Monitoring machinery in wastewater treatment plants is crucial due to its impact on sensitive issues such as environmental health and quality of life. A designed and fabricated monitoring system ensures compliance with all operating and safety conditions. In the initial phase, the assessment of the electrical panel using non-destructive methodology was conducted. A thermographic survey, combined with an artificial intelligence algorithm, verified thermal dissipation and led to the creation of an current consumption database. Information derived from the measurement campaign assists in establishing a control system for machinery operation. Upon identifying the causes of malfunctions, data were sent in real-time to a monitoring platform consisting of current sensors and a control unit based on a Raspberry Pi and an Arduino board. Real-time transmission of data to the monitoring platform occurred via a 4G L TE internet stick. The collected data and results optimize consumption by managing the on/off switching of monitored machinery. Activation times can be set to control electrical overload values. The proposed system provides more accurate consumption and operating forecasts than existing systems. Finally, the system offers end-users suggestions on classifying thermal energy dissipated on the switchboard, distinguishing machinery or devices presenting overload issues. This classification translates into information on lower current consumption and enhanced process quality.

Sensors and Integrated Electronic Circuits for Monitoring Machinery on Wastewater Treatment: Artificial Intelligence Approach / Prattico, D.; Lagana, F.; Oliva, G.; Fiorillo, A. S.; Pullano, S. A.; Calcagno, S.; De Carlo, D.; Foresta, F. L.. - 5:(2024), pp. 1-6. (Intervento presentato al convegno 2024 IEEE Sensors Application Symposium SAS tenutosi a Napoli, Italy nel 23-25 July, 2024) [10.1109/SAS60918.2024.10636531].

Sensors and Integrated Electronic Circuits for Monitoring Machinery on Wastewater Treatment: Artificial Intelligence Approach

Calcagno S.;De Carlo D.;
2024-01-01

Abstract

Monitoring machinery in wastewater treatment plants is crucial due to its impact on sensitive issues such as environmental health and quality of life. A designed and fabricated monitoring system ensures compliance with all operating and safety conditions. In the initial phase, the assessment of the electrical panel using non-destructive methodology was conducted. A thermographic survey, combined with an artificial intelligence algorithm, verified thermal dissipation and led to the creation of an current consumption database. Information derived from the measurement campaign assists in establishing a control system for machinery operation. Upon identifying the causes of malfunctions, data were sent in real-time to a monitoring platform consisting of current sensors and a control unit based on a Raspberry Pi and an Arduino board. Real-time transmission of data to the monitoring platform occurred via a 4G L TE internet stick. The collected data and results optimize consumption by managing the on/off switching of monitored machinery. Activation times can be set to control electrical overload values. The proposed system provides more accurate consumption and operating forecasts than existing systems. Finally, the system offers end-users suggestions on classifying thermal energy dissipated on the switchboard, distinguishing machinery or devices presenting overload issues. This classification translates into information on lower current consumption and enhanced process quality.
2024
979-8-3503-6925-0
Non-destructive Evaluation , Energy and Smart Grid , Infrared thermography , Deep learning , Convolutional Neural Network , Wastewater Treatment
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12318/151948
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact