A fault diagnosis method for wireless sensor network nodes based on a belief rule base with adaptive attribute...

Area of Science:

• Computer Science
• Electrical Engineering
• Network Engineering

Background:

• Wireless sensor networks (WSNs) face node failures due to harsh environments and long operation times.
• Accurate fault diagnosis in WSN nodes is crucial for reliable data collection.
• Traditional fault diagnosis methods struggle with effectively distinguishing fault types due to feature weighting limitations.

Purpose of the Study:

• To develop an enhanced fault diagnosis model for WSN nodes.
• To introduce the belief rule base with adaptive attribute weights (BRB-AAW) for improved fault identification.
• To enhance the accuracy and effectiveness of WSN node fault diagnosis.

Main Methods:

• Data features were extracted from neighboring nodes as input attributes.
• A novel fault diagnosis model, BRB-AAW, was established integrating expert knowledge and data features.
• The projection covariance matrix adaptive evolution strategy (P-CMA-ES) algorithm optimized the model's initial parameters.

Main Results:

• The proposed BRB-AAW model demonstrated significantly improved accuracy in WSN node fault diagnosis.
• A comprehensive case study validated the effectiveness of the enhanced method.
• The adaptive attribute weighting in BRB-AAW improved the distinction between various fault types.

Conclusions:

• The BRB-AAW model offers a superior approach to WSN node fault diagnosis.
• The integration of P-CMA-ES optimization enhances model performance.
• This method provides a more reliable solution for maintaining WSN integrity.