小样本下基于领域自适应的间歇过程质量预测

摘要针对间歇过程因样本量不足导致预测精度低的问题,提出一种基于领域自适应的间歇过程质量预测模型方法。首先,引入空间注意力机制自适应地增强与质量指标相关性高的输入变量,结合一维卷积层和长短期记忆网络单元分别挖掘数据的空间特征和时间特征。其次,将领域自适应方法引入到建模过程中,进行目标域数据和源域数据之间特征的自适应匹配,降低2个数据集因分布差异对模型预测精度的影响。该方法在慢时变的青霉素生产过程仿真数据集和酚醛树脂工业生产过程进行了验证。实验结果表明,所提出的模型能有效地提高小样本下间歇过程质量预测的精度。

	Service

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	Email Alert
	RSS
	作者相关文章
	范振杰
	罗娜

关键词：间歇过程小样本领域自适应

Abstract： In batch process modeling, only few samples are collected which is not enough to develop high accurate model. To solve this problem, a model based on domain adaptation under small sample was proposed. Spatial attention mechanism was introduced to the model first in order to enhance input variables with high correlation to quality index. After that, one-dimension convolutional layer and long and short term memory units was also borrowed to mine spatial and temporal characteristics of data, respectively. Secondly, the domain adaptation method was introduced into the modeling process to perform adaptive matching of features between the target domain data and the source domain data to reduce the impact of the difference in distribution of the two data sets on the prediction accuracy of the model. The method was validated on the slowly time-varying penicillin production process simulation data set and the phenolic resin industrial production process. Experimental results showed that the proposed model can effectively improve the accuracy of batch process quality prediction under few shot.

Keywords： batch process few shot domain adaptation

Received 2023-03-07;

Fund:杭州市萧山区2022年高层次人才创业创新"5213"计划项目。

Corresponding Authors: 罗娜,副研究员,E-mail:naluo@ecust.edu.cn。 Email: naluo@ecust.edu.cn

About author: 范振杰(1995-),男,硕士研究生,现从事基于深度学习的工业过程建模方面的研究。

引用本文:

范振杰, 罗娜.小样本下基于领域自适应的间歇过程质量预测[J]. 化学工业与工程, 2024,41(3): 142-153

FAN Zhenjie, LUO Na.Quality prediction of batch process based on domain adaptation under few shot[J]. Chemcial Industry and Engineering, 2024,41(3): 142-153

[1] 梁秀霞, 庞荣荣, 郭鹭, 等. 基于AMWPSO-LSTM的多阶段间歇过程故障预测[J]. 北京化工大学学报(自然科学版), 2022, 49(2): 116-124 LIANG Xiuxia, PANG Rongrong, GUO Lu,et al. Multi-stage intermittent process fault prediction based on AMWPSO-LSTM[J]. Journal of Beijing University of Chemical Technology (Natural Science Edition), 2022, 49(2): 116-124(in Chinese)
[2] 纪成, 顾俊发, 王健红, 等. 基于长短时记忆神经网络和支持向量数据描述的间歇过程监测方法[J]. 化学工业与工程, 2022, 39(2): 32-36 JI Cheng, GU Junfa, WANG Jianhong,et al. A batch process monitoring method based on long short term memory network and support vector data description[J]. Chemical Industry and Engineering, 2022, 39(2): 32-36(in Chinese)
[3] NOMIKOS P, MACGREGOR J F. Multi-way partial least squares in monitoring batch processes[J]. Chemometrics and Intelligent Laboratory Systems, 1995, 30(1): 97-108
[4] JIANG Q, YAN X, YI H,et al. Data-driven batch-end quality modeling and monitoring based on optimized sparse partial least squares[J]. IEEE Transactions on Industrial Electronics, 2020, 67(5): 4098-4107
[5] LUO L, BAO S, MAO J,et al. Quality prediction and quality-relevant monitoring with multilinear PLS for batch processes[J]. Chemometrics and Intelligent Laboratory Systems, 2016, 150: 9-22
[6] 王普, 曹彩霞, 高学金, 等. 基于扩展得分矩阵的多阶段间歇过程质量预测[J]. 高校化学工程学报, 2019, 33(3):664-671 WANG Pu, CAO Caixia, GAO Xuejin,et al. Quality prediction of multistage batch processes based on extended score matrices[J]. Journal of Chemical Engineering of Chinese Universities, 2019, 33(3): 664-671(in Chinese)
[7] WANG K, GOPALUNI R B, CHEN J,et al. Deep learning of complex batch process data and its application on quality prediction[J]. IEEE Transactions on Industrial Informatics, 2020, 16(12): 7233-7242
[8] QI J, LUO N. Using stacked auto-encoder and Bi-directional LSTM for batch process quality prediction[J]. Journal of Chemical Engineering of Japan, 2021, 54(4): 144-151
[9] 李泽龙, 杨春节, 刘文辉, 等. 基于LSTM-RNN模型的铁水硅含量预测[J]. 化工学报, 2018, 69(3): 992-997 LI Zelong, YANG Chunjie, LIU Wenhui,et al. Research on hot metal Si-content prediction based on LSTM-RNN[J]. CIESC Journal, 2018, 69(3): 992-997(in Chinese)
[10] ZOU G, YAN Z, ZHANG C,et al. Transfer learning with CNN-LSTM model for capacity prediction of lithium-ion batteries under small sample[J]. Journal of Physics: Conference Series, 2022, 2258(1): 012042
[11] MA J, ZENG X, XUE X,et al. Metro emergency passenger flow prediction on transfer learning and LSTM model[J]. Applied Sciences, 2022, 12(3): 1644
[12] 郑真, 朱峰, 马小丽, 等. 基于TL-LSTM的新能源功率短期预测[J]. 综合智慧能源, 2023(1): 41-48 ZHENG Zhen, ZHU Feng, MA Xiaoli,et al. Short-term new energy power prediction based on TL-LSTM[J]. Integrated Intelligent Energy, 2023(1): 41-48(in Chinese)
[13] CHEN W, CHEN W, LIU H,et al. A RUL prediction method of small sample equipment based on DCNN-BiLSTM and domain adaptation[J]. Mathematics, 2022, 10(7): 1022
[14] FU B, WU Z, GUO J. Remaining useful life prediction under multiple operation conditions based on domain adaptive sparse auto-encoder[C]//2020 IEEE International Conference on Prognostics and Health Management (ICPHM). Detroit, MI, USA. IEEE, 2020
[15] LI X, ZHANG W, DING Q,et al. Multi-Layer domain adaptation method for rolling bearing fault diagnosis[J]. Signal Processing, 2019, 157: 180-197
[16] DE OLIVEIRA DA COSTA P R, AKÇAY A, ZHANG Y Q,et al. Remaining useful lifetime prediction via deep domain adaptation[J]. Reliability Engineering & System Safety, 2020, 195: 106682
[17] LIU J, ZHOU Z, HE X,et al. Winter wheat yield estimation method based on NDWI and convolutional neural network[J].Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(12): 273-280
[18] ZHAO J, MAO X, CHEN L. Speech emotion recognition using deep 1D & 2D CNN LSTM networks[J]. Biomedical Signal Processing and Control, 2019, 47: 312-323
[19] 冯勇, 冯述放, 罗娜. 基于时钟触发长短期记忆的多元时序预测[J]. 华东理工大学学报(自然科学版), 2023, 49(2): 255-268 FENG Yong, FENG Shufang, LUO Na. Multivariate time series prediction based on clockwork triggered long short term memory[J]. Journal of East China University of Science and Technology, 2023, 49(2): 255-268(in Chinese)
[20] YUAN X, LI L, SHARDT Y A W,et al. Deep learning with spatiotemporal attention-based LSTM for industrial soft sensor model development[J]. IEEE Transactions on Industrial Electronics, 2021, 68(5): 4404-4414
[21] DING Y, ZHU Y, FENG J,et al. Interpretable spatio-temporal attention LSTM model for flood forecasting[J]. Neurocomputing, 2020, 403: 348-359
[22] GUPTA J, PATHAK S, KUMAR G. Deep learning (CNN) and transfer learning: A review[J]. Journal of Physics: Conference Series, 2022, 2273(1): 012029
[23] 成于思, 施云涛. 基于深度学习和迁移学习的领域自适应中文分词[J]. 中文信息学报, 2019, 33(9):9-16, 23 CHENG Yusi, SHI Yuntao. Domain adaption of Chinese word segmentation based on deep learning and transfer learning[J]. Journal of Chinese Information Processing, 2019, 33(9): 9-16, 23(in Chinese)
[24] ZHOU Q, ZHOU W, WANG S,et al. Multiple adversarial networks for unsupervised domain adaptation[J]. Knowledge-Based Systems, 2021, 212: 106606
[25] 褚菲, 彭闯, 贾润达, 等. 基于多尺度核JYMKPLS迁移模型的间歇过程产品质量的在线预测方法[J]. 化工学报, 2021, 72(4):2178-2189 CHU Fei, PENG Chuang, JIA Runda,et al. Online prediction method of batch process product quality based on multi-scale kernel JYMKPLS transfer model[J]. CIESC Journal, 2021, 72(4): 2178-2189(in Chinese)