYS Workbench software. A sequential coupling method used to calculate temperature filed and mechanical stress field of solenoid valve is put forward. The simulation result shows the sequential coupling method can calculate and analyze temperature and stress distribution of solenoid valve accurately, which has been verified through the accelerated life test. Kalman filtering algorithm is introduced to the data processing, which can effectively reduce measuring deviation and restore more accurate data information. Based on different driving current, a kind of failure mechanism which can easily cause the degradation of coils is obtained and an optimization design scheme of electro-insulating rubbers is also proposed. The high temperature generated by driving current and the thermal stress resulting from thermal expansion can easily cause the degradation of coil wires, which will decline the electrical resistance of coils and result in the eventual failure of solenoid valve. The method of finite element analysis can be applied to fault diagnosis and prognostic of various solenoid valves and improve the reliability of solenoid valve’s health management.

As a critical part of prognostics and health management (PHM), remaining useful life (RUL) prediction can provide manufacturers and users with system lifetime information and improve the reliability of maintainable systems. Particle filters (PFs) are powerful tools for RUL prediction because they can represent the uncertainty of results well. However, due to the lack of measurement data, the parameters of the measurement model cannot be updated during the long-term prediction process. Additionally, for complex systems, the measurement model of a system often cannot be obtained in an analytical form. In this paper, a fusion prognostic method based on an extended belief rule base (EBRB) and a PF is designed to solve these problems. In the proposed framework, a double-layer maximum mean discrepancy-extended belief rule base (DMMD-EBRB) model with time delay is adopted to estimate and predict the hidden behavior of a degrading system. The unknown parameters of the degradation model are identified by the PF using the output of the EBRB. Afterwards, the system state is further predicted by the PF. The effectiveness of the proposed method is validated with the NASA-PCoE and CALCE lithium-ion battery degradation experiment datasets. In addition, several other related fusion methods are investigated for comparison with the proposed method. The experiments show that the proposed method yields better performance than the existing methods.