Abstract: To address the challenges in controlling hydraulic fracture propagation trajectories and stimulated volumes within multi-lithologic coal measure strata, particularly those caused by formation interfaces and interlayer strength variations, a combined finite-discrete element method (FDEM) was used to investigate hydraulic fracture behavior. The results show twelve distinct propagation modes under multifactor coupling conditions, which can be classified into four categories: interface penetration, penetration with interface extension, interface tracking, and interface arrest. A novel hybrid artificial intelligence model integrating BP neural networks with differential evolution (DE) and grey wolf optimization (GWO) algorithms (BP-DEGWO) was developed to predict fracture trajectories and stimulation effectiveness. Key controlling factors, including rock strength contrast coefficient, interface dip angle, interfacial strength, injection rate and perforation angle were identified, and their relative importance under varying in-situ stress conditions was quantified. A further intelligent optimization framework for hydraulic fracturing design in stratified formations was proposed based on the BP-DEGWO model. This approach provides a predictive tool for fracture geometry in heterogeneous coal-bearing strata and a methodological reference for AI-assisted fracturing optimization. The findings are instructive in enhancing stimulation efficiency in multi-lithologic unconventional reservoirs.