An Enhanced Spherical Fuzzy WASPAS Approach for Smart Detection of Network Cable Faults

Fault detection, which is dependable and real-time, is critical in large-scale network infrastructures to reduce service disruption. The traditional diagnostic methods tend to malfunction when dealing with uncertain circumstances, as they use strict cut-offs and deterministic paradigms. The present paper presents a further improvement of spherical fuzzy weighted aggregated sum product assessment (SF-WASPAS) as a multi-criteria decision-making (MCDM) method to be applied to intelligent detection of network cable faults. The approach uses spherical fuzzy sets (SFS) in order to manage hypothetical data which is ambiguous and uncertain, and an adaptive weighting scheme is used to provide dynamic priority of the diagnostic indicators. The essential parameters, including signal attenuation, change in impedance, packet loss and cable ageing, are assessed and ranked systematically to determine the possible faults. The efficiency of the suggested method is proven with the help of theoretical data, which demonstrate a significant increase in detection rate, false alarm rate, and sensitivity to minor flaws in comparison with traditional diagnostic tools. The architecture is strong, scalable, and can be coupled with the already existing network management systems, hence, proactive maintenance and operational resiliency.