Español

Authors

DOI:

https://doi.org/10.31908/19098367.2880

Keywords:

Autoclave, diagnosis by means of sound, Machine Learning, Signal Processing, vacuum pump

Abstract

Autoclaves are vital equipment in the hospital sterilization processes. They are so important in any hospital center that a failure in the equipment can result in the total suspension of surgical activity, as they represent the main tool when it comes to prevent the spread of infections to which medical procedures are exposed [1]. Vacuum pumps are essential elements in the operation of autoclaves, since a successful sterilization process depends on their performance. This article intends to introduce a method to automatically detect the failure condition of an autoclave's vacuum pump, based on the characteristics of the acoustic signal produced by the equipment during its operation. Initially, the acoustic signals emitted by the pump in both normal and failure conditions were captured. The results obtained by different signal analysis methods were compared, and it was determined which of them ended up being more suitable in order to perform a diagnosis of the equipment's operating condition. The results obtained showed that, in order to identify the specific type of failure analyzed, the analysis within the time domain ended up being more suitable than the analysis within the frequency domain. Finally, an algorithm that detects the presence or absence of water in the vacuum pump of the autoclave was obtained.

Author Biographies

  • Jhon Jairo Padilla Aguilar, Universidad Pontificia Bolivariana
    Doctor en telemática, Universitat Politècnica de Catalunya. Magíster en informática, Universidad Industrial de Santander. Ingeniero Electrónico y de Telecomunicaciones, Universidad del Cauca. Intereses de investigación: Aprendizaje automático, Ingeniería de tráfico, Comunicaciones móviles, Calidad de Servicio en Internet.
  • Raúl Restrepo Agudelo, Universidad Pontificia Bolivariana
    Magíster en ingeniería, Universidad Pontificia Bolivariana. Especialista en automatización de procesos industriales, Universidad de los Andes. Ingeniero electricista, Universidad Industrial de Santander. Intereses de investigación: Procesamiento de señales, Comunicaciones por la red eléctrica, Procesamiento del sonido.      
  • Jann Nicolás Mayorga, Universidad Pontificia Bolivariana
    Ingeniero Electrónico, Universidad Pontificia Bolivariana. Intereses de investigación: Automatización.

References

Major Process Equipment Maintenance and Repair, Chapter 3. Ed. Gulf Publishing Company. Heinz P. Bloch, Fred K. Geitner. 1997.

Machinery failure analysis and troubleshooting, Chapter 5. Ed. Elsevier. Heinz P. Bloch, Fred K. Geitner. 2012.

Investigation of effect of pump rotational speed on performance and detection of cavitation within a centrifugal pump using vibration analysis, Ahmed Ramadhan Al-Obaidi. Elsevier, Heliyon 5 (2019) 1-19.

Experimental study on gas-liquid transient flow in liquid-ring vacuum pump and its hydraulic excitation. Renhui Zhang, Guangqiang Guo. Elsevier, Science Direct, Vacuum 171 (2020), 1-8.

Fault diagnosis of rotating machinery based on multiple probabilistic classifiers. Jian-Hua Zhong, Pak Kin Wong, Zhi-Xin Yang. Elsevier, Science Direct, Mechanical Systems and Signal Processing 108 (2018) 99–114.

Fault diagnosis of rotating machinery through visualisation of sound signals. Katsuhiko Shibata, Atsushi Takahashi and Takuya Shirai. Mechanical Systems and Signal Processing (2000) 14(2), 229-241.

Flow noise identification using acoustic emission (AE) energy decomposition for sand monitoring in flow pipeline. M.G. Droubia, R.L. Reubenb, J.I. Steel. Applied Acoustics 131 (2018) 5–15.

Machinery fault diagnosis using signal analysis. Zoltan German-Sallo, Gabriela Strnad. Procedia Manufacturing 32 (2019) 585–590.

A review on machinery diagnostics and prognostics implementing condition-based maintenance. Andrew K.S. Jardine, Daming Lin, Dragan Banjevic. Mechanical Systems and Signal Processing 20 (2006) 1483–1510.

Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications. Jay Lee, Fangji Wu, Wenyu Zhao, Masoud Ghaffari, Linxia Liao, David Siegel. Mechanical Systems and Signal Processing 42 (2014) 314–334.

Standard deviation based acoustic emission signal analysis for detecting valve internal leakage. Guo-Yang Yea, Ke-Jun Xua, Wen-Kai Wua. Sensors and Actuators A 283 (2018) 340–347.

Stick-Slip Squeal in a Dry Scroll Vacuum Pump. John Calhoun, James Moore, Ronald Forni. 23rd International Compressor Engineering Conference at Purdue, July 11-14, 2016, 1-8.

Vibration and noise in centrifugal pumps - sources and diagnosis methods. Ravindra Birajdar Rajashri Patil, Kedar Khanzode. 3rd International Conference on Integrity, Reliability and Failure, Porto/Portugal, 20-24 July 2009, Paper Ref: S1163_P0437, 1-12.

An Introduction to Predictive Maintenance, second edition, R. Keith Mobley. Google Books. Butterworth-Heinemann (2002).

Bearing Signature Analysis as a Medium for Fault Detection: A Review. M. S. Patil, Jose Mathew, P. K. Rajendra Kumar. Journal of Tribology, Transactions of the ASME, January 2008, Vol. 130 / 014001-1.

Vibration analysis of bearing for fault detection using time domain features and neural network. Manish yadav, Sulochana wadhwani. International Journal of Applied Research in Mechanical Engineering, Volume-1, Issue-1, 2011

Downloads

Published

2023-07-04

Issue

Vol. 17 No. 33 (2023)

Section

Artículos

How to Cite

Español. (2023). Entre Ciencia E ingeniería, 17(33), 24-30. https://doi.org/10.31908/19098367.2880