Predictive control of particlesize distribution of crystallization process using deep learning based image analysis

Wang, Liangyong; Zhu, Yaolong; Gan, Chenyang

doi:10.1002/aic.17817

Cited by 4 publications

(3 citation statements)

References 41 publications

(79 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average detection time floated slightly around 10 s, and the fixed average detection time indicated that the computational costs of Mask R‐CNN would not fluctuate severely with image qualities. However, compared to the related work, the processing speed of Mask R‐CNN still needs to be improved to meet the requirements of process control 15 …”

Section: Resultsmentioning

confidence: 99%

“…14 Moreover, the processing speed of image-based ANN can satisfy the process control requirements of solution crystallization. Wang et al proposed a novel nonlinear model predictive control method for the crystallization process using deep-learning based image analysis technology as an online monitoring tool for CSD 15 control. Different types of ANNs have a wide range of capabilities for the analysis of crystal microscopic images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep‐learning based in situ image monitoring crystal polymorph and size distribution: Modeling and validation

Yao,

Liu,

Wan

et al. 2023

AIChE Journal

View full text Add to dashboard Cite

In situ monitoring and closed‐loop control of the solution crystallization process are the modern trends for pharmaceutical development, in which the critical process parameters (CPPs) as well as the product critical quality attributes (CQAs) can be regulated and guaranteed during the manufacturing process. In this study, an in situ image monitoring methodology based on a state‐of‐the‐art deep‐learning model was developed to track the CQAs such as polymorph ratio, two‐dimensional crystal size, and crystal shape in a solvent‐mediated polymorphic transformation (SMPT) process. Coupled with the multidimensional process information, a 2D population balance model (PBM) was developed and validated using the results of the in situ image‐based CQAs analysis. The 2D‐PBM was solved using a high‐resolution finite volume method (HR‐FVM) which could provide a high dimensional particle‐size distribution. Through the validation between the process image analysis and the 2D‐PBM, the accuracy of image analysis was discussed, and the potential and challenges of in situ image analysis were proposed. This work aims to integrate the crystal polymorphism and two‐dimensional crystal size distribution (2D‐CSD) information in the SMPT process using intelligent microscopic image analysis and then to validate the results of neural network processing by solving the numerical solution of the multidimensional PBM.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep‐learning based in situ image monitoring crystal polymorph and size distribution: Modeling and validation

Yao,

Liu,

Wan

et al. 2023

AIChE Journal

View full text Add to dashboard Cite

show abstract

“…Anandan et al developed a controller based on reinforcement learning and applied it to the crystallization of paracetamol to achieve the desired crystal size . Machine learning approaches have also been used to control crystallization processes based on image analysis. − Furthermore, many applications in the literature propose hybrid modeling approaches that use neural networks combined with the population balance. − …”

Section: Introductionmentioning

confidence: 99%

Modeling and Predictive Control of Cooling Crystallization of Potassium Sulfate by Dynamic Image Analysis: Exploring Phenomenological and Machine Learning Approaches

Moraes

Lima

Lage

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Representative mathematical modeling is essential for understanding the batch cooling crystallization processes. Efficient process design and operation are relevant to achieving high-quality criteria and minimizing variation between batches. This work first presents the modeling of batch cooling crystallization based on online dynamic image analysis. A flow-through microscope was used to track the temporal evolution of the crystal population. A population balance modeling (PBM) approach, parameter estimation, and validation were obtained for the batch cooling crystallization of potassium sulfate in water. The performed experiments provided new experimental data, giving dynamic information about the crystal size throughout each run. The kinetic model parameters for crystal nucleation and growth were estimated using a hybrid optimization algorithm, followed by the confidence region construction using a more exploratory particle swarm algorithm. In the parameter estimation framework, in addition to solute concentration, the first fourth-order moments computed throughout all experiments were included in the objective function. A linear size-dependent growth rate was found to capture well the dynamics of the potassium sulfate crystal size distribution. The experimental results evidenced that the crystal shape of potassium sulfate is predominantly constant, allowing the adequacy of the developed model. The validated PBM was also employed as a digital twin of the crystallization process to develop a machine-learning-based control for the process. Then, a surrogate model based on a recurrent neural network, called an echo state network (ESN), was applied in a nonlinear model predictive controller approach (ESN-NMPC). The ESN model could predict the moments of the population balance model up to five steps (5 min) forward. The ESN-NMPC achieved the desired control scenarios for the crystal size and its coefficient of variation. Its performance was comparable to the controller that uses the PBM as the internal model (PB-NMPC).

show abstract

Design and optimization of spherical agglomeration process based on machine learning strategy

Zhao,

Liu,

Guo

et al. 2024

AIChE Journal

View full text Add to dashboard Cite

Spherical particles stand out as high‐value products with superior macroscopic properties and enhanced downstream processing efficiency. In this study, an integrated digital design strategy, combining artificial neural networks (ANN) and genetic algorithms (GA) has been employed to optimize the spherical agglomeration (SA) process. Initially, a dataset of benzoic acid SA processes was created, which was subsequently employed for training and testing the ANN model. An environmental impact sustainability index (STI) was constructed to assess the environmental effects associated with each operational variable in the SA process. To attain multi‐objective optimization, a GA was employed in combination with the ANN model. In addition, a Score function was formulated to generate Pareto fronts, tailored to meet the specific needs of real scenarios, considering variations in the assigned weights. Furthermore, the model was adapted for aspirin SA process, enhancing predictive abilities with only 20% of original data on operating conditions.

show abstract

Predictive control of particlesize distribution of crystallization process using deep learning based image analysis

Cited by 4 publications

References 41 publications

Deep‐learning based in situ image monitoring crystal polymorph and size distribution: Modeling and validation

Deep‐learning based in situ image monitoring crystal polymorph and size distribution: Modeling and validation

Modeling and Predictive Control of Cooling Crystallization of Potassium Sulfate by Dynamic Image Analysis: Exploring Phenomenological and Machine Learning Approaches

Design and optimization of spherical agglomeration process based on machine learning strategy

Contact Info

Product

Resources

About