eduzhai > Applied Sciences > Engineering >

Optical oxygen sensing with artificial intelligence

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 15 pages

Abstract: Luminescence-based sensors for measuring oxygen concentration are widely usedboth in industry and research due to the practical advantages and sensitivityof this type of sensing. The measuring principle is the luminescence quenchingby oxygen molecules, which results in a change of the luminescence decay timeand intensity. In the classical approach, this change is related to an oxygenconcentration using the Stern-Volmer equation. This equation, which in most ofthe cases is non-linear, is parametrized through device-specific constants.Therefore, to determine these parameters every sensor needs to be preciselycalibrated at one or more known concentrations. This work explores an entirelynew artificial intelligence approach and demonstrates the feasibility of oxygensensing through machine learning. The specifically developed neural networklearns very efficiently to relate the input quantities to the oxygenconcentration. The results show a mean deviation of the predicted from themeasured concentration of 0.5 percent air, comparable to many commercial andlow-cost sensors. Since the network was trained using synthetically generateddata, the accuracy of the model predictions is limited by the ability of thegenerated data to describe the measured data, opening up future possibilitiesfor significant improvement by using a large number of experimentalmeasurements for training. The approach described in this work demonstrates theapplicability of artificial intelligence to sensing of sensors.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×