Under extreme driving conditions, such as emergency braking, rapid acceleration, and high-speed cornering, the tire, as the vehicle’s only direct connection to the road, plays a critical role in influencing dynamic performance and driving stability. Accurately predicting and tire longitudinal force under such combined slip conditions is key to improving vehicle control precision and ensuring driving safety. This study proposes a tire longitudinal force estimation strategy based on an intelligent tire system. The core of this system consists of three integrated PVDF (Polyvinylidene Fluoride) sensors embedded in the tire, which, due to their exceptional sensitivity, can precisely capture dynamic deformation information of the tire under varying conditions. This provides real-time, detailed data to better understand the complex interaction forces between the tire and the road. To study and validate the longitudinal force estimation model, the research team employed a high-precision indoor tire test platform, simulating real tire conditions under different operating scenarios. By integrating strain data collected from the intelligent tire system with tire states and using advanced data analysis techniques to extract highly relevant features, a Gaussian Process Regression algorithm was used to develop a tire longitudinal force estimation model suitable for combined slip conditions. The model leverages the high-precision measurement capabilities of PVDF sensors to accurately predict tire longitudinal forces. Validation results indicate that the model demonstrates excellent accuracy and robustness under challenging combined slip conditions, laying a technical foundation for improving vehicle stability and safety.