With the rapid expansion of the EV industry, the operational health of charging piles has become a critical factor affecting charging safety and operation and maintenance (O&M) efficiency. To address the challenges posed by complex multi-source data coupling and the limited nonlinear fitting and feature extraction capabilities of traditional models in charging pile health degree prediction, this paper proposes a KAN-BiLSTM-SA-based health degree prediction method. First, the health degree is defined by taking the remaining time before fault occurrence as the core indicator, and hierarchical health levels are established accordingly. Then, a self-attention (SA) mechanism is embedded into the BiLSTM module of the KAN-BiLSTM architecture, enabling adaptive weighting of fault-sensitive temporal features and enhancing the model's ability to capture degradation patterns preceding failures. Experimental results based on real-world operation and maintenance data demonstrate that the proposed method achieves superior prediction accuracy and stability compared with several representative baseline models. Furthermore, simulation-based engineering validation confirms that an operation and maintenance strategy guided by the proposed model can effectively support preventive maintenance and provide decision-making references for intelligent charging pile management.