| 引用本文: | 沈飞凤,杨慧中.基于自联想核回归的带离群值化工过程故障检测[J].控制理论与应用,2023,40(3):583~592.[点击复制] |
| SHEN Fei-feng,YANG Hui-zhong.Fault detection for chemical processes with outliers based on auto-associative kernel regression[J].Control Theory and Technology,2023,40(3):583~592.[点击复制] |
|
| 基于自联想核回归的带离群值化工过程故障检测 |
| Fault detection for chemical processes with outliers based on auto-associative kernel regression |
| 摘要点击 1494 全文点击 504 投稿时间：2021-10-23 修订日期：2023-02-20 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/CTA.2022.11013 |
| 2023,40(3):583-592 |
| 中文关键词 离群值 鲁棒白化 自联想核回归 指数加权滑动平均 故障检测 |
| 英文关键词 outliers robust whitening auto-associative kernel regression exponentially weighted moving average fault detection |
| 基金项目 国家自然科学基金项目( 61773181), 中央高校基本科研业务费专项资金项目( JUSRP51733B)资助. |
|
| 中文摘要 |
| 基于数据驱动的故障检测模型通常要求训练数据必须是正常操作条件下的测量值. 然而在实际工业生产
过程中, 即使在正常工况下, 数据集中也难以避免存在离群值. 此时若仍采用传统的基于多元统计分析的方法, 其监
测模型的控制限会受到严重影响, 造成故障漏报. 因此, 为了确保当训练数据包含离群值时, 监测模型仍然呈现较
好的故障检测效果, 本文提出了一种基于自联想核回归的故障检测方法. 首先基于最小化 散度的鲁棒预白化算法
对训练集进行白化计算, 消除变量之间相关性对样本相似度度量的影响. 然后通过自联想核回归算法重构正常工况
下的验证数据, 根据重构误差建立模型监测指标. 为了消除离群值对故障样本重构的影响, 构造截断函数来避免离
群样本参与相似故障数据的重构, 并对所有参与构建Q统计量的残差变量基于指数加权滑动平均方法自适应加权,
得到新的监测统计量. 将该方法运用于田纳西–伊斯曼过程并与其他方法进行比较, 验证了本文所提故障检测算法
的有效性. |
| 英文摘要 |
| The data driven fault detection models usually require that the training data must be measured under normal
operating conditions. However, in the actual industrial processes, it is possible that the collected data set contains outliers
even under normal working conditions. In this case, the control limits of the traditional method based on multivariate
statistical analysis are often heavily influenced by the outliers, which results in a large number of missed failures. Therefore,
in order to ensure that the monitoring model still has good performance even when the training data contains outliers, this
paper proposed a fault detection method based on auto-associative kernel regression (AAKR). First, the training set is
whitened on the basis of a robust whitening algorithm that minimizes divergence to eliminate the influence of correlation
between variables on sample similarity measurement. Then, AAKR reconstructs the validation data under normal working
conditions to obtain the residuals and establish the correct detection index. In order to avoid the influence of outliers on
the reconstructions of faulty test data, a truncation function is constructed to avoid the involvement of outliers similar to
the faulty samples in reconstruction. All residual variables involved in Q statistic construction were weighted based on the
exponentially weighted moving average (EWMA) to obtain the new monitoring statistic. The proposed method is applied
to the Tennessee Eastman (TE) process to verify the effectiveness of the proposed fault detection algorithm. |
|
|
|
|
|