The use of challenging, heterogeneous fuels and multi-fuel combustion is characteristic for modern-day circulating fluidized bed (CFB) combustion. This increases the need for monitoring the performance of the process. However, long-term online measurement of different phenomena in CFB boilers is a challenging task, and the lack of measurements complicates direct monitoring of the process. For this reason there is a need for new methods like soft sensors, which could be used to support or compensate the direct measurements of bed diagnostics. This paper demonstrates an adaptive soft sensor that utilizes process data to estimate the quality of the bed by predicting the grain size distribution in the bottom ash of circulating fluidized bed boilers. The grain size fractions from the sieving of bottom ash are used as reference values for bed quality. Either linear or nonlinear regression can be used to train the model. Adaptive variable selection is performed before constructing the dynamic model, which utilizes the selected variables to estimate the different grain size fractions online. The new approach has been tested using process data and grain size distributions measured from three individual CFB boilers fired by biomass, and the results show that the adaptive approach provides a useful tool for bed diagnostics. (C) 2011 Elsevier B.V. All rights reserved.