Comprehensive algorithm for risk assessment and disaster prevention capability improvement of transmission lines

Transmission lines are critical to power system reliability but remain continuously exposed to diverse operational and environmental hazards. Traditional risk assessment and disaster prevention approaches often suffer from limited scalability, heavy dependence on image-based or simulation data, and a lack of integration between fault classification and preventive decision-making. To address these limitations, this paper proposes a two-stage intelligent framework that combines a Genetic Algorithm–optimised Backpropagation (GA-BP) neural network with the Analytic Hierarchy Process (AHP). In the first stage, the GA-BP model utilises structured transmission line fault data, incorporating key operational parameters such as voltage, current, and power factor, along with relevant environmental factors. Genetic optimisation enhances classification accuracy and convergence efficiency by optimising the initial weights and biases of the BP neural network. The model categorises transmission line risks into six distinct fault classes with high precision. In the second stage, the AHP module identifies optimal mitigation strategies by evaluating multiple criteria, including cost, reliability, environmental impact, and implementation feasibility. By integrating predictive analytics with systematic decision-making, the proposed architecture supports effective disaster prevention planning. Experimental results demonstrate superior performance, achieving 99.93% accuracy, precision, and F1-score, with a recall of 99.92%. The proposed method is lightweight, explainable, and scalable, offering valuable decision support for power utilities to enhance grid resilience, improve response speed, and optimise resource allocation in high-risk operating environments.