Tiny hole inspection of aircraft engine nacelle in 3D point cloud via robust statistical fitting

Tang, Hao; Zhou, Laishui; Liu, Yuanpeng; Wang, Jun

doi:10.1016/j.measurement.2022.111250

Cited by 10 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, with the proliferation of edge computing, robotics and autonomous driving applications are latency-sensitive and commonly deployed on edge devices to interact with its surrounding environment promptly [25,39,60,64]. Although it is close to the data sources, edge computing is provisioned with limited computation power.…”

Section: Fig 1 2d Object Detection Vs 3d Object Detectionmentioning

confidence: 99%

2D-Empowered 3D Object Detection on the Edge

Li¹,

Cai²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

3D object detection has a pivotal role in a wide range of applications, most notably autonomous driving and robotics. These applications are commonly deployed on edge devices to promptly interact with the environment, and often require near real-time response. With limited computation power, it is challenging to execute 3D detection on the edge using highly complex neural networks. Common approaches such as offloading to the cloud brings latency overheads due to the large amount of 3D point cloud data during transmission. To resolve the tension between wimpy edge devices and compute-intensive inference workloads, we explore the possibility of transforming fast 2D detection results to extrapolate 3D bounding boxes. To this end, we present Moby, a novel system that demonstrates the feasibility and potential of our approach. Our main contributions are two-fold: First, we design a 2D-to-3D transformation pipeline that takes as input the point cloud data from LiDAR and 2D bounding boxes from camera that are captured at exactly the same time, and generate 3D bounding boxes efficiently and accurately based on detection results of the previous frames without running 3D detectors. Second, we design a frame offloading scheduler that dynamically launches a 3D detection when the error of 2D-to-3D transformation accumulates to a certain level, so the subsequent transformations can draw upon the latest 3D detection results with better accuracy. Extensive evaluation on NVIDIA Jetson TX2 with the autonomous driving dataset KITTI and real-world 4G/LTE traces shows that, Moby reduces the end-to-end latency by up to 91.9% with mild accuracy drop compared to baselines. Further, Moby shows excellent energy efficiency by saving power consumption and memory footprint up to 75.7% and 48.1%, respectively. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing systems and tools; • Computer systems organization → Robotics.

show abstract

Section: Fig 1 2d Object Detection Vs 3d Object Detectionmentioning

confidence: 99%

2D-Empowered 3D Object Detection on the Edge

Li¹,

Cai²,

Liu³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A boundary point detection (BPD) method was developed in (Mineo, Pierce, and Summan 2018) based on the idea that a circle created using a boundary point (BP) and its two neighbours should not include any other points. The BP detector created by (Mineo, Pierce, and Summan 2018) was further refined by (Tang et al 2022) who introduced a densitybased threshold making the point-in-circle problem more robust to small outliers. They used their circle extraction algorithm to find tiny drill holes in an aircraft engine nacelle.…”

Section: Feature Extractionmentioning

confidence: 99%

“…The algorithm uses a modification of the original BPD method developed by (Mineo, Pierce, and Summan 2018) based on the idea that a circle created using a BP and its two nearest neighbours should not include any other points. The BPD method was further refined by (Tang et al 2022) who introduced a density-based threshold making the points-in-circle problem more robust to small outliers around the edge of a boundary, Figure 3. However, the threshold was tuned for extremely high-density simulated data, and therefore is not applicable to a construction grade laser scanner such as the RTC360, Figure 4.…”

Section: Feature Extractionmentioning

confidence: 99%

“…The value is computed for each boundary point, and potential boundary points are kept if the value is larger than the threshold. The threshold value in (Tang et al 2022) was experimentally derived to be 0.95 based on the point cloud resolution and the qualities of the scanned surface. The neighbourhood size is not given.…”

Section: Feature Extractionmentioning

confidence: 99%

“…However, the method is very sensitive to a change in the threshold value, with a higher threshold meaning less points are detected, while a lower threshold means more points are detected as boundary points. Figure 4 demonstrates that in data from the RTC360 scanning in high resolution, the threshold used by (Tang et al 2022) does not detect enough BPs to determine the outline of the holes in the drilling template. The outline of the drill holes as well as the edges of the drilling template become clearer as the threshold is decreased, meaning more points are permitted within the created boundary circle.…”

Section: Feature Extractionmentioning

confidence: 99%

See 2 more Smart Citations

Registration and Feature Extraction From Terrestrial Laser Scanner Point Clouds for Aerospace Manufacturing

Pexman

Robson

2022

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Aircraft wing manufacture is becoming increasingly digitalised. For example, it is becoming possible to produce on-line digital representations of individual structural elements, components and tools as they are deployed during assembly processes. When it comes to monitoring a manufacturing environment, imaging systems can be used to track objects as they move about the workspace, comparing actual positions, alignments, and spatial relationships with the digital representation of the manufacturing process. Active imaging systems such as laser scanners and laser trackers can capture measurements within the manufacturing environment, which can be used to deduce information about both the overall stage of manufacture and progress of individual tasks. This paper is concerned with the in-line extraction of spatial information such as the location and orientation of drilling templates which are used with hand drilling tools to ensure drilled holes are accurately located. In this work, a construction grade terrestrial laser scanner, the Leica RTC360, is used to capture an example aircraft wing section in mid-assembly from several scan locations. Point cloud registration uses 1.5” white matte spherical targets that are interchangeable with the SMR targets used by the Leica AT960 MR laser tracker, ensuring that scans are connected to an established metrology control network used to define the coordinate space. Point cloud registration was achieved to sub-millimetre accuracy when compared to the laser tracker network. The location of drilling templates on the surface of the wing skin are automatically extracted from the captured and registered point clouds. When compared to laser tracker referenced hole centres, laser scanner drilling template holes agree to within 0.2mm.

show abstract

Micro drilling characterization of the carbon and carbon–aramid (hybrid) composites

Sen,

Eryilmaz,

Bakir

2024

Polymer Composites

View full text Add to dashboard Cite

In this study, micro‐drilling tests were carried out on composite laminates reinforced with hybrid (aramid‐carbon) and carbon fibers. Thrust force, hole quality, tool wear, and temperature parameters were measured and assessed following each drilling test. The quality of holes includes circularity, overcut, hole damage factor (HDF), and taper ratio. Micro‐drilling was performed on a CNC milling machine using 0.6 mm drill diameter, 7500 rpm, and 0.5 mm/min feed parameters. The plates are 3.05 mm (carbon fiber) and 3.45 mm (hybrid) thick. According to the results, the maximum thrust force (29.8 N) was measured in the hybrid composite due to the high fracture toughness of the aramid. In addition, it was determined that the thrust force and drill wear were related. The increase in thrust force during drilling caused an increase in drill wear values. While the average wear of the drill in carbon composite was 0.013 mm, the average wear of the drill in hybrid composite was 0.021 mm. Thrust force and tool temperatures were found to have a similar trend. The highest tool temperature was measured as 86.7°C in the hybrid composite. Hole quality results showed that drilling in carbon composite was more successful than in hybrid composite. Holes drilled in carbon composite have lower values for overcut (0.017 mm), HDF (1.028), and taper ratio (0.008). It has been understood that hole quality depends on thrust force and damage formation.Highlights Carbon and hybrid (carbon‐aramid) composites were produced with a vacuum infusion process (VIP). Micro‐drilling of composites was investigated focusing on thrust force, tool temperature, and hole quality. Hybrid composites exhibited greater thrust forces due to their higher toughness compared to carbon composites. Hybrid composites showed higher maximum tool temperatures compared to carbon composites. The carbon composites exhibited better hole quality compared to the hybrid composites.

show abstract

Tiny hole inspection of aircraft engine nacelle in 3D point cloud via robust statistical fitting

Cited by 10 publications

References 21 publications

2D-Empowered 3D Object Detection on the Edge

2D-Empowered 3D Object Detection on the Edge

Registration and Feature Extraction From Terrestrial Laser Scanner Point Clouds for Aerospace Manufacturing

Micro drilling characterization of the carbon and carbon–aramid (hybrid) composites

Contact Info

Product

Resources

About