Development of a Raman method to follow the evolution of coating thickness of pellets

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.

Assessment of Mini-Tablets Coating Uniformity as a Function of Fluid Bed Coater Inlet Conditions

This study concerned the quality of mini-tablets’ coating uniformity obtained by either the bottom spray chamber with a classical Wurster distributor (CW) or a swirl distributor (SW). Mini-tablets with a diameter of 2.0, 2.5, and 3.0 mm were coated with hypromellose using two different inlet air distributors as well as inlet airflow rates (130 and 156 m³/h). Tartrazine was used as a colorant in the coating layer and the coating uniformity was assessed by spectrophotometric analysis of solutions obtained after disintegration of the mini-tablets (n = 100). Higher uniformity of coating material distribution among the mini-tablets was observed in the case of SW distributor, even for the biggest mini-tablets (d = 3.0 mm), with an RSD no larger than 5.0%. Additionally, coating thickness was evaluated by colorimetric analysis (n = 1000), using a scanner method, and expressed as a hue value. A high correlation (R = 0.993) between inter-tablet variability of hue and UV-Vis results was obtained. Mini-tablets were successfully coated in a fluid bed system using both a classical Wurster distributor as well as a swirl generator. However, regardless of the mini-tablets’ diameter, better film uniformity was achieved in the case of a distributor with a swirl generator.

Development of a PAT tool for monitoring the Wurster coater performance

Real-time process analytical technology (PAT) is proposed as an effective approach for monitoring the performance of a Wurster coater. The coater was used for coating of 0.78 mm pharmaceutical pellets. The coating solution consisted of Hydroxypropyl methylcellulose/Poly ethylene glycol. During the coating process, small amounts of pellets (∼2 g) were sampled at 10 min. intervals and the pressure fluctuations were recorded at the same time. The signals were analyzed using the wavelet transform (WT) and decomposed into different sub-signals. Principal component analysis (PCA) was employed to the energies of these sub-signals, whose outliers were eliminated using the Mahalanobis distance method. The reference coating thickness data were obtained via spectrophotometry during the coating process. The partial least squares (PLS) regression was incorporated with the PCA for the development of a model for prediction of the coating thickness. The PLS regression revealed that the pressure fluctuations can be used to evaluate the thickness with a good precision. This study demonstrated the applicability of pressure fluctuations for the prediction of the coating thickness. This method can be regarded as a new robust, fast and non-intrusive PAT approach for monitoring the coating process which can be easily used by engineers and practitioners.

Raman Spectroscopy for Process Analytical Technologies of Pharmaceutical Secondary Manufacturing

As the process analytical technology (PAT) mindset is progressively introduced and adopted by the pharmaceutical companies, there is an increasing demand for effective and versatile real-time analyzers to address the quality assurance challenges of drug manufacturing. In the last decades, Raman spectroscopy has emerged as one of the most promising tools for non-destructive and fast characterization of the pharmaceutical processes. This review summarizes the achieved results of the real-time application of Raman spectroscopy in the field of the secondary manufacturing of pharmaceutical solid dosage forms, covering the most common secondary process steps of a tablet production line. In addition, the feasibility of Raman spectroscopy for real-time control is critically reviewed, and challenges and possible approaches to moving from real-time monitoring to process analytically controlled technologies (PACT) are discussed.