The gas path system is an important part of an aero-engine, whose health states can affect the security of the airplane. During the process of aircraft operation, the gas path system will have different working conditions over time, owing to the change of control parameters. However, the different working conditions which change the symmetry of the system will affect parameters of the health state prediction model for the gas path system. The symmetry of the system will also change. Therefore, it is important to consider the influence of variable working conditions when predicting the health states of gas path system. The accuracy of the health state prediction results of the gas path system will be low if the same evaluation standard is used for different working conditions. In addition, the monitoring data of the gas path system’s health state feature quantity is huge while the fault data which can reflect the health states of the gas path system are poor. Thus, it is difficult to establish a health state prediction model only by using the monitoring data of the gas path system. In order to avoid problems, this paper proposes a health state prediction model considering multiple working conditions based on time domain analysis and a belief rule base. First, working condition is divided by using time domain characteristics. Then, a belief rule base (BRB) theory-based health state prediction model is built, which can fuse expert knowledge and fault monitoring data to improve modeling accuracy. The reference value of the feature is given by the fuzzy C-means algorithm in a model. To decrease the uncertainty of expert knowledge, the covariance matrix adaptive evolution strategy (CMA-ES) is used as the optimization algorithm. Finally, a NASA public dataset without labels is used to verify the proposed health state model. The results show that the proposed health prediction model of a gas path system can accurately realize health state prediction under multiple working conditions.

Health state prediction is an effective way to improve the reliability for sensors. In the process of sensor degradation, it is difficult to obtain more effective monitoring data. And in the classification of health states, how to identify the adjacent state is also a problem. This paper proposed a health state prediction model based on belief rule base (BRB) and membership function (MF), which is called BRB-MF. In the model, BRB can make full use of expert knowledge and poor effective data. In the prediction results of BRB, it may be not completely logical or not entirely appropriate facing adjacent states of sensor. In order to solve the problem, MF is used to continue the analysis of the predicted results of BRB. In the BRB-MF model, the covariance matrix adaptation evolutionary strategies (CMA-ES) optimization algorithm is used to update the model parameters to make up for the uncertainty of expert knowledge. In the end, the brightness sensor of the rail vehicle LED lighting system is taken as a case study. The results show that the BRB-MF model can predict the health state of sensor with a high accuracy and a reasonable state.

No abstract

No abstract