Lei Wang

Lei Wang

Auto-generated profile, based on publicly available information

Lei Wang

School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, China

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
16 November 2023 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
FZFengyuan Zuo
Fengyuan Zuo
JLJinhai Liu
Jinhai Liu
XZXiang Zhao
Xiang Zhao
LCLixin Chen
Lixin Chen
LWLei Wang
Lei Wang
In the special equipment systems, welding quality assessment based on X-ray flaw detection is related to the industrial production safety. As a key component in weld quality monitoring, automatic defect detection system aims to locate and identify numerous welding defects (e.g., air holes and cracks). Some current defect detection methods are difficult to accurately detect dense and small defects in low-quality X-ray images. In order to tackle the current challenges, this article proposes an effective weld defect detection method, termed integrated and iterative deep network (I2D-Net). First, the original weld image is decomposed by using frequency domain filtering to make full utilization of high- and low-frequency information and enhance the weak defect features. Second, a parallel detection network based on residual connection blocks of different depth and width is designed, which can flexibly capture defect features from multiple perspectives. Then, an integrated and iterative model prediction method is proposed to better extract the feature representation of small defects, thus effectively improving the overall performance. In the experiment, we built a hardware testing platform and conducted a large number of defect detection experiments and analyses. In addition, we also elaborated on practical application cases to prove that the proposed method has high industrial application value. Finally, the evaluation results of the datasets of weld defects of pressure pipeline and vessel show that the proposed I2D-Net is superior to the state-of-the-art (SoTA) methods in terms of average precision (AP increased by 7.7%, recall increased by 11.5%, and detection rate reached 98.4%).

25 April 2025 in Computers in Industry
Verified
Journal Article
Closed access
XSXiangkai Shen
Xiangkai Shen
JLJinhai Liu
Jinhai Liu
YRYifu Ren
Yifu Ren
LJLin Jiang
Lin Jiang
LWLei Wang
Lei Wang
RLRui Li
Rui Li

13 June 2024 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
FZFengyuan Zuo
Fengyuan Zuo
JLJinhai Liu
Jinhai Liu
MFMingrui Fu
Mingrui Fu
LWLei Wang
Lei Wang
ZZZhen Zhao
Zhen Zhao
Welding is a key technical means to ensure the safe and stable connection between pipeline systems. The intelligent welding defect assessment based on X-ray inspection helps to improve the efficiency and accuracy of pipeline welding fault diagnosis. However, this work is highly challenging and systematic, and includes multiple critical subtasks, such as weld area extraction and defect detection. The existing methods have fallen into the quagmire of various task flow concatenation, resulting in unsatisfactory accuracy and efficiency. To overcome this dilemma, a multiexpert inspection method based on X-ray is proposed to perform welding defect assessment. First, a preprocessing method based on window width and window level adjustment is designed to calibrate original data to ensure high-quality input of the subsequent neural network. Second, a basic network layer with universal representation ability initialization is designed to extract discriminative multitask feature representations. Next, a novel task-specific experts is presented to perform weld area extraction and defect detection in a divide and conquer manner. Finally, a rule-based defect postprocessing is designed to evaluate the level of weld defects. In the experiment, the performance of defect detection expert and weld seam segmentation expert based on hardware testing platform is systematically verified and discussed. In practical defect assessment application cases, we obtained competitive results (recall: 98.5%, precision: 95.2%, accuracy: 97.4%). Hence, the proposed intelligent multiexpert method has shown great potential in actual pipeline weld maintenance and significantly saves operators time and costs.

5 October 2022 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
LWLei Wang
Lei Wang
HZHua-Guang Zhang
Hua-Guang Zhang
JLJinhai Liu
Jinhai Liu
FQFuming Qu
Fuming Qu
FZFengyuan Zuo
Fengyuan Zuo
Defect size quantification plays a vital role in pipeline magnetic flux leakage detection system. However, most existing methods suffer from poor applicability and low precision due to the complex industrial process. Moreover, they often overlook the valuable knowledge that may be beneficial for defect size quantification. To solve this problem, a defect size quantification method based on multilevel knowledge-guided neural network is proposed, which effectively integrates prior knowledge and specific data. First, at the feature level, a recursive residual subnet is proposed to inject the mechanism features into the network, so that the network performance can be enhanced. Second, an experience-aided subnet is proposed to incorporate expert experience at the decision level, which supervises the network training with labels, so that the network stability can be improved. Third, at the modeling level, a cascade expression subnet based on two-point representation is first proposed in the defect size quantification area, where both the value and distribution of labels are considered to boost the network precision. These three parts are jointly trained and promote each other. Finally, extensive experiments are conducted with defects from a pipeline network in northern China and the experimental results highlight the superiority of our method.

24 February 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
HZHua-Guang Zhang
Hua-Guang Zhang
LWLei Wang
Lei Wang
JWJianfeng Wang
Jianfeng Wang
FZFengyuan Zuo
Fengyuan Zuo
JLJinhai Liu
Jinhai Liu
Defect inversion, as a key step in magnetic flux leakage (MFL) inspection widely used in nondestructive testing (NDT) systems, is critical to quantitative analysis of pipeline risk level. However, the conventional methods are difficult to achieve desirable results with complex and changeable MFL signals, mainly because the defect inversion procedure relies on prior knowledge and the features of MFL signals are not fully mined. To resolve the above problem, a novel direct inversion method based on cascading abstract features is proposed in this article, capable of handling feature extraction and defect size estimation problems effectively under complicated conditions. First, an adaptive abstract defect feature extraction network with stacked multipath denoising sparse autoencoder (sMPDS-AE) is constructed, and several extra feature transmitting channels are created, so that abstract features can be transferred across multiple layers. Second, multifeature fusion and sparsity rules are designed to strengthen the sMPDS-AE model and unify abstract feature dimensions. Third, a novel ensemble-backed predictor is developed to study the complex nonlinear relationship between abstract features and defect sizes. With above-mentioned structure, the proposed method can mining out abstract features of pipeline defects from MFL signals adequately and distinguish defects with different sizes more accurately. Finally, several comparison experiments are conducted on a pipeline network with MFL signals. Experimental results and comprehensive analysis with other mainstream inversion methods validate the superiority of this method.

14 March 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
FZFengyuan Zuo
Fengyuan Zuo
JLJinhai Liu
Jinhai Liu
MFMingrui Fu
Mingrui Fu
LWLei Wang
Lei Wang
ZZZhen Zhao
Zhen Zhao
In the welding process of long-distance pipelines, cracks pose significant risks and can cause severe damages. Intelligent detection of hazardous defects in pipeline welds, with a focus on complex crack features with different shapes and scales, is a necessary but challenging task. Current deep learning-based visual detection models exhibit weak generalization and transfer capabilities when it comes to complex defect features. To address these challenges, this paper proposes a spatial transformation-based multi-scale attention network (STMA-Net) for weld defect detection with multi-scale and shape-variant features in X-ray images. First, a novel spatial transformation attention network (STAN) is designed to capture the complex deformation features, which enhances the generalization ability of the feature extraction network. Then, in order to better utilize the discriminative features, a multi-level attention feature fusion network (MAFFN) is designed to improve the prediction accuracy of multi-scale defects. Furthermore, a multi-level deep supervision is proposed to better update network parameters and enhance the inference ability of multi-level detection heads. Finally, three types of X-ray weld crack datasets in the real world are collected to guide a series of experiments and analyses. The results show that the generalization and transfer capabilities of the proposed method outperforms other detectors in the detection task of cracks and other defects (AP increased by 6.5%).