Chihang Wei

Prof. Chihang Wei


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications

12 June 2018 in IEEE Transactions on Automation Science and Engineering
Verified
Journal Article
Closed access
CWChihang Wei
Chihang Wei
JCJunghui Chen
Junghui Chen
ZSZhihuan Song
Zhihuan Song
CCChun-I. Chen
Chun-I. Chen
The prediction accuracy of the traditional kernel with data-driven regression methods strongly depends on the appropriate selection of the kernel function and aims at solving the nonlinearity of the input space. In this paper, a self-learning kernel regression model is proposed. A special kernel space from the measured data is learned and designed, so that combined with dimension reductions on the input variables, the regression behavior between the projected input variables and the output variable is found. The model is posed as a semidefinite programming problem with the objective function to find the maximum variance between the learned manifolds. The kernel is data dependent and can be generated online whenever a new data point is available. The effectiveness of the proposed algorithm is demonstrated through the case studies on a simple nonlinear system and a real semiconductor process.

1 January 2020 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
CWChihang Wei
Chihang Wei
ZSZhihuan Song
Zhihuan Song
The process monitoring performance of traditional kernel-based modeling methods strongly depends on the appropriate selection of the kernel function which solely aims at solving the nonlinearity and totally ignores the relationships between the process variables and the quality variables. In this paper, a supervised self-optimizing kernel model (S2-OK) is firstly proposed. A special kernel space with data-dependent kernel function is designed and learned from the modeling data, so that the accurate relationships between the process variables and quality variables can be discovered and extracted combined with dimension reduction on the process variables. To be more general than the common-used semi-supervised assumptions, the generalized semi-supervised self-optimizing kernel model (GS3-OK) is successively proposed to full use of the collected information in the modeling data with irregular measurements of quality variables. Both of the proposed models only contain one compact step of optimization with scalable parameters. The feasibility and efficiency of the proposed algorithms are demonstrated and evaluated through the industrial case studies.

10 August 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
JQJinchuan Qian
Jinchuan Qian
CWChihang Wei
Chihang Wei
ZSZhihuan Song
Zhihuan Song
A valid fault pattern clustering method for stored fault data can effectively help offline fault diagnosis, and the clustering results can provide solid data support for the training of the fault diagnosis model. To achieve it, a novel sequence discriminative feature extraction network (SDFEN) is developed for extracting the discriminative features underlying the industrial time series. The proposed SDFEN composes a prediction network and an extraction network, which are trained successively. The prediction network is designed for preliminary extraction of the discriminative features, and a set of contribution rate sequences are calculated for the supervised training. Besides, to extract local information and contract the features from the same class, a local information extraction network is further connected, trained by reconstruction and neighbor prediction. Dynamic time warping helps to select neighbors among time series, while a parallel strategy is designed to reduce computing load. The final clustering result is given by the Gaussian mixture model. The feasibility and effectiveness of the proposed method are verified by experiments on the Tennessee Eastman benchmark process and the multiphase flow facility.

17 March 2021 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
CWChihang Wei
Chihang Wei
LZLiyun Zuo
Liyun Zuo
Xinmin ZhangXinmin Zhang
Xinmin Zhang
ZSZhihuan Song
Zhihuan Song
The integration of semisupervised modeling and discriminative information has been sporadically discussed in the research literature of traditional classification modeling, while the former one would make full use of the collected data and the latter one would further improve the classification performance. In this article, the Hessian semisupervised scatter regularized classification model is proposed as a coherent framework for the nonlinear process classification upon both labeled and unlabeled data. It is innovatively designed with a loss function to evaluate the classification accuracy and three regularization terms, respectively, corresponding to the geometry information, discriminative information, and model complexity. Both cases of the coherent framework, respectively, casted to the reproducing kernel Hilbert space and linear space, enjoy a theoretically guaranteed analytical solution. Experiments on process classification tasks on a benchmark dataset and a real industrial polyethylene process illustrate the merits of the proposed method in a sense that the class information of novel collected data is accurately predicted.

7 June 2023 in Sensors
Verified
Journal Article
Open access
PDF file
CWChihang Wei
Chihang Wei
ZSZhihuan Song
Zhihuan Song
Subsurface inclusions are one of the most common defects that affect the inner quality of continuous casting slabs. This increases the defects in the final products and increases the complexity of the hot charge rolling process and may even cause breakout accidents. The defects are, however, hard to detect online by traditional mechanism-model-based and physics-based methods. In the present paper, a comparative study is carried out based on data-driven methods, which are only sporadically discussed in the literature. As a further contribution, a scatter-regularized kernel discriminative least squares (SR-KDLS) model and a stacked defect-related autoencoder back propagation neural network (SDAE-BPNN) model are developed to improve the forecasting performance. The scatter-regularized kernel discriminative least squares is designed as a coherent framework to directly provide forecasting information instead of low-dimensional embeddings. The stacked defect-related autoencoder back propagation neural network extracts deep defect-related features layer by layer for a higher feasibility and accuracy. The feasibility and efficiency of the data-driven methods are demonstrated through case studies based on a real-life continuous casting process, where the imbalance degree drastically vary in different categories, showing that the defects are timely (within 0.01 ms) and accurately forecasted. Moreover, experiments illustrate the merits of the developed scatter-regularized kernel discriminative least squares and stacked defect-related autoencoder back propagation neural network methods regarding the computational burden; the F1 scores of the developed methods are clearly higher than common methods.