Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
237534 | Powder Technology | 2011 | 8 Pages |
Many industrial processes require on-line measurement of particle size and particle size distribution for process monitoring and control. The available techniques for reliable on-line measurement are, however, limited. In this paper, based on the captured surface images of randomly disarranged ore particles, the image uniformity was characterized. Particle size distribution was then investigated by applying a neural network-based modeling with the obtained image uniformity. The proposed soft sensor provides an improved prediction model and can be used for real time measurement of particle size distribution in the industrial operations.
Graphical abstractMany industrial processes require on-line particle size measurement. In this paper, particle size distribution is investigated using image analysis and neural network modeling. In addition to the information used by the available commercial software, the model also includes the uniformity characterized from the particle images and provides an improvement in measuring particle size distributions.Figure optionsDownload full-size imageDownload as PowerPoint slideHighlights► Uniformity is characterized for images of mineral particles. ► Neural network models are obtained using the WipFrag and uniformity results. ► The obtained model provides an improved prediction for particle size variation. ► The model can serve as a soft sensor for on-line particle size distribution.