Description:
Monitoring of structures to identify types of damages that occur under loading is essential in practical applications of civil infrastructure. In this paper, we detect and visualize damage based on several non-destructive testing (NDT) methods. A machine learning (ML) approach based on the Support Vector Machine (SVM) method is developed to prevent misdirection of the event interpretation of what is happening in the material. The objective is to identify cracks in the early stages, to reduce the risk of failure in structures. Theoretical and experimental analyses are derived by computing the performance indicators on the smart aggregate (SA)-based sensor data for concrete and reinforced-concrete (RC) beams. Validity assessment of the proposed indices was addressed through a comparative analysis with traditional SVM. The developed ML algorithms are shown to recognize cracks with a higher accuracy than the traditional SVM. Additionally, we propose different algorithms for microwave- or millimeter-wave imaging of steel plates, composite materials, and metal plates, to identify and visualize cracks. The proposed algorithm for steel plates is based on the gradient magnitude in four directions of an image, and is followed by the edge detection technique. Three algorithms were proposed for each of composite materials and metal plates, and are based on 2D fast Fourier transform (FFT) and hybrid fuzzy c-mean techniques, respectively. The proposed algorithms were able to recognize and visualize the cracking incurred in the structure more efficiently than the traditional techniques. The reported results are expected to be beneficial for NDT-based applications, particularly in civil engineering.
Description:
Monitoring of structures to identify types of damages that occur under loading is essential in practical applications of civil infrastructure. In this paper, we detect and visualize damage based on several non-destructive testing (NDT) methods. A machine learning (ML) approach based on the Support Vector Machine (SVM) method is developed to prevent misdirection of the event interpretation of what is happening in the material. The objective is to identify cracks in the early stages, to reduce the risk of failure in structures. Theoretical and experimental analyses are derived by computing the performance indicators on the smart aggregate (SA)-based sensor data for concrete and reinforced-concrete (RC) beams. Validity assessment of the proposed indices was addressed through a comparative analysis with traditional SVM. The developed ML algorithms are shown to recognize cracks with a higher accuracy than the traditional SVM. Additionally, we propose different algorithms for microwave- or millimeter-wave imaging of steel plates, composite materials, and metal plates, to identify and visualize cracks. The proposed algorithm for steel plates is based on the gradient magnitude in four directions of an image, and is followed by the edge detection technique. Three algorithms were proposed for each of composite materials and metal plates, and are based on 2D fast Fourier transform (FFT) and hybrid fuzzy c-mean techniques, respectively. The proposed algorithms were able to recognize and visualize the cracking incurred in the structure more efficiently than the traditional techniques. The reported results are expected to be beneficial for NDT-based applications, particularly in civil engineering.
Description:
Monitoring of structures and defining the severity of damages that occur under loading are essential in practical applications of civil infrastructure. In this article, we analyze failure using a smart aggregate sensor–based approach. The signals captured by smart aggregate sensors mounted on the structure under loading are de-noised using wavelet de-noising technique to prevent misdirection of the event interpretation of what is happening in the material. The performance of different mother wavelets on the de-noising process was investigated and analyzed. The objective is to identify the optimal mother wavelet for assessing and potentially reducing the effects of existing noise on signal properties for structural damage detection. In addition, we propose two innovative damage indices, entropy-based dispersion and entropy-based beta, for diagnostic purposes. The proposed entropy-based dispersion damage index is based on the modified wavelet packet tree and root mean square deviation, whereas the entropy-based beta damage index is based on the modified wavelet packet tree and slope of linear regression (beta). In both damage indices, the modified wavelet packet tree uses entropy as a high-level feature. Theoretical and experimental analyses are derived by computing indices on smart aggregate–based sensor data for concrete and reinforced-concrete beams. Validity assessment of the proposed indices was addressed through a comparative analysis with root mean square deviation damage index (benchmark) and the loading history. The proposed indices recognized the cracks faster than other measures and well before major cracking incurs in the structure. This article is expected to be beneficial for smart aggregate–based structural health monitoring applications particularly when damages occurred under loading.