Near-infrared spectroscopy monitoring and control of the fluidized bed granulation and coating processes-A review

Implementation of near-infrared spectroscopy and convolutional neural networks for predicting particle size distribution in fluidized bed granulation

Monitoring the particle size distribution (PSD) is crucial for controlling product quality during fluidized bed granulation. This paper proposed a rapid analytical method that quantifies the D10, D50, and D90 values using a Convolutional Block Attention Module-Convolutional Neural Network (CBAM-CNN) framework tailored for deep learning with near-infrared (NIR) spectroscopy. This innovative framework, which fuses CBAM with CNN, excels at extracting intricate features while prioritizing crucial ones, thereby facilitating the creation of a robust multi-output regression model. To expand the training dataset, we incorporated the C-Mixup algorithm, ensuring that the deep learning model was trained comprehensively. Additionally, the Bayesian optimization algorithm was introduced to optimize the hyperparameters, improving the prediction performance of the deep learning model. Compared with the commonly used Partial Least Squares (PLS), Support Vector Machine (SVM), and Artificial Neural Network (ANN) models, the CBAM-CNN model yielded higher prediction accuracy. Furthermore, the CBAM-CNN model avoided spectral preprocessing, preserved the spectral information to the maximum extent, and returned multiple predicted values at one time without degrading the prediction accuracy. Therefore, the CBAM-CNN model showed better prediction performance and modeling convenience for analyzing PSD values in fluidized bed granulation.

Evaluation of near-infrared spectroscopy as a contactless method for health monitoring of resin-based coating materials applied to concrete surfaces

The surfaces of concrete structures are often coated with protective materials to minimize corrosion and weathering-based deterioration. Therefore, it is important to monitor the aging of the coating materials and their overall condition to extend the service lifetime of the structure effectively. Near-infrared spectroscopy (NIRS) is a contactless, nondestructive, rapid, and convenient method for material characterization; therefore, it is useful for onsite inspection of coating materials. Hence, in this study, we attempt to determine whether NIRS can be used for simple inspection for health monitoring of organic resin-based coating materials. In addition to identifying different severities of peeling damage, we characterize the ultraviolet-induced deterioration of coating materials with different thicknesses using diffuse reflection spectra acquired in the near-infrared wavelength region. For independent comparison with the NIR spectra, the state of the coating materials on the mortar specimens was analyzed using a combination of Fourier-transform infrared spectroscopy and scanning electron microscopy, while the state of the underlying mortar specimens was analyzed using permeability and salt-water immersion tests. The results confirm that the NIRS could detect the degradation of coating materials at early stages of deterioration before their permeability had been affected. NIRS offers the possibility of intermittent monitoring of coating deterioration. In addition, because the NIR spectrometer is portable, it can help in inspecting high-rise areas and areas that are difficult to reach. Therefore, we believe that NIRS is a simple, safe, and inexpensive method for inspection of surface coating materials.

Real-time in-line prediction of drug loading and release rate in the coating process of diclofenac sodium spheres based on near infrared spectroscopy

The preparation of diclofenac sodium spheres by fluidized bed is a common production mode for the pharmaceutical preparations at present, but the critical material attributes in the production process is mostly analyzed off-line, which is time-consuming and laborious, and the analysis results lag behind. In this paper, the real-time in-line prediction of drug loading of diclofenac sodium and the release rate during the coating process was realized by using near infrared spectroscopy. For the best near infrared spectroscopy (NIRS) model of drug loading, R²_cv, R²_p, RMSECV, RMSEP were 0.9874, 0.9973, 0.002549 mg/g, 0.001515 mg/g respectively. For the best NIRS model of three release time points, the R²_cv, R²_p, RMSECV and RMSEP were 0.9755, 0.9823, 3.233%, 4.500%; 0.9358, 0.9965, 2.598%, 0.7939% and 0.9867, 0.9927, 0.4085%, 0.4726% respectively. And the analytical ability of these model was verified. The organic combination of these two parts of work constituted an important basis for ensuring the safety and effectiveness of diclofenac sodium spheres from the perspective of production process.

Experimental study on the scale-up of a multi-ring inclined nozzle spout-fluid bed by electrical capacitance tomography

Scale-up studies of fluidized beds are important for numerous fields. Fluidization in a multi-ring inclined nozzle spout-fluid bed (MRIN spout-fluid bed) is one of the most critical factors that affect the coating efficiency and uniformity of tri-structural isotropic (TRISO) nuclear particles in the fluidized bed chemical vapor deposition (FB-CVD) process. In this work, the flow pattern similarity principle was proposed to scale up a specially designed spout-fluid bed, which was aimed at maintaining the gas-solid contact efficiency, and was validated by electrical capacitance tomography (ECT) measurements. First, the traditional ECT method was developed for the specially designed MRIN spout-fluid bed according to the filling method. Then, the reconstruction algorithms were updated using the alternating direction multiplier method (ADMM) by introducing optimization constraints. The fluidization laws were investigated for different superficial gas velocities and distributor structures. We found that the gas distributor structure affected the merge point of the jets, which played an essential role in fluidization pattern changes. The statistically-based coefficient of variation (Cv) was proposed to distinguish the different flow patterns. Multi-ring spouting was then selected as a typical flow pattern for good fluidization and mixing, where the Cv ranged from 0.25 to 0.65. Then, the optimal design principles for the enlarged spout-fluid bed gas distributor were obtained. We determined that a smaller nozzle diameter (0.71d 0), larger nozzle spacing (1.12x 0), and slightly inclined angle (1.50θ 0) could improve fluidization, and that nozzle spacing was the most important factor. This study may be beneficial for the industrial design of the FB-CVD process and for the fabrication of high-density nuclear fuel particles. Additionally, it could be presented to a more general audience for scaling-up fluidized beds with a complex distributor, which would be beneficial for the fluidization research community.

Industrial application of QbD and NIR chemometric models in quality improvement of immediate release tablets

Quality by Design (QbD) and chemometric models are different sides of the same coin. While QbD models utilize experimentally designed settings for optimization of some quality attributes, these settings can also be utilized for chemometric prediction of the same attributes. We aimed to synchronize optimization of comparative dissolution results of carvedilol immediate release tablets with chemometric prediction of dissolution profile and content uniformity of the product. As an industrial application, selection of variables for optimization was done by performing risk assessment utilizing the archived product records at the pharmaceutical site. Experimental tablets were produced with 20 different settings with the variables being contents of sucrose, sodium starch glycolate, lactose monohydrate, and avicel Ph 101. Contents of the excipients were modelled with F1 dissimilarity factor and F2 similarity factor in HCL, acetate, and USP dissolution media to determine the design space. We initiatively utilized Partial Least Square based Structural Equation Modelling (PLS-SEM) to explore how the excipients and their NIR records explained dissolution of the product. Finally, the optimized formula was utilized with varied content of carvedilol for chemometric prediction of the content uniformity.

Application of Near-Infrared Spectroscopy Analysis Technology to Total Nucleosides Quality Control in the Fermented Cordyceps Powder Production Process

Product quality control is a prerequisite for ensuring safety, effectiveness, and stability. However, because of the different strain species and fermentation processes, there was a significant difference in quality. As a result, they should be clearly distinguished in clinical use. Among them, the fermentation process is critical to achieving consistent product quality. This study aims to introduce near-infrared spectroscopy analysis technology into the production process of fermented Cordyceps powder, including strain culture, strain passage, strain fermentation, strain filtration, strain drying, strain pulverizing, and strain mixing. First, high performance liquid chromatography (HPLC) was used to measure the total nucleosides content in the production process of 30 batches of fermented Cordyceps powder, including uracil, uridine, adenine, guanosine, adenosine, and the process stability and interbatch consistency were analyzed with traditional Chinese medicine (TCM) fingerprinting, followed by the near-infrared spectroscopy (NIRS) combined with partial least squares regression (PLSR) to establish a quantitative analysis model of total nucleosides for online process monitoring of fermented Cordyceps powder preparation products. The model parameters indicate that the established model with good robustness and high measurement precision. It further clarifies that the model can be used for online process monitoring of fermented Cordyceps powder preparation products.

Empirical prediction model based process optimization for droplet size and spraying angle during pharmaceutical fluidized bed granulation

The objective of this study was to predict the droplet size and the spraying angle during the process of binder atomization in pharmaceutical fluidized bed granulation using an empirical model. The effects of the binder viscosity, the atomization pressure, and the spray rate on the droplet size and the spraying angle were investigated using a response surface central composite design and analysis of variance. Prediction models for droplet size and spraying angle were then established using stepwise regression analysis and were validated by comparing the measured and predicted values. The results showed that the droplet size model and the spraying angle model were well established, with an R² of 0.93 (p < 0.0001) and a root mean square error (RMSE) of 10.10, and an R² of 0.82 (p < 0.0001) and an RMSE of 3.69, respectively. The error between the measured and predicted values of the droplet size and the spraying angle were less than 10%, indicating that the established models were accurate. The results of the present study were significant in predicting the droplet size and spraying angle in the process of pharmaceutical fluidized bed granulation.

Fast, Spectroscopy-Based Prediction of In Vitro Dissolution Profile of Extended Release Tablets Using Artificial Neural Networks

The pharmaceutical industry has never seen such a vast development in process analytical methods as in the last decade. The application of near-infrared (NIR) and Raman spectroscopy in monitoring production lines has also become widespread. This work aims to utilize the large amount of information collected by these methods by building an artificial neural network (ANN) model that can predict the dissolution profile of the scanned tablets. An extended release formulation containing drotaverine (DR) as a model drug was developed and tablets were produced with 37 different settings, with the variables being the DR content, the hydroxypropyl methylcellulose (HPMC) content and compression force. NIR and Raman spectra of the tablets were recorded in both the transmission and reflection method. The spectra were used to build a partial least squares prediction model for the DR and HPMC content. The ANN model used these predicted values, along with the measured compression force, as input data. It was found that models based on both NIR and Raman spectra were capable of predicting the dissolution profile of the test tablets within the acceptance limit of the f2 difference factor. The performance of these ANN models was compared to PLS models using the same data as input, and the prediction of the ANN models was found to be more accurate. The proposed method accomplishes the prediction of the dissolution profile of extended release tablets using either NIR or Raman spectra.

Real-time monitoring of particle size distribution in a continuous granulation and drying process by near infrared spectroscopy

In continuous granulation, it can be important to control granules particle size distribution (PSD), as it may affect final product quality. Near infrared spectroscopy (NIRS) is already a routine analytical procedure within pharmaceutical continuous manufacturing for the in-line analysis of chemical material-characteristics. Consequently, the extraction of additional information related to granules' physical properties like particle size distribution is tempting, as it would enhance process knowledge without the need for new capital investments. Three in-line NIRS methods were developed via partial least squares regression, to predict dried granules PSD-fractions X10, X50, and X90 within a GMP-qualified continuous twin-screw wet granulation and fluid-bed drying process. Methods were developed for the size range of 20-234 µm (X10), 98-1017 µm (X50), and 748-2297 µm (X90) and assessed with one internal and three external validation datasets in agreement with current guidelines on NIRS. Internal validation indicated root mean square error of predictions (RMSEPs) of 17 µm, 97 µm, and 174 µm, for PSD X10, X50, and X90 respectively, with acceptable linearity, slope, and bias. Furthermore, the ratio of prediction to deviation (RPD), the ratio of prediction error to laboratory error (PRL), and the range error ratio (RER) were evaluated, with all values within the acceptance range for adequate to good NIR methods (1.75 > RPD < 3, PRL ≤ 2, RER ≥ 10). Methods applicability to in-line processes and their robustness towards water content and active pharmaceutical ingredient content was further demonstrated with three independent in-line datasets in real-time, showing good agreement between predicted and reference values. In summary, methods demonstrated to be sufficient for their intended purpose to monitor trends and sudden changes in dried granules PSD during continuous granulation and drying. Because of their fast response time, they are unique tools to characterize the dynamic behavior and navigate the agglomeration state of the material in static and transient process conditions during continuous granulation and drying.

Development of a NIR Method for the In-Line Quantification of the Total Polyphenolic Content: A Study Applied on Ajuga genevensis L. Dry Extract Obtained in a Fluid Bed Process

This study describes an innovative in-line near-infrared (NIR) process monitoring method for the quantification of the total polyphenolic content (TPC) of Ajuga genevensis dry extracts. The dry extract was obtained in a fluidized bed processor, by spraying and adsorbing a liquid extract onto an inert powder support. NIR spectra were recorded continuously during the extract’s spraying process. For the calibration of the in-line TPC quantification method, samples were collected during the entire process. The TPC of each sample was assessed spectroscopically, by applying a UV-Vis reference method. The obtained values were further used in order to develop a quality OPLS prediction model by correlating them with the corresponding NIR spectra. The final dry extract registered good flowability and compressibility properties, a concentration in active principles three times higher than the one of the liquid extract and an overall process yield of 85%. The average TPC’s recovery of the NIR in-line prediction method, compared with the reference UV-Vis one, was 98.7%, indicating a reliable monitoring method which provided accurate predictions of the TPC during the process, permitting a good process overview and enabling us to establish the process’s end point at the exact moment when the product reaches the desired TPC concentration.

Fault Detection Based on Near-Infrared Spectra for the Oil Desalting Process

The fault detection problem of the oil desalting process is investigated in this paper. Different from the traditional fault detection approaches based on measurable process variables, near-infrared (NIR) spectroscopy is applied to acquire the process fault information from the molecular vibrational signal. With the molecular spectra data, principal component analysis was explored to calculate the Hotelling T² and squared prediction error, which act as fault indicators. Compared with the traditional fault detection approach based on measurable process variables, NIR spectra-based fault detection illustrates more sensitivity to early failure because of the fact that the changes in the molecular level can be identified earlier than the physical appearances on the process. The application results show that the detection time of the proposed method is earlier than the traditional method by about 200 min.