A novel distribution rate predicting method of dense medium cyclone in the Taixi coal preparation plant

• Soft sensor modeling of distribution curve indexes is proposed based on field data.
• The data is acquired from modified single machine checks by uniform design.
• Real-time distribution rates are obtained by the models and onsite sensor values.

To predict real-time distribution curve of dense medium cyclone in the Taixi coal preparation plant, a new method based on field data was presented. A group of uniformly designed single machine checks (sampling test of a dense medium cyclone) were carried out for modeling field operating parameters and distribution curve indexes. Then three real-time indexes could be predicted by onsite sensor values, and the present distribution curve model was able to be calculated. Predicting part of the method was also compared with the usual approximate formula method based on the proposed models. The models were proved to be acceptable as the RMS accuracy reached 0.73%, 0.77%, and 0.90% respectively in the training set and 0.76%, 0.63%, and 0.51% for the test example. The predicting results were also verified to be better and more reasonable than the approximate formula method.