A WSN Node Fault Diagnosis Model Based on BRB with Self-Adaptive Quality Factor

Wireless sensor networks (WSNs) operate in complex and harsh environments; thus, node faults are inevitable. Therefore, fault diagnosis of the WSNs node is essential. Affected by the harsh working environment of WSNs and wireless data transmission, the data collected by WSNs contain noisy data, leading to unreliable data among the data features extracted during fault diagnosis. To reduce the influence of unreliable data features on fault diagnosis accuracy, this paper proposes a belief rule base (BRB) with a self-adaptive quality factor (BRB-SAQF) fault diagnosis model. First, the data features required for WSN node fault diagnosis are extracted. Second, the quality factors of input attributes are introduced and calculated. Third, the model inference process with an attribute quality factor is designed. Fourth, the projection covariance matrix adaptation evolution strategy (P-CMA-ES) algorithm is used to optimize the model’s initial parameters. Finally, the effectiveness of the proposed model is verified by comparing the commonly used fault diagnosis methods for WSN nodes with the BRB method considering static attribute reliability (BRB-Sr). The experimental results show that BRB-SAQF can reduce the influence of unreliable data features. The self-adaptive quality factor calculation method is more reasonable and accurate than the static attribute reliability method.