Vibration Anomaly Detection in Machinery Using Low-Cost MEMS Sensors
DOI:
https://doi.org/10.61273/neyart.v3i5.141Keywords:
MPU6050, accelerometer, low-cost sensors, vibration measurement, condition monitoringAbstract
This work evaluated the feasibility of the low-cost MPU6050 inertial sensor for vibration measurement in academic and industrial settings. A data acquisition system was implemented using the MPU6050 sensor connected to an Arduino UNO board via the I2C bus to monitor vibration in a machine under test—in this case, a 3D printer. Acceleration data were collected at a frequency of 20 Hz and analyzed using the root mean square (RMS) and the crest factor (cf) to identify differences between normal and abnormal operating conditions.
The results demonstrated that the measurements acquired with the sensor allow to identify abnormal operating conditions derived from the detection of vibration anomalies. It was concluded that the MPU6050 sensor is a viable and cost-effective alternative for preventive monitoring and experimental research applications under controlled conditions. However, the sensor's inherent limitations in terms of resolution, dynamic range, and calibration must be considered.
Downloads
Metrics
References
Adafruit Learning System. (s.f.). MPU-6050 6-DoF accelerometer and gyroscope. https://learn.adafruit.com/mpu6050-6-dof-accelerometer-and-gyroscope
Arduino Playground. (s.f.). MPU-6050. https://playground.arduino.cc/Main/MPU-6050/
Descripción y funcionamiento del bus I2C. (s.f.). https://robots-argentina.com.ar/didactica/descripcion-y-funcionamiento-del-bus-i2c/
Fedorov, D., Ivoylov, A., Zhmud, V., & Trubin, V. (2015). Using of measuring system MPU6050 for the determination of the angular velocities and linear accelerations. Automatics & Software Engineering, 1(11), 76–81.
Flovik, V. (2018). How to use machine learning for anomaly detection and condition monitoring. Towards Data Science. https://towardsdatascience.com/how-to-use-machine-learning-for-anomaly-detection-and-condition-monitoring-9c0f1314de9d
Ghazali, M., Abdalla, A. N., Oumer, A. N., & Mohamed, A. A. (2021). Vibration analysis for machine monitoring and diagnosis: A systematic review. Shock and Vibration, 2021, 1–20. https://doi.org/10.1155/2021/9469318 DOI: https://doi.org/10.1155/2021/9469318
InvenSense. (s.f.). MPU-6000 and MPU-6050 product specification (Rev. 3.4). https://invensense.tdk.com/wp-content/uploads/2015/02/MPU-6000-Datasheet1.pdf
Iqbal, A., Mian, N. S., Longstaff, A., & Fletcher, S. (2022). Performance evaluation of low-cost vibration sensors in industrial IoT applications. International Journal of Automation Technology, 16(3), 329–339. https://doi.org/10.20965/ijat.2022.p0329 DOI: https://doi.org/10.20965/ijat.2022.p0329
Komarizadehasl, S., Mobaraki, B., Ma, H., Lozano-Galant, J.-A., & Turmo, J. (2021). Development of a low-cost system for the accurate measurement of structural vibrations. Sensors, 21(18), 6191. https://doi.org/10.3390/s21186191 DOI: https://doi.org/10.3390/s21186191
Li, Y., Zhao, W., Li, Q., Wang, T., & Wang, G. (2019). In-situ monitoring and diagnosing for fused filament fabrication process based on vibration sensors. Sensors, 19(11). https://doi.org/10.3390/s19112589 DOI: https://doi.org/10.3390/s19112589
Ronquillo, C. (2023). Predicción del estado de operación de una impresora 3D mediante redes de sensores y algoritmos de aprendizaje profundo (Tesis de maestría). Tecnológico Nacional de México. https://rinacional.tecnm.mx/jspui/handle/TecNM/7856
Soto-Ocampo, C. R., Mera, J. M., Cano-Moreno, J. D., & García-Bernardo, J. L. (2020). Low-cost, high-frequency data acquisition system for condition monitoring of rotating machinery through vibration analysis: Case study. Sensors, 20(12), 3493. https://doi.org/10.3390/s20123493 DOI: https://doi.org/10.3390/s20123493
SparkFun. (s.f.). MPU-6050 6-DoF IMU breakout. https://www.sparkfun.com/products/11028
Vos, K., Peng, Z., Jenkins, C., Shahriar, M. R., Borghesani, P., & Wang, W. (2022). Vibration-based anomaly detection using LSTM/SVM approaches. Mechanical Systems and Signal Processing, 169, 108752. https://doi.org/10.1016/j.ymssp.2021.108752 DOI: https://doi.org/10.1016/j.ymssp.2021.108752
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Carlos Alberto Ronquillo Salas , Laura Elizabeth Silva Leyva , Irving Bruno López Santos , Jesús Armando Holguín López , Ismael Esquivel Mancha
This work is licensed under a Creative Commons Attribution 4.0 International License.
