Search

Tunnel settlement has a significant impact on property security and personal safety. Accurate tunnel-settlement predictions can quickly reveal problems that may be addressed to prevent accidents. However, each acquisition point in the tunnel is only monitored once daily for around two months. This paper presents a new method for predicting tunnel settlement via transfer learning. First, a source model is constructed and trained by deep learning, then parameter transfer is used to transfer the knowledge gained from the source model to the target model, which has a small dataset. Based on this, the training complexity and training time of the target model can be reduced. The proposed method was tested to predict tunnel settlement in the tunnel of Shanghai metro line 13 at Jinshajiang Road and proven to be effective. Artificial neural network and support vector machines were also tested for comparison. The results showed that the transfer-learning method provided the most accurate tunnel-settlement prediction.

To realize real-time detection of the operating environment of bridge cranes, this paper presents a three-dimensional mapping method using a binocular camera and laser ranging sensor. First, the left and right images are obtained by using the binocular camera, and the block matching is used for stereo correspondence to obtain the disparity image. Then, according to the reprojection matrix and the disparity image, the depth value of each pixel is obtained, and the depth image can be transformed into a three-dimensional point cloud of the current frame. Relying on the camera position data obtained by the laser ranging sensor, the three-dimensional point cloud generated from different positions is registered to obtain the three-dimensional point cloud of the craneʼs global operating environment. Finally, an octree map is used to represent the operating environment. To simulate the construction process of the operating environment of the bridge crane, an experimental platform was built, and experiments were carried out using the method proposed in this paper. The experimental results verified the feasibility of the method proposed in this paper.

With the development of information technology, intermodal transport research pays more attention to dynamic optimization and multi-role cooperation. The core issue of this paper was to realize container routing with dynamic adjustment, real-time optimization, and multi-role cooperation characteristics in the intermodal transport network. This paper first introduces the Intermodal Transport Cooperation Protocol (ITCP) that describes the operation and analysis of intermodal transport systems with the concept of encapsulation and layering. Then, a new network flow control method was built based on Model Predictive Control (MPC) in the ITCP framework. The method takes real-time information from all ITCP layers as input and generates flow control decisions for containers. To evaluate the method’s effectiveness, a discrete event simulation experiment is applied. The results show that the proposed method outperforms the all-or-nothing method in scenarios with high freight volume, which means the method proposed in this paper can effectively balance the network transport load and reduce network operating costs. The research of this paper may throw some new light on intermodal transport research from the perspectives of digitization, multi-role cooperation, dynamic optimization, and system standardization.

An improved soft kill option (SKO) method is proposed to achieve the optimization design of tower crane boom. For a better optimization performance, a parabolic weight coefficient is suggested and the displacement constraint is taken into consideration. In order to eliminate the numerical instability phenomena like checkerboard and mesh dependence, element temperature filter function is added into SKO method. Through the optimization data comparison of rectangular cantilever plate, it is verified that the improved SKO method can achieve a better result with more uniform stress and higher efficiency. Based on the dimension and load parameters of QTZ63 tower crane boom, an optimization model is established, and a periodic SKO method is put forward to optimize this model. The optimization result of the crane boom can provide a new thought for tower crane boom design.

A new method combined continuum topology with discrete truss is proposed for truss optimization. The optimized material distribution is obtained by means of continuum topology optimization and then transformed into initial truss. Based on the element principal stress and 8-neighborhood elements of continuum, force flow path extraction method is presented to obtain the initial truss layout. For section size optimization, criterion is deduced from a mathematical model by Lagrange multiplier method. Leveraging the free-form nature of continuum, this method can avoid the restriction of traditional ground structure. And it can achieve a better solution with less mass, smaller deformation and more uniform stress.

Deep learning methods have been widely used in the field of intelligent fault diagnosis due to their powerful feature learning and classification capabilities. However, it is easy to overfit depth models because of the large number of parameters brought by the multilayer-structure. As a result, the methods with excellent performance under experimental conditions may severely degrade under noisy environment conditions, which are ubiquitous in practical industrial applications. In this paper, a novel method combining a one-dimensional (1-D) denoising convolutional autoencoder (DCAE) and a 1-D convolutional neural network (CNN) is proposed to address this problem, whereby the former is used for noise reduction of raw vibration signals and the latter for fault diagnosis using the de-noised signals. The DCAE model is trained with noisy input for denoising learning. In the CNN model, a global average pooling layer, instead of fully-connected layers, is applied as a classifier to reduce the number of parameters and the risk of overfitting. In addition, randomly corrupted signals are adopted as training samples to improve the anti-noise diagnosis ability. The proposed method is validated by bearing and gearbox datasets mixed with Gaussian noise. The experimental result shows that the proposed DCAE model is effective in denoising and almost causes no loss of input information, while the using of global average pooling and input-corrupt training improves the anti-noise ability of the CNN model. As a result, the method combined the DCAE model and the CNN model can realize high-accuracy diagnosis even under noisy environment.

Accurate degradation state recognition of rolling bearing is critical to effective condition based on maintenance for improving reliability and safety. In this work, a new architecture is proposed to recognize the degradation state of the rolling bearing. Firstly, the time-domain features including RMS, kurtosis, skewness and RMSEE, and Mel-frequency cepstral coefficients features are extracted from bearing vibration signals, which are then used as the input of k-means algorithm. These unlabeled features are clustered by k-means in order to define the different categories of the bearing degradation state. In this way, the original vibration signals can be labeled. Then, the convolutional neural network recognition model is built, which takes the bearing vibration signals as input, and outputs the degradation state category. So, interference brought by human factors can be eliminated, and further, the bearing degradation can be grasped so as to make maintenance plan in time. The proposed method was tested by bearing run-to-failure dataset provided by the Center for Intelligent Maintenance System, and the result proved the feasibility and reliability of the methodology.