Shifu Yan

Shifu Yan

A Ph.D Candidate at ECUST

I focus on Machine learning and Data mining algorithms with applications in industrial big data, such as Anomaly/Outlier detection, time series analysis.
Also, I am interested in recommendation system, root cause analysis ...

News:

@Yansf677

My Github Address

@Yan Shifu

Paper list at Google Scholar

@Shifu Yan

Profile at Linkedin

Education

  • East China University of Science and Technology
    2017-2022

    Ph.D. in Control Science and Engineering

  • East China University of Science and Technology
    2013-2017

    B.S. in Automation GPA: 3.75/ 4.0

Work

  • Red Avenue Group
    2018.8-2020.6

    Data Scientist Intern: Responsible for processing data from historical and real-time database, analyzing the correlation between different attributes, using machine learning algorithms to reduce the frequency of laboratory analysis and improve production efficiency.

Project

  • Delay Master Equations
    2020.6-2021.2

    A research project for developing neural network based algorithms for the stochastic models in gene expression and predict the behaviors of genes.

  • Decentralized quality monitoring of PTA production based on neural networks
    2017.9-present

    A research project by National Natural Science Foundation. Responsible for developing neural network based algorithms to improve the predictive performance of key performance indicators in PTA production, and detect quality-related anomalies for reducing unnecessary losses

  • Plant-level nonlinear fault diagnosis based on deep correlation feature learning
    2018.9-present

    A research project by National Natural Science Foundation. Responsible for fusing statistical algorithms and neural networks for feature engineering and improve the classification performance of nonlinear faults.

  • Data-driven prediction of product quality during tire material production
    2018.8-2020.6

    Responsible for feature engineering and modeling the production process using support vector machine, intelligent optimization algorithm, neural networks. Develop Python software for guiding the production to increase profit. Two Chinese public patents and a registered software have been published.

  • Custom product design based on rapid modeling and 3D printing
    2016.1-2017.6

    Responsible for developing a VBA plug-in for rapid modeling in SolidWorks according to the model components required by customers, and use 3D printing to make personalized molds.

Journal papers

Quality-Driven Autoencoder for Nonlinear Quality-Related and Process-Related Fault Detection Based on Least-Squares Regularization and Enhanced Statistics

Shifu Yan, Xuefeng Yan

Industrial & Engineering Chemistry Research, vol. 59, no. 26, pp. 12136-12143, June, 2020. [pdf]

Design teacher and supervised dual stacked auto-encoders for quality-relevant fault detection in industrial process

Shifu Yan, Xuefeng Yan

Applied Soft Computing Journal, vol. 81, Aug. 2019. [pdf]

Using Labeled Autoencoder to Supervise Neural Network Combined with k -Nearest Neighbor for Visual Industrial Process Monitoring

Shifu Yan, Xuefeng Yan

Industrial & Engineering Chemistry Research, vol. 58, no. 23, pp. 9952-9958, May. 2019. [pdf]

Joint monitoring of multiple quality-related indicators in nonlinear processes based on multi-task learning

Shifu Yan, Xuefeng Yan

Measurement, vol. 165, 108158, Dec. 2020. [pdf]

Monitoring of quality-relevant and quality-irrelevant blocks with characteristic-similar variables based on self-organizing map and kernel approaches

Shifu Yan, Xuefeng Yan

Journal of Process Control, vol. 73, pp. 103-112, Jan. 2019. [pdf]

Quality-relevant dynamic process monitoring based on dynamic total slow feature regression model

Shifu Yan, Qingchao Jiang, Haiyong Zheng, Xuefeng Yan

Measurement Science and Technology, vol. 31, 2020. [pdf]

Robust Chemical Process Monitoring Based on CDC-MVT-PCA Eliminating Outliers and Optimally Selecting Principal Component

Junping Huang*, Shifu Yan*, Qingchao Jiang, Haiyong Zheng, Xuefeng Yan

Canadian Journal of Chemical Engineering, vol. 97, no. 6, pp. 1848-1857, 2019. [pdf]

Local-Global Modeling and Distributed Computing Framework for Nonlinear Plant-Wide Process Monitoring with Industrial Big Data

Qingchao Jiang, Shifu Yan, Hui Cheng, Xuefeng Yan

IEEE Transactions on Neural Network and Learning Systems, Early Access, 2020. [pdf]

Data-Driven 2D Deep Correlated Representation Learning for Nonlinear Batch Process Monitoring

Qingchao Jiang, Shifu Yan, Xuefeng Yan, Hui Yi, Furong Gao

IEEE Transactions on Industrial Informatics, vol. 16, no. 4, pp. 2839 - 2848, 2020. [pdf]

Data-driven individual–joint learning framework for nonlinear process monitoring

Qingchao Jiang, Shifu Yan, Xuefeng Yan, Shutian Chen, Jinggao Sun

Control Engineering Practice, vol. 95, 2020. [pdf]



Patents

Step-by-step modeling for multi-component prediction of industrial p-tertylphenol synthesis reaction (in Chinese)

CN110867216A 2020. [online]

A method for predicting the quality of phenolic resin products under the uncertainty of raw materials (in Chinese)

CN110867216A 2020. [online]

Address

130 Meilong Road, Xuhui District, Shanghai

Phone

(+86) 175 2133 2443

Email

shifuyan677 at hotmail dot com

Last updated Feb. 2021, Shifu Yan (shifuyan677 at hotmail dot com)