Feedback Control of Crystal Characteristics Based on Deep Learning Image Analysis

doi:10.12068/j.issn.1005-3026.2022.12.003

Abstract

Abstract: Aiming at the online control of crystal size expectation and standard deviation characteristics， an online feedback control method based on deep learning image analysis is proposed. Firstly， the crystal image analysis method using deep learning neural network is introduced to analyze the shape and size of crystals online. Then， mathematical statistical analysis is performed to obtain the size expectation and standard deviation of a certain batch of crystals. Finally， a feedback controller combining path tracking algorithm and PID algorithm is designed to deal with under-input characteristics， so that the target size expectation and standard deviation is obtained. The effectiveness and feasibility of the proposed method is verified by the alum cooling crystallization experiment.

Key words: cooling crystallization; crystal characteristics; image analysis; path tracking; online feedback control

CLC Number:

TP273

WANG Liang-yong， ZHU Yao-long， GAN Chen-yang. Feedback Control of Crystal Characteristics Based on Deep Learning Image Analysis[J]. Journal of Northeastern University(Natural Science), 2022, 43(12): 1688-1693.

References

[1]赵绍磊，王耀国，张腾，等.制药结晶中的先进过程控制［J］.化工学报，2020，71(2):459-474.(Zhao Shao-lei，Wang Yao-guo，Zhang Teng，et al.Advanced process control in pharmaceutical crystallization［J］.CIESC Journal，2020，71(2):459-474.)
[2]Gao Z G，Rohani S，Gong J B，et al.Recent developments in the crystallization process:toward the pharmaceutical industry［J］.Engineering，2017，3(3):343-353.
[3]Crowley T，Edward S，Meadows E，et al.Control of particle size distribution described by a population balance model of semibatch emulsion polymerization［J］.Journal of Process Control，2000，10(5):419-432.
[4]Nagy Z K，Fevotte G，Kramer H，et al.Recent advances in the monitoring，modelling and control of crystallization systems［J］.Chemical Engineering Research and Design，2013，91(10):1903-1922.
[5]Ruf A，Worlitschek J，Mazzotti M.Modeling and experimental analysis of PSD measurements through FBRM［J］.Particle & Particle Systems Characterization，2000，17(4):167-179.
[6]Gao Z G，Wu Y Y，Bao Y，et al.Image analysis for in-line measurement of multidimensional size，shape，and polymorphic transformation of l-glutamic acid using deep learning-based image segmentation and classification［J］.Crystal Growth & Design，2018，18(8):4275-4281.
[7]Manee V，Zhu W，Romagnoli J A.A deep learning image-based sensor for real-time crystal size distribution characterization［J］.Industrial & Engineering Chemistry Research，2019，58(51):23175-23186.
[8]Beckman J R，Randolph A D.Crystal size distribution dynamics in a classified crystallizer.Part II:simulated control of crystal size distribution［J］.AIChE Journal，1977，23(4):510-520.
[9]Rawlings J B，Miller S M，Witkowski W R.Model identification and control of solution crystallization processes:a review［J］.Industrial & Engineering Chemistry Research，1993，32(7):1275-1296.
[10]Hermanto M W，Chiu M S，Braatz R D.Nonlinear model predictive control for the polymorphic transformation of l-glutamic acid crystals［J］.AIChE Journal，2009，55(10):2631-2645.
[11]Mesbah A，Landlust J，Huesman A，et al.A model-based control framework for industrial batch crystallization processes［J］.Chemical Engineering Research & Design，2010，88(9):1223-1233.
[12]Mesbah A，Nagy Z K，Huesman A，et al.Nonlinear model-based control of a semi-industrial batch crystallizer using a population balance modeling framework［J］.IEEE Transactions on Control Systems Technology，2012，20(5):1188-1201.
[13]Ghadipasha N，Romagnoli J A，Tronci S，et al.A model-based approach for controlling particle size distribution in combined cooling-antisolvent crystallization processes［J］.Chemical Engineering Science，2018，190:260-272.
[14]Szilágyi B，Agachi P S，Nagy Z K.Chord length distribution based modeling and adaptive model predictive control of batch crystallization processes using high fidelity full population balance models［J］.Industrial & Engineering Chemistry Research，2018，57(9):3320-3332.
[15]Nagy Z K，Braatz R D.Advances and new directions in crystallization control［J］.Annual Review of Chemical and Biomolecular Engineering，2012，3(1):55-75.
[16]Bakar M A，Nagy Z K，Saleemi A N，et al.The impact of direct nucleation control on crystal size distribution in pharmaceutical crystallization processes［J］.Crystal Growth & Design，2009，9(3):1378-1384.
[17]Btschi S，Rajagopalan A K，Morari M，et al.Feedback control for the size and shape evolution of needle-like crystals in suspension.IV:modeling and control of dissolution［J］.Crystal Growth & Design，2019，19(5):2845-2861.