Optimization of dropping process of Xuesaitong dropping pills based on quality by design concept and machine vision.

OBJECTIVE: The drooping process of the Xuesaitong dropping pills (XDPs) was optimized based on quality by design concept. Meanwhile, a machine vision (MV) technology was creatively introduced in this study to predict the critical quality attributes (CQAs) rapidly and accurately. SIGNIFICANCE: This study improves the understanding of dropping process, and has reference value for the guidance of pharmaceutical process research and industrial production. METHODS: The study mainly consisted of three stages: the first stage involved the prediction model to establish and evaluate the CQAs, and the second stage involved assessing the quantitative relationships between critical process parameters (CPPs) and CQAs by the mathematical models that were established through the Box-Behnken experimental design. Finally, a probability-based design space for the dropping process was calculated and verified according to the qualification criteria of each quality attribute. RESULTS: The results show that the prediction accuracy of the random forest (RF) model was high and met the analysis requirements, and the CQAs of dropping pills can meet the standard by running in the design space. CONCLUSION: The MV technology developed in this study can be applied to the optimization process of the XDPs. In addition, the operation in the design space can not only ensure the quality of XDPs to meet the criteria, but also help to improve the consistency of XDPs.

A feasibility research on the application of machine vision technology in appearance quality inspection of Xuesaitong dropping pills.

Defect detection is a critical issue for the quality control of dropping pills, which is a special dosage form of traditional Chinese Medicine. Machine vision is a non-destructing testing technology and cost-effective with high accuracy that can be used to predict the detects of both interior and exterior of the sample by employing the camera. In this research, a machine vision system for inspecting quality of the Xuesaitong dropping pills (XDPs) that include non-spherical, abnormal sizes and colors was developed to evaluate the appearance quality of XDPs rapidly and accurately. Firstly, 270 images of XDPs containing qualified and three different types of defects were collected. Subsequently, the processing of the XDPs images were carried out. Finally, Three defecting categories classification models were developed and compared based on contour and color features. The experimental results showed that the Random Forest outperformed all the explored models and the classification accuracy for non-spherical, abnormal sizes and colors reached 98.52%, 100.00% and 100.00%, respectively. In summary, the method established in this research is scientific, reliable, fast and accurate, which has great application potential and can provide technical support for the automatic defect detection of dropping pills.

[Identification of critical influencing factors in dropping process of Xuesaitong Dropping Pills].

With the dropping process of Xuesaitong Dropping Pills(XDP) as the study object, critical factors affecting the quality indicators of pill pass rate, average weight of drop pills and roundness were screened out, so as to deepen the understanding of the dropping process. The critical process units, critical quality attributes and potential critical process influencing factors of XDP were determined by risk analysis and prior knowledge, and then the critical influencing factors were screened out by Plackett-Burman design. First, according to the risk assessment, the critical technique of XDP preparation process was dropping, and then the critical quality attributes of dropping process were pill pass rate, average weight of drop pills and roundness. Then, according to fishbone diagram and failure mode and effects analysis(FMEA), potential critical influencing factors were determined as flow rate, matrix ratio, solid-liquid ratio, feed-liquid temperature, top temperature of condensate, bottom temperature of condensate and dropping distance. Finally, among these seven potential factors, the critical influencing factors were determined as material liquid ratio, dropping distance, top temperature of condensate, bottom temperature of condensate. This study revealed the potential of Plackett-Burman design in screening and understanding the influence of selected factors on XDP dropping process, which could provide a reference for studying the dropping process.

Identification of critical influencing factors in dropping process of Xuesaitong Dropping Pills / 中国中药杂志

With the dropping process of Xuesaitong Dropping Pills(XDP) as the study object, critical factors affecting the quality indicators of pill pass rate, average weight of drop pills and roundness were screened out, so as to deepen the understanding of the dropping process. The critical process units, critical quality attributes and potential critical process influencing factors of XDP were determined by risk analysis and prior knowledge, and then the critical influencing factors were screened out by Plackett-Burman design. First, according to the risk assessment, the critical technique of XDP preparation process was dropping, and then the critical quality attributes of dropping process were pill pass rate, average weight of drop pills and roundness. Then, according to fishbone diagram and failure mode and effects analysis(FMEA), potential critical influencing factors were determined as flow rate, matrix ratio, solid-liquid ratio, feed-liquid temperature, top temperature of condensate, bottom temperature of condensate and dropping distance. Finally, among these seven potential factors, the critical influencing factors were determined as material liquid ratio, dropping distance, top temperature of condensate, bottom temperature of condensate. This study revealed the potential of Plackett-Burman design in screening and understanding the influence of selected factors on XDP dropping process, which could provide a reference for studying the dropping process.