Jingying Feng

Optimal maintenance decision for a sensor network aims to intelligently determine the optimal repair time. The accuracy of the optimal maintenance decision method directly affects the reliability and safety of the sensor network. This paper develops a new optimal maintenance decision method based on belief rule base considering attribute correlation (BRB-c), which is designed to address three challenges: the lack of observation data, complex system mechanisms, and characteristic correlation. This method consists of two sections: the health state assessment model and the health state prediction model. Firstly, the former is accomplished through a BRB-c-based health assessment model that considers characteristic correlation. Subsequently, based on the current health state, a Wiener process is used to predict the health state of the sensor network. After predicting the health state, experts are then required to establish the minimum threshold, which in turn determines the optimal maintenance time. To demonstrate the proposed method is effective, a case study for the wireless sensor network (WSN) of oil storage tank was conducted. The experimental data were collected from an actual storage tank sensor network in Hainan Province, China. The experimental results validate the accuracy of the developed optimal maintenance decision model, confirming its capability to efficiently predict the optimal maintenance time.

Health prediction plays an essential role in improving the reliability of a sensor network by guiding the network maintenance. However, affected by interference factors in the real operational environment, the reliability of the monitoring information about the sensor network tends to decline, which affects the health prediction accuracy. Furthermore, the lack of monitoring information and high complexity of the network increase the difficulty of health prediction. To solve these three problems, this paper proposes a new sensor network health prediction model based on the belief rule base model with attribute reliability (BRB-r). The BRB-r model is an expert system that fully considers the qualitative knowledge and quantitative data of the sensor network. In addition, it can address the fuzziness and nondeterminacy of this qualitative knowledge. In the new model, the unreliable monitoring information of the sensor network is handled by the attribute reliability mechanism. The reliability of the sensor is calculated by the average distance method. Due to the effect of the fuzziness and nondeterminacy of expert knowledge, the health status of the sensor network cannot be accurately estimated by the initial health prediction model. Consequently, the optimization model for the health prediction model is established. Finally, a case study regarding a sensor network for oil storage tanks is conducted, and the validity of this method is demonstrated.