面向变工况数据填补与软测量的部分迁移网络
Partial transfer learning network for data imputation and soft sensor under various operation conditions
任嘉毅 1陈旭 1赵春晖1
作者信息
- 1. College of Control Science and Engineering,Zhejiang University,Hangzhou 310027,China
- 折叠
摘要
软测量在工业过程的安全运行和产品的质量控制中起着关键作用.在工业过程中,操作条件的切换可能导致训练数据(源域)和测试数据(目标域)之间的分布差异以及维度不一致,从而导致软测量模型失配问题的出现.此外,由于传感器传输失败,可能会引发数据缺失,进而影响软测量的准确性.本文介绍了一种针对不同操作条件下缺失数据的软传感器的部分迁移学习网络(PTL-Net).首先,用源域数据构建了数据填补和软测量模块,专门设计一个紧致性损失来诱导样本特征相互靠近,以减轻从缺失数据映射得到异常特征的影响.然后,提出一种部分迁移策略来减少源数据和目标数据之间的分布差异.所提出的策略选择两个领域之间的公共变量进行部分知识迁移,而不是直接继承所有参数,这可以避免模型结构失配.最后,在核电数据集以及三相流数据上完成了相应的数据填补和软测量性能验证.
Abstract
Soft sensor plays a key role in the safe operation of industrial processes and product quality control.In industrial processes,the switching of operation conditions may lead to distribution discrepancy and dimension inconsistency between the training data(source domain)and testing data(target domain),leading to the soft sensor model mismatch problem.In addition,the data may be incomplete because of sensor transmission failure,where the missing values may influence the accuracy of the soft sensor.This article introduces a partial transfer learning network(PTL-Net)for soft sensors under different operation conditions with missing data.First,the imputation and soft sensor modules are constructed for source domain data,where a compactness loss is designed to induce feature aggregation to alleviate the influence of abnormal features mapped from missing data.Then a partial transfer strategy is proposed to reduce the distribution discrepancy between the source and target data.Furthermore,the proposed strategy selects the common components between two domains for partial knowledge transfer rather than inheriting all the parameters directly,which can overcome the model mismatch problem.The effectiveness of PTL-Net is verified under the nuclear dataset and the three-phase flow process.
关键词
部分迁移/多工况/维数不一致/数据缺失/软测量Key words
partial transfer/various operation conditions/dimension inconsistency/missing data/soft sensor引用本文复制引用
基金项目
国家重点研发计划(2022YFB3304703)
出版年
2023
NETL
NSTL
万方数据