Block-based approach to modelling of granulated fertilizersʹ quality

Fertilizer manufacturing is a customer-driven industry, where the quality of a product is a key factor in order to survive the competition. However, measuring the most important feature with granulated fertilizers, flowability, is tedious, time-consuming and thus expensive. ility can be defined through testing the flow rate with, e.g., seed drill. Besides the chemical composition, flowability can be considered as one of the most important characteristics. There are numerous factors affecting the flowability of a granulated fertilizer, several of them related to the particle size distribution. Particle size distribution of the granulated product has to be within the customer specification, but is also a highly significant factor to the quality, especially in the presence of moisture. This can affect numerous phenomena, inter alia, agglomeration and aggregation of granules and Ostwald ripening, where the smallest crystals dissolve while the large ones grow. Chemical composition affects the crystallization process and is significant for particle shape and various physical properties. mes, as in this case, the variables form a natural division into blocks. It may be of interest to observe the different effect of the blocks on the modelling task. The present approach is based on priority PLS and multi-block PLS. The data is measured from the final product and is divided into blocks between physical properties, such as granule hardness and roundness, chemical composition and particle size distribution. The goals are to find a reliable model for flowability using this data and to find the most important variables and to identify the effect of blocks to the quality.