Yinan Wang

Yinan Wang

Auto-generated profile, based on publicly available information

Yinan Wang

Rensselaer Polytechnic Institute

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
10 February 2021 in npj Materials Degradation
Verified
Journal Article
Open access
PDF file
YWYinan Wang
Yinan Wang
DODiane Oyen
Diane Oyen
WGWeihong "Grace" Guo
Weihong "Grace" Guo
AMAnishi Mehta
Anishi Mehta
CSCory Braker Scott
Cory Braker Scott
XYXiaowei Yue
Xiaowei Yue
Catastrophic failure in brittle materials is often due to the rapid growth and coalescence of cracks aided by high internal stresses. Hence, accurate prediction of maximum internal stress is critical to predicting time to failure and improving the fracture resistance and reliability of materials. Existing high-fidelity methods, such as the Finite-Discrete Element Model (FDEM), are limited by their high computational cost. Therefore, to reduce computational cost while preserving accuracy, a deep learning model, StressNet, is proposed to predict the entire sequence of maximum internal stress based on fracture propagation and the initial stress data. More specifically, the Temporal Independent Convolutional Neural Network (TI-CNN) is designed to capture the spatial features of fractures like fracture path and spall regions, and the Bidirectional Long Short-term Memory (Bi-LSTM) Network is adapted to capture the temporal features. By fusing these features, the evolution in time of the maximum internal stress can be accurately predicted. Moreover, an adaptive loss function is designed by dynamically integrating the Mean Squared Error (MSE) and the Mean Absolute Percentage Error (MAPE), to reflect the fluctuations in maximum internal stress. After training, the proposed model is able to compute accurate multi-step predictions of maximum internal stress in approximately 20 seconds, as compared to the FDEM run time of 4 h, with an average MAPE of 2% relative to test data.

26 January 2022 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
YLYinhua Liu
Yinhua Liu
WZWenzheng Zhao
Wenzheng Zhao
HLHongpeng Liu
Hongpeng Liu
YWYinan Wang
Yinan Wang
XYXiaowei Yue
Xiaowei Yue
The optical scanning gauges mounted on the robots are commonly used in quality inspection, such as verifying the dimensional specification of sheet structures. Coverage path planning (CPP) significantly influences the accuracy and efficiency of robotic quality inspection. Traditional CPP strategies focus on minimizing the number of viewpoints or traveling distance of robots under the condition of full coverage inspection. The measurement uncertainty when collecting the scanning data is less considered in the free-form surface inspection. To address this problem, a novel CPP method with the optimal viewpoint sampling strategy is proposed to incorporate the measurement uncertainty of key measurement points (MPs) into free-form surface inspection. At first, the feasible ranges of measurement uncertainty are calculated based on the tolerance specifications of the MPs. The initial feasible viewpoint set is generated considering the measurement uncertainty and the visibility of MPs. Then, the inspection cost function is built to evaluate the number of selected viewpoints and the average measurement uncertainty in the field of views of all the selected viewpoints. Afterward, an enhanced rapidly exploring random tree algorithm is proposed for viewpoint sampling using the inspection cost function and CPP optimization. Case studies, including simulation tests and inspection experiments, have been conducted to evaluate the effectiveness of the proposed method. Results show that the scanning precision of key MPs is significantly improved compared with the benchmark method.

31 October 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YWYinan Wang
Yinan Wang
WSWenbo Sun
Wenbo Sun
JJJionghua Jin
Jionghua Jin
ZKZhenyu Kong
Zhenyu Kong
XYXiaowei Yue
Xiaowei Yue
The training and testing data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the testing samples are drawn from a distribution that is sufficiently far away from that of the training samples (a.k.a. out-of-distribution (OOD) samples), the trained neural network has a tendency to make high-confidence predictions for these OOD samples. Detection of the OOD samples is critical when training a neural network used for image classification, object detection, etc. It can enhance the classifier's robustness to irrelevant inputs, and improve the system's resilience and security under different forms of attacks. Detection of OOD samples has three main challenges: (i) the proposed OOD detection method should be compatible with various architectures of classifiers (e.g., DenseNet, ResNet) without significantly increasing the model complexity and requirements on computational resources; (ii) the OOD samples may come from multiple distributions, whose class labels are commonly unavailable; (iii) a score function needs to be defined to effectively separate OOD samples from in-distribution (InD) samples. To overcome these challenges, we propose a Wasserstein-based out-of-distribution detection (WOOD) method. The basic idea is to define a Wasserstein-based score that evaluates the dissimilarity between a test sample and the distribution of InD samples. An optimization problem is then formulated and solved based on the proposed score function. The statistical learning bound of the proposed method is investigated to guarantee that the loss value achieved by the empirical optimizer approximates the global optimum. The comparison study results demonstrate that the proposed WOOD consistently outperforms other existing OOD detection methods.

16 April 2021 in IISE Transactions
Verified
Journal Article
Closed access
YWYinan Wang
Yinan Wang
WGWeihong "Grace" Guo
Weihong "Grace" Guo
XYXiaowei Yue
Xiaowei Yue
Feature extraction for tensor data serves as an important step in many tasks such as anomaly detection, process monitoring, image classification, and quality control. Although many methods have been proposed for tensor feature extraction, there are still two challenges that need to be addressed: (i) how to reduce the computation cost for high dimensional and large volume tensor data; (ii) how to interpret the output features and evaluate their significance. The most recent methods in deep learning, such as Convolutional Neural Network, have shown outstanding performance in analyzing tensor data, but their wide adoption is still hindered by model complexity and lack of interpretability. To fill this research gap, we propose to use CP-decomposition to approximately compress the convolutional layer (CPAC-Conv layer) in deep learning. The contributions of our work include three aspects: (i) we adapt CP-decomposition to compress convolutional kernels and derive the expressions of forward and backward propagations for our proposed CPAC-Conv layer; (ii) compared with the original convolutional layer, the proposed CPAC-Conv layer can reduce the number of parameters without decaying prediction performance. It can combine with other layers to build novel Deep Neural Networks; (iii) the value of decomposed kernels indicates the significance of the corresponding feature map, which provides us with insights to guide feature selection.

1 May 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YLYanzheng Li
Yanzheng Li
YWYinan Wang
Yinan Wang
YLYinhua Liu
Yinhua Liu
Point cloud is widely available in the manufacturing system with the continuous development of three-dimensional (3D) sensors. Accurate point cloud segmentation can automatically identify different components during the manufacturing process, which is essential to the quality assurance of the final product. However, the existing methods for point cloud segmentation fail to accurately identify the boundary of each region, which decays the quality of many manufacturing operations (i.e., welding). In this paper, a point cloud segmentation model, AR-PointNet, is proposed to improve the segmentation accuracy, especially on the regions’ boundaries. More specifically, the PointNet is used as the backbone, and the novel channel and spatial statistical feature attention modules are proposed and combined to enhance the features along the regions’ edges. In addition, context features among different regions in the point cloud are further extracted to consider the interactions among components. The experiments are conducted on the ShapeNet dataset and the real-scanned dataset of manufactured products, respectively. The results demonstrated that (1) on the ShapeNet dataset, the proposed method outperforms the state-of-the-art segmentation models. The mean Intersection-over-Union (mIoU) is selected as the evaluation metric to indicate the segmentation accuracy. The proposed method improves mIoU by 2.3% compared with its backbone (PointNet); (2) on the simulated and real-scanned sheet metal part, it successfully recognizes the boundaries of components in the sheet metal part and significantly improves the recognition accuracy. Boundary Mean Accuracy (BMA) is defined as the evaluation metric to indicate the boundary recognition accuracy. Results of the simulated data and the real-scanned data show that the proposed method improves the BMA by 4.4% and 3.6%, respectively, compared to its backbone (PointNet).

10 July 2023 in The International Journal of Advanced Manufacturing Technology
Verified
Journal Article
Closed access
PDF file
WZWenzheng Zhao
Wenzheng Zhao
YLYinhua Liu
Yinhua Liu
YWYinan Wang
Yinan Wang
XYXiaowei Yue
Xiaowei Yue