This paper provides a deep learning-based methods for civil structures monitoring in aerial imagery from unmanned aerial vehicles (UAVs). This algorithm is prepared to increase the level of structures monitoring when combined with UAVs techniques. The case study presented herein is the use of drones to monitor the cracks in concrete structures. The structures monitoring using existing UAV method is mainly aimed at the extraction of structures state maps. At the same time, the influence of UAV self-motion on the detection accuracy of cracks has not been overcome, and it is difficult to meet the application of intelligent monitoring system for concert crack detection. Therefore a concrete crack detection using UAV perception method based on UAV imaging and deep learning algorithm fusion is proposed. First, the development architecture of deep convolutional neural network (CNN) in the field of computer vision for UAV generated image processing are introduced. Then, the existing crack image datasets and model performance evaluation metrics are summarized. Finally, UAV platform for crack detection in civil infrastructure are summarized. The results show that the proposed CNN network has achieved better performance, reaching 96.4%, 93.7%, 91.3%, and 125s in terms of accuracy, regression, F1-score, and training time, respectively, which can realize the automatic extraction of high-dimensional, complex, and abstract features of civil structures, in addition, the detection results can reduce interference, reduce detection error, obtain more completion, and clear the civil structures detection effect.
A pressure vessel is a pressurized container, often cylindrical or spherical. The pressure acting on the inner surface is resisted by tensile stresses in the walls of the vessel. Pressure vessels are commonly used in industrial applications such as gas, oil, water, and chemical industries. Pressure vessels can be dangerous, and fatal accidents have occurred in the history of their development and operation. Consequently, pressure vessel design, manufacture, and operation are regulated by engineering authorities backed by legislation. For these reasons, the definition of a pressure vessel varies from country to country. This chapter examines the types of pressure vessels in mechanical applications, and covers the full design of different pressure vessel types, along with examples and solved/unsolved problems. The chapter explains the stress–strain analysis of pressure vessel types such as thin cylindrical shell, thick cylindrical shell, thin spherical shell, and multi-layer composite pipe. This chapter can be used as teaching material for courses in machine design for mechanical and industrial engineering majors in colleges and universities, and can also be used as a reference for scientific and technical personnel engaged in scientific and engineering calculations.
Comprising a total of seven articles divided into five research articles, one review article, and one editorial article, this Special Issue is dedicated to new techniques for piezoelectric energy harvesting and its design, optimization, applications, and analysis [...]
Smart cities need smart transport services. Proper movement of people, goods, and services accelerates the growth and development of a region. A well-planned
One of the major problems in glass fiber reinforced epoxy (GFRE) composite pipes is the durability under water absorption. This condition is generally recognized to cause degradations in strength and mechanical properties. Therefore, there is a need for an intelligent system for detecting the absorption rate and computing the mass of water absorption (M%) as a function of absorption time (t). The present work represents a new non-destructive evaluation (NDE) technique for detecting the water absorption rate by evaluating the dielectric properties of glass fiber and epoxy resin composite pipes subjected to internal hydrostatic pressure at room temperature. The variation in the dielectric signatures is employed to design an electrical capacitance sensor (ECS) with high sensitivity to detect such defects. ECS consists of twelve electrodes mounted on the outer surface of the pipe. Radius-electrode ratio is defined as the ratio of inner and outer radius of pipe. A finite element (FE) simulation model is developed to measure the capacitance values and node potential distribution of ECS electrodes on the basis of water absorption rate in the pipe material as a function of absorption time. The arrangements for positioning12-electrode sensor parameters such as capacitance, capacitance change and change rate of capacitance are analyzed by ANSYS and MATLAB to plot the mass of water absorption curve against absorption time (t). An analytical model based on a Fickian diffusion model is conducted to predict the saturation level of water absorption (MS) from the obtained mass of water absorption curve. The FE results are in excellent agreement with the analytical results and experimental results available in the literature, thus, validating the accuracy and reliability of the proposed expert system.
Delamination is the most common failure mode in layered composite materials. The author have found that the electrical potential change (EPC) technique using response surfaces method is very effective in assessment delamination in basalt fiber reinforced polymer (FRP) laminate composite pipe by using electrical capacitance sensor (ECS). In the present study, the effect of the electrodes number on the method is investigated using FEM analyses for delamination location/size detection by ANSYS and MATLAB, which are combined to simulate sensor characteristic. Three cases of electrodes number are analyzed here are eight, twelve and sixteen electrodes, afterwards, the delamination is introduced into between the three layers [<TEX>$0^{\circ}/90^{\circ}/0^{\circ}$</TEX>]s laminates pipe, split into eight, twelve and sixteen scenarios for cases of eight, twelve and sixteen electrodes respectively. Response surfaces are adopted as a tool for solving inverse problems to estimate delamination location/size from the measured EPC of all segments between electrodes. As a result, it was revealed that the estimation performances of delamination location/size depends on the electrodes number. For ECS, the high number of electrodes is required to obtain high estimation performances of delamination location/size. The illustrated results are in excellent agreement with solutions available in the literature, thus validating the accuracy and reliability of the proposed technique.
In this paper, the structural mode shapes extracted from the finite element model of a simply supported reinforced concrete beam are employed for damage identification using different types of wavelets. To start with, the parity of signals, wavelets, and their convolution, that is, wavelet transform properties, are verified. In light of the mathematical modeling complexity of modal frequency, which relates to the localization and quantification of damage in the reinforced concrete beam, the maximum curves based on multiresolution wavelet transform coefficient differences and the corresponding theoretical assumptions are described and analyzed. It is concluded that the maximum curve reaches a peak value at a specific scale for a specific case, based upon which, a new mode shape based algorithm and damage index are proposed for damage identification. The accuracy of localization as well as the sensitivity of quantification is further discussed.
Pipelines are major part of any oil and petrochemical industry. It is common to burry transportation pipelines under soil for mechanical protection. However, corrosion in soil can reach high rates and becomes a major loss especially in costal environments and wet soils. In this paper, a numerical simulation analysis of pipeline corrosion is developed by using a new technique for corrosion evaluation. This technique is electrical capacitance tomography (ECT). The electrical capacitance system consists of number of electrodes mounted on the outer surface of pipeline, radius-electrode ratio is defined as the ratio of inner and outer radius of pipeline. The electrodes will act as a capacitance detector and the resulting capacitance can be measured between the electrodes. This capacitance will therefore vary when the pipeline thickness changes with time (that is, when the corrosion occurs). The finite element simulation technology can be used to calculate capacitance value to obtain the capacitance-sensitive field distribution electrode sensors. The effect of pipe wall corrosion on sensor capacitance measurements is presented in this work. It is based on the finite element model. The simulation results are obtained using ANSYS and MATLAB software.
Microencapsulated phase change materials have better thermal stability, and are widely used in the field of energy storage. In this paper, the core and wall material characteristics of microencapsulated phase change materials are reviewed. Several preparation methods, such as in-situ polymerisation, interfacial polymerisation, and suspension-like polymerisation, are analysed and the applications of microencapsulated phase change materials in fibre fabric, building, military camouflage and heat conduction are summarised.
The paper is focused on the application of artificial neural networks (ANNs) in predicting the natural frequency of basalt fiber reinforced polymer (FRP) laminated, variable thickness plates. The author has found that the finite strip transition matrix (FSTM) approach is very effective to study the changes of plate natural frequencies due to intermediate elastic support (IES), but the method difficulty in terms of, a lot of calculations with large number of iterations is the main drawback of the method. For training and testing of the ANN model, a number of FSTM results for different classical boundary conditions (CBCs) with different values of elastic restraint coefficients (<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msub><mml:mrow><mml:mi>K</mml:mi></mml:mrow><mml:mrow><mml:mi>T</mml:mi></mml:mrow></mml:msub></mml:math>) for IES have been carried out to training and testing an ANN model. The ANN model has been developed using multilayer perceptron (MLP) Feed-forward neural networks (FFNN). The adequacy of the developed model is verified by the regression coefficient (<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"><mml:msup><mml:mrow><mml:mi>R</mml:mi></mml:mrow><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msup></mml:math>) and Mean Square error (MSE) It was found that the R2 and MSE values are 0.986 and 0.0134 for train and 0.9966 and 0.0122 for test data respectively. The results showed that, the training algorithm of FFNN was sufficient enough in predicting the natural frequency in basalt FRP laminated, variable thickness plates with IES. To judge the ability and efficiency of the developed ANN model, MSE has been used. The results predicted by ANN are in very good agreement with the FSTM results. Consequently, the ANN is show to be effective in predicting the natural frequency of laminated composite plates.
This chapter examines belt and chain drives. The chain transmission is the most common transmission method, with a simple structure, easy maintenance, and cheap price, but it has quite a few disadvantages, such as the fact that chain wear will elongate it and need to be adjusted, maintenance is required during use, the noise is obviously too great, and motion inertia is large. The belt transmission is more common in cars, especially the toothed belt. The belt transmission has many advantages, such as stable transmission, low noise, maintenance-free nature, long life, and small motion inertia (toothed belt). There is almost no maintenance in the later stage, but this type of belt does not resist stones and dust like chains. In this chapter we discuss belt and chain selection, and share the belt and chain selection process from the aspects of belt and chain charts and tables, to help in understanding belts and chains correctly. Examples and solved/unsolved problems for selection of belt and chain size are also presented. This chapter can be used as a teaching tool for courses on machine design for mechanical and industrial engineering and materials engineering majors in colleges and universities, and can also be used as a reference for scientific and technical personnel engaged in scientific and engineering calculations.
