Xiaoguang Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaoguang Wu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:
- Junguang Wang
School of Highway, Chang’an University, Xi’an 710064, China
2 shared publications - Kejian Hu
Highway School, Chang'an University, Xi'an, China
2 shared publications - Qian Huang
School of Highway, Chang’an University, Xi’an 710064, China
2 shared publications - Di Mo
School of Highway, Chang’an University, Xi’an 710064, China
1 shared publication - Hui Wei
China Railway 20th Bureau Group Co., Ltd., Xi’an 710016, China
1 shared publication - Jiahao Yin
School of Highway, Chan’an University, Xi’an 710000, China
1 shared publication
Latest Publications
- Open Access
- 21 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12386
Research on Technical Condition of Concrete Bridges Based on FastText+CNN
Addressing the challenges of scarce measured data for Class 3–4 bridges and strong subjectivity in manual assessments in bridge technical-condition evaluation, this study innovatively proposes a FastText+CNN evaluation model that integrates semantic features with spatial pattern recognition. By constructing a hierarchical data structure of bridge scale matrices using the analytic hierarchy process (AHP) and generating a balanced training set encompassing Class 1–5 bridges through computational code, the model overcomes the bottleneck of training under small-sample conditions. It employs N-Gram embeddings to achieve semantic representation of defect feature combinations, combines one-dimensional convolutional neural networks to capture cross-component spatial correlation patterns, and utilizes hierarchical Softmax to optimize multi-classification efficiency. Experiments show that the model achieves 92.4% accuracy on the test set, outperforming random forest and multi-layer CNN models by 15.9% and 3.7%, respectively, with recognition rates for Class 3–5 bridges rising to 85% and cross-entropy loss reduced to 0.36. Validated with data from 30 actual bridges, the model maintains 92.3% accuracy and demonstrates the ability to discover implicit patterns in cross-component defect chains, providing an intelligent solution for bridge technical condition evaluation that combines semantic understanding with spatial feature extraction.
- 21 November 2025
- Published by MDPI AG in Applied Sciences
- Vol. 15 (23) , 12386
Open AccessResearch on Technical Condition of Concrete Bridges Based on FastText+CNN
Addressing the challenges of scarce measured data for Class 3–4 bridges and strong subjectivity in manual assessments in bridge technical-condition evaluation, this study innovatively proposes a FastText+CNN evaluation model that integrates semantic features with spatial pattern recognition. By constructing a hierarchical data structure of bridge scale matrices using the analytic hierarchy process (AHP) and generating a balanced training set encompassing Class 1–5 bridges through computational code, the model overcomes the bottleneck of training under small-sample conditions. It employs N-Gram embeddings to achieve semantic representation of defect feature combinations, combines one-dimensional convolutional neural networks to capture cross-component spatial correlation patterns, and utilizes hierarchical Softmax to optimize multi-classification efficiency. Experiments show that the model achieves 92.4% accuracy on the test set, outperforming random forest and multi-layer CNN models by 15.9% and 3.7%, respectively, with recognition rates for Class 3–5 bridges rising to 85% and cross-entropy loss reduced to 0.36. Validated with data from 30 actual bridges, the model maintains 92.3% accuracy and demonstrates the ability to discover implicit patterns in cross-component defect chains, providing an intelligent solution for bridge technical condition evaluation that combines semantic understanding with spatial feature extraction.
- Open Access
Study on the Shear Lag Calculation Method for Damaged Box Girder
Shear lag stresses increase significantly in cracked concrete box girders; however, most existing models assume intact sections and are, therefore, unsuitable for rapid field diagnosis. This study integrates a stepped stiffness model with deflection influence lines to accurately capture the mechanical response of damaged, simply supported box girders. Regions containing flexural cracks are assigned a reduced bending stiffness , whereas intact zones retain the original stiffness . A closed-form stiffness-reduction coefficient is obtained from crack geometry and, independently, from the second derivative of the deflection influence line. Embedding in a variational shear lag formulation yields explicit expressions for flange displacement and normal stress without numerical iteration. This approach is validated by finite element simulations of a plexiglass scale model with four preset damage levels and by a load test on a 30 m prestressed concrete box girder bridge. Field measurements show that midspan stiffness decreased to 81% of the as-built value; the proposed method reproduces this value with a deviation of 3%. Predicted upper-flange stresses differ from measured values by 5.7–13.6% and from finite element results by less than 10% for damage ratios up to 40%. The second derivative of the influence line difference exhibits a distinct peak at the cracked region, accurately localizing the damage. Compared with classical formulas, the proposed model (i) is fully closed-form, (ii) links global deflection data to local shear lag stresses, and (iii) delivers conservative estimates suitable for routine bridge assessment.Open AccessStudy on the Shear Lag Calculation Method for Damaged Box Girder
Shear lag stresses increase significantly in cracked concrete box girders; however, most existing models assume intact sections and are, therefore, unsuitable for rapid field diagnosis. This study integrates a stepped stiffness model with deflection influence lines to accurately capture the mechanical response of damaged, simply supported box girders. Regions containing flexural cracks are assigned a reduced bending stiffness , whereas intact zones retain the original stiffness . A closed-form stiffness-reduction coefficient is obtained from crack geometry and, independently, from the second derivative of the deflection influence line. Embedding in a variational shear lag formulation yields explicit expressions for flange displacement and normal stress without numerical iteration. This approach is validated by finite element simulations of a plexiglass scale model with four preset damage levels and by a load test on a 30 m prestressed concrete box girder bridge. Field measurements show that midspan stiffness decreased to 81% of the as-built value; the proposed method reproduces this value with a deviation of 3%. Predicted upper-flange stresses differ from measured values by 5.7–13.6% and from finite element results by less than 10% for damage ratios up to 40%. The second derivative of the influence line difference exhibits a distinct peak at the cracked region, accurately localizing the damage. Compared with classical formulas, the proposed model (i) is fully closed-form, (ii) links global deflection data to local shear lag stresses, and (iii) delivers conservative estimates suitable for routine bridge assessment. - Open Access
- 1 December 2024
- Published by Tsinghua University Press in Journal of Highway and Transportation Research and Development (English Edition)
- Vol. 18 (4) , 128-135
Degradation analysis of concrete bridge load-bearing capacity based on crack distribution
In-service reinforced concrete bridges, following prolonged operational periods, frequently undergo alterations in structural integrity and significant deterioration of material properties. As a result, it becomes imperative to evaluate and analyze these bridge structures. This study focuses on a specific in-service concrete bridge and employs finite element simulation analysis to investigate the failure behavior and degradation of load-bearing capacity in concrete beam bridge structures. The research examines the impact of various crack distributions and types, specifically addressing the effects of bending and shear cracks on the failure behavior and degradation of load-bearing capacity in concrete bridge structures. Load simulations are conducted on the bridge, revealing that bending cracks exert a relatively minor influence on the failure mode of the structures. The load-deflection curves demonstrate minimal variation across different crack heights, indicating that the structures do not experience abrupt brittle failure, and their structural performance is largely optimized in this context. Conversely, shear cracks have a pronounced effect on the failure mode of the bridge structures. Notably, when the crack height reaches 0.6h, the load-deflection curve exhibits a significant alteration, leading to brittle failure attributed to shear cracks, thereby indicating that the structural performance is not fully realized. Given that the deformations in cracked bridge structures comprise two components, stiffness reduction formulas are introduced. Utilizing the stiffness reduction formula outlined in the standard (JCT3362—2018) for cracked components, a formula for calculating residual load-bearing capacity is derived. Calculations pertaining to the mid-span section load-bearing capacity of the selected bridge reveal deviations within 5%. This study offers a valuable methodology and reference for assessing the residual load-bearing capacity of reinforced concrete bridges exhibiting crack damage.
- 1 December 2024
- Published by Tsinghua University Press in Journal of Highway and Transportation Research and Development (English Edition)
- Vol. 18 (4) , 128-135
Open AccessDegradation analysis of concrete bridge load-bearing capacity based on crack distribution
In-service reinforced concrete bridges, following prolonged operational periods, frequently undergo alterations in structural integrity and significant deterioration of material properties. As a result, it becomes imperative to evaluate and analyze these bridge structures. This study focuses on a specific in-service concrete bridge and employs finite element simulation analysis to investigate the failure behavior and degradation of load-bearing capacity in concrete beam bridge structures. The research examines the impact of various crack distributions and types, specifically addressing the effects of bending and shear cracks on the failure behavior and degradation of load-bearing capacity in concrete bridge structures. Load simulations are conducted on the bridge, revealing that bending cracks exert a relatively minor influence on the failure mode of the structures. The load-deflection curves demonstrate minimal variation across different crack heights, indicating that the structures do not experience abrupt brittle failure, and their structural performance is largely optimized in this context. Conversely, shear cracks have a pronounced effect on the failure mode of the bridge structures. Notably, when the crack height reaches 0.6h, the load-deflection curve exhibits a significant alteration, leading to brittle failure attributed to shear cracks, thereby indicating that the structural performance is not fully realized. Given that the deformations in cracked bridge structures comprise two components, stiffness reduction formulas are introduced. Utilizing the stiffness reduction formula outlined in the standard (JCT3362—2018) for cracked components, a formula for calculating residual load-bearing capacity is derived. Calculations pertaining to the mid-span section load-bearing capacity of the selected bridge reveal deviations within 5%. This study offers a valuable methodology and reference for assessing the residual load-bearing capacity of reinforced concrete bridges exhibiting crack damage.
- Open Access
- 12 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (2) , 641
A PZT-Based Smart Anchor Washer for Monitoring Prestressing Force Based on the Wavelet Packet Analysis Method
Prestressed steel strands in prestressed structures offset or reduce the tensile stress caused by external loads, making them the primary load-bearing components. Great concerns have been raised about prestress monitoring due to the growing use of structural health monitoring (SHM). Piezoceramic (PZT) active sensing methods are commonly used in this field. However, there appears to be a problem of “energy saturation” in the utilization of piezoceramic active sensing methods. In this study, a smart anchor washer with semi-cylinders was developed to alleviate the saturation problem. An intelligent monitoring system is formed by combining the upper and lower annular cylinders with two piezoelectric patches. The piezoelectric patch on the upper annular cylinder is used as an actuator to emit signals through the contact interface of the smart anchor washer, which are then received by the piezoelectric patch on the lower annular cylinder. Based on wavelet packet decomposition, we investigate the correlation between the energy of the received signal and the applied tension force. Finally, a prestressing force index is developed for monitoring prestressing force using Shannon entropy. It is found that the index decreases with the increase in tension. The proposed design and index are also sensitive to early monitoring of prestressing force and can be used to monitor the entire prestressing process of steel strands.
- 12 January 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (2) , 641
Open AccessA PZT-Based Smart Anchor Washer for Monitoring Prestressing Force Based on the Wavelet Packet Analysis Method
Prestressed steel strands in prestressed structures offset or reduce the tensile stress caused by external loads, making them the primary load-bearing components. Great concerns have been raised about prestress monitoring due to the growing use of structural health monitoring (SHM). Piezoceramic (PZT) active sensing methods are commonly used in this field. However, there appears to be a problem of “energy saturation” in the utilization of piezoceramic active sensing methods. In this study, a smart anchor washer with semi-cylinders was developed to alleviate the saturation problem. An intelligent monitoring system is formed by combining the upper and lower annular cylinders with two piezoelectric patches. The piezoelectric patch on the upper annular cylinder is used as an actuator to emit signals through the contact interface of the smart anchor washer, which are then received by the piezoelectric patch on the lower annular cylinder. Based on wavelet packet decomposition, we investigate the correlation between the energy of the received signal and the applied tension force. Finally, a prestressing force index is developed for monitoring prestressing force using Shannon entropy. It is found that the index decreases with the increase in tension. The proposed design and index are also sensitive to early monitoring of prestressing force and can be used to monitor the entire prestressing process of steel strands.
- Open Access
- 27 October 2023
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 439, 02003
Analysis of the flexural performance of Precast Box Girders Reinforced with a combination of Steel-Slab-Concrete Plus Unbonded Prestressing
Due to the serious development of cracks in precast box girders, there is no reliable method to detect the loss of prestress and carry out effective reinforcement of box girders. This paper proposes a reinforcement method of steel plate - concrete with unbonded prestressing, and applies this method to a 30m reinforced concrete prestressed box girder bridge. This paper uses FEA software to carry out a comparative analysis of the load-deflection curve of the reinforced mid-span section by comparing with the conventional bonded steel reinforcement method and the load test data, and through the analysis results, the calculation formula of the flexural load capacity of the steel plate-concrete with unbonded prestressing reinforcement method is derived. The results show that the flexural load carrying capacity of the strengthened mid-span section is significantly improved, and the proposed calculation formulae deviate from the finite element simulation results within 5%, which can be applied to actual projects.
- 27 October 2023
- Published by EDP Sciences in E3S Web of Conferences
- Vol. 439, 02003
Open AccessAnalysis of the flexural performance of Precast Box Girders Reinforced with a combination of Steel-Slab-Concrete Plus Unbonded Prestressing
Due to the serious development of cracks in precast box girders, there is no reliable method to detect the loss of prestress and carry out effective reinforcement of box girders. This paper proposes a reinforcement method of steel plate - concrete with unbonded prestressing, and applies this method to a 30m reinforced concrete prestressed box girder bridge. This paper uses FEA software to carry out a comparative analysis of the load-deflection curve of the reinforced mid-span section by comparing with the conventional bonded steel reinforcement method and the load test data, and through the analysis results, the calculation formula of the flexural load capacity of the steel plate-concrete with unbonded prestressing reinforcement method is derived. The results show that the flexural load carrying capacity of the strengthened mid-span section is significantly improved, and the proposed calculation formulae deviate from the finite element simulation results within 5%, which can be applied to actual projects.
- Open Access
- 19 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (18) , 9373
Proposed New Analytical Method of Tower Load in Large-Span Arch Bridge Cable Lifting Construction
The cable lifting construction method is the most widely used construction method for large-span arch bridges. The correct calculation and analysis of cable lifting construction is essential to ensure the safety and linearity in the construction of arch bridges. The existing research mainly focuses on the construction scheme and finite element analysis of cable lifting for large-span arch bridges. There is relatively little research on calculation theory, and there is no analytical method for cable lifting construction of arch bridges. To calculate and analyze cable lifting construction more quickly and accurately, based on the deformation coordination principle and suspension cable theory, a practical calculation method is proposed to calculate the load of the tower acting by a cable system in the cable lifting construction of arch bridges. A large-span arch bridge under construction was used as a case study, and the correctness of the calculation method was verified by measuring the displacements of the tower top. A brief description of the structure, verification method, and verification process is presented. The displacement results are calculated by the numerical calculation software SAP2000, the actual measured displacement data are discussed and comparatively analyzed, and the correctness and calculation accuracy of the proposed calculation method are also evaluated. The results show that the calculation method has sufficient accuracy. The tower load calculation is mainly undertaken to prepare for the analysis of the tower mechanical properties; therefore, the calculation method is applied to towers of the case engineering, and the stability, load carrying capacity, and deformation of the tower are analyzed to verify whether its mechanical properties meet the engineering requirements. The results show that steel pipe columns of the buckle tower are prone to twisting instability. The normal stress of the tower’s part of the pressurized rod or pressurized bending rod is larger. Wind cable load calculation models and tower design-related recommendations are presented in this tower analysis. The tower load calculation method and tower mechanics analysis method in this study can provide guidance for the calculation and analysis of the cable lifting construction of large-span arch bridges.
- 19 September 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (18) , 9373
Open AccessProposed New Analytical Method of Tower Load in Large-Span Arch Bridge Cable Lifting Construction
The cable lifting construction method is the most widely used construction method for large-span arch bridges. The correct calculation and analysis of cable lifting construction is essential to ensure the safety and linearity in the construction of arch bridges. The existing research mainly focuses on the construction scheme and finite element analysis of cable lifting for large-span arch bridges. There is relatively little research on calculation theory, and there is no analytical method for cable lifting construction of arch bridges. To calculate and analyze cable lifting construction more quickly and accurately, based on the deformation coordination principle and suspension cable theory, a practical calculation method is proposed to calculate the load of the tower acting by a cable system in the cable lifting construction of arch bridges. A large-span arch bridge under construction was used as a case study, and the correctness of the calculation method was verified by measuring the displacements of the tower top. A brief description of the structure, verification method, and verification process is presented. The displacement results are calculated by the numerical calculation software SAP2000, the actual measured displacement data are discussed and comparatively analyzed, and the correctness and calculation accuracy of the proposed calculation method are also evaluated. The results show that the calculation method has sufficient accuracy. The tower load calculation is mainly undertaken to prepare for the analysis of the tower mechanical properties; therefore, the calculation method is applied to towers of the case engineering, and the stability, load carrying capacity, and deformation of the tower are analyzed to verify whether its mechanical properties meet the engineering requirements. The results show that steel pipe columns of the buckle tower are prone to twisting instability. The normal stress of the tower’s part of the pressurized rod or pressurized bending rod is larger. Wind cable load calculation models and tower design-related recommendations are presented in this tower analysis. The tower load calculation method and tower mechanics analysis method in this study can provide guidance for the calculation and analysis of the cable lifting construction of large-span arch bridges.
- Open Access
- 22 August 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (16) , 8370
Innovative Design of Novel Main and Secondary Arch Collaborative Y-Shaped Arch Bridge and Research on Shear Lag Effect of Its Unconventional Thin-Walled Steel Box Arch Ribs
The first main and secondary collaborative Y-shaped steel box arch bridge under construction in China is a rarely seen innovative practice among bridges already built at home and abroad, which is an attractive engineering research topic in the field of advanced bridge design and construction, and the investigation of this bridge has made a groundbreaking contribution. The structure of unconventional thin-walled steel box arch ribs is very novel, abandoning the traditional two-dimensional arch rib structure form and adopting the new structural mode of single–double combination and joint working of main and secondary arches. However, for this innovative design, many technical difficulties including innovative design details, mechanical behavior of thin-walled structures and construction methods still need to be pioneeringly explored and thoroughly researched. In this paper, the innovative design concept of unconventional thin-walled arch ribs for spatial Y-shaped steel box arch bridges is described, and a comparative analysis with the corresponding conventional single arch rib structure is carried out. Due to the limitations of the common conventional arch bridge research methods, a combined global and local finite element method is used to analyze the static and dynamic properties of the structure, and the shear lag effect of the thin-walled steel box arch ribs is studied in a pioneering and exploratory approach. In addition, the stress distribution of the bifurcated section of the arch ribs and the configuration of the diaphragm are analyzed in detail to verify the reasonableness, advantage and applicability of the innovative design. The results show that the main and secondary arch collaboration Y-shaped steel box arch bridge has reasonable structure and superior mechanical properties and has a greater value for promotion The design concept and analysis method are worthy of use as a reference for the aesthetical and mechanical design of similar spatial Y-shaped arch bridges in the future.
- 22 August 2022
- Published by MDPI AG in Applied Sciences
- Vol. 12 (16) , 8370
Open AccessInnovative Design of Novel Main and Secondary Arch Collaborative Y-Shaped Arch Bridge and Research on Shear Lag Effect of Its Unconventional Thin-Walled Steel Box Arch Ribs
The first main and secondary collaborative Y-shaped steel box arch bridge under construction in China is a rarely seen innovative practice among bridges already built at home and abroad, which is an attractive engineering research topic in the field of advanced bridge design and construction, and the investigation of this bridge has made a groundbreaking contribution. The structure of unconventional thin-walled steel box arch ribs is very novel, abandoning the traditional two-dimensional arch rib structure form and adopting the new structural mode of single–double combination and joint working of main and secondary arches. However, for this innovative design, many technical difficulties including innovative design details, mechanical behavior of thin-walled structures and construction methods still need to be pioneeringly explored and thoroughly researched. In this paper, the innovative design concept of unconventional thin-walled arch ribs for spatial Y-shaped steel box arch bridges is described, and a comparative analysis with the corresponding conventional single arch rib structure is carried out. Due to the limitations of the common conventional arch bridge research methods, a combined global and local finite element method is used to analyze the static and dynamic properties of the structure, and the shear lag effect of the thin-walled steel box arch ribs is studied in a pioneering and exploratory approach. In addition, the stress distribution of the bifurcated section of the arch ribs and the configuration of the diaphragm are analyzed in detail to verify the reasonableness, advantage and applicability of the innovative design. The results show that the main and secondary arch collaboration Y-shaped steel box arch bridge has reasonable structure and superior mechanical properties and has a greater value for promotion The design concept and analysis method are worthy of use as a reference for the aesthetical and mechanical design of similar spatial Y-shaped arch bridges in the future.
- Open Access
- 1 January 2022
- Published by Wiley in Advances in Civil Engineering
- Vol. 2022 (1)
A Bridge Structure 3D Representation for Deep Neural Network and Its Application in Frequency Estimation
Currently, most predictions related to bridge geometry use shallow neural networks, which limit the network’s ability to fit since the input form limits the depth of the neural network. Therefore, this study proposed a new 3D representation of bridge structures. Based on the geometric parameters of the bridge structure, three 4D tensors were formed. This form of representation not only retained all geometric information but also expressed the spatial relationship of the structure. Then, this study constructed the corresponding 3D convolutional neural network and used it to estimate the frequency of the bridge. In addition, this study also developed a traditional shallow neural network for comparison. The application of 3D representation and 3D convolution could effectively reduce the prediction error. The 3D representation presented in this study could be used not only for frequency prediction but also for any prediction problems related to bridge geometry.
- 1 January 2022
- Published by Wiley in Advances in Civil Engineering
- Vol. 2022 (1)
Open AccessA Bridge Structure 3D Representation for Deep Neural Network and Its Application in Frequency Estimation
Currently, most predictions related to bridge geometry use shallow neural networks, which limit the network’s ability to fit since the input form limits the depth of the neural network. Therefore, this study proposed a new 3D representation of bridge structures. Based on the geometric parameters of the bridge structure, three 4D tensors were formed. This form of representation not only retained all geometric information but also expressed the spatial relationship of the structure. Then, this study constructed the corresponding 3D convolutional neural network and used it to estimate the frequency of the bridge. In addition, this study also developed a traditional shallow neural network for comparison. The application of 3D representation and 3D convolution could effectively reduce the prediction error. The 3D representation presented in this study could be used not only for frequency prediction but also for any prediction problems related to bridge geometry.
- Open Access
- 1 January 2022
- Published by Wiley in Advances in Civil Engineering
- Vol. 2022 (1)
Prediction of Effective Width of Varying Depth Box‐Girder Bridges Using Convolutional Neural Networks
Effective flange width is widely used in bridge design to consider the effect of shear lag. The simplified formula for the effective flange width of box girder bridges of variable depth in existing codes and studies may not be conservative, and accurate methods, such as the finite element method, are time‐consuming. The purpose of this research is to develop a method that uses a convolutional neural network (CNN) to predict the effective width of box girder bridges of varying depths. These models have been trained, validated, and tested on datasets generated from thousands of finite element models. The lower error in the test set indicates that the CNN model can be used to predict the effective width. In addition, the impact of different architectures is also studied. The proposed method makes real‐time analysis possible and has a wide range of applications in the analysis and design of box‐girder bridges at different depths.
- 1 January 2022
- Published by Wiley in Advances in Civil Engineering
- Vol. 2022 (1)
Open AccessPrediction of Effective Width of Varying Depth Box‐Girder Bridges Using Convolutional Neural Networks
Effective flange width is widely used in bridge design to consider the effect of shear lag. The simplified formula for the effective flange width of box girder bridges of variable depth in existing codes and studies may not be conservative, and accurate methods, such as the finite element method, are time‐consuming. The purpose of this research is to develop a method that uses a convolutional neural network (CNN) to predict the effective width of box girder bridges of varying depths. These models have been trained, validated, and tested on datasets generated from thousands of finite element models. The lower error in the test set indicates that the CNN model can be used to predict the effective width. In addition, the impact of different architectures is also studied. The proposed method makes real‐time analysis possible and has a wide range of applications in the analysis and design of box‐girder bridges at different depths.
- Open Access
- 1 January 2020
- Published by Tech Science Press in Structural Durability & Health Monitoring
- Vol. 14 (4) , 355-374
Research on Concrete Beam Crack Recognition Algorithm Based on Block Threshold Value Image Processing
To solve the problem that the digital image recognition accuracy of concrete structure cracks is not high under the condition of uneven illumination and complex surface color of concrete structure, this paper has proposed a block segmentation method of maximum entropy threshold based on the digital image data obtained by the ACTIS automatic detection system. The steps in this research are as follows: 1. The crack digital images of concrete specimens with typical features were collected by using the Actis system of KURABO Co., Ltd., of Japan in the concrete beam bending test. 2. The images are segmented into blocks to distinguish backgrounds of different grayscale. 3. The maximum interclass average gray difference method is used to distinguish the sub-blocks and screen out the image blocks that need to be segmented. 4. Segmentation is made to the image with 2D maximum entropy threshold segmentation method to obtain the binary image, and the target image can be obtained by screening the connected domain features of the binary image. Results have shown that compared with other algorithms, the proposed method can effectively decrease the image over-segmentation and under segmentation rates, highlight the characteristics of the target cracks, solve the problems of excessive difference between the identified length and actual length of cracks caused by background gray level change and uneven illumination, and effectively improve the recognition accuracy of bridge concrete cracks.
- 1 January 2020
- Published by Tech Science Press in Structural Durability & Health Monitoring
- Vol. 14 (4) , 355-374
Open AccessResearch on Concrete Beam Crack Recognition Algorithm Based on Block Threshold Value Image Processing
To solve the problem that the digital image recognition accuracy of concrete structure cracks is not high under the condition of uneven illumination and complex surface color of concrete structure, this paper has proposed a block segmentation method of maximum entropy threshold based on the digital image data obtained by the ACTIS automatic detection system. The steps in this research are as follows: 1. The crack digital images of concrete specimens with typical features were collected by using the Actis system of KURABO Co., Ltd., of Japan in the concrete beam bending test. 2. The images are segmented into blocks to distinguish backgrounds of different grayscale. 3. The maximum interclass average gray difference method is used to distinguish the sub-blocks and screen out the image blocks that need to be segmented. 4. Segmentation is made to the image with 2D maximum entropy threshold segmentation method to obtain the binary image, and the target image can be obtained by screening the connected domain features of the binary image. Results have shown that compared with other algorithms, the proposed method can effectively decrease the image over-segmentation and under segmentation rates, highlight the characteristics of the target cracks, solve the problems of excessive difference between the identified length and actual length of cracks caused by background gray level change and uneven illumination, and effectively improve the recognition accuracy of bridge concrete cracks.