 |
International Society of Science and Applied Technologies |
| Prediction of Quality Risk in the Production Process of Chinese Herbal Medicine Pieces Based on Optimized BP Neural Network | ||||
| Author | Liming Lou
|
|||
| Co-Author(s) | Ying Bai; Kaiye Gao
|
|||
| Abstract | This study proposes a prediction method based on genetic algorithm (GA) optimized back propagation neural network (BPNN) for addressing the issue of quality risk prediction in the production process of traditional Chinese medicine (TCM) decoction pieces. The traditional BP neural network suffers from limitations such as slow convergence speed and susceptibility to local optima in predicting the quality risk of TCM decoction piece production. In this study, GA is employed to optimize the connection weights of the BP neural network, aiming to enhance prediction accuracy and stability. The results indicate that after optimization by GA, the mean square error of the BP neural network is significantly reduced, the coefficient of determination is notably improved, and it exhibits stronger generalization ability in cross-validation. Therefore, the GA-optimized BP neural network can effectively predict the quality risk in the production process of TCM decoction pieces.
|
|||
| Keywords | Back propagation Neural Network (BPNN), Genetic Algorithm (GA), Traditional Chinese Medicine (TCM) Decoction Pieces, Quality Risk, Prediction | |||
| Article #: RQD2024-234 | ||||
Proceedings of 29th ISSAT International Conference on Reliability & Quality in Design |