欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对间歇过程的在线故障诊断需要预测过程变量的未知输出问题,提出了一种数据展开和故障分类器数据选择相结合的方法。首先,对包含批次信息的三维数据进行数据展开,对间歇过程的多阶段分别建立PCA模型并进行过程的故障监测;然后,选取故障发生时刻之后的部分长度采样时刻的数据进行故障的特征提取,离线建立LSSVM的故障分类器模型;最后,通过故障分类器进行在线故障诊断,实现故障分类并确定发生了某类故障。该方法提高了间歇过程在线故障诊断的实时性和准确性,通过青霉素发酵仿真过程的应用,进一步验证所提方法的可行性和有效性。
英文摘要：
Considering that online fault diagnosis of batch process involves the prediction of unknown output variables, a fault diagnosis approach based on data expansion and fault classifier data selection is therefore proposed in this paper. Firstly, the three-dimensional dataset which contains batch information is unfolded to establish multi-stage PCA models for fault detection. Then, a few continuous time samples after the fault occurred moment are selected for fault feature extraction, and a LSSVM fault classification model is built during the offline stage afterwards. Finally, online fault diagnosis is realized through the established fault classifier, and classification and identification of fault can be achieved. For batch process, the real-time performance and accuracy of fault diagnosis can all be en- hanced, and the feasibility and effectiveness of the proposed method are further verified through an application of the penicillin fermen- tation process.
同期刊论文项目
同项目期刊论文
Effectof temperature on Chinese rice wine brewing with high concentration pre-steamedwhole sticky ri
期刊信息
位置：