摘要
在发酵过程中 ,罐批异常 (如染菌 )会导致产率和产品质量的下降 ,如果能及时给出预警 ,就能采取相应措施避免或减少经济损失。利用三层BP网络 ,以头孢菌素C发酵为例 ,对罐批进行了超前 3步预报 ,比较了正常罐批和异常罐批的预报误差 ,给出了异常罐批的三个特征 ,并利用这些特征和其它辅助信息 ,成功地对异常罐批进行了故障早诊断。
During fermentation, it is often difficult to detect the abnormalities, for example, caused by contamination on_line. Instead, the faults were detected usually by off_line laboratory analysis or other ways, which in most cases, is too late to remedy the situation. In this paper, a simple three_layers BP network was used for the early prediction of the amount of product, based on the difference in prediction errors between normal and abnormal charges and other accessorial information, such as profit function and pH value. In addition, three indications characteristic to abnormal charge are incorporated in practical operation. The prediction for Cephalosporin C Fed_batch Fermentation in a Chinese pharmaceutical factory was studied in details as an example and the result shows the abnormal charge can be discovered early successfully using the method.
出处
《生物工程学报》
CAS
CSCD
北大核心
2005年第1期102-106,共5页
Chinese Journal of Biotechnology
基金
国家自然科学基金资助项目 (No .60 3 75 0 3 9)
华东理工大学生物反应器国家重点实验室开放基金。~~
关键词
发酵过程
神经网络
故障诊断
预报误差
fermentation process, neural networks, fault detection, prediction error
