| 基于MNNPLS的间歇过程的故障诊断 |
| |
| 引用本文： | 郭磊,赵忠盖,刘飞. 基于MNNPLS的间歇过程的故障诊断[J]. 江南大学学报(自然科学版), 2011, 10(3): 253-257 |
| |
| 作者姓名： | 郭磊 赵忠盖 刘飞 |
| |
| 作者单位： | 江南大学轻工过程先进控制教育部重点实验室,江苏无锡,214222 |
| |
| 基金项目： | 教育部博士点新教师基金项目(200802951038) |
| |
| 摘 要： | 针对间歇生产过程的特点及多向部分最小二乘在故障诊断中存在的问题,提出了一种多向神经网络部分最小二乘方法,实现对间歇过程的在线监控和故障诊断。该方法结合了部分最小二乘的鲁棒性和神经网络表现输入输出非线性关系的能力,提高了模型的预测精度。将此方法应用于监测青霉素发酵过程中,仿真结果表明,它比传统多向部分最小二乘方法能更及时、准确地检测到故障。
|
| 关 键 词： | 间歇过程 部分最小二乘 神经网络部分最小二乘 故障诊断 |
Fault Diagnosis for Batch Processes Based on MNNPLS |
| |
| GUO Lei,ZHAO Zhong-gai,LIU Fei. Fault Diagnosis for Batch Processes Based on MNNPLS[J]. Journal of Southern Yangtze University:Natural Science Edition, 2011, 10(3): 253-257 |
| |
| Authors: | GUO Lei ZHAO Zhong-gai LIU Fei |
| |
| Affiliation: | GUO Lei,ZHAO Zhong-gai,LIU Fei(Key Laboratory of Advanced Process Control for Light Industry,Ministry of Education,Jiangnan University,Wuxi 214122,China) |
| |
| Abstract: | In view of characteristics of batch process and the drawbacks of traditional multi-way partial least squares(MPLS),an improved statistical batch monitoring approach for fault diagnosing called multi-way neural networks partial least squares(MNNPLS) is proposed.The method combines the robust properties of partial least squares(PLS) with the capacity of disposing nonlinear relationship of neural network to improve the prediction accuracy of the model.The proposed method is applied to detecting and identifying... |
| |
| Keywords: | batch process PLS MNNPLS fault diagnosis |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
