A Hybrid Neuro‐Fuzzy Optimization Framework for Self‐Healing and Lifetime Enhancement in Wireless Sensor Networks

ABSTRACT Wireless sensor networks (WSNs) are important in real‐time applications such as environmental monitoring, health, and automation in industries. Nevertheless, maintaining stable communication and energy efficiency during topology changes and node failures also comes as one of the major challenges. The majority of the currently existing frameworks, such as GSO, OEPO‐FPA, and fuzzy‐based clustering, specialize in either optimization of energy consumption or fault tolerance, yet many of them do not combine those two concepts effectively. Also, such approaches usually do not have adaptive intelligence to adapt to the evolving network conditions. In order to overcome these shortcomings, the present study is proposing a hybrid neuro‐fuzzy optimization (NFO) framework, that is a synergistic combination of fuzzy inference to handle the uncertainty and multilayer perceptron (MLP) to learn fault patterns dynamically, and use particle swarm optimization (PSO) to optimize routing and duty cycles on a global scale. The implementation of the model took place with MATLAB R2023b and NS‐3 and was tested on the WSN‐DS dataset that includes the main network parameters of residual energy, PDR, and link quality. The proposed approach achieved 92.4% fault detection accuracy, 85% packet delivery ratio, 80% residual energy retention, and extended network lifetime up to 970 rounds, resulting in an improvement of over 15%–25% compared with existing methods. The inclusion of a dynamic feedback loop ensures continuous rule refinement and performance adaptation. This unified and lightweight solution offers a scalable, resilient, and intelligent architecture for self‐healing WSNs, presenting a promising direction for future deployments in resource‐constrained, mission‐critical environments.