Slurry-fed ceramic melter

BM Wise, DJ Veltkamp, NL Ricker, BR Kowalski, SM Barnes, and V Arakali. Application of multivariate statistical process control (M-SPC) to the West Valley slurry-fed ceramic melter process. In Proceedings of Waste Management 91, pages 169-176, Tucson, AZ, 1991. 

In the PLSdata data set, the aim is to obtain a regression model that relates 20 temperatures measured in a Slurry-Fed Ceramic Melter (SFCM) with the level of molten glass. The x-block contains 20 variables which correspond to temperatures collected in two vertical thermowells. Variables 1 to 10 are taken from the bottom to the top in thermowell 1, and variables 11 to 20 from the bottom to the top in thermowell 2. The data set includes 300 training observations... 

Fig. 7. Loading plots from the PLS model in the Slurry-Fed Ceramic Melter data set.

Table 1. Comparison of three PLS models in the Slurry-Fed Ceramic Melter data set. The variance in both blocks of data and the Root Mean Square Error of Calibration (RMSEC), Cross-validation (RMSECV) and Prediction (RMSEP) are compared.

Fig. 16. Measured vs predicted values of molten glass level in the PLS model with 3 LVs fitted from the Slurry-Fed Ceramic Melter (SFCM) data set in (32).

---