Based on the natural characters of stratum,complicated geological mining conditions and the essence of mining rock mass destruction,the complexity of rock mass destruction caused by miningw as analyzed.The inner link ...Based on the natural characters of stratum,complicated geological mining conditions and the essence of mining rock mass destruction,the complexity of rock mass destruction caused by miningw as analyzed.The inner link between rock mass destruction phenomena caused by mining and nonlinear science was revealed.There are numerous cracks in natural rock mass.The cracks’distribution is irregular and is of statistical fractal structure.Self-organizational nonlinear evolution of the inner structure flaws leads to the rock mass destruction with external force.The evolution includes single fault’s fractal development,formation and evolution of fractal crack network and coordination of fractal crack network,etc.The law of fractal crack network’s evolution was introduced,at the same time,the coordination of fractal crack network was analyzed.Finally,based on coordination the principal equation of mining-caused subsidence of structural rock mass was established and its steady-state solution and unsteady-state solution were found.展开更多
Manual inspections of infrastructures such as highway bridge, pavement, dam, and multistoried garage ceiling are time consuming, sometimes can be life threatening, and costly. An automated computerized system can redu...Manual inspections of infrastructures such as highway bridge, pavement, dam, and multistoried garage ceiling are time consuming, sometimes can be life threatening, and costly. An automated computerized system can reduce time, faulty inspection, and cost of inspection. In this study, we developed a computer model using deep learning Convolution Neural Network (CNN), which can be used to automatically detect the crack and non-crack type structure. The goal of this research is to allow application of state-of-the-art deep neural network and Unmanned Aerial Vehicle (UAV) technologies for highway bridge girder inspection. As a pilot study of implementing deep learning in Bridge Girder, we study the recognition, length, and location of crack in the structure of the UTC campus old garage concrete ceiling slab. A total of 2086 images of crack and non-crack were taken from UTC Old Library parking garage ceiling using handheld mobile phone and drone. After training the model shows 98% accuracy with crack and non-crack types of structures.展开更多
The purpose of the research is to obtain an effective method to predict the hot ductility of low-carbon steels, which will be a reference to evaluate the crack sensitivity of steels. Several sub-networks modeled from ...The purpose of the research is to obtain an effective method to predict the hot ductility of low-carbon steels, which will be a reference to evaluate the crack sensitivity of steels. Several sub-networks modeled from BP network were constructed for different temperature use, and the measured reduction of area (A(R)) of 12 kinds of low-carbon steels under the temperature of 600 to 1000 degreesC were processed as training samples. The result of software simulation shows that the model established is relatively effective for predicting the hot ductility of steels.展开更多
A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF ...A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.展开更多
Artificial neural network(ANN) technology was applied to predict weld hot crack susceptibility of the T-type welded joints of aluminum alloys. A primary prediction model was established by training and testing models ...Artificial neural network(ANN) technology was applied to predict weld hot crack susceptibility of the T-type welded joints of aluminum alloys. A primary prediction model was established by training and testing models with different structures and committee models with different numbers of sub models. The models were improved by decreasing the input variables and data-covering space. Then welding hot crack prediction model committee for T-type joints of aluminum plates was developed. Its input parameters include base metal composition, filler metal composition and welding technique, the output parameter is the total length of the weld hot crack. The performance analysis shows that the predicted trend agrees well with the previous research work.展开更多
Fiber loop ringdown (FLRD) has demonstrated to be capable of sensing various quantities, such as chemical species, pressure, refractive index, strain, temperature, etc.;and it has high potential for the development of...Fiber loop ringdown (FLRD) has demonstrated to be capable of sensing various quantities, such as chemical species, pressure, refractive index, strain, temperature, etc.;and it has high potential for the development of a sensor network. In the present work, we describe design and development of three different types of FLRD sensors for water, cracks, and temperature sensing in concrete structures. All of the three aforementioned sensors were indigenously developed very recently in our laboratory and their capabilities of detecting the respective quantities were demonstrated. Later, all of the sensors were installed in a test grout cube for real-time monitoring. This work presents the results obtained in the laboratory-based experiments as well as the results from the real-time monitoring process in the test cube.展开更多
基金Foundatinitem Project(50274044)supported by the National Natural Science Foundation of China.
文摘Based on the natural characters of stratum,complicated geological mining conditions and the essence of mining rock mass destruction,the complexity of rock mass destruction caused by miningw as analyzed.The inner link between rock mass destruction phenomena caused by mining and nonlinear science was revealed.There are numerous cracks in natural rock mass.The cracks’distribution is irregular and is of statistical fractal structure.Self-organizational nonlinear evolution of the inner structure flaws leads to the rock mass destruction with external force.The evolution includes single fault’s fractal development,formation and evolution of fractal crack network and coordination of fractal crack network,etc.The law of fractal crack network’s evolution was introduced,at the same time,the coordination of fractal crack network was analyzed.Finally,based on coordination the principal equation of mining-caused subsidence of structural rock mass was established and its steady-state solution and unsteady-state solution were found.
文摘Manual inspections of infrastructures such as highway bridge, pavement, dam, and multistoried garage ceiling are time consuming, sometimes can be life threatening, and costly. An automated computerized system can reduce time, faulty inspection, and cost of inspection. In this study, we developed a computer model using deep learning Convolution Neural Network (CNN), which can be used to automatically detect the crack and non-crack type structure. The goal of this research is to allow application of state-of-the-art deep neural network and Unmanned Aerial Vehicle (UAV) technologies for highway bridge girder inspection. As a pilot study of implementing deep learning in Bridge Girder, we study the recognition, length, and location of crack in the structure of the UTC campus old garage concrete ceiling slab. A total of 2086 images of crack and non-crack were taken from UTC Old Library parking garage ceiling using handheld mobile phone and drone. After training the model shows 98% accuracy with crack and non-crack types of structures.
文摘The purpose of the research is to obtain an effective method to predict the hot ductility of low-carbon steels, which will be a reference to evaluate the crack sensitivity of steels. Several sub-networks modeled from BP network were constructed for different temperature use, and the measured reduction of area (A(R)) of 12 kinds of low-carbon steels under the temperature of 600 to 1000 degreesC were processed as training samples. The result of software simulation shows that the model established is relatively effective for predicting the hot ductility of steels.
基金Projects(60974031,60704011,61174128)supported by the National Natural Science Foundation of China
文摘A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.
文摘Artificial neural network(ANN) technology was applied to predict weld hot crack susceptibility of the T-type welded joints of aluminum alloys. A primary prediction model was established by training and testing models with different structures and committee models with different numbers of sub models. The models were improved by decreasing the input variables and data-covering space. Then welding hot crack prediction model committee for T-type joints of aluminum plates was developed. Its input parameters include base metal composition, filler metal composition and welding technique, the output parameter is the total length of the weld hot crack. The performance analysis shows that the predicted trend agrees well with the previous research work.
文摘Fiber loop ringdown (FLRD) has demonstrated to be capable of sensing various quantities, such as chemical species, pressure, refractive index, strain, temperature, etc.;and it has high potential for the development of a sensor network. In the present work, we describe design and development of three different types of FLRD sensors for water, cracks, and temperature sensing in concrete structures. All of the three aforementioned sensors were indigenously developed very recently in our laboratory and their capabilities of detecting the respective quantities were demonstrated. Later, all of the sensors were installed in a test grout cube for real-time monitoring. This work presents the results obtained in the laboratory-based experiments as well as the results from the real-time monitoring process in the test cube.
