Diagnóstico predictivo de motores eléctricos basado en TinyML y análisis de firma de corriente

Autores/as

DOI:

https://doi.org/10.36825/RITI.13.30.006

Palabras clave:

TinyML, Mantenimiento Predictivo, Firma de Corriente del Motor, Diagnóstico en el Borde, CNN 1D

Resumen

La continuidad operativa de los motores eléctricos es esencial para la productividad industrial, ya que sus fallas imprevistas generan pérdidas económicas y riesgos de seguridad. Este estudio propone un sistema de diagnóstico predictivo basado exclusivamente en el análisis de la firma de corriente del motor (MCSA) con inferencia local mediante TinyML, orientado a entornos con recursos limitados. El diseño incluye la adquisición de la señal de corriente mediante un transductor no invasivo, su acondicionamiento analógico, preprocesamiento por cálculo de valor eficaz en ventanas solapadas y normalización, y el entrenamiento de un modelo ligero de convolución unidimensional optimizado para ejecución en microcontrolador. El prototipo fue evaluado con un conjunto de datos balanceado entre clases, aplicando métricas estándar de clasificación y perfiles de uso de recursos. Los resultados muestran una discriminación perfecta entre condiciones normales y anómalas asociadas a perturbaciones de electrónica de potencia, con tiempos de inferencia compatibles con monitoreo en tiempo real y un bajo consumo de memoria. Se concluye que la MCSA, combinada con inferencia en el borde, es una alternativa viable y de bajo costo para el mantenimiento predictivo, especialmente en instalaciones con limitaciones de infraestructura, y que su integración en sistemas multivariables podría ampliar la cobertura de modos de falla mecánicos.

Citas

Castorena Peña, J. A., Domínguez Lugo, A. J., Cantú González, J. R., Alba Cisneros, D. M. (2024). Técnica de ciencia de datos para el pronóstico de consumo de gas natural en la industria siderúrgica. Revista de Investigación en Tecnologías de la Información, 12 (26), 77–93. https://doi.org/10.36825/RITI.12.26.007

Njor, E., Hasanpour, M. A., Madsen, J., Fafoutis, X. (2024). A Holistic Review of the TinyML Stack for Predictive Maintenance. IEEE Access, 12, 184861-184882. https://doi.org/10.1109/ACCESS.2024.3512860

de la Fuente, R., Radrigan, L., Morales, A. S. (2024). Enhancing Predictive Maintenance in Mining Mobile Machinery through a TinyML-enabled Hierarchical Inference Network (Versión 2). arXiv. https://doi.org/10.48550/ARXIV.2411.07168

Arciniegas, S., Rivero, D., Piñan, J., Diaz, E., Rivas, F. (2025). IoT device for detecting abnormal vibrations in motors using TinyML. Discover Internet of Things, 5 (1), 1-18. https://doi.org/10.1007/s43926-025-00142-4

Kiranyaz, S., Devecioglu, O. C., Alhams, A., Sassi, S., Ince, T., Abdeljaber, O., Avci, O., Gabbouj, M. (2024). Zero-shot motor health monitoring by blind domain transition. Mechanical Systems and Signal Processing, 210, 1-16. https://doi.org/10.1016/j.ymssp.2024.111147

Ayankoso, S., Dutta, A., He, Y., Gu, F., Ball, A., Pal, S. K. (2024). Performance of vibration and current signals in the fault diagnosis of induction motors using deep learning and machine learning techniques. Structural Health Monitoring, 1-17. https://doi.org/10.1177/14759217241289874

Diversi, R., Lenzi, A., Speciale, N., Barbieri, M. (2025). An Autoregressive-Based Motor Current Signature Analysis Approach for Fault Diagnosis of Electric Motor-Driven Mechanisms. Sensors, 25 (4), 1-24. https://doi.org/10.3390/s25041130

Zhang, Q., Wei, X., Wang, Y., Hou, C. (2024). Convolutional Neural Network with Attention Mechanism and Visual Vibration Signal Analysis for Bearing Fault Diagnosis. Sensors, 24 (6), 1-16. https://doi.org/10.3390/s24061831

Ribeiro Junior, R. F., dos Santos Areias, I. A. D., Mendes Campos, M., Teixeira, C. E., Borges da Silva, L. E., Ferreira Gomes, G. (2022). Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals. Measurement, 190. https://doi.org/10.1016/j.measurement.2022.110759

Tan, X., Mahjoubi, S., Zou, X., Meng, W., Bao, Y. (2023). Metaheuristic inverse analysis on interfacial mechanics of distributed fiber optic sensors undergoing interfacial debonding. Mechanical Systems and Signal Processing, 200. https://doi.org/10.1016/j.ymssp.2023.110532

Hua, Z., Shi, J., Luo, Y., Huang, W., Wang, J., Zhu, Z. (2021). Iterative matching synchrosqueezing transform and application to rotating machinery fault diagnosis under nonstationary conditions. Measurement, 173. https://doi.org/10.1016/j.measurement.2020.108592

Zhu, Z., Au, S.-K. (2022). Uncertainty quantification in Bayesian operational modal analysis with multiple modes and multiple setups. Mechanical Systems and Signal Processing, 164. https://doi.org/10.1016/j.ymssp.2021.108205

Bala, A., Rashid, R. Z. J. A., Ismail, I., Oliva, D., Muhammad, N., Sait, S. M., Al-Utaibi, K. A., Amosa, T. I., Memon, K. A. (2024). Artificial intelligence and edge computing for machine maintenance-review. Artificial Intelligence Review, 57 (119), 1-33. https://doi.org/10.1007/s10462-024-10748-9

Tsoukas, V., Gkogkidis, A., Boumpa, E., Kakarountas, A. (2024). A Review on the emerging technology of TinyML. ACM Computing Surveys, 56 (10), 1–37. https://doi.org/10.1145/3661820

Singh, R., Singh Gill, S. (2023). Edge AI: A survey. Internet of Things and Cyber-Physical Systems, 3, 71–92. https://doi.org/10.1016/j.iotcps.2023.02.004

Bartolomé-Tomás, A., Sánchez-Reolid, R., Fernández-Sotos, A., Latorre, J. M., Fernández-Caballero, A. (2020). Arousal Detection in Elderly People from Electrodermal Activity Using Musical Stimuli. Sensors, 20 (17), 1-16. https://doi.org/10.3390/s20174788

M, S., K, S., Prasanth, N. (2022). A novel framework for deployment of CNN models using post-training quantization on microcontroller. Microprocessors and Microsystems, 94. https://doi.org/10.1016/j.micpro.2022.104634

Surianarayanan, C., Lawrence, J. J., Chelliah, P. R., Prakash, E., Hewage, C. (2023). A Survey on Optimization Techniques for Edge Artificial Intelligence (AI). Sensors, 23 (3), 1-33. https://doi.org/10.3390/s23031279

Alajlan, N. N., & Ibrahim, D. M. (2022). TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications. Micromachines, 13 (6), 1-22. https://doi.org/10.3390/mi13060851

Paes Salomon, C., Ferreira, C., Sant’Ana, W. C., Lambert-Torres, G., Borges Da Silva, L. E., Bonaldi, E. L., de Lacerda de Oliveira, L. E., Silva Torres, B. (2019). A Study of Fault Diagnosis Based on Electrical Signature Analysis for Synchronous Generators Predictive Maintenance in Bulk Electric Systems. Energies, 12 (8), 1-16. https://doi.org/10.3390/en12081506

Dilena, M., Fedele Dell’Oste, M., Fernández-Sáez, J., Morassi, A., Zaera, R. (2019). Mass detection in nanobeams from bending resonant frequency shifts. Mechanical Systems and Signal Processing, 116, 261–276. https://doi.org/10.1016/j.ymssp.2018.06.022

Namdar, A. (2022). A robust principal component analysis-based approach for detection of a stator inter-turn fault in induction motors. Protection and Control of Modern Power Systems, 7 (48), 1-24. https://doi.org/10.1186/s41601-022-00269-4

Liu, Z., Zhang, P., He, S., Huang, J. (2021). A Review of Modeling and Diagnostic Techniques for Eccentricity Fault in Electric Machines. Energies, 14 (14), 1-21. https://doi.org/10.3390/en14144296

Brockmann, S., Schlippe, T. (2024). Optimizing Convolutional Neural Networks for Image Classification on Resource-Constrained Microcontroller Units. Computers, 13 (7), 1-18. https://doi.org/10.3390/computers13070173

Vela, D., Sharp, A., Zhang, R., Nguyen, T., Hoang, A., & Pianykh, O. S. (2022). Temporal quality degradation in AI models. Scientific Reports, 12(1), 11654. https://doi.org/10.1038/s41598-022-15245-z

Mudraje, I., Vogelgesang, K., Herfet, T. (2025). A 1-D CNN inference engine for constrained platforms (Versión 1). arXiv. https://doi.org/10.48550/ARXIV.2501.17269

Lamrini, M., Chkouri, M. Y., Touhafi, A. (2023). Evaluating the Performance of Pre-Trained Convolutional Neural Network for Audio Classification on Embedded Systems for Anomaly Detection in Smart Cities. Sensors, 23 (13), 127. https://doi.org/10.3390/s23136227

Ooko, S. O., Karume, S. M. (2024). Application of Tiny Machine Learning in Predicative Maintenance in Industries. Journal of Computing Theories and Applications, 2 (1), 131–150. https://doi.org/10.62411/jcta.10929

Bolat, Y., Murray, I., Ren, Y., Ferdosian, N. (2025). Decentralized Distributed Sequential Neural Networks Inference on Low-Power Microcontrollers in Wireless Sensor Networks: A Predictive Maintenance Case Study. Sensors, 25 (15), 1-32. https://doi.org/10.3390/s25154595

Azari, M. S., Flammini, F., Santini, S., Caporuscio, M. (2023). A Systematic Literature Review on Transfer Learning for Predictive Maintenance in Industry 4.0. IEEE Access, 11, 12887–12910. https://doi.org/10.1109/ACCESS.2023.3239784

Descargas

Publicado

2025-11-19

Cómo citar

Bojorquez Delgado, G., Bojorquez Delgado, J., & Flores Rosales, M. A. (2025). Diagnóstico predictivo de motores eléctricos basado en TinyML y análisis de firma de corriente. Revista De Investigación En Tecnologías De La Información, 13(30), 71–83. https://doi.org/10.36825/RITI.13.30.006

Número

Sección

Artículos