Imputation of Missing Values in Time Series Using an Adaptive-Learned Median-Filled Deep Autoencoder

Missing values are ubiquitous in industrial data sets because of multisampling rates, sensor faults, and transmission failures. The incomplete data obstruct the effective use of data and degrade the performance of data-driven models. Numerous imputation algorithms have been proposed to deal with missing values, primarily based on supervised learning, that is, imputing the missing values by constructing a prediction model with the remaining complete data. They have limited performance when the amount of incomplete data is overwhelming. Moreover, many methods have not considered the autocorrelation of time-series data. Thus, an adaptive-learned median-filled deep autoencoder (AM-DAE) is proposed in this study, aiming to impute missing values of industrial time-series data in an unsupervised manner. It continuously replaces the missing values by the median of the input data and its reconstruction, which allows the imputation information to be transmitted with the training process. In addition, an adaptive learning strategy is adopted to guide the AM-DAE paying more attention to the reconstruction learning of nonmissing values or missing values in different iteration periods. Finally, two industrial examples are used to verify the superior performance of the proposed method compared with other advanced techniques.

[1]  Steven X. Ding,et al.  Data-Driven Fault Diagnosis for Traction Systems in High-Speed Trains: A Survey, Challenges, and Perspectives , 2022, IEEE Transactions on Intelligent Transportation Systems.

[2]  M. Saif,et al.  DLIN: Deep Ladder Imputation Network , 2021, IEEE Transactions on Cybernetics.

[3]  Ningrinla Marchang,et al.  KNN-ST: Exploiting Spatio-Temporal Correlation for Missing Data Inference in Environmental Crowd Sensing , 2021, IEEE Sensors Journal.

[4]  Zhiwen Yu,et al.  End-to-End Incomplete Time-Series Modeling From Linear Memory of Latent Variables , 2020, IEEE Transactions on Cybernetics.

[5]  Kaixin Liu,et al.  A thermographic data augmentation and signal separation method for defect detection , 2020 .

[6]  Liyong Zhang,et al.  Autoencoder-based multi-task learning for imputation and classification of incomplete data , 2020, Appl. Soft Comput..

[7]  Paul Jen-Hwa Hu,et al.  A deep learning-based, unsupervised method to impute missing values in electronic health records for improved patient management , 2020, J. Biomed. Informatics.

[8]  Hadi Meidani,et al.  IGANI: Iterative Generative Adversarial Networks for Imputation With Application to Traffic Data , 2020, IEEE Access.

[9]  Ge Yu,et al.  MIDIA: exploring denoising autoencoders for missing data imputation , 2020, Data Mining and Knowledge Discovery.

[10]  Kaixin Liu,et al.  Generative Principal Component Thermography for Enhanced Defect Detection and Analysis , 2020, IEEE Transactions on Instrumentation and Measurement.

[11]  Zhen Xu,et al.  Distributed Semi-Supervised Learning With Missing Data , 2020, IEEE Transactions on Cybernetics.

[12]  Kup-Sze Choi,et al.  A Transfer-Based Additive LS-SVM Classifier for Handling Missing Data , 2020, IEEE Transactions on Cybernetics.

[13]  Bin Jiang,et al.  A Review of Fault Detection and Diagnosis for the Traction System in High-Speed Trains , 2020, IEEE Transactions on Intelligent Transportation Systems.

[14]  Wei Lu,et al.  Imputations of missing values using a tracking-removed autoencoder trained with incomplete data , 2019, Neurocomputing.

[15]  Patrik Edén,et al.  Establishing strong imputation performance of a denoising autoencoder in a wide range of missing data problems , 2019, Neurocomputing.

[16]  Heung-Il Suk,et al.  Uncertainty-Aware Variational-Recurrent Imputation Network for Clinical Time Series , 2019, IEEE Transactions on Cybernetics.

[17]  Gunnar Rätsch,et al.  GP-VAE: Deep Probabilistic Time Series Imputation , 2019, AISTATS.

[18]  Simone Scardapane,et al.  Efficient data augmentation using graph imputation neural networks , 2019, IIH-MSP.

[19]  Mihaela van der Schaar,et al.  GAIN: Missing Data Imputation using Generative Adversarial Nets , 2018, ICML.

[20]  Zhigang Liu,et al.  Automatic Defect Detection of Fasteners on the Catenary Support Device Using Deep Convolutional Neural Network , 2018, IEEE Transactions on Instrumentation and Measurement.

[21]  Yijie Shi,et al.  Data imputation and dimensionality reduction using deep learning in industrial data , 2017, 2017 3rd IEEE International Conference on Computer and Communications (ICCC).

[22]  Chao Shang,et al.  VIGAN: Missing view imputation with generative adversarial networks , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[23]  Jiayu Zhou,et al.  Missing Modalities Imputation via Cascaded Residual Autoencoder , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Biao Huang,et al.  GMM and optimal principal components-based Bayesian method for multimode fault diagnosis , 2016, Comput. Chem. Eng..

[25]  J. Zupan,et al.  Self-organizing maps for imputation of missing data in incomplete data matrices , 2015 .

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Ping Zhang,et al.  A comparison study of basic data-driven fault diagnosis and process monitoring methods on the benchmark Tennessee Eastman process , 2012 .

[28]  Aníbal R. Figueiras-Vidal,et al.  Pattern classification with missing data: a review , 2010, Neural Computing and Applications.

[29]  Thomas J. McAvoy,et al.  Fault Detection and Diagnosis in Industrial Systems , 2002 .

[30]  Weihua Gui,et al.  A classification-driven neuron-grouped SAE for feature representation and its application to fault classification in chemical processes , 2021, Knowl. Based Syst..

[31]  Weihua Gui,et al.  A novel deep learning based fault diagnosis approach for chemical process with extended deep belief network. , 2019, ISA transactions.

[32]  Zhiqiang Ge,et al.  Review and big data perspectives on robust data mining approaches for industrial process modeling with outliers and missing data , 2018, Annu. Rev. Control..

[33]  Léon Bottou,et al.  Stochastic Gradient Descent Tricks , 2012, Neural Networks: Tricks of the Trade.