Automated vision-based inspection of drilled CFRP composites using multi-light imaging and deep learning

Maghami, Ali; Salehi, Meshkat; Khoshdarregi, Matt

doi:10.1016/j.cirpj.2021.07.015

Cited by 21 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Challenges in hole quality evaluation of drilled holes in CFRP panels have recently been examined, including developing new methodologies [22,24] and the use of multi-light imaging [26]. While these studies showed good results in principle, these reported techniques may not be feasible for in situ inspection.…”

Section: Resultsmentioning

confidence: 99%

“…To address these concerns, an inspection procedure is typically performed after a hole is drilled. Non-destructive testing techniques including C-scan, X-ray, digital photography and thermography are commonly used for inspecting aerospace structures [10,14,[18][19][20][21][22][23][24][25][26]. The advantage of C-scan and X-ray techniques is their ability to allow the detection and characterisation of interlaminar delamination damage [27,28].…”

Section: Introductionmentioning

confidence: 99%

“…Hrechuk et al [22] used the Moore-Neighbor tracing algorithm and the Delaunay triangulation method to define a damage contour with optical microscopy. Maghami et al [26] designed and developed a multi-light imaging robotic end-effector to achieve a clear visual of the component by ensuring even lighting is omitted at the drilled hole for inspection. These investigations were carried out in a controlled environment and were performed manually at the end of the drilling process.…”

Section: Introductionmentioning

confidence: 99%

“…Such approaches are relatively insensitive to variations and are versatile in detecting distinct features in various application conditions [34]. These include using a convolutional neural network (CNN) to automate the vision-based inspection of CFRP composites [26], a tele-operated robot to detect defects on an aircraft surface using a deep learning algorithm [35] and visual inspection combined with deep learning to quantify the condition of the fastening bolts of a train [36]. CNNs are designed to work with image data, and a support vector machine (SVM) is a robust generic classifier developed to classify multiple-dimensional space data.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A vision-based hole quality assessment technique for robotic drilling of composite materials using a hybrid classification model

Lee,

Simeth,

Hinchy

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Robotic drilling has advantages over traditional computer numerical control machines due to its flexibility and dexterity and the potential for rapid production and process automation. The dexterity and reach of the robotic drill end-effector enable the efficient drilling of large composite components, such as aircraft wing structures. Due to the anisotropy and inhomogeneity of fibre-reinforced polymer composite materials, drilling remains a challenging task. Inspection of the drilled hole is required at the end of the process to ensure that the final product is free from defects. Typically, such inspections require the parts to be transferred to a dedicated inspection station, which is a time-consuming non-value-added task and impractical for large components. In the interest of an efficient and sustainable manufacturing process, this work proposes a hybrid classification model implemented with a robotic drilling system to investigate the quality of drilled holes in situ. The classifier is trained and tested with a random selection of drilled holes, and the most accurate classifier is implemented. The selected classifier returns 90% overall prediction accuracy on unseen drilled holes. This machine learning-based approach, using a convolutional neural network and support vector machine classifier, can significantly improve inspection reliability while reducing production time for drilled composite components. This is the first study that demonstrates a hole quality assessment technique for robotic drilling of composite material in situ at scale.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A vision-based hole quality assessment technique for robotic drilling of composite materials using a hybrid classification model

Lee,

Simeth,

Hinchy

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

show abstract

“…Given the above-mentioned limitations, future research will introduce machine vision and other methods to automatically identify and calculate hole defects to improve the measurement efficiency [24][25][26][27][28][29] and the orthogonal test method [30,31] to reduce the number of tests and the order of the fuzzy complementary judgment matrix.…”

Section: Discussionmentioning

confidence: 99%

Synthesize evaluation method of characteristic defects in hole drilling of carbon fiber reinforced polymer

Liang

Liu

Guan

2023

Preprint

View full text Add to dashboard Cite

Carbon fiber reinforced polymer (CFRP) composites are widely used in various fields because of their high strength, good toughness, and low density. However, owing to their unique forming process, some complex structures such as holes and grooves cannot be formed directly. Therefore, traditional machining procedures are also required. The drilling process is one of the most common machining methods for CFRP material holes, but owing to the complex structure and difficulty in processing CFRP composite material, the quality of the drilling process is often challenging to guarantee. Moreover, the hole-forming defects also have complex forms and lack uniform evaluation indexes. This study summarizes the common orifice defects in the process of CFRP drilling, establishes a comprehensive evaluation method of orifice defects by introducing the relevant theory of the fuzzy complementary judgment matrix, and experimentally verifies the accuracy and reliability of this method. Then, based on the experimental results, a non-linear cutting parameter optimization model is established, which effectively suppresses the orifice defects to ensure the accuracy of the hole size, roundness, and hole wall roughness. The hole-forming quality is subsequently improved. The hole quality evaluation method proposed in this study reduced the dimension of the evaluation index to ensure relevance and effectiveness and improved the convenience of quality inspection and parameter optimization in actual production.

show abstract

Research solution for automatic hole quality analysis when drilling fiber-reinforced composites

Hrechuk

Hörndahl

Schultheiss

2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Fiber-reinforced polymers are highly demanding composites in aerospace and automotive areas because of their excellent mechanical properties such as stiffness and strength-to-weight ratio. The drilling remains the major machining operation applied to composites to provide high-quality holes for joints between parts. Due to composites plied structure, the drilling is accompanied with unusual form metal cutting defects such as delamination and uncut fibers around the drilled hole. Considering that the tool life of some drills reaches over thousands of holes, the research of composites machinability becomes difficult due to demanded labor intensity in manual inspection of the hole quality. Therefore, this paper develops the research solution for automatic analysis of the hole quality in drilled fiber-reinforced materials. The paper proposes a complex of solutions aimed to speed up the analysis of the hole quality when composites drilling. The solution consists of the developed vacuum table, robot arm with high-speed camera, developed top and bottom lightning systems, and Image Processing algorithms for defect detection from captured images. The paper results show how the developed solution can be used for high routine research activities. The output data, including tested 72 cutting data parameters and full-size tool life test, allowed identifying the operational window for high-speed steel drills and the range of tool life, where drill ensures a certain hole quality. The paper shows the efficiency of the developed research solution can reach 5 s per hole including drilling and full cycle of measurements having measurement error of 1–3%.

show abstract

Automated vision-based inspection of drilled CFRP composites using multi-light imaging and deep learning

Cited by 21 publications

References 31 publications

A vision-based hole quality assessment technique for robotic drilling of composite materials using a hybrid classification model

A vision-based hole quality assessment technique for robotic drilling of composite materials using a hybrid classification model

Synthesize evaluation method of characteristic defects in hole drilling of carbon fiber reinforced polymer

Research solution for automatic hole quality analysis when drilling fiber-reinforced composites

Contact Info

Product

Resources

About