Qi Gao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Qi Gao has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Enyi He
College of Mechanical & Power Engineering China Three Gorges University Yichang China
2 shared publicationsLin Hua
School of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, People’s Republic of China
2 shared publicationsMengwu Wu
School of Automotive Engineering, Wuhan University of Technology, Wuhan 430070, People’s Republic of China
2 shared publicationsTangming Yan
College of Mechanical & Power Engineering China Three Gorges University Yichang China
2 shared publicationsXicong Ye
College of Mechanical & Power Engineering China Three Gorges University Yichang China
2 shared publicationsXunpeng Qin
Hubei Longzhong Laboratory, Xiangyang 441000, People’s Republic of China
2 shared publications
Latest Publications
- 26 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 5010313
Intelligent Recognition and 3-D Reconstruction of Surface Defects in Automotive Forgings
In the realm of surface defect detection for automotive forgings, the identification of surface cracks holds paramount importance, as it is crucial for ensuring both the surface integrity and internal quality of the components. Once defects are detected, the affected areas of automotive forgings must undergo grinding and polishing, a process that relies on accurately determining 3D spatial location of these defects. Consequently, the 3D reconstruction of surface defects on forgings emerges as an indispensable step. However, the intricate morphology of surface cracks in forged components presents a significant challenge for automated detection. To address this issue, this study proposes an innovative cascade framework comprising segmentation-detection-segmentation. The first segmentation module primarily segments the forged component, the detection module aims to localize areas of surface defects in the forging, while the second segmentation module precisely extracts pixel-level features within the crack region. Building upon the accurate segmentation results, the system subsequently performs stereo matching and 3D reconstruction processes, ultimately yielding precise 3D coordinates of the crack defects. The experimental results demonstrate that the U-Net model achieved a mIoU score of 99.03%, providing strong quantitative evidence of its effectiveness in generating precise and reliable segmentation results for the forging components. The YOLO11 object detection model achieved a mAP@0.5:0.95 of 85.9%, outperforming YOLOv5s (82.0%) and YOLOv8s (83.1%). The model achieves an impressive accuracy of 99.3%, with a mAP@0.5:0.95 reaching 85.9%. Furthermore, the U2-Net segmentation model achieved a Dice coefficient of 95.31%, the highest among the three evaluated segmentation models, attaining a Dice similarity coefficient of 95.31%. Quantitative evaluation of the reconstructed cracks reveals high precision, with relative deviations of less than 4% from ground truth for both length and width measurements.
- 26 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 5010313
Intelligent Recognition and 3-D Reconstruction of Surface Defects in Automotive Forgings
In the realm of surface defect detection for automotive forgings, the identification of surface cracks holds paramount importance, as it is crucial for ensuring both the surface integrity and internal quality of the components. Once defects are detected, the affected areas of automotive forgings must undergo grinding and polishing, a process that relies on accurately determining 3D spatial location of these defects. Consequently, the 3D reconstruction of surface defects on forgings emerges as an indispensable step. However, the intricate morphology of surface cracks in forged components presents a significant challenge for automated detection. To address this issue, this study proposes an innovative cascade framework comprising segmentation-detection-segmentation. The first segmentation module primarily segments the forged component, the detection module aims to localize areas of surface defects in the forging, while the second segmentation module precisely extracts pixel-level features within the crack region. Building upon the accurate segmentation results, the system subsequently performs stereo matching and 3D reconstruction processes, ultimately yielding precise 3D coordinates of the crack defects. The experimental results demonstrate that the U-Net model achieved a mIoU score of 99.03%, providing strong quantitative evidence of its effectiveness in generating precise and reliable segmentation results for the forging components. The YOLO11 object detection model achieved a mAP@0.5:0.95 of 85.9%, outperforming YOLOv5s (82.0%) and YOLOv8s (83.1%). The model achieves an impressive accuracy of 99.3%, with a mAP@0.5:0.95 reaching 85.9%. Furthermore, the U2-Net segmentation model achieved a Dice coefficient of 95.31%, the highest among the three evaluated segmentation models, attaining a Dice similarity coefficient of 95.31%. Quantitative evaluation of the reconstructed cracks reveals high precision, with relative deviations of less than 4% from ground truth for both length and width measurements.
- 16 December 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (3)
Machine Vision Driven Magnetic Particle Inspection Technology: Principles, Applications and Trends
As a classical non-destructive testing (NDT) method, magnetic particle inspection (MPI) holds a significant position in industrial applications due to its simplicity, cost-effectiveness, and reliability. With the advancement of intelligent technologies, MPI is evolving from traditional manual visual inspection toward high-precision intelligent inspection systems by integrating automation control and intelligent analysis algorithms. This paper systematically discusses the current industrial status quo in the field of MPI, and analyses the key factors affecting the display of MPI (magnetic field strength, magnetization current, magnetization method, and magnetic powder performance). The study further explores the evolutionary trajectory of intelligent MPI technology, encompassing three core components: image acquisition systems, image processing systems, and spatial positioning systems.Finally, the work identifies persistent challenges in achieving fully intelligent MPI, while proposing future development directions focused on enhancing automation levels and optimizing inspection accuracy to advance intelligent MPI technology.
- 16 December 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (3)
Machine Vision Driven Magnetic Particle Inspection Technology: Principles, Applications and Trends
As a classical non-destructive testing (NDT) method, magnetic particle inspection (MPI) holds a significant position in industrial applications due to its simplicity, cost-effectiveness, and reliability. With the advancement of intelligent technologies, MPI is evolving from traditional manual visual inspection toward high-precision intelligent inspection systems by integrating automation control and intelligent analysis algorithms. This paper systematically discusses the current industrial status quo in the field of MPI, and analyses the key factors affecting the display of MPI (magnetic field strength, magnetization current, magnetization method, and magnetic powder performance). The study further explores the evolutionary trajectory of intelligent MPI technology, encompassing three core components: image acquisition systems, image processing systems, and spatial positioning systems.Finally, the work identifies persistent challenges in achieving fully intelligent MPI, while proposing future development directions focused on enhancing automation levels and optimizing inspection accuracy to advance intelligent MPI technology.
- 6 September 2025
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 37 (8) , 1-19
Detection and localization system for surface defects of automotive forgings based on machine vision
- 6 September 2025
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 37 (8) , 1-19
Detection and localization system for surface defects of automotive forgings based on machine vision
- 21 December 2024
- Published by Elsevier in Journal of Alloys and Compounds
- Vol. 1010
Effect of N substitution for Ni on the high-temperature oxidation resistance of GX40CrNiSi25-12 austenitic heat-resistant steel
- 21 December 2024
- Published by Elsevier in Journal of Alloys and Compounds
- Vol. 1010
Effect of N substitution for Ni on the high-temperature oxidation resistance of GX40CrNiSi25-12 austenitic heat-resistant steel
- 4 July 2024
- Published by Wiley in Polymer Composites
- Vol. 45 (15) , 13829-13843
3D printed fabrication of ultra‐structured composites of carbonyl iron powder@carbon@carbon black/polylactic acid for efficient microwave absorption
Designing an electromagnetic wave absorber that can meet the needs of wide frequency, high efficiency, wide‐angle absorption and strong mechanical bearing capacity is still a challenge. In this paper, a core‐shell structure Carbonyl iron powder (CIP)@Carbon (C)@Carbon black (CB) composite material was prepared by coating and vacuum carbonization process. Using it as a filler, PLA as a matrix to prepare 3D printing composites. The unique structure and material distribution of CIP@C@CB gives the composite a variety of loss mechanisms that greatly improve microwave absorption capacity. Superstructure electromagnetic wave absorbers with integrating broadband microwave absorption and good mechanical bearing performance were designed and prepared by using CIP@C@CB/PLA 3D printing composites. By optimizing the parameters of this superstructure absorber, an EAB of 5.5–18 GHz is realized, and its yield limit reaches 11.5 MPa. In addition, the superstructure absorber also has excellent wide‐angle absorption capacity, with an effective absorption bandwidth (EAB) of 10GHz at 0°–40° transverse radio (TE) and 0–70° transverse magnetic wave (TM). This research offers a straightforward and effective method for crafting broadband wide‐angle absorbers that possess the added advantage of mechanical load‐bearing capacity.Highlights: The core‐shell structure was prepared by coating and carbonization processes. The unique structure of CIP@C@CB enhances the interfacial polarization effect. At a thickness of 2 mm, 30% CIP@C@CB/PLA achieves a maximum EAB of 5.0 GHz. The stepped structure achieves 90% effective absorption in the 5.5–18 GHz range.
- 4 July 2024
- Published by Wiley in Polymer Composites
- Vol. 45 (15) , 13829-13843
3D printed fabrication of ultra‐structured composites of carbonyl iron powder@carbon@carbon black/polylactic acid for efficient microwave absorption
Designing an electromagnetic wave absorber that can meet the needs of wide frequency, high efficiency, wide‐angle absorption and strong mechanical bearing capacity is still a challenge. In this paper, a core‐shell structure Carbonyl iron powder (CIP)@Carbon (C)@Carbon black (CB) composite material was prepared by coating and vacuum carbonization process. Using it as a filler, PLA as a matrix to prepare 3D printing composites. The unique structure and material distribution of CIP@C@CB gives the composite a variety of loss mechanisms that greatly improve microwave absorption capacity. Superstructure electromagnetic wave absorbers with integrating broadband microwave absorption and good mechanical bearing performance were designed and prepared by using CIP@C@CB/PLA 3D printing composites. By optimizing the parameters of this superstructure absorber, an EAB of 5.5–18 GHz is realized, and its yield limit reaches 11.5 MPa. In addition, the superstructure absorber also has excellent wide‐angle absorption capacity, with an effective absorption bandwidth (EAB) of 10GHz at 0°–40° transverse radio (TE) and 0–70° transverse magnetic wave (TM). This research offers a straightforward and effective method for crafting broadband wide‐angle absorbers that possess the added advantage of mechanical load‐bearing capacity.Highlights: The core‐shell structure was prepared by coating and carbonization processes. The unique structure of CIP@C@CB enhances the interfacial polarization effect. At a thickness of 2 mm, 30% CIP@C@CB/PLA achieves a maximum EAB of 5.0 GHz. The stepped structure achieves 90% effective absorption in the 5.5–18 GHz range.
- 10 December 2022
- Published by Elsevier in Journal of Alloys and Compounds
- Vol. 937
Graphene/carbonyl iron powder composite microspheres enhance electromagnetic absorption of 3D printing composites
- 10 December 2022
- Published by Elsevier in Journal of Alloys and Compounds
- Vol. 937
Graphene/carbonyl iron powder composite microspheres enhance electromagnetic absorption of 3D printing composites