Background: In the context of rapid urbanization, the need for building safety and durability assessment is becoming increasingly prominent. Objective: The aim of this paper is to review the strengths and weaknesses of the main non-destructive testing (NDT) techniques in construction engineering, with a focus on the application of deep learning in image-based NDT. Design: We surveyed more than 80 papers published within the last decade to assess the role of deep learning techniques combined with NDT in automated inspection in construction. Results: Deep learning significantly enhances defect detection accuracy and efficiency in construction NDT, particularly in image-based techniques such as infrared thermography, ground-penetrating radar, and ultrasonic inspection. Multi-technology fusion and data integration effectively address the limitations of single methods. However, challenges remain, including data complexity, resolution limitations, and insufficient sample sizes in NDT images, which hinder deep learning model training and optimization. Conclusions: This paper not only summarizes the existing research results, but also discusses the future optimization direction of the target detection network for NDT defect data, aiming to promote intelligent development in the field of non-destructive testing of buildings, and to provide more efficient and accurate solutions for building maintenance.

It is crucial to optimize the proportioning parameters of manufactured sand concrete by combining particle shape images. This article adopts a research method combining theoretical analysis and physical experiments, using DIP method to obtain quantitative image characterization parameters of mechanism sand particle shape,study the mechanical performance laws of manufactured sand concrete affected by different characterization parameters, and obtain reasonable quantitative parameters of particle shape characterization and optimized mix proportion of manufactured sand concrete. The research results indicate that: (1) The DIP particle shape image method is used to accurately obtain the random parameters of dispersed manufactured sand, and the roundness, edge angle, and particle size ratio are used to characterize the particle shape distribution characteristics more accurately. Small particle size manufactured sand exhibits more uniform particle shape images. (2) Establishing an optimization model for compressive performance with water cement ratio, fly ash mineral powder admixture, and sand ratio as influencing factors, analyzing the changes in mechanical properties of Manufactured Sand concrete under the influence of influencing factors.(3) Comparative analysis shows that the water cement ratio has the most significant impact on the compressive strength of manufactured sand concrete, while the effect of fly ash and mineral powder admixture and sand ratio is relatively small. The optimal ratio is a water cement ratio of 0.32, mineral powder content of 20%, and sand ratio of 45%. The research results provide effective data support for the quantitative application of manufactured sand production.

The concrete of bridge pile foundations always bear excessive axial loads, and accompanying with its internal failure and crack process, elastic waves will be emitted. In order to quantify the characteristics of the entire instability evolution process of concrete, the temporal and spatial evolution characteristics of acoustic emission in the whole loading process of concrete specimens drilled in situ from bridge pile foundation structures were studied and synchronous monitoring tests of axial compression and acoustic emission were conducted. The relation between the whole process of compressive instability and the acoustic emission ringing counts, energy release, focal locations and other characterization parameters were analyzed. Then, a quantitative description of the correlation between the loading process and acoustic emission characteristics was obtained, and its instability evolution process was analyzed. The results indicated that the stress of concrete specimens under axial compression was consistent with the change law of the acoustic emission ringing counts and energy release with times, and the acoustic emission positioning points mainly located in a macro “positioning zone” in the shear stress concentration area, which was consistent with the development and failure of concrete cracks. The loading stage of concrete could be quantitatively judged according to activity of acoustic emission, which could reflected the critical characteristics of concrete instability, and was of great significance to service monitoring of pile foundation concrete.