Zhaomin Lv

Zhaomin Lv

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhaomin Lv has a total of 46 co-authors. Here are the top co-authors by number of shared publications:

  • Xingjie Chen

    School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai 201620, China

    5 shared publications
  • Shubin Zheng

    School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai, China

    3 shared publications
  • Xiaodong Chai

    School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai, China

    3 shared publications
  • Yijin Qiu

    School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai, China

    3 shared publications
  • Anqi Ma

    School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai, China

    2 shared publications
  • Liming Li

    School of Urban Railway Transportation, Shanghai University of Engineering Science, Shanghai, China

    2 shared publications

Latest Publications

  • KT-RC: Kernel Time-Delayed Reservoir Computing for Time Series Prediction

    by Heshan Wang, Mengmeng Chen, Kunjie Yu, Jing Liang, Zhaomin Lv, Zhong Zhang

    Reservoir computing (RC) is an efficient recurrent neural network (RNN) method. However, the performance and prediction results of traditional RCs are susceptible to several factors, such as their network structure, parameter setting, and selection of input features. In this study, we employ a kernel time-delayed RC (KT-RC) method for time series prediction. The KT-RC transforms input vectors linearly to obtain a high-dimensional set of time-delayed linear eigenvectors, which are then transformed by various kernel functions to represent the nonlinear characteristics of the input signal. Finally, the Bayesian optimization algorithm adjusts the few remaining weights and kernel parameters to minimize the manual adjustment process. The advantages of KT-RC can be summarized as follows: 1) KT-RC solves the problems of uncertainty in weight matrices and difficulty in large-scale parameter selection in the input and hidden layers of RCs. 2) The KT module can avoid massive reservoir hyperparameters and effectively reduce the hidden layer size of the traditional RC. 3) The proposed KT-RC shows good performance, strong stability, and robustness in several synthetic and real-world datasets for one-step-ahead and multistep-ahead time series prediction. The simulation results confirm that KT-RC not only outperforms some gate-structured RNNs, kernel vector regression models, and recently proposed prediction models but also requires fewer parameters to be initialized and can reduce the hidden layer size of the traditional RCs. The source code is available at https://github.com/whs7713578/RC.

  • Open Access

    Maximum Margin Local Domain Adaptation for Bearing Fault Diagnosis Under Multiple Operating Conditions

    by Zifeng Wang, Zhaomin Lv, Xingjie Chen, Hong Zhang, Zhiwei Li

    Unsupervised domain adaptation (UDA) has been extensively studied for bearing fault diagnosis under multiple operating conditions by mitigating distribution discrepancies across domains. However, in cross-domain imbalanced scenarios, bearing vibration signals are affected by both feature shift and class imbalance. Although a robust decision boundary learned from the source domain is critical for reliable transfer, classifier discriminability and robustness can be degraded by hard samples located near the boundary. As a result, the decision boundary may become ambiguous during adaptation, leading to degraded diagnostic performance in the target domain. To address these issues, a Maximum Margin Local Domain Adaptation (MMLDA) framework is proposed in which a multi-scale convolutional neural network is adopted as the backbone. Three core components are integrated into our framework: first, category-level reweighting to alleviate source-domain class imbalance; second, cross-domain local category alignment to reduce fine-grained feature discrepancies and feature shift; and finally, maximum-margin loss regularization to impose adaptive margin constraints on hard samples for improved decision boundary robustness. To evaluate the proposed method, cross-domain imbalanced transfer tasks under multiple operating conditions were constructed on two public bearing fault datasets, and comparative experiments were conducted. The results under different imbalance protocols demonstrate improved robustness and generalization of MMLDA.

  • Open Access

    Point-Cloud Filtering Algorithm for Port-Environment Perception Based on 128-Line Array Single-Photon LiDAR

    by Wenhao Zhao, Zhaomin Lv, Ziqiang Peng, Xiaokai She

    Light detection and ranging (LiDAR) has been widely used in navigation and environmental perception owing to its excellent beam directivity and high spatial resolution. Among its modalities, single-photon (photon-counting) LiDAR offers higher detection sensitivity at long ranges and under weak-return conditions and has therefore attracted considerable attention. However, this high sensitivity also introduces substantial background counts into the raw measurements; without effective filtering, downstream tasks such as image reconstruction and target recognition are hindered. In this work, a 128-line single-photon LiDAR system for port-environment perception was designed, and a histogram-based statistical filtering engineering solution was proposed. The algorithm incorporates distance-based piecewise adaptive parameterization and adjacent-channel fusion while maintaining a small memory footprint and facilitating deployment. Field experiments using datasets collected in Qingdao and Shanghai demonstrated good denoising performance at ranges up to 2.4 km. In simulation experiments using synthetic data with ground truth, an F1 score of 0.9091 was achieved by RA-ACF HSF, outperforming the baseline methods DBSCAN (0.6979) and ROR (0.7500). The proposed system and method provide a practical engineering solution for maritime navigation and port-environment perception.

  • Weighted Local Adversarial Domain Adaptation With Wide Kernels for Bearing Fault Diagnosis Under Multiple Conditions

    by Zhaomin Lv, Tong Niu, Yang Li

    Domain adaptation is the mainstream method for bearing fault diagnosis under multiple conditions. The feature alignment between the source domain and the target domain faces three challenges. Firstly, due to the noises, features cannot be aligned at the global level; Secondly, due to the fine-grained differences in subdomains, features cannot be aligned at the local level; Thirdly, due to the high diagnostic difficulty of individual categories, the features cannot be aligned at the individual level. Considering these issues, theWeighted Local Adversarial Domain Adaptation with Wide Kernels (WWLADA) method is proposed in this paper, which can integrate global, local and individual feature alignment mechanism and establish a unified three-level feature transfer framework. The effectiveness of the proposed WWLADA method is assessed in fault diagnosis transfer tasks across two datasets, achieving peak accuracy rates of 100% and 98% in the most challenging transfer cases, demonstrating its excellent diagnostic performance and transferability in rolling bearing fault diagnosis under multiple conditions.


  • t-SNVAE: Deep Probabilistic Learning With Local and Global Structures for Industrial Process Monitoring

    by Jian Huang, Zizhuo Liu, Xu Yang, Yupeng Liu, Zhaomin Lv, Kaixiang Peng, Okan K. Ersoy

    Variational autoencoder is a generative deep learning model with a probabilistic structure, which makes it tolerant to process uncertainties and more suitable for process monitoring. However, the probabilistic model may disrupt the topological structure of data and lead to the loss of neighborhood information. To address this issue, a process monitoring approach based on t-distributed stochastic neighbor variational autoencoder (t- SNVAE) is proposed to capture probabilistic features that elucidate both local and global structures within the raw data. Specifically, the distances between neighboring data points are transformed into joint probabilities by using t-SN Embedding. Through minimizing the Kullback-Leibler divergence of joint probabilities between the original data and the reconstructed data, variational autoencoder learns Gaussian features containing both local and global neighborhood information. Finally, monitoring statistics are constructed for monitoring. The efficiency of the proposed approach is verified on a multiphase flow facility and a waste-water treatment process.


  • Open Access

    Rolling bearing fault diagnosis method based on 2D grayscale images and Wasserstein Generative Adversarial Nets under unbalanced sample condition

    by Jiaxing He, Zhaomin Lv, Xingjie Chen

    Accurate diagnosis of rolling bearing faults plays a crucial role in ensuring the stable operation of rotating machinery systems. However, in actual engineering applications, a significant disparity between the volume of normal data and the quantity of fault data collected impairs diagnostic performance. Bearing fault diagnosis under sample imbalance conditions is an engineering challenge encountered in the field of fault diagnosis. To improve the fault diagnosis accuracy under unbalanced sample conditions, a rolling bearing fault diagnosis method based on 2D grayscale images and Wasserstein Generative Adversarial Networks (WGAN) is proposed. The method consists of three main steps. First, the acquired bearing vibration signals are transformed into 2D grayscale images. Second, the WGAN generation model is used to generate more fault samples. Finally, both the original samples and the generated samples are used to train the Convolutional Neural Networks classification model. The validity and effectiveness of the proposed method are evaluated and compared to other bearing fault diagnosis approaches using the Case Western Reserve University Bearing Data Center dataset. The experimental results demonstrate the superior quality of the generated samples and the improved fault identification accuracy achieved by the proposed method.


  • Open Access

    Underdetermined Blind Source Separation Method Based on a Two-Stage Single-Source Point Screening

    by Zhanyu Zhu, Xingjie Chen, Zhaomin Lv

    Underdetermined blind source separation is a signal processing technique that is more suitable for practical applications and aims to separate the source signals from the mixed signals. The mixing matrix estimation is a major step in the underdetermined blind source separation. Since the current methods for estimating the mixing matrix have the disadvantages of insufficient accuracy or weak noise immunity, a two-stage single-source point screening that combines the cosine angle algorithm and the L1-norm optimization algorithm is proposed. During the first stage, the first-stage single-source points are extracted from the original mixed signals using the cosine angle algorithm. During the second stage, based on the L1-norm optimization algorithm, the reference single-source points are extracted from the original mixed signals. The reference single-source points are then clustered to obtain the clustering center, which is defined as the reference center. In combination with the reference center, the deviation and interference points in the first-stage single-source points are eliminated by the cosine distance. The remaining signal points are considered as the second-stage single-source points, which are clustered to obtain the mixing matrix estimation. Experiments on simulated and speech signals show that the proposed method can obtain more accurate and robust mixing matrix estimation, leading to better separation of the source signals.


  • Open Access

    Rail Fastener Status Detection Based on MobileNet-YOLOv4

    by Junpeng Fu, Xingjie Chen, Zhaomin Lv

    As an important part of track inspection, the detection of rail fasteners is of great significance to improve the safety of train operation. Additionally, rail fastener detection belongs to small-target detection. The YOLOv4 algorithm is relatively fast in detection and has some advantages in small-target detection. Therefore, YOLOv4 is used for rail fastener status detection. However, YOLOv4 still suffers from the following two problems in rail fastener status detection. First, the features extracted by the original feature extraction network of YOLOv4 are relatively rough, which is not conducive to crack anomaly detection on rail fasteners. In addition, the traditional convolutional neural network has a larger number of parameters and calculations, which are difficult to run on the embedded system with low memory and processing power. To effectively solve those two problems, this paper proposes a rail fastener status detection algorithm based on MobileNet-YOLOv4 (M-YOLOv4). The edge features and texture features of rail fasteners are very important for rail fastener detection, and CSPDarknet53 cannot effectively extract the features of fasteners. The MobileNet is used to replace the CSPDarknet53 feature extraction network in the YOLOv4 algorithm, which can extract subtle features of rail fasteners and reduce the number of parameters and calculations of the algorithm. The experimental results show that the M-YOLOv4 algorithm has high detection accuracy and low resource consumption in rail fastener status detection. The false-alarm rate (FAR), missed-alarm rate (MAR), and error rate (ER) were 5.71%, 1.67%, and 4.24%, respectively, and the detection speed reached 59.8 fps. Compared with YOLOv4, the number of parameters and calculations were reduced by about 80.75% and 83.20%, respectively.


  • Open Access

    Research on track fastener positioning method based on local unidirectional template matching

    by Liang Li, Zhaomin Lv, Xingjie Chen, Yijin Qiu, Liming Li, Anqi Ma, Shubin Zheng, Xiaodong Chai

    Commonly used fastener positioning methods include pixel statistics (PS) method and template matching (TM) method. For the PS method, it is difficult to judge the image segmentation threshold due to the complex background of the track. For the TM method, the search in both directions of the global is easily affected by complex background, as a result, the locating accuracy of fasteners is low. To solve the above problems, this paper combines the PS method with the TM method and proposes a new fastener positioning method called local unidirectional template matching (LUTM). First, the rail positioning is achieved by the PS method based on the gray-scale vertical projection. Then, based on the prior knowledge, the image of the rail and the surrounding area of the rail is obtained which is referred to as the 1-shaped rail image; then, the 1-shaped rail image and the produced offline symmetrical fastener template is pre-processed. Finally, the symmetrical fastener template image is searched from top to bottom along the rail and the correlation is calculated to realize the fastener positioning. Experiments have proved that the method in this paper can effectively realize the accurate locating of the fastener for ballastless track and ballasted track at the same time.