YHYimeng He

Yimeng He

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yimeng He has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Comprehensive Review on Deep Learning With Noisy Labels: Challenges, Solutions, and Frontiers

    by Jingzhong Fang, Zidong Wang, Weibo Liu, Yong Zhang, Yimeng He, Xiaohui Liu

    Deep learning has been widely adopted across various industrial domains due to its powerful learning capacity and effective feature extraction capabilities. However, the development of reliable deep learning models depends heavily on the availability of large-scale, high-quality annotated training data. In practice, the labels provided by human experts or generated through automated annotation tools are often prone to errors, either due to human oversight or inherent limitations in the labeling algorithms. These inaccuracies give rise to the challenge known as the noisy label problem. In recent years, learning with noisy labels has garnered significant attention within the research community. This review presents a comprehensive and up-to-date overview of recent advancements in this area. In particular, two primary categories of strategies are reviewed: methods aimed at improving the quality of training data (e.g., sample selection and label correction) and approaches focused on developing robust training mechanisms to mitigate the impact of label noise. A structured tabular comparison of reviewed LNL approaches is also presented. Furthermore, the practical applications of these techniques are examined in representative domains, including image analysis and natural language processing. Finally, several emerging research directions are identified and discussed to guide future exploration in this evolving field.


  • A Novel Phase-Aware Neural Network Framework for Fault Detection in Multiphase Processes via Feature Augmentation and Phase Discrimination

    by Yimeng He, Zidong Wang, Weibo Liu, Jingzhong Fang, Linwei Chen, Zhihuan Song

    The dynamic nature of multiphase processes presents significant challenges to industrial fault detection. Most existing fault detection methods for multiphase processes, which have been developed to focus on creating a local fault detector for each phase, are hindered by two key challenges. Firstly, accurately matching test samples to their respective phases proves difficult, which leads to what is known as the phase matching problem. Secondly, constructing a reliable fault detector becomes challenging when limited data is available for specific phases. To overcome these challenges, a novel phase-aware neural network (PANN) is proposed in this paper for multiphase fault detection. The PANN is composed of a feature augmentation module, an encoder, a phase discriminator, and a decoder. Multiscale convolutional neural networks are employed to construct the feature augmentation module, which is used to extract multiscale features from the input data. The pseudo labels, which capture knowledge of the multiphase process, are used during the training of the phase discriminator to address the phase matching issue. A joint loss function is designed to train the entire PANN by integrating the loss terms for phase discrimination and future sample prediction. Validation of the proposed PANN is carried out using a numerical example. To further assess its practical application, the PANN is tested on a penicillin fermentation process dataset. Experimental results demonstrate that the proposed PANN achieves higher fault detection rates compared to several popular models currently used for fault detection in multiphase processes.

  • Label-Noise-Resistant Time-Series Classification With Self-Supervised Label Correction

    by Yimeng He, Zidong Wang, Weibo Liu, Jingzhong Fang, Linwei Chen, Zhihuan Song

    The reliable operation of industrial systems requires not only the prompt detection of faults but also their accurate classification into the appropriate categories. At present, numerous data-driven industrial fault detection and diagnosis models, which have been developed based on historical fault data, frequently neglect the issue of label noise. When labels are corrupted by noise, a significant degradation in the performance of industrial fault detection models can be observed. In this article, a label-noise-resistant time-series classification (LNRTSC) method based on consistency-driven label correction is proposed. First, an attention-based temporal correlation-enhanced encoder is introduced to extract low-dimensional representations of industrial time series. Then, label confidence, which is assessed based on local label consistency, is utilized to correct noisy labels during training. In addition, a two-stage self-supervised enhancement strategy is designed to guarantee the reliability of the corrected labels. Specifically, a reconstruction loss term is introduced to assist feature extraction in the warming-up stage, and a newly designed contrastive loss term is added to the loss function for the LNL training stage, which mitigates the effect of false negatives. Finally, the effectiveness of the LNRTSC method is validated on the Tennessee Eastman process and the SEU-gearbox datasets. When compared to peer methods, the LNRTSC approach demonstrates substantial improvements in fault classification performance on corrupted data.


  • Learning With Noisy Labels for Industrial Time Series Outlier Detection: A Transformer-Embedded Contrastive Learning Framework

    by Jingzhong Fang, Zidong Wang, Weibo Liu, Nianyin Zeng, Yimeng He, Yu Cao, Linwei Chen, Xiaohui Liu

    In many real-world industrial scenarios, acquiring accurately labeled data are often challenging due to limited resources or unexpected errors. Learning with noisy labels (LNL) has emerged as a significant research topic, aiming to develop reliable deep learning models using noisy-labeled training data. In this article, a novel Transformer-embedded LNL framework with fuzzy-clustering-assisted contrastive learning is developed for industrial time series outlier detection under noisy labels. Specifically, a fuzzy-clustering-assisted contrastive learning strategy is proposed to enhance the robustness of the Transformer encoder against noisy labels by leveraging the intrinsic characteristics of raw data. Furthermore, a dynamic two-stage training scheme is introduced to train the outlier detector. In the first training stage, the Transformer encoder is pretrained through data reconstruction to improve feature extraction capabilities for industrial time series. In the second stage, the outlier detector is jointly trained with the Transformer encoder, incorporating a joint learning strategy. Furthermore, a label-consistency regularization term is designed to enhance the robustness of the outlier detector against noisy labels by minimizing the discrepancy between the outputs of the outlier detector and the clustering algorithm. The proposed framework is applied to industrial time series data collected from a real-world wire arc additive manufacturing (WAAM) process. Experimental results demonstrate that the developed framework outperforms selected representative LNL approaches in WAAM outlier detection under both low and high noise ratios.


  • Deep Probabilistic Principal Component Analysis for Process Monitoring

    by Xiangyin Kong, Yimeng He, Zhihuan Song, Tong Liu, Zhiqiang Ge

    Probabilistic latent variable models (PLVMs), such as probabilistic principal component analysis (PPCA), are widely employed in process monitoring and fault detection of industrial processes. This article proposes a novel deep PPCA (DePPCA) model, which has the advantages of both probabilistic modeling and deep learning. The construction of DePPCA includes a greedy layer-wise pretraining phase and a unified end-to-end fine-tuning phase. The former establishes a hierarchical deep structure based on cascading multiple layers of the PPCA module to extract high-level features. The latter builds an end-to-end connection between the raw inputs and the final outputs to further improve the representation of the model to high-level features. After constructing the model structure of DePPCA, we first present the detailed training processes of the pretraining and fine-tuning stages, then clarify the theoretical merits of the proposed model from the perspective of variational inference. For process monitoring purposes, we develop two statistics based on the established DePPCA. The monitoring performance of these two statistics can remain superior even if the features extracted by DePPCA are significantly compressed to univariate. This makes the feature extraction process and online monitoring procedure of DePPCA quite fast. In other words, the proposed DePPCA can achieve accurate and efficient process monitoring by only extracting one feature for each sample. Finally, the effectiveness of DePPCA is evaluated on the Tennessee Eastman (TE) process and the multiphase flow (MPF) facility.


  • Causal Generative Model for Root-Cause Diagnosis and Fault Propagation Analysis in Industrial Processes

    by Yimeng He, Le Yao, Zhiqiang Ge, Zhihuan Song

    Fault tracing technology, including root-cause diagnosis and propagation analysis, has become a growing hot spot in the field of industrial process monitoring. However, it is currently limited by the use of restricted alarm sequence data and the analysis without fault propagation analysis. To solve these problems, this article proposes a novel fault tracing method, namely causal topology-based variable-wise generative model (CTVGM). The CTVGM is first established according to the topological order of the variable causal graph. It contains a series of causal functions that are trained with normal data. Then, fault samples can be restored by the CTVGM to build up a diagnosis index called the recovery ratio (RR), which is used to determine the root causes. Meanwhile, the fault propagation paths are inferred by the recovery routes. In addition, a hierarchical CTVGM-based fault tracing strategy is designed to reduce the computation burden and enhance the modeling efficiency for large-scale complicated processes. The effectiveness of the proposed fault tracing method is verified on a numerical example and the Tennessee Eastman process case. Compared with existing methods, the results show that the proposed method not only achieves more accurate root-cause diagnosis performance but also obtains fault tracing results that are highly consistent with the process mechanisms.


  • Neural Network Weight Comparison for Industrial Causality Discovering and Its Soft Sensing Application

    by Yimeng He, Xiangyin Kong, Le Yao, Zhiqiang Ge

    Due to the complex reaction mechanisms of industrial process units, causality and correlations exist between industrial process variables. Causal discovery algorithms have been utilized to discover the knowledge on variable relationships and guide process modeling and control optimization. However, most of them are limited by strict assumptions, such as linear relationships, additive noise, steady-state process, etc. Therefore, these methods cannot gain good performance for most practical industrial processes. To solve these problems, a novel weight comparison causal mining (WCCM) algorithm is proposed in this article for industrial causal graph discovery. It first trains a group of hidden layer neural networks with process data, then mines an undirected skeleton of the process variables according to the comparison of the network weights, and further determines the causal directions of the undirected edges in the skeleton to get a directed causal graph. The effectiveness of WCCM is verified on a benchmark and a practical industrial case from the urea synthesis process. The undirected and direct edges mined by WCCM show high consistency with the ground truths. Moreover, the causal discovery results of WCCM are utilized to guide the feature selection of soft sensor modeling, resulting in improved prediction accuracy and enhanced model interpretability.