Real-Time Image Processing Based Online Feedback Control System for Cooling Batch Crystallization

Research on LIBS online monitoring criteria for aircraft skin laser paint removal based on OPLS-DA

Online monitoring technology plays a pivotal role in advancing the utilization of laser paint removal in aircraft maintenance and automation. Through the utilization of a high-frequency infrared pulse laser paint removal laser-induced breakdown spectroscopy (LIBS) online monitoring platform, this research conducted data collection encompassing 60 sets of LIBS spectra during the paint removal process. Classification and identification models were established employing principal component analysis (PCA), partial least squares discriminant analysis (PLS-DA), and orthogonal partial least squares discriminant analysis (OPLS-DA). These models served as the foundation for creating criteria and rules for the online LIBS monitoring of the controlled paint removal process for aircraft skin. In this research, 12 selected characteristic spectral lines were used to construct the OPLS-DA model, with a predictive root mean square error (RMSEP) of 0.2873. Both full spectrum and feature spectral line data achieved a predictive accuracy of 94.4%. The selection of feature spectral lines maintains predictive performance while significantly reducing the amount of input data. Consequently, this research offers a methodological reference for further advancements in online monitoring technology for laser paint removal in aircraft skin.

Real-time coating thickness measurement and defect recognition of film coated tablets with machine vision and deep learning

This paper presents a system, where images acquired with a digital camera are coupled with image analysis and deep learning to identify and categorize film coating defects and to measure the film coating thickness of tablets. There were 5 different classes of defective tablets, and the YOLOv5 algorithm was utilized to recognize defects, the accuracy of the classification was 98.2%. In order to characterize coating thickness, the diameter of the tablets in pixels was measured, which was used to measure the coating thickness of the tablets. The proposed system can be easily scaled up to match the production capability of continuous film coaters. With the developed technique, the complete screening of the produced tablets can be achieved in real-time resulting in the improvement of quality control.

In Situ Measurement Method Based on Edge Detection and Superpixel for Crystallization Imaging at High-Solid Concentrations

To facilitate measuring crystal sizes during batch crystallization at high-solid concentrations by using an invasive imaging system, an in situ imaging measurement strategy based on edge detection and superpixel is proposed for the ambiguous boundary problem of large amounts of crystals. Firstly, an image filtering is employed to cope with image degradation caused by noise disturbance and suspension turbulence in the crystallizer. Subsequently, an image segmentation method is developed by utilizing improved edge detection and superpixel, which can be easily performed for crystal extraction. Accordingly, crystal size measurement can be developed for evaluation of the crystal size distribution. The experiment results on α-form L-glutamic acid present the effectiveness of the proposed method.

Feedback Control of Crystal Size Distribution for Cooling Batch Crystallization Using Deep Learning-Based Image Analysis

The shape of the crystal size distribution directly determines the quality of crystal products. It is often assumed that distributional properties of crystal size conform to the Gaussian distribution or the log normal distribution. The mean and variance or relative crystal number are widely adopted to describe the crystal size distribution and taken as the control objectives. Therefore, the resulting control methods have difficulties in controlling the crystal size distribution with a general shape. In this article, a novel feedback control system of crystal size distribution based on image analysis is designed for the effective control of crystal size distribution with a general shape. First, a deep learning network-based image analysis method is adopted and implemented to extract the crystal size distribution. Second, the crystal size distribution is approximated by a radial basis function neural network. Consequently, a feedback controller is designed and the tracking control of the target crystal size distribution is finally realized. The results of crystallization experiments demonstrate the effectiveness of the proposed method.

Application of PAT-Based Feedback Control Approaches in Pharmaceutical Crystallization

Crystallization is one of the important unit operations for the separation and purification of solid products in the chemical, pharmaceutical, and pesticide industries, especially for realizing high-end, high-value solid products. The precise control of the solution crystallization process determines the polymorph, crystal shape, size, and size distribution of the crystal product, which is of great significance to improve product quality and production efficiency. In order to develop the crystallization process in a scientific method that is based on process parameters and data, process analysis technology (PAT) has become an important enabling platform. In this paper, we review the development of PAT in the field of crystallization in recent years. Based on the current research status of drug crystallization process control, the monitoring methods and control strategies of feedback control in the crystallization process were systematically summarized. The focus is on the application of model-free feedback control strategies based on the solution and solid information collected by various online monitoring equipment in product engineering, including improving particle size distribution, achieving polymorphic control, and improving purity. In this paper, the challenges of feedback control strategy in the crystallization process are also discussed, and the development trend of the feedback control strategy has been prospected.

Size measurement and prediction for L-glutamic acid crystal growth during stirred crystallization based on imaging analysis

In this paper, a crystal image analysis method is presented to measure and predict crystal sizes, based on cooling crystallization of β-form L-glutamic acid (LGA) by using an in-situ non-invasive imaging system. The proposed method consists of image restoration, image segmentation, crystal size measurement, and size prediction. To cope with the effects of noise pollution, uneven illumination and movement blurring, the image processing method is conducted for segmenting crystal images captured from the stirring reactor. Thus, the crystal size distribution for crystal population is obtained by using a probability density function. In addition, a short-term prediction method is given for crystal sizes. An experimental study on the cooling crystallization process of β-form LGA is shown to demonstrate the effectiveness of the proposed method.

Automated image processing as an analytical tool in cell cryopreservation for bioprocess development

The continuous availability of cells with defined cell characteristics represents a crucial issue in the biopharmaceutical and cell therapy industry. Here, development of cell banks with a long-term stability is essential and ensured by a cryopreservation strategy. The strategy needs to be optimized for each cell application individually and usually comprises controlled freezing, storage at ultra-low temperature, and fast thawing of cells. This approach is implemented by the development of master and working cell banks. Currently, empirical cryopreservation strategy development is standard, but a knowledge-based approach would be highly advantageous. In this article, we report the development of a video-based tool for the characterisation of freezing and thawing behaviour in cryopreservation process to enable a more knowledge-based cryopreservation process development. A successful tool validation was performed with a model cryopreservation process for the β-cell line INS-1E. Performance was evaluated for two working volumes (1.0 mL and 2.0 mL), based on freezing-thawing rates (20 °C to - 80 °C) and cell recovery and increase of biomass, to determine tool flexibility and practicality. Evaluation confirmed flexibility by correctly identifying a delay in freezing and thawing for the larger working volume. Further more, a decrease in cell recovery from 0.94 (± 0.14) % using 1.0 mL working volume to 0.61 (± 0.05) % using a 2.0 mL working volume displays tool practicality. The video-based tool proposed in this study presents a powerful tool for cell-specific optimisation of cryopreservation protocols. This can facilitate faster and more knowledge-based cryopreservation process development In this study, a video-based analytical tool was developed for the characterisation of freezing and thawing behaviour in cryopreservation process development. Evaluation of the practicality and flexibility of the developed tool was done based on a scale-up case study with the cell line INS-1E. Here, the influence of sample working volume on process performance was investigated. Increasing the volume from 1to 2 mL led to a delay in freezing and thawing behaviour which caused cell recovery loss. We believe that the developed tool will facilitate more directed and systematic cryopreservation process development.

Real-time feedback control of twin-screw wet granulation based on image analysis

The present paper reports the first dynamic image analysis-based feedback control of continuous twin-screw wet granulation process. Granulation of the blend of lactose and starch was selected as a model process. The size and size distribution of the obtained particles were successfully monitored by a process camera coupled with an image analysis software developed by the authors. The validation of the developed system showed that the particle size analysis tool can determine the size of the granules with an error of less than 5 µm. The next step was to implement real-time feedback control of the process by controlling the liquid feeding rate of the pump through a PC, based on the real-time determined particle size results. After the establishment of the feedback control, the system could correct different real-life disturbances, creating a Process Analytically Controlled Technology (PACT), which guarantees the real-time monitoring and controlling of the quality of the granules. In the event of changes or bad tendencies in the particle size, the system can automatically compensate the effect of disturbances, ensuring proper product quality. This kind of quality assurance approach is especially important in the case of continuous pharmaceutical technologies.