Wood construction damage detection and localization using deep convolutional neural network with transfer learning

Hacıefendioğlu, Kemal; Ayas, Selen; Başağa, Hasan Basri; Toğan, Vedat; Mostofi, Fatemeh; Can, Ahmet

doi:10.1007/s00107-022-01815-5

Cited by 15 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The positive strain in the x-direction at a measurement station is given, if h(x) is the length of the beam that connects that measurement site to the neutral layer, as (8) where e jwt is the vibration mode of the structure. This is observed from the agreement between the strain modes obtained from Equation ( 8) and the curvature modes that the curvature modes and the strain modes differ by just one constant term only.…”

Section: Mutual Correspondence Of Strain Modes With Displacement and ...mentioning

confidence: 99%

See 1 more Smart Citation

Wooden Beams Modal Damage Identification Parameters Based on Strain

Cao,

Meng,

Gao

et al. 2023

Buildings

View full text Add to dashboard Cite

This study completely investigates the damage detection problem based on strain modal characteristics using simply supported wooden beams as the research object. First, modal analysis was performed, and finite element models of both damaged and undamaged timber beams were created using ABAQUS. Second, a number of strain modal characteristics (strain modal, strain modal difference, and strain modal curvature difference) were used to identify the damage to the wooden beam construction. Lastly, the modal parameters of the wooden beam under various damage scenarios were ascertained using damage identification experiments, and the test results were contrasted with those obtained from a numerical simulation. The findings showed that, while each of the three damage identification indices has a distinct identification effect, they can all locate the damage to wooden beams. Strain mode curvature difference > strain mode difference > strain mode is the order of them. The results of this study can be used as a reference to identify damage to timber beams in the future.

show abstract

Section: Mutual Correspondence Of Strain Modes With Displacement and ...mentioning

confidence: 99%

“…Researchers have been studying damage identification more and more in recent years [6][7][8]. Damage identification is an essential part of keeping historic buildings' timber structures healthy.…”

Section: Introductionmentioning

confidence: 99%

Wooden Beams Modal Damage Identification Parameters Based on Strain

Cao,

Meng,

Gao

et al. 2023

Buildings

View full text Add to dashboard Cite

show abstract

“…The computer vision methods of image classification and object detection have proven successful for this task. Haciefendioglu et al detected and classified common damage in wooden structures [13]. Ale et al utilized object detection to automatically find pavement cracks from roadway images [14].…”

Section: Introductionmentioning

confidence: 99%

Machine-Aided Bridge Deck Crack Condition State Assessment Using Artificial Intelligence

Zhang

Wogen

Liu

et al. 2023

Sensors

View full text Add to dashboard Cite

The Federal Highway Administration (FHWA) mandates biannual bridge inspections to assess the condition of all bridges in the United States. These inspections are recorded in the National Bridge Inventory (NBI) and the respective state’s databases to manage, study, and analyze the data. As FHWA specifications become more complex, inspections require more training and field time. Recently, element-level inspections were added, assigning a condition state to each minor element in the bridge. To address this new requirement, a machine-aided bridge inspection method was developed using artificial intelligence (AI) to assist inspectors. The proposed method focuses on the condition state assessment of cracking in reinforced concrete bridge deck elements. The deep learning-based workflow integrated with image classification and semantic segmentation methods is utilized to extract information from images and evaluate the condition state of cracks according to FHWA specifications. The new workflow uses a deep neural network to extract information required by the bridge inspection manual, enabling the determination of the condition state of cracks in the deck. The results of experimentation demonstrate the effectiveness of this workflow for this application. The method also balances the costs and risks associated with increasing levels of AI involvement, enabling inspectors to better manage their resources. This AI-based method can be implemented by asset owners, such as Departments of Transportation, to better serve communities.

show abstract

“…Convolutional neural networks have also been proposed to process remote sensing and aerial images in order to monitor forest infestation and health conditions or detect fires 23 – 28 . Deep learning has also entered automatic wood quality control and nondesctructive testing technology, where convolutional neural networks have been proposed to detect defects and anomalies in wood products, such as wood knots, dead knots, cracks, splits, or pest damages 29 – 37 , wood composites failure predication 35 , wood log tracing 38 or categorizing the damaged wooden elements 39 .…”

Section: Introductionmentioning

confidence: 99%

Automatic resin duct detection and measurement from wood core images using convolutional neural networks

Fabijańska

Cahalan

2023

Sci Rep

View full text Add to dashboard Cite

The structure and features of resin ducts provide valuable information about environmental conditions accompanying the growth of trees in the genus Pinus. Therefore analysis of resin duct characteristics has been an increasingly common measurement in dendrochronology. However, the measurement is tedious and time-consuming since it requires thousands of ducts to be manually marked in an image of an enlarged wood surface. Although tools exist to automate some stages of this process, no tool exists to automatically recognize and analyze the resin ducts and standardize them with the tree rings they belong to. This study proposes a new fully automatic pipeline that quantifies the properties of resin ducts in terms of the tree ring area to which they belong. A convolutional neural network underlays the pipeline to detect resin ducts and tree-ring boundaries. Also, a region merging procedure is used to identify connected components corresponding to successive rings. Corresponding ducts and rings are next related to each other. The pipeline was tested on 74 wood images representing five Pinus species. Over 8000 tree-ring boundaries and almost 25,000 resin ducts were analyzed. The proposed method detects resin ducts with a sensitivity of 0.85 and precision of 0.76. The corresponding scores for tree-ring boundary detection are 0.92 and 0.99, respectively.

show abstract

Wood construction damage detection and localization using deep convolutional neural network with transfer learning

Cited by 15 publications

References 18 publications

Wooden Beams Modal Damage Identification Parameters Based on Strain

Wooden Beams Modal Damage Identification Parameters Based on Strain

Machine-Aided Bridge Deck Crack Condition State Assessment Using Artificial Intelligence

Automatic resin duct detection and measurement from wood core images using convolutional neural networks

Contact Info

Product

Resources

About