Concrete Cracks Detection and Monitoring Using Deep Learning-Based Multiresolution Analysis

In this paper, we propose a new methodology for crack detection and monitoring in concrete structures. This approach is based on a multiresolution analysis of a sample or a specimen of concrete material subjected to several types of solicitation. The image obtained by ultrasonic investigation and processed by a customized wavelet is analyzed at various scales in order to detect internal cracks and crack initiation. The ultimate objective of this work is to propose an automatic crack type identification scheme based on convolutional neural networks (CNN). In this context, crack propagation can be monitored without access to the concrete surface and the goal is to detect cracks before they are visible. This is achieved through the combination of two major data analysis tools which are wavelets and deep learning. This original procedure is shown to yield a high accuracy close to 90%. In order to evaluate the performance of the proposed CNN architectures, we also used an open access database, SDNET2018, for the automatic detection of external cracks.

Concrete Cracks Monitoring using Deep Learning-based Multiresolution Analysis

In this paper, we propose a new methodology for crack monitoring in concrete structures. This approach is based on a n this paper, we propose a new methodology for monitoring cracks in concrete structures. This approach is based on a multi-resolution analysis of a sample or a specimen of the studied material subjected to several types of solicitation. The image obtained by ultrasonic investigation and processing by a dedicated wavelet will be analyzed according to several scales in order to detect internal cracks and crack initiation. The ultimate goal of this work is to propose an automatic crack type identification scheme based on convolutional neural networks (CNN). In this context, crack propagation can be monitored without access to the concrete surface and the goal is to detect cracks before they are visible on the concrete surface. The key idea allowing such a performance is the combination of two major data analysis tools which are wavelets and Deep Learning. This original procedure allows to reach a high accuracy close to 0.90. In this work, we have also implemented another approach for automatic detection of external cracks by deep learning from publicly available datasets.

Ultrasonic Investigation of Binary Solutions of Petrolium And Its Products

<p>Experiment values of densities and ultrasonic speed of petroleum product Gasoline (Petrol) and 2T Oil were taken in different volume concentrations from 5%, 10%------, and 95% at different temperatures from 298.15K to 318.15K having difference of 5K. From the experimental data, Apparent Molar Compressibility (<em>ϕ_K</em>), Relative Association (<em>R_A</em>), Solvation Number (<em>S_n</em>), Free Energy of Activation (<em>ΔE</em>), Excess Adiabatic Compressibility (<em>β_ad^E</em>), Excess Volume (<em>V^E</em>), Excess Free Length (<em>L_f^E</em>) have been computed. These parameters are used to focus light on the nature of component molecules of binary liquids and the excess functions are found to be sensitive to the nature and extent of the intermolecular interactions taking place in these binary mixtures.</p>

Acoustical Parameters of Polyvinyl Alcohol

Ultrasonic investigation provides a wealth of information in understanding the intermolecular interaction of solute and solvent. An attempt has been made to measure density, viscosity and ultrasonic velocity of aqueous solution of polyvinyl alcohol of molecular weight approximately 140,000 at different temperatures 35οC, 40oC, 45οC, 50oC, 55οC, 60oC, 65οC at 0.8% concentration. Ultrasonic velocity is measured using ultrasonic interferometer at 1 MHz frequency. The acoustical parameters like, adiabatic compressibility, acoustic impedance, intermolecular free length and relaxation time have been calculated at different temperatures. These parameters were used to understand the behaviour of solute and solvent.