Development of multiple-step soft-sensors using a Gaussian process model with application for fault prognosis
详细信息 查看全文
- 作者：Yiqi Liua ; aulyq@scut.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Hongjun Xiaoa ; Yongping Panb ; biepany@nus.edu.sg" class="auth_mail" title="E-mail the corresponding author ; Daoping Huanga ; audhuang@scut.edu.cn" class="auth_mail" title="E-mail the corresponding author ; Qilin Wangc ; q.wang@awmc.uq.edu.au" class="auth_mail" title="E-mail the corresponding author
- 关键词：Soft-sensors ; Fault diagnosis ; Fault prognosis ; Multi-step-ahead prediction ; Wastewater
- 刊名：Chemometrics and Intelligent Laboratory Systems
- 出版年：2016
- 出版时间：15 October 2016
- 年：2016
- 卷：157
- 期：Complete
- 页码：85-95
- 全文大小：2275 K
文摘
- class="listitem" id="list_l0005">
- class="label">•
A GPR is used for multi-step prediction depending on the data trend.
- class="label">•
Direct, Recursive and Direct-recursive methods are employed to generalize GPR model.
- class="label">•
The uncertainty information generated from GPR facilitates fault pre-caution.
- class="label">•
Multi-step prediction can support fault diagnosis and prognosis efficiently.