To address the challenge of robotic inspection and maintenance in unmanned environments, this paper presents an integrated approach combining Conv2D-PSE-iTransformer for equipment state prediction, Dynamic Analytic Hierarchy Process (D-AHP) for health assessment, and deep reinforcement learning for optimized path planning. The Conv2D-PSE-iTransformer accurately predicts the operational state of electrical equipment, which serves as a critical input for the D-AHP evaluation. Based on the predicted state, D-AHP dynamically assesses the health of the equipment, enabling the identification of high-risk components that require immediate attention. Based on these evaluations, the DRL-based path planning generates optimized inspection routes that prioritize these high-risk areas while ensuring complete coverage with minimal inspection time. Experimental results demonstrate the effectiveness of this integrated method, highlighting its ability to reduce inspection time and enhance the overall efficiency, safety, and reliability of robotic inspections in complex, high-risk environments.