On-line flow visualization in multiphase reactors using neural networks

Godfroy, Larin; Larachi, Faı̈çal; Kennedy, G.; Grandjean, Bernard P. A.; Chaouki, Jamal

doi:10.1016/s0969-8043(96)00183-2

Cited by 41 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The spurious velocities are estimated by using a space-resolution mapping established from the calibration procedure. Readers interested in more details on the velocity calibration and the evaluation of the 3-D resolutions are referred to the following papers (Larachi et al, 1994;Godfroy et al, 1995). By assuming axisymmetry of the solids flow, the angular dimension is taken out by averaging azimuthally the ensemble-averaged velocities.…”

Section: Solids Kinematicsmentioning

confidence: 99%

Flow structure of the solids in a 3‐D gas–liquid–solid fluidized bed

et al. 1996

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Solids Kinematicsmentioning

confidence: 99%

Flow structure of the solids in a 3‐D gas–liquid–solid fluidized bed

et al. 1996

Self Cite

View full text Add to dashboard Cite

show abstract

“…Godfroy et al attempted an ANN based reconstruction algorithm using the package NNFit (http://www.grandjean-bpa.com/NNfit/index.html) for online visualization in a three phase fluidized bed reactor. In current work, ANN‐based reconstruction is shown as a base case of ML algorithms, and as will be shown, is outperformed by the other, more contemporary ML reconstruction methods.…”

Section: Ann Based Rpt Reconstructionmentioning

confidence: 99%

Machine learning based position‐rendering algorithms for radioactive particle tracking experimentation

et al. 2020

View full text Add to dashboard Cite

Radioactive particle tracking (RPT) is one of the most widely used non-intrusive velocimetry technique for multiphase reactors. The large volume of interrogation and the presence of internals limit the application of RPT in large-scale real-world systems. The main challenge lies in having fast reconstruction algorithms applicable to conventional (i.e., bubble columns, fluidized beds, etc.) as well as new vessels. In this contribution, a reconstruction methodology is proposed based on machine learning. Three machine-learning algorithms, namely, artificial neural network (ANN), support vector regression (SVR), and relevance vector regression (RVR), have been employed for RPT reconstruction. The results show that the position reconstruction accuracy of SVR was best for all cases and that the accuracy of RVR was comparable to SVR for large training datasets. Whereas, in terms of reconstruction speed, RVR outperforms SVR significantly, owing to sparser RVR model. SVR and RVR based reconstruction algorithms expedite the position reconstruction. K E Y W O R D S artificial neural networks (ANN), radioactive particle tracking (RPT), relevance vector regression (RVR), support vector regression (SVR)

show abstract

“…During subsequent tracking, the experimental count rates in the various detectors are compared to the modelled rates, searching for the location that best matches the measured values (Larachi et al, 1995). A neural network approach has also been used (Godfroy et al, 1997). A problem with all these methods is that they are unable to correct for temporal variations in attenuation due to moving parts or changes in bed holdup.…”

Section: Radioactive Particle Trackingmentioning

confidence: 99%

Radioisotope tracer techniques

Parker

2015

Industrial Tomography

View full text Add to dashboard Cite

On-line flow visualization in multiphase reactors using neural networks

Cited by 41 publications

References 11 publications

Flow structure of the solids in a 3‐D gas–liquid–solid fluidized bed

Flow structure of the solids in a 3‐D gas–liquid–solid fluidized bed

Machine learning based position‐rendering algorithms for radioactive particle tracking experimentation

Radioisotope tracer techniques

Contact Info

Product

Resources

About