More Like this

1. Rational Function-Based Approach for Integrating Tableting Reduced-Order Models with Upstream Unit Operations: Dry Granulation Case Study

   https://doi.org/10.3390/ph17091158  

   Bachawala, Sunidhi; Lagare, Rexonni B; Delaney, Abigail B; Nagy, Zoltan K; Reklaitis, Gintaras V; Gonzalez, Marcial (September 2024, Pharmaceuticals)

   We present a systematic and automatic approach for integrating tableting reduced-order models with upstream unit operations. The approach not only identifies the upstream critical material attributes and process parameters that describe the coupling to the first order and, possibly, the second order, but it also selects the mathematical form of such coupling and estimates its parameters. Specifically, we propose that the coupling can be generally described by normalized bivariate rational functions. We demonstrate this approach for dry granulation, a unit operation commonly used to enhance the flowability of pharmaceutical powders by increasing granule size distribution, which, inevitably, negatively impacts tabletability by reducing the particle porosity and imparting plastic work. Granules of different densities and size distributions are made with a 10% w/w acetaminophen and 90% w/w microcrystalline cellulose formulation, and tablets with a wide range of relative densities are fabricated. This approach is based on product and process understanding, and, in turn, it is not only essential to enabling the end-to-end integration, control, and optimization of dry granulation and tableting processes, but it also offers insight into the granule properties that have a dominant effect on each of the four stages of powder compaction, namely die filling, compaction, unloading, and ejection. 

   more » « less
2. Predicting Powder Blend Flowability from Individual Constituent Properties Using Machine Learning

   https://doi.org/10.1007/s11095-025-03855-x  

   Owasit, Anna; Tripathi, Siddharth; Davé, Rajesh; Young, Joshua (April 2025, Pharmaceutical Research)

   Abstract PurposePredicting powder blend flowability is necessary for pharmaceutical manufacturing but challenging and resource-intensive. The purpose was to develop machine learning (ML) models to help predict flowability across multiple flow categories, identify key predictive features, and arrive at formulations with improved flow properties. MethodsA dataset of 410 blends, composed of 9 active pharmaceutical ingredients (APIs) and 18 excipients with varying silica dry-coating parameters, was analyzed. Supervised ML models were trained to predict various flowability categories (very cohesive, cohesive, semi-cohesive, well-flowing, and free-flowing). Particle size, morphology, surface properties, and coating parameters were used as features. Classification algorithms, including Random Forest (RF) and Extreme Gradient Boosting (XGBoost), were evaluated. Unsupervised clustering identified natural groupings within flowability data. ResultsThe best-performing models achieved up to 85% accuracy for predicting flowability regimes of individual components and 87% for blends. Individual components generally showed higher accuracy than blends, except in the uncoated scenario with 2 flow regimes, where blends outperformed with 94.67%. SHapley Additive exPlanations (SHAP) and Feature Importance analysis indicated dry coating parameters as the most influential factors, followed by particle size and morphology. ML models effectively identified category transitions between flow regimes, offering insights into blend optimization. ConclusionIntegrating ML with mechanistic approaches effectively predicted powder blend flowability across diverse categories and elucidated feature-property relationships. These outcomes can facilitate the rational design of blends having enhanced flow properties at reduced experimental effort through judiciously selected dry coating of a blend constituent; making this approach promising for advancing pharmaceutical process and product development. 

   more » « less
3. Pre-nucleation in high-shear wet granulation

   https://doi.org/10.1016/j.powtec.2024.119522  

   Kumar, Diana S; Oka, Sarang; Emady, Heather N (March 2024, Powder Technology)

   Wet granulation is broken down into three rate processes that are often inseparable from each other, hindering characterization of the relationship between operating conditions and product properties. Single-drop granulation is a form of drop-controlled nucleation intended to isolate the Wetting & Nucleation rate process. In this work, single-dropped granules (pre-nucleated granules) were charged to a mixer granulator under varied conditions to observe how the individual rate processes and resulting granulated product were affected by various pre-nucleation conditions. Batches with larger fractions of pre-nucleated granules tended to produce a larger granule size than batches with few or no pre-nucleated granules. A clear and consistent trend of deviation from traditional granulation results is observed. Liquid to solid ratio is ruled out as a sole cause for the deviation, indicating that pre-nucleation may have applications in granular material production with respect to liquid dosing in granules, granule size control, and efficient material usage. 

   more » « less
4. Pre-Nucleation in High-Shear Wet Granulation

   Kumar, D.S.; Oka, S.; Emady, H.N. (January 2023, Proceedings for 10th International Granulation Workshop)

   Wet granulation can be broken down into three rate processes: Wetting & Nucleation, Consolidation & Growth, and Breakage & Attrition. These stages are often inseparable from each other, which hinders the characterization of the relationship between operating conditions and product properties in wet granulation processes. Single-drop granulation is a form of drop-controlled nucleation intended to isolate the Wetting & Nucleation rate process by allowing a single droplet to form a single granule upon impacting a static powder bed. Single-dropped granules (pre-nucleated granules) were charged to a mixer granulator under varied conditions to observe how the individual rate processes and resulting granulated product are affected by various pre-nucleation conditions. Batches with larger fractions of pre-nucleated granules tended to produce a larger granule size than batches with few or no pre-nucleated granules. Pre-nucleated granules on their own failed to produce a reasonable granular product, but performed well under conditions with standard liquid addition. A difference in granular product can also be identified between the formation mechanisms utilized to produce the pre-nucleated granules. 

   more » « less
5. A Machine Learning-assisted Hybrid Model to Predict Ribbon Solid Fraction, Granule Size Distribution and Throughput in a Dry Granulation Process

   Yan-Shu Huang, David Sixon (July 2023, Computer aided chemical engineering)

   Kokossis, A.; Georgiadis, M.C.; Pistikopoulos, E.N. (Ed.)

   A quantitative model can play an essential role in controlling critical quality attributes of products and in designing the associated processes. One of the challenges in designing a dry granulation process is to find the optimal balance between improving powder flowability and sacrificing powder tabletability, both of which are highly affected by ribbon solid fraction and granule size distribution (GSD). This study is focused on developing a hybrid machine learning (ML)-assisted mechanistic model to predict ribbon solid fraction, GSD, and throughput for the purpose of implementing model predictive control of an integrated continuous dry granulation tableting process. It is found that the predictability of ribbon solid fraction and throughput are improved when modification is made to Johanson’s model by incorporating relationships between roll compaction parameters and ribbon elastic recovery. Such relationships typically are either not considered or assumed to be a constant in the models reported in the literature. To describe the nature of the bimodal size distribution of roller compactor granules instead of only using traditional 𝐷𝐷10, 𝐷𝐷50 and 𝐷𝐷90 values, the GSD is represented by a bimodal Weibull distribution with five fitting parameters. Furthermore, these five GSD parameters are predicted by ML models. The results indicate the ribbon solid fraction and screen size are the two most significant factors affecting GSD. 

   more » « less