Under complex and extreme operating conditions, the road adhesion coefficient emerges as a critical state parameter for tire force analysis and vehicle dynamics control. In contrast to model-based estimation methods, intelligent tire technology enables the real-time feedback of tire-road interaction information to the vehicle control system. This paper proposes an approach that integrates intelligent tire systems with machine learning to acquire precise road adhesion coefficients for vehicles. Firstly, taking into account the driving conditions, sensor selection is conducted to develop an intelligent tire hardware acquisition system based on MEMS (Micro-Electro-Mechanical Systems) three-axis acceleration sensors, utilizing a simplified hardware structure and wireless transmission mode. Secondly, through the collection of real vehicle experiment data on different road surfaces, a dataset is gathered for machine learning training. This dataset is subsequently analyzed to discern the tire-ground relationships and signal characteristics. Finally, the utilization of a MiniRocket model, which employs binary multiple convolutional kernels to efficiently extract multiple signal features and enhance computational efficiency, facilitates feature learning from acceleration time-series data. By comparing the training results with other neural network models, the effectiveness, accuracy, and adaptability of the proposed MiniRocket neural network model for road surface recognition are comprehensively validated, even with limited training data. The road surface recognition solution presented in this paper successfully achieves real-time road identification. The seamlessly integrated hardware, software architecture, and neural network model are well-suited for vehicle system integration, providing real-time and precise road surface information for improved vehicle motion control.