Identification, Detection and Modeling of Process Anomalies in Fluidized Bed Spray Agglomeration to Ensure Product Quality

Katharina Mohrdieck, M.Sc.

Motivation

Fluidized bed processes are widely used in industries such as food, pharmaceuticals and chemicals to produce granular products, including instant powders, catalysts, detergents and fertilizers. These processes enable intense momentum, heat and mass transfer, facilitating the formation of diverse particle structures. A key mechanism is agglomeration, where particles are bonded through solid bridges. The properties of the resulting agglomerates are influenced by process parameters like liquid spray rate and fluidization air temperature. While extensive research has investigated these effects using different mediums, the complex interactions between solid, liquid and gaseous phases are not yet fully understood. Deviations from optimal process conditions can lead to defects or operational failures, such as over-wetting, particle clumping and equipment blockages. These issues may arise from human errors, faulty equipment or a lack of process understanding. Effective control of process parameters is crucial to ensure consistent product quality and prevent costly production interruptions

Project Aim and Methodology

The goal of this project is to develop a systematic approach for detecting and responding to anomalies in fluidized bed agglomeration. Initially, potential scenarios and causes of defective production, as well as suitable parameters (e.g. particle size or moisture content) for detection, will be identified. To accomplish this objective, the project will employ advanced sensor technologies to enable continuous monitoring of critical parameters, including water flow rate, temperature and velocity of fluidizing gas within the fluidized bed. Based on experimental investigations, a data-driven machine learning model will be developed for real-time anomaly detection, enabling automatic identification of deviations. Since the quality of training data is a crucial factor for the accuracy of machine learning models, meticulous data preprocessing is essential. This includes handling incorrect or missing measurements, conducting sensitivity analyses of input parameter combinations and scaling or transforming qualitative and quantitative values. Furthermore, recommendations for responding to undesirable phenomena in the process will be formulated, laying the groundwork for automated intervention via the plant's operating software. Utilizing this integrated approach, the project aims to formulate a robust strategy to guarantee and improve product quality within fluidized bed agglomeration processes.

Contact Details