HWHuangang Wang

Huangang Wang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huangang Wang has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    CAMBranch: Contrastive Learning with Augmented MILPs for Branching

    by Jiacheng Lin, Meng Xu, Zhihua Xiong, Huangang Wang

    Recent advancements have introduced machine learning frameworks to enhance the Branch and Bound (B\&B) branching policies for solving Mixed Integer Linear Programming (MILP). These methods, primarily relying on imitation learning of Strong Branching, have shown superior performance. However, collecting expert samples for imitation learning, particularly for Strong Branching, is a time-consuming endeavor. To address this challenge, we propose \textbf{C}ontrastive Learning with \textbf{A}ugmented \textbf{M}ILPs for \textbf{Branch}ing (CAMBranch), a framework that generates Augmented MILPs (AMILPs) by applying variable shifting to limited expert data from their original MILPs. This approach enables the acquisition of a considerable number of labeled expert samples. CAMBranch leverages both MILPs and AMILPs for imitation learning and employs contrastive learning to enhance the model's ability to capture MILP features, thereby improving the quality of branching decisions. Experimental results demonstrate that CAMBranch, trained with only 10\% of the complete dataset, exhibits superior performance. Ablation studies further validate the effectiveness of our method.

  • Open Access

    Semi-Supervised Deep Kernel Active Learning for Material Removal Rate Prediction in Chemical Mechanical Planarization

    by Chunpu Lv, Jingwei Huang, Ming Zhang, Huangang Wang, Tao Zhang

    The material removal rate (MRR) is an important variable but difficult to measure in the chemical–mechanical planarization (CMP) process. Most data-based virtual metrology (VM) methods ignore the large number of unlabeled samples, resulting in a waste of information. In this paper, the semi-supervised deep kernel active learning (SSDKAL) model is proposed. Clustering-based phase partition and phase-matching algorithms are used for the initial feature extraction, and a deep network is used to replace the kernel of Gaussian process regression so as to extract hidden deep features. Semi-supervised regression and active learning sample selection strategies are applied to make full use of information on the unlabeled samples. The experimental results of the CMP process dataset validate the effectiveness of the proposed method. Compared with supervised regression and co-training-based semi-supervised regression algorithms, the proposed model has a lower mean square error with different labeled sample proportions. Compared with other frameworks proposed in the literature, such as physics-based VM models, Gaussian-process-based regression models, and stacking models, the proposed method achieves better prediction results without using all the labeled samples.


  • Material Removal Rate Prediction with Phase Sensitive Variables Selection and Phase Partition

    by Chunpu Lv, Tao Zhang, Huangang Wang

    In the Chemical Mechanical Planarization (CMP) process of the semiconductor industry, high accuracy prediction of Material Removal Rate (MRR) is essential to achieve wafer-to-wafer (W2W) control. Therefore, data-driven Virtual Metrology (VM) methods for MRR prediction have received much attention. Traditional methods focus on extracting features from raw data along the time dimension. However, a CMP process is a batch process with multi-phase and uneven-length characteristics, and different phases have different operating points and data correlations. In this paper, a novel VM method based on phase partition and feature selection is proposed. The phase-sensitive variables are selected by a wrapped approach and combined with a clustering algorithm for phase partition. After extracting the phase features, a suitable subset of features is selected using multiple feature selection methods and input to a regressor for prediction. The results in the PHM16 Dataset validate the effectiveness of the proposed method, which has higher prediction accuracy compared with the methods without phase partition.

  • Hybrid Gait Recognition Method Based on Phase Trajectory

    by Pinjie Li, Tao Xue, Tao Zhang, Huangang Wang, Ming Zhang

    Gait recognition is critical to the activity monitoring, health management, assistance control of prostheses and exoskeletons, etc. This study aims to improve the gait classification performance on daily hybrid locomotions. We found the hip angle phase trajectories present significantly gait-dependent patterns, whereas the phase patterns show repeated limit cycles for periodic gaits while half-cycles or dots for aperiodic gaits. By converting the gait recognition issue into an image classification problem, we propose to use a convolution neural network (CNN) to learn the gait-dependent phase pattern images. Besides, to enhance the gait transition stability, we further integrate the prior state transition probability with category likelihood via dynamic Bayesian network. The proposed method has been experimented with 6 healthy subjects on standing, sitting, stand-to-sit, sit-to-stand, walking, running, stair ascending, and stair descending gaits. The overall leave-one-out cross-validation accuracy in continuous time is 96.15%.

  • Wafer Lot Assignment for Parallel-Producing Tools Based on Heuristic Clustering Algorithm

    by Fuzuo Zhang, Qinghua Tao, Yuanyuan Yan, Xin Li, Fuquan Zhang, Ying Gao, Bing Yang, Huangang Wang

    Beyond the widely-studied scheduling of wafers within cluster tools, a novel and important perspective is raised in this paper to tackle an upper-level optimization problem in real-world production, i.e., the assignment of hybrid types of wafer lots to a set of cluster tools with parallel modules to minimize the maximum completion time for the lots. The main difficulty in addressing such a problem is that the objective, i.e., the maximum completion time, cannot be calculated explicitly beforehand. To make this problem tractable, the associated maximal overlap among tools is utilized to heuristically evaluate the objective for the problem. Besides, since the cluster tools for processing are identical, we further tackle this problem as a clustering issue. Accordingly, a clustering algorithm based on greedy searching is proposed to allocate wafer lots into cluster tools while minimizing the maximal overlap. To elucidate our method and its significance in real-world production, the wet bench tool in wet cleaning process is taken as a case study. We compare the proposed algorithm with the empirical method in fabs and several intelligent optimization algorithms, and the experimental results verify the effectiveness of our proposed method in terms of improved efficiency.


  • Center-Aware Adversarial Autoencoder for Anomaly Detection

    by Daoming Li, Qinghua Tao, Jiahao Liu, Huangang Wang

    Anomaly detection based on subspace learning has attracted much attention, in which the compactness of subspace is commonly considered as the core concern. Most related studies directly optimize the distance from the subspace representation to the fixed center, and the influence of the anomaly level of each normal sample is not considered to adjust the normal concentrated areas. In such cases, it is difficult to isolate the normal areas from the anomaly ones by making the subspace compact. To this end, we propose a center-aware adversarial autoencoder (CA-AAE) method, which detects anomaly samples by acquiring more compact and discriminative subspace representations. To fully exploit the subspace information to improve the compactness, anomaly-level description and feature learning are novelly integrated herein by dividing the output space of the encoder into presubspace and postsubspace. In presubspace, the toward-center prior distribution is imposed by the adversarial learning mechanism, and the anomaly level of normal samples can be described from a probabilistic perspective. In postsubspace, a novel center-aware strategy is established to enhance the compactness of the postsubspace, which achieves adaptive adjustment of the normal areas by constructing a weighted center based on the anomaly level. Then, a flexible anomaly score function is constructed in the testing stage, in which both the toward-center loss and the reconstruction loss are combined to balance the information in the learned subspace and the original space. Compared to other related methods, the proposed CA-AAE shows the effectiveness and advantages in numerical experiments.


  • Deep Reinforcement Learning Based Three-Dimensional Area Coverage With UAV Swarm

    by Zhiyu Mou, Yu Zhang, Feifei Gao, Huangang Wang, Tao Zhang, Zhu Han

    Unmanned aerial vehicle (UAV) technology is recognized as a promising solution to area coverage problems (ACPs) and has been extensively studied recently. In this paper, we study the 3D irregular terrain surface coverage problem with a hierarchical UAV swarm. We first build the 3D model of a random irregular terrain and propose a geometric way to project the 3D terrain surface into many weighted 2D patches. Then we develop a two-level hierarchical UAV swarm architecture, including the low-level follower UAVs (FUAVs) and the high-level leader UAVs (LUAVs). For FUAVs, we design a coverage trajectory algorithm to carry out specific coverage tasks within patches based on the star communication topology. For LUAVs, we propose a swarm deep Q-learning (SDQN) reinforcement learning algorithm to select patches. Moreover, an observation history model based on convolutional neural networks (CNNs) and the mean embedding method is integrated into SDQN to address the communication limitation problems of LUAVs. The numerical results show that FUAVs can cover the entire area of each patch with little redundancies, and the total coverage time of the SDQN is less than that of existing methods, which demonstrates the effectiveness of the proposed algorithms.