As the generalization of fuzzy systems, the belief rule base (BRB) expert system is transparent and interpretable. However, the interpretability of BRB has almost been ignored recently and leads to the decrease of model credibility. The main reason is the lack of unified guidelines for establishing an interpretable BRB expert system. In this article, the interpretability characteristics of BRB are summarized systematically, which can be used as the guideline of BRB establishment. Four interpretability criteria are proposed to ensure the interpretability of BRB in the optimization. A modified optimization algorithm with the interpretability constraints transformed from the interpretability criteria is further developed. As such, an interpretable BRB can be established. A case study for health state evaluation of the aerospace relay is conducted to verify the effectiveness of the proposed method.

In the technology of wireless sensor network (WSN), wireless sensor fault diagnosis based on fusion data analysis has attracted attention in the wireless sensor field. It can detect and correct the faults of sensor nodes in time to improve the accuracy of sensor data fusion. In this paper, the data characteristics of WSN are analyzed, and a method is proposed for fault diagnosis of WSN based on a belief rule base (BRB) model. First, the sensor fault diagnosis process is described based on the characteristics of a wireless sensor in WSN. Then, the characteristics of sensors are analyzed from the aspects of time, space, and attributes. Finally, a fault diagnosis model is proposed based on the hierarchical BRB model. To make the results more accurate, a covariance matrix adaptation evolution strategy algorithm is used to optimize the initial parameters of the proposed model. A case study using the Intel lab data set of sensors is designed to verify the effectiveness of the proposed model. The results show that the proposed method is effective in fault diagnosis of WSN.

As an important part of a smart city, intelligent transport can effectively reduce energy consumption and environmental pollution. Traffic flow forecasting provides a reliable traffic dispatch basis for intelligent transport, and most of the existing prediction methods only predict a single saturation or speed and do not use the saturation and speed in a unified way. This paper proposes a new traffic flow prediction method based on RNN-GCN and BRB. First, the belief rule base (BRB) is used for data fusion to obtain new traffic flow data, then the recurrent neural network (RNN) and graph convolution neural network (GCN) model is used to obtain the time correlation of the traffic data, and finally, the traffic flow is predicted by the topology graph. The experimental results show that the method has a better performance than ARIMA, LSTM, and GCN.