Desenvolvimento de aplicativo para análise de padrões de vibração de compressores

João Vitor Gouveia de Lima; Meuse Nogueira de Oliveira Júnior

doi:10.47236/2594-7036.2026.v10.1887

Authors

João Vitor Gouveia de Lima Federal Institute of Pernambuco https://orcid.org/0009-0005-2501-0621
Meuse Nogueira de Oliveira Júnior Federal Institute of Pernambuco https://orcid.org/0000-0001-7670-0765

DOI:

https://doi.org/10.47236/2594-7036.2026.v10.1887

Keywords:

IoT, Predictive maintenance, Signal processing, Software development, Vibration analysis

Abstract

This work presents an application for analyzing vibration patterns in compressors used in HVAC systems. The main objective was to validate a software architecture capable of processing, storing, and visualizing signals from noisy MEMS sensors, common in resource-constrained scenarios. The methodology was based on developing a desktop application in Python, integrating capture via MQTT protocol, persistence in a PostgreSQL database, and signal processing via Fast Fourier Transform (FFT) and Short-Time Fourier Transform (STFT) algorithms. For the application validation, an acquisition node based on ESP8266 and MPU-6050 sensor was used on an induction motor. The results showed that the system processed 256-sample buffers with a transmission and rendering latency of 3.4 seconds. Spectral analysis identified the fundamental vibration frequency around 120 Hz to 125 Hz, presenting an acceptable deviation from the theoretical expectation (120 Hz) given the spectral resolution imposed by the sampling window. It is concluded that the developed model is effective for screening and remote monitoring, compensating for hardware limitations through robust processing and visualization techniques, offering a cost-effective alternative that acts as a monitoring hub to assist maintenance teams.

Downloads

Download data is not yet available.

Author Biographies

João Vitor Gouveia de Lima, Federal Institute of Pernambuco

Student of the Technology in Systems Analysis and Development course at the Recife Campus of the Federal Institute of Pernambuco. Recife, Pernambuco, Brazil. Email address: jvgl@discente.ifpe.edu.br. Orcid: https://orcid.org/0009-0005-2501-0621. Lattes Curriculum: http://lattes.cnpq.br/3176336326143248.
Meuse Nogueira de Oliveira Júnior, Federal Institute of Pernambuco

PhD in Computer Science from the Federal University of Pernambuco. Professor in the areas of Biomedical Engineering and Computer Science in Basic, Technical, and Technological Education at the Recife Campus of the Federal Institute of Pernambuco. Recife, Pernambuco, Brazil. Email address: meusejunior@recife.ifpe.edu.br. Orcid: https://orcid.org/0000-0001-7670-0765. Lattes Curriculum: http://lattes.cnpq.br/8250068675147894.

References

BALDISSARELLI, L. N.; FABRO, E. Manutenção preditiva na indústria 4.0. Scientia cum Industria, [S. l.], v. 7, n. 2, p. 12-22, 2019. Disponível em: https://sou.ucs.br/etc/revistas/index.php/scientiacumindustria/article/view/6835. Acesso em: 9 fev. 2026.

CYRINO, L. Diagnóstico de falhas das vibrações. 2017. Disponível em: https://www.manutencaoemfoco.com.br/diagnostico-de-falhas-das-vibracoes/. Acesso em: 8 jan. 2025.

FINLEY, W. R.; HODOWANEC, M. M.; HOLTER, W. G. An analytical approach to solving motor vibration problems. In: IEEE INDUSTRY APPLICATIONS SOCIETY ANNUAL MEETING, 46., 1999, Phoenix. Conference Record [...]. Phoenix: IEEE, 1999. p. 217–232.

HARRIS, C. R. et al. Array programming with NumPy. Nature, London, v. 585, n. 7825, p. 357–362, 2020.

HUNTER, J. D. Matplotlib: A 2D graphics environment. Computing in Science & Engineering, New York, v. 9, n. 3, p. 90–95, 2007.

JARDINE, A. K. S.; LIN, D.; BANJEVIC, D. A review on machinery diagnostics and prognostics implementing condition-based maintenance. Mechanical Systems and Signal Processing, Amsterdam, v. 20, n. 7, p. 1483-1510, 2006.

KANBAN UNIVERSITY. The Kanban Guide. 2021. Disponível em: https://kanban.university/kanban-guide/. Acesso em: 20 jan. 2025.

LEE, J.; BAGHERI, B.; KAO, H.-A. A Cyber-Physical Systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters, [S.l.], v. 3, p. 18-23, 2015.

MCFEE, B. et al. Librosa: Audio and Music Signal Analysis in Python. In: PYTHON IN SCIENCE CONFERENCE, 14., 2015, Austin. Proceedings [...]. Austin: SciPy, 2015. p. 18-24.

OPPENHEIM, A. V.; SCHAFER, R. W. Discrete-Time Signal Processing. 3. ed. Upper Saddle River: Pearson, 2010.

PDOC. Pdoc Documentation. 2025. Disponível em: https://pdoc.dev/docs/pdoc.html. Acesso em: 25 set. 2025.

PEREIRA, A. C.; SIMONETTO, E. O. Indústria 4.0: conceitos e perspectivas para o Brasil. Revista da Universidade Vale do Rio Verde, Três Corações, v. 16, n. 1, p. 1-12, 2018.

POSTGRESQL GLOBAL DEVELOPMENT GROUP. PostgreSQL 16.1 Documentation. 2025. Disponível em: https://www.postgresql.org/docs/. Acesso em: 11 jan. 2025.

SAFIZADEH, M. S.; LAKIS, A. A.; THOMAS, M. Using Short-Time Fourier Transform in Machinery Diagnosis. In: INTERNATIONAL CONFERENCE ON CONDITION MONITORING AND DIAGNOSTIC ENGINEERING MANAGEMENT, 18., 2005, Cranfield. Proceedings [...]. Cranfield: COMADEM, 2005. p. 305-314.

SCHWABER, K.; SUTHERLAND, J. The Scrum Guide: The definitive guide to Scrum. 2020. Disponível em: https://scrumguides.org/scrum-guide.html. Acesso em: 20 jan. 2025.

SMITH, S. W. The Scientist and Engineer's Guide to Digital Signal Processing. San Diego: California Technical Publishing, 1997.

THINGSBOARD. ThingsBoard Documentation. 2025. Disponível em: https://thingsboard.io/docs/. Acesso em: 25 set. 2025.

VAVASSORI, M. M. et al. Análise de falhas em equipamentos utilizando sensores de baixo custo, como método de manutenção preditiva. Periódico Científico da UniSATC, Criciúma, v. 7, n. 2, p. 136–194, 2022.

VISUAL STUDIO CODE. Documentation. 2025. Disponível em: https://code.visualstudio.com/docs. Acesso em: 11 jan. 2025.