Transforming CMM Inspection Reports into NVH-Relevant Feature Sets

Abstract:

This work presents a methodology for extracting NVH-relevant, machine-learning–ready features from CMM-based gear inspection reports available only in PDF format. Although raw point-cloud measurements are not available, the approach demonstrates how curve-level geometric information—such as profile and lead deviation, pitch behavior, and runout shape patterns—can be interpreted directly from the plotted diagrams. These curve-derived descriptors capture qualitative shape phenomena that are not represented in tabulated tolerances and can be transformed into structured numerical features suitable for future correlation with NVH indicators such as transmission-error variability or tonal-noise risk. The method enables digitization of historical PDF-only metrology archives and provides a foundation for data-driven NVH assessment and predictive quality workflows. Similar approaches that extract geometric and dynamic features from profile or error curves have been shown to reveal excitation mechanisms underlying transmission error and tonal noise generation.

• Periodical: Advances in Science and Technology (Volume 181)
• Pages: 293-302
• DOI: https://doi.org/10.4028/p-s36NGl
• Online since: August 2026
• Authors: Krisztian Horvath*, Ambrus Zelei
• Keywords: CMM Inspection, Data-Driven, Feature Extraction, Gear Metrology, Gear Noise

References

[1] Bejar, F., Perret-Liaudet, J., Bareille, O., Ichchou, M., & Fontana, M. (2024). Review and benchmarking study of different gear contact analysis software in terms of the static transmission error response. Results in Engineering.

DOI: 10.1016/j.rineng.2024.102286

[2] Peruń, G., Kozuba, J., & Pil'a, J. (2016). Modelling and simulation of power transmission system oriented on diagnosis of failures in toothed gear. Journal of KONES. Powertrain and Transport, 23, 275-284.

DOI: 10.5604/12314005.1213603

[3] Mughal, H., Sivayogan, G., Dolatabadi, N., & Rahmani, R. (2022). An efficient analytical approach to assess root cause of nonlinear electric vehicle gear whine. Nonlinear Dynamics, 110, 3167 - 3186.

DOI: 10.1007/s11071-022-07800-0

[4] Horváth, K., & Zelei, A. (2024). Simulating Noise, Vibration, and Harshness Advances in Electric Vehicle Powertrains: Strategies and Challenges. World Electric Vehicle Journal.

DOI: 10.3390/wevj15080367

[5] Mahe, H., Magne, S., & Pitchai, G. (2024). Automotive powertrain electrification: system methodology to guarantee acoustic comfort. INTER-NOISE and NOISE-CON Congress and Conference Proceedings.

DOI: 10.3397/in_2024_3658

[6] Wang, X., Liu, M., Yao, T., Zheng, K., Zhao, C., Xiao, L., Zhu, D., & Shi, Z. (2024). A Novel Method for Obtaining Analytical Parameters Based on Double-Flank Measurement. Sensors (Basel, Switzerland), 24.

DOI: 10.3390/s24092734

[7] Wang, J., Lei, S., Ding, F., Jinli, L., Hou, L., & Miao, E. (2024). A digital twin modeling and application for gear rack drilling rigs lifting system. Scientific Reports, 14.

DOI: 10.1038/s41598-024-73954-z

[8] Shi, Z., Sun, Y., Wang, X., Zhao, B., & Song, H. (2022). Acquisition and Assessment of Gear Holistic Deviations Based on Laser Measurement. Photonics.

DOI: 10.3390/photonics9100735

[9] Kawano, K., Iba, D., Uriu, K., Inoue, H., & Moriwaki, I. (2021). Expression of gear-tooth-flank deviations for Hobbing-Machine-Diagnosis system (Learning-data collection through hobbing simulation and their compression with network representation). Transactions of the JSME (in Japanese).

DOI: 10.1299/transjsme.21-00220

[10] Olofsson, A., Köhn, M., & Jonsson, S. (2018). Identifying process parameters influencing gear runout. Material wissenschaft und Werkstofftechnik, 49.

DOI: 10.1002/mawe.201700133

[11] Böttger, J., Kimme, S., & Drossel, W. (2021). Characterization of vibration in continuous generating grinding and resulting influence on tooth flank topography and gear excitation. Procedia CIRP, 99, 208-213.

DOI: 10.1016/j.procir.2021.03.029

[12] Wang, Y., Li, G., Tao, Y., Zhao, X., & He, X. (2025). Loaded tooth contact analysis for helical gears with surface waviness error. Mechanical Systems and Signal Processing.

DOI: 10.1016/j.ymssp.2024.112045

[13] Palermo, A., Britte, L., Janssens, K., Mundo, D., & Desmet, W. (2018). The measurement of Gear Transmission Error as an NVH indicator: Theoretical discussion and industrial application via low-cost digital encoders to an all-electric vehicle gearbox. Mechanical Systems and Signal Processing.

DOI: 10.1016/j.ymssp.2018.03.005

[14] Qiu, P., Zhao, N., & Wang, F. (2016). Optimum microgeometry modifications of herringbone gear by means of fitness predicted genetic algorithm. Journal of Vibroengineering, 18, 4964-4979.

DOI: 10.21595/jve.2016.17179