IoT-Driven Vibration Sensing and Decision-Tree Analytics for Multi-Class Tyre Pressure Diagnostics

Mohd Saifunnaim bin Mat Zain; Ahmad Kadri bin Junoh

doi:10.58915/aset.v5i1.3209

Authors

Mohd Saifunnaim bin Mat Zain Advanced Technology College Jitra Campus
Ahmad Kadri bin Junoh Universiti Malaysia Perlis

DOI:

https://doi.org/10.58915/aset.v5i1.3209

Keywords:

IoT, Vibration sensing, Tyre pressure diagnostics, Signal processing, Decision tree

Abstract

Maintaining correct tire pressure is essential for ensuring vehicle safety, fuel efficiency, and ride stability. However, conventional tire pressure monitoring systems commonly rely on direct pressure sensors or indirect wheel-speed estimation, which limits diagnostic resolution and scalability for multi-level pressure conditions. This study introduces an IoT-enabled vibration-based monitoring framework that leverages machine learning for improved accuracy and interpretability to assessing tire pressure states.
Four MPU-9250 triaxial accelerometers were mounted near each tire and interfaced with a Raspberry Pi 5 using a TCA9548A I²C multiplexer. Vibration signals were collected at nine distinct tire pressure levels, ranging from optimal to progressively lower pressure. Time-domain features and frequency-domain characteristics were extracted to capture tire–road interaction dynamics influenced by pressure changes. A decision tree classifier was employed to evaluate the separability and diagnostic performance across all classes. The model achieved clear discrimination between optimal and low-pressure states, confirming that vibration signatures contain sufficient information for reliable, multi-class pressure detection. The system integrates a MariaDB backend, a Flask-based dashboard, and secure remote connectivity to enable real-time monitoring. The results demonstrate that IoT-driven vibration sensing, combined with interpretable machine-learning analytics, offers a low-cost, scalable, and accurate alternative to conventional TPMS for intelligent, adaptive vehicle maintenance.

References

[1] Yu, S., Niu, L., Chen, J. Experimental and numerical studies on bond quality of fully grouted rockbolt under confining pressure and pull-out load. Shock and Vibration (2022) pp.1–12.

[2] Hussain, M., Lee, Y., Kim, D. Frequency-domain analysis of tire–road interaction for tire condition monitoring. Mechanical Systems and Signal Processing, vol 135 (2020) pp.14-18.

[3] Jiang, H., Ji, X., Yang, Y., Qu, Y., Wu, M. Vibration signal analysis of roadheader based on referential manifold learning. Shock and Vibration (2023) pp.1–11.

[4] Zhou, L., Sun, D., Liu, Q. Edge computing for smart vehicle diagnostics: A vibration monitoring perspective. Mechanical Systems and Signal Processing, vol 190 (2023) pp.1-15.

[5] Hassan, I. U., Panduru, K., Walsh, J. An in-depth study of vibration sensors for condition monitoring. Sensors, vol 24 (2024) pp.740-755.

[6] Hajnayeb, A. Cavitation analysis in centrifugal pumps based on vibration bispectrum and transfer learning. Shock and Vibration (2021) pp.1–8.

[7] Sun, G., Hu, Y., Wu, B., Zhou, H. Parallel-machine scheduling with DeJong’s learning effect, delivery times, rate-modifying activity, and resource allocation. Shock and Vibration (2021) pp.1–13.

[8] Sun, L., Wu, B., Ning, L. Identification of vibration signal for residual pressure utilization hydraulic unit using MRFO-BP neural network. Shock and Vibration (2022) pp.1–36.

[9] Dong, Z., Liu, Y., Kang, J., Zhang, S. A stochastic learning algorithm for machine fault diagnosis. Shock and Vibration (2022) pp.1–9.

[10] Huang, T., Xu, B., Wang, Y., Zhu, J., Wan, Z. Mine microseismic signal denoising based on a deep convolutional autoencoder. Shock and Vibration (2023) pp.1–15.

[11] Kibrete, F., Woldemichael, D. E., Gebremedhen, H. S. Optimization of sample size, data points, and data augmentation stride in vibration signal analysis for deep learning-based fault diagnosis of rotating machines. Shock and Vibration (2025) pp.1–16.

[12] Zhu, H., Miao, C. Seismic fragility analysis of the reinforced concrete continuous bridge piers based on machine learning and symbolic regression fusion algorithms. Shock and Vibration (2021) pp.1-8.

[13] Feng, X., Chen, Z., Li, Z., Zeng, Q., Wang, J., Wang, P. Machine learning–enhanced microseismic analysis for evaluating rock crack trajectory. Shock and Vibration (2024) pp.1-11.

[14] Tu, W., Chen, Y. Vibration transmission characteristics and measuring points analysis of bearing housing system. Shock and Vibration (2022) pp.1–12.

[15] Han, G., Xu, L. Effects of resonator shape on nonlinear resonant frequencies of a microresonant pressure sensor. Shock and Vibration (2022) pp.1–18.

[16] Huang, W., Yan, X., Zhang, S., Li, Z., Hassan, J. N. A., Chen, D., Wen, G., Chen, K., Deng, G., Huang, Y. Mems and moems gyroscopes: A review. Photonic Sensors, vol 13 (2023) pp.1-26.

[17] Wang, C., Tu, X., Chen, Q., Yang, Q., Fang, T. Movable surface rotation angle measurement system using imu. Sensors, vol 22, issue 22 (2022) pp.123-130.

[18] Fang, Y., Xu, Y., Wang, J. Vehicle vibration-based condition monitoring using low-cost MEMS sensors. Sensors, vol 20, issue 6 (2020) pp.1-17.

[19] Al-Fuqaha, A., Guizani, M., Mohammadi, M., Aledhari, M., Ayyash, M. Internet of things: A survey on enabling technologies, protocols, and applications. IEEE Communications Surveys & Tutorials, vol 17, issue 4 (2015) pp.2347–2376.

[20] Sicari, S., Rizzardi, A., Grieco, L. A., Coen-Porisini, A. Security, privacy and trust in internet of things: The road ahead. Computer Networks, vol 76 (2015) pp.146–164.

[21] Chang, H., Park, J., Kim, S. Vibration-based tire pressure monitoring using accelerometers. Sensors, vol 18, issue 10 (2018) pp.1-15.

[22] Lee, Y., Kim, D. Tire pressure monitoring through vibration signature analysis. Vehicle System Dynamics, vol 57, issue 8 (2019) pp.1153–1173.

[23] Anoop, P. S., Sugumaran, V. Classifying machine learning features extracted from vibration signal to monitor automobile tyre pressure. Structural Durability & Health Monitoring, vol 11, issue 2 (2017) pp.191–208.

[24] Kolok, P. Low-cost IoT-based predictive maintenance using vibration monitoring. Sensors, vol 25, issue 21 (2025) pp.1-26.

[25] Li, H., Zhang, Y., Wang, X. Internet-of-things enabled vehicle condition monitoring: Architecture, sensing strategies, and applications. IEEE Internet of Things Journal, vol 9, issue 15 (2022) pp.13412–13425.

[26] Khan, S., Ali, M., Rehman, A. Smart automotive health monitoring using embedded iot platforms. Sensors, vol 21, issue 4 (2021) pp.1-18.

[27] Zhang, T., Chen, Y. Cloud-connected vibration analytics for predictive maintenance in automotive systems. Journal of Intelligent Manufacturing, vol 35, issue 2 (2024) pp.455–470.