Scholarlink

With growing emphasis on sustainable infrastructure, the maintenance and durability of existing concrete structures are critical factors. This paper proposes a novel approach leveraging Deep Learning (DL) Techniques for finding and estimating of the health of concrete buildings. The offered approach integrates advanced image processing and machine learning algorithms to analyze visual data obtained through non-destructive testing methods. Our framework focuses on first capturing and then interpreting the refined indicators of structural degradation, such as cracks, spalling, and surface irregularities, through the application of convolutional neural networks (CNNs). By training the model on a varied dataset of pictures of buildings under several environmental conditions, the system learns to identify and classify different levels of damage with high accuracy. The proposed DL-based approach offers several advantages over traditional inspection methods, including real-time analysis, cost-effectiveness, and reduced dependence on human interpretation. Having said that, with the collaboration of Artificial Intelligence (AI), the identification, detection and characterization of degradation and damage in all types of engineering structures consumes less time. Computational techniques (CT) are playing progressively important role in structural health monitoring, allowing for more accurate and efficient analysis of data from sensors and providing valuable insights into the health of structures. Machine Learning (ML) and DL models are taught from data without being specifically programmed. In other words, they take the help of algorithms to automatically learn patterns and make predictions based on the data is fed into the system. In this chapter, the researchers discuss how AI can be useful for civil engineers and mechanical engineers to monitor the health of buildings and day-by-day implementation of advanced deep learning methods is profitable to civil engineers in terms of cost as well as reduced human-efforts and people in terms of their safety.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning-Enabled Health Assessment for Sustainable Maintenance of Existing Concrete Structures: A Review

  • 章节

  • 发表日期：

    2025年

查看全文
  • Punita Panwar,
  • Khushi Goyal,
  • Jatin Kumar Shandilya

摘要

With growing emphasis on sustainable infrastructure, the maintenance and durability of existing concrete structures are critical factors. This paper proposes a novel approach leveraging Deep Learning (DL) Techniques for finding and estimating of the health of concrete buildings. The offered approach integrates advanced image processing and machine learning algorithms to analyze visual data obtained through non-destructive testing methods. Our framework focuses on first capturing and then interpreting the refined indicators of structural degradation, such as cracks, spalling, and surface irregularities, through the application of convolutional neural networks (CNNs). By training the model on a varied dataset of pictures of buildings under several environmental conditions, the system learns to identify and classify different levels of damage with high accuracy. The proposed DL-based approach offers several advantages over traditional inspection methods, including real-time analysis, cost-effectiveness, and reduced dependence on human interpretation. Having said that, with the collaboration of Artificial Intelligence (AI), the identification, detection and characterization of degradation and damage in all types of engineering structures consumes less time. Computational techniques (CT) are playing progressively important role in structural health monitoring, allowing for more accurate and efficient analysis of data from sensors and providing valuable insights into the health of structures. Machine Learning (ML) and DL models are taught from data without being specifically programmed. In other words, they take the help of algorithms to automatically learn patterns and make predictions based on the data is fed into the system. In this chapter, the researchers discuss how AI can be useful for civil engineers and mechanical engineers to monitor the health of buildings and day-by-day implementation of advanced deep learning methods is profitable to civil engineers in terms of cost as well as reduced human-efforts and people in terms of their safety.