Accurate prediction of structural forces in segmental tunnel linings is essential for ensuring the safety and longevity of underground infrastructure. This study presents an innovative approach that leverages Finite Element Method (FEM) enhanced artificial neural networks (ANNs) to efficiently predict structural forces in segmental tunnel linings. By integrating the capabilities of FEM with the computational power of ANNs, this method provides a robust and precise predictive model. The FEM-ANN model is trained using a dataset comprising various tunnel geometries, loading conditions, and material properties, ensuring its versatility and applicability to a wide range of tunneling projects. The model's performance is validated through rigorous testing and comparison with traditional analytical methods, demonstrating its superior predictive accuracy and efficiency. The proposed FEM-ANN approach offers a valuable tool for engineers and researchers engaged in tunnel design and construction, enabling them to optimize structural designs and enhance tunneling safety.