Evaluasi Performa Prototipe Sistem Monitoring dan Proteksi Termal Motor DC Berbasis Edge Machine Learning pada ESP32

Muflikhul Hakim; Ahmad Syamsuri; Muhammad Dana Shulkhi; Fariz Rifqi Zul Fahmi; Fressy  Nugroho; Fuad Dwi  Hanggara

doi:10.33005/santika.v6i1.1129

Authors

Muflikhul Hakim Universitas Islam Negeri Maulana Malik Ibrahim Malang
Ahmad Syamsuri UIN Maulana Malik Ibrahim Malang
Muhammad Dana Shulkhi UIN Maulana Malik Ibrahim Malang
Fariz Rifqi Zul Fahmi UIN Maulana Malik Ibrahim Malang
Fressy Nugroho UIN Maulana Malik Ibrahim Malang
Fuad Dwi Hanggara UIN Maulana Malik Ibrahim Malang

DOI:

https://doi.org/10.33005/santika.v6i1.1129

Keywords:

Motor DC, edge machine learning, proteksi termal, relay cutoff, ESP32, IoT

Abstract

Abstrak— Penelitian ini merancang dan membangun prototipe sistem monitoring dan proteksi termal motor DC berbasis ESP32 yang mengintegrasikan tiga mekanisme respons secara hierarkis. Deteksi dini dilakukan menggunakan model edge machine learning yang dilatih melalui platform Edge Impulse untuk mengklasifikasikan pola kenaikan suhu berdasarkan lima data terakhir sensor DS18B20, kemudian mengaktifkan kipas pendingin dan buzzer sebagai respons awal. Apabila suhu motor melampaui ambang batas kritis 40°C, sistem secara deterministik memutus suplai daya motor melalui modul relay tanpa bergantung pada proses inferensi machine learning. Hasil pengujian menunjukkan bahwa model klasifikasi mencapai akurasi 99,4% dengan F1-score 99,0% pada deteksi kondisi rise. Sistem proteksi bertingkat mampu merespons kondisi kenaikan suhu dengan waktu respons 300 ms untuk aktivasi pendingin dan 200 ms untuk pemutusan daya melalui relay. Pengujian operasi kontinu selama ±1 jam menunjukkan keberhasilan inferensi 100%, tanpa kegagalan komunikasi MQTT, serta tidak ditemukan missed detection pada kondisi kritis. Dengan demikian, pendekatan hybrid yang menggabungkan edge machine learning dan proteksi deterministik berbasis relay terbukti efektif meningkatkan keandalan sistem proteksi termal motor DC skala kecil berbasis IoT.

References

S. J. Chapman, Electric Machinery Fundamentals, 5th ed. New York, NY, USA: McGraw-Hill, 2012.

International Electrotechnical Commission, IEC 60034-1: Rotating Electrical Machines — Part 1: Rating and Performance, Geneva, Switzerland: IEC, 2017.

J. Pyrhonen, T. Jokinen, and V. Hrabovcova, Design of Rotating Electrical Machines. Chichester, UK: Wiley, 2014.

J. Gubbi, R. Buyya, S. Marusic, and M. Palaniswami, "Internet of Things (IoT): A vision, architectural elements, and future directions," Future Generation Computer Systems, vol. 29, no. 7, pp. 1645–1660, 2013.

A. Banks and R. Gupta, MQTT Version 3.1.1, OASIS Standard, 2014.

C. B. Sogen, "Monitoring suhu pada kamar mesin kapal berbasis Arduino Uno," Jurnal Politeknik ATI Makassar, vol. 5, no. 1, pp. 12–18, 2023.

D. A. N. K. Suhermanto et al., "Monitoring DC Motor Based on LoRa and IoT," Journal of Robotics and Control (JRC), vol. 5, no. 1, pp. 54–61, 2024.

X. Yang and Y. Liu, "Thermal monitoring and protection of DC motors based on temperature threshold," IEEE Access, vol. 6, pp. 74215–74223, 2018.

W. Shi, J. Cao, Q. Zhang, Y. Li, and L. Xu, "Edge computing: Vision and challenges," IEEE Internet of Things Journal, vol. 3, no. 5, pp. 637–646, 2016.

C. R. Banbury et al., "Benchmarking TinyML systems," Proc. Machine Learning and Systems, vol. 3, pp. 211–244, 2021.

M. Rußwurm et al., "Self-attention for raw optical satellite time series classification," ISPRS J. Photogramm. Remote Sens., vol. 169, pp. 421–435, 2020.

B. K. Iwana and S. Uchida, "An empirical survey of data augmentation for time series classification with neural networks," PLOS ONE, vol. 16, no. 7, e0254841, 2021.

Edge Impulse Inc., Edge Impulse Documentation: Embedded Machine Learning, 2023. https://docs.edgeimpulse.com/

S. Sakr et al., "Machine learning on edge devices: A survey," IEEE Internet of Things Journal, vol. 7, no. 10, pp. 9341–9356, 2020.

A. V. Oppenheim and R. W. Schafer, Discrete-Time Signal Processing, 3rd ed. Upper Saddle River, NJ, USA: Prentice-Hall, 2010.

L. Breiman, "Random Forests," Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

T. Saito and M. Rehmsmeier, "The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets," PLOS ONE, vol. 10, no. 3, 2015.

H. W. Penrose, A Practical Guide to Electrical Motor Predictive and Preventive Maintenance. ALL-TEST Pro, LLC, 2008.

U. Hunkeler, H. L. Truong, and A. Stanford-Clark, "MQTT-S — A publish/subscribe protocol for wireless sensor networks," IEEE COMSWARE, 2008