Search

A 3D dynamic finite element model is developed to study the response of the existing tunnels’ concrete structure under the influence of different train speeds and undercrossing with fixed shield excavation. The intersection area of Metro Line 3 in Guangzhou and the intercity railway between Foshan and Dongguan is used as the case study. A programming idea simulating oblique moving-axle loads in the numerical model by using function expressions to constrain activity area is proposed. The Hilber–Hughes–Taylor time-integration scheme is used to calculate the dynamic response parameters of the double-channel rectangular cross section tunnels. Considering fixed excavation steps in the process of shield crossing, acceleration and deformation of the existing tunnels were analyzed under the moving-axle loads of trains at different speeds. From the perspective of the vibration and deformation of existing tunnels, shield excavation and moving speed have their own emphasis on the dynamic influence of the existing tunnel. In addition, the calculation results of the numerical simulation are in good agreement with the data obtained from some field tests, which further verifies the reliability of the calculation method of the numerical model. The results of this research can guide the arrangements for reinforcement measures for existing tunnels in the later stage.

The use of the convolutional neural network for fault diagnosis has been a common method of research in recent years. Since this method can automatically extract fault features, it has played a good role in some research studies. However, this method has a clear drawback that the signals will be significantly affected by working conditions and sample size, and it is difficult to improve diagnostic accuracy by directly learning faults, regardless of working conditions. It is therefore a research orientation worthy of a diagnosis of high precision defect in various working conditions. In this article, using a fine-grained classification algorithm, the operating conditions of the object system are considered an approximate classification. A specific failure in different working conditions is considered a beautiful classification. Samples of different faults in different working conditions are learned uniformly and the common characteristics are extracted from the convolutional network so that different faults of different working conditions can simultaneously be identified on the basis of the entire sample. Experimental results show that the method effectively uses the set of samples of the working conditions of the variables to obtain the dual recognition of defects and specific working conditions and the accuracy of the recognition is significantly higher than the method of learning regardless of working conditions.