Intelligent tire technology significantly enhances vehicle performance and driving safety by integrating sensors and electronics within the tire to facilitate the real-time monitoring of tire–road interactions. However, its testing and validation face challenges due to the absence of integrated bench and road testing frameworks. This paper introduces a novel, comprehensive testing system designed to support the full lifecycle development of intelligent tire technologies across both laboratory and real-world driving scenarios, focusing on accelerometer and strain-based sensing. Featuring a modular, distributed architecture, the system integrates an instrumented wheel equipped with multiple embedded tire sensors and a wheel force transducer (WFT), as well as vehicle motion and driving behavior sensors. A robust data acquisition platform based on NI CompactRIO supports multiple-channel high-precision sensing, with sampling rates of up to 50 kHz. The system ensures that data performance aligns with diverse intelligent tire sensing principles, supports a wide range of test parameters, and meets the distinct needs of each development stage. The testing system was applied and validated in a tire vertical load estimation study, which systematically explored and validated estimation methods using multiple accelerometers and PVDF sensors, compared sensor characteristics and estimation performance under different installation positions and sensor types, and culminated in a product-level assessment in road conditions. The experimental results confirmed the higher accuracy of accelerometers in vertical load estimation, validated the developed estimation algorithms and the intelligent tire product, and demonstrated the functionality and performance of the testing system. This work provides a versatile and reliable platform for advancing intelligent tire technologies, supporting both future research and industrial applications.

Accurate vertical load measurement through intelligent tire technology is crucial for vehicle stability, handling, and safety. Existing studies have mainly focused on modeling and bench experiments, overlooking a detailed comparative analysis of real sensor performance and validation under actual driving conditions. This study addresses this gap by performing sensor comparisons and extensive real-road validation to ensure the accuracy and reliability of the proposed methods. First, finite element modeling (FEM) is used to assess the feasibility of accelerometer and strain-based sensors for vertical load prediction. High-precision bench tests quantitatively compare the performance of multiple triaxial Integrated Electronics Piezoelectric (IEPE) accelerometers and Polyvinylidene Fluoride (PVDF) sensors, identifying accelerometers as the superior choice due to their better stability and linearity. Vertical load prediction algorithms are developed using Support Vector Machine (SVM) and linear regression, considering variables like contact length, vehicle speed, and tire pressure. The algorithms are validated under real-road conditions using high-performance instruments across constant speed, acceleration, braking, and cornering, and a self-designed compact Intelligent Tire Test Unit (ITTU) is deployed for product-level implementation, confirming its effectiveness in real-world driving scenarios. The findings provide a validated framework for accurate vertical load estimation and real-time tire parameter prediction, offering practical insights for improving intelligent tire technology in dynamic driving conditions.

Intelligent tire technology enables real-time monitoring of tire–ground interaction states and provides an effective approach for improving the intelligence of wheeled tractors. However, the relative effectiveness of different sensing signals for vertical load sensing in agricultural tractor tires remains insufficiently understood. To address this issue, a feature selection framework combining finite element analysis, random forest, and Pearson correlation analysis was developed. A finite element model of a 280/85 R24 tractor radial tire was established in ABAQUS and validated through static loading experiments, with the maximum error in radial deformation remaining below 7%. Based on the validated model, tire rolling simulations were conducted under different vertical loads, inflation pressures, and slip ratios, and strain, radial displacement, and radial acceleration signals were extracted during tire–ground interaction. Seventeen time- and frequency-domain features were constructed for each sensing signal, and informative and non-redundant features were identified using random forest importance and Pearson correlation analysis. The resulting feature subsets contained 10, 7, and 6 features for strain, displacement, and acceleration signals, respectively. Within the final selected feature subsets, the highest correlations with vertical load were obtained for the strain T-mean feature (r = 0.97), the acceleration FA-max feature (r = 0.96), and the displacement FA-max feature (r = 0.72). These results demonstrate that strain signals contain the strongest load-related information, followed by acceleration signals, whereas displacement signals show relatively limited effectiveness. The findings provide guidance for sensor selection and the development of tire-based vertical load sensing systems for agricultural vehicles.

Accurate tire load information is crucial for improving agricultural vehicle traction, mobility, and soil protection, yet real-time monitoring is difficult due to nonlinear tire deformation under varying conditions. This study developed an intelligent tire sensing system using PVDF sensors and conducted bench tests on a 280/85 R24 agricultural radial tire under different loads, inflation pressures, and speeds. Based on qualitative waveform observations, the sidewall-mounted sensor was selected for subsequent feature analysis and load-estimation modeling. Four load-sensitive features were extracted and used to train a GA-BP neural network for tire load estimation. Under the sample-level validation protocol used in this study, the GA-BP model achieved an RMSE of 34.454 N, a correlation coefficient of 99.985%, and a maximum prediction error below 1.2%. These results demonstrate the feasibility of the proposed PVDF-based tire load estimation framework under the represented experimental conditions, while independent grouped validation is required to assess its generalization to unseen operating conditions. The findings demonstrate that PVDF sensors provide an accurate and efficient method for tire load estimation in intelligent agricultural vehicles.