-
公开(公告)号：US11714024B2
公开(公告)日：2023-08-01
申请号：US16768165
申请日：2018-11-30
Applicant: University of Kansas
Inventor： Jian Li , Xiangxiong Kong
IPC: G01M5/00
CPC classification number: G01M5/0033 , G01M5/0008 , G01M5/0091
Abstract: A computer-vision-based fatigue crack detection approach using a short video is described. Feature tracking is applied to the video for tracking the surface motion of the monitored structure under repetitive load. Then, a crack detection and localization algorithm is established to search for differential features at different frames in the video. The effectiveness of the proposed approach is validated through testing two experimental specimens with in-plane and out-of-plane fatigue cracks. Results indicate that the proposed approach can robustly identify fatigue cracks, even when the cracks are under ambient lighting conditions, surrounded by other crack-like edges, covered by complex surface textures, or invisible to human eyes due to crack closure. The approach enables accurate quantification of crack openings under fatigue loading with good accuracy.
-
公开(公告)号：US20250108581A1
公开(公告)日：2025-04-03
申请号：US18830006
申请日：2024-09-10
Applicant: University of Kansas
Inventor： Jian Li , Mona Shaheen , Caroline Bennett , William Collins
Abstract: Various examples are provided related to reducing global vibrations of tubular structures. In one example, a structure includes a tubular base structure extending along a longitudinal axis; a viscoelastic (VE) layer disposed on and distributed about the tubular base structure; and a constraining layer including a plurality of sections distributed about the tubular base structure and disposed on the VE layer, each section extending along the longitudinal axis of the tubular base structure and separated from an adjacent section by a longitudinal slit extending over an entire length of the section. In another example, a method includes disposing a VE layer on a tubular base structure extending along a longitudinal axis, the VE layer distributed about the tubular base structure; and disposing a constraining layer on the VE layer, the constraining layer including a plurality of sections distributed about the longitudinal axis of the tubular base structure.
-
Patent Agency Ranking
公开(公告)号：US20200284686A1
公开(公告)日：2020-09-10
申请号：US16768165
申请日：2018-11-30
Applicant: University of Kansas
Inventor： Jian Li , Xiangxiong Kong
IPC: G01M5/00
Abstract: A computer-vision-based fatigue crack detection approach using a short video is described. Feature tracking is applied to the video for tracking the surface motion of the monitored structure under repetitive load. Then, a crack detection and localization algorithm is established to search for differential features at different frames in the video. The effectiveness of the proposed approach is validated through testing two experimental specimens with in-plane and out-of-plane fatigue cracks. Results indicate that the proposed approach can robustly identify fatigue cracks, even when the cracks are under ambient lighting conditions, surrounded by other crack-like edges, covered by complex surface textures, or invisible to human eyes due to crack closure. The approach enables accurate quantification of crack openings under fatigue loading with good accuracy.
-
公开(公告)号：US11354814B2
公开(公告)日：2022-06-07
申请号：US16982226
申请日：2019-03-22
Applicant: University of Kansas
Inventor： Xiangxiong Kong , Jian Li
Abstract: A computer vision-based fastener loosening detection approach is described. A first image is captured at a first time and a second image is captured at a second time. A feature-based image registration is performed to create a third image. An intensity-based image registration is performed to create a fourth image. Registration errors are determined based on a comparison of the first and fourth images. A feature enhancement process is performed on the registration errors to determine whether the fastener has loosened between the first time and the second time.
-
公开(公告)号：US20210027475A1
公开(公告)日：2021-01-28
申请号：US16982226
申请日：2019-03-22
Applicant: University of Kansas
Inventor： Xiangxiong Kong , Jian Li
Abstract: A computer vision-based fastener loosening detection approach is described. A first image is captured at a first time and a second image is captured at a second time. A feature-based image registration is performed to create a third image. An intensity-based image registration is performed to create a fourth image. Registration errors are determined based on a comparison of the first and fourth images. A feature enhancement process is performed on the registration errors to determine whether the fastener has loosened between the first time and the second time.
-
公开(公告)号：US11954844B2
公开(公告)日：2024-04-09
申请号：US17265902
申请日：2019-08-20
Applicant: University of Kansas
Inventor： Xiangxiong Kong , Jian Li
CPC classification number: G06T7/001 , G06T5/002 , G06T7/337 , G06T2207/30136 , G06T2207/30184
Abstract: An approach for fatigue crack detection is described. In one example, a first image of a structure is captured at a first time, and a second image of the structure is captured at a second time. A feature-based image registration is performed to align features of the second image with the first image, and an intensity-based image registration is performed to further align features of the second image with the first image. A registration error map is determined by performing a pixel-by-pixel intensity comparison of the first image and the second image. Additionally, an edge-aware noise reduction process can be performed on the registration error map. The registration error map can be referenced to identify certain fatigue cracks in the structure.
-
公开(公告)号：US20210166366A1
公开(公告)日：2021-06-03
申请号：US17265902
申请日：2019-08-20
Applicant: University of Kansas
Inventor： Xiangxiong Kong , Jian Li
Abstract: An approach for fatigue crack detection is described. In one example, a first image of a structure is captured at a first time, and a second image of the structure is captured at a second time. A feature-based image registration is performed to align features of the second image with the first image, and an intensity-based image registration is performed to further align features of the second image with the first image. A registration error map is determined by performing a pixel-by-pixel intensity comparison of the first image and the second image. Additionally, an edge-aware noise reduction process can be performed on the registration error map. The registration error map can be referenced to identify certain fatigue cracks in the structure.
-
-
-
-
-
-
Search Results
7
records
(took 0.013 seconds)
