基于循环神经网络的盾构隧道#br# 引发地面最大沉降预测

伴随着计算机技术的快速发展,机器学习等新兴算法正在被越来越多地运用于预测隧道掘进引发的地面最大沉降。在隧道施工过程中,由盾构机和地面监测点位采集的数据具有很强的序列化特征,而传统的机器学习算法对序列数据的处理存在一定的局限性。循环神经网络(RNN)具有极强的对时序型数据的处理能力,在视频识别、语音翻译等领域有着广泛的应用。采用两种RNN模型(LSTM、GRU)和传统的BP神经网络模型,以地质参数、几何参数和盾构机参数作为输入,对隧道施工过程中引发的地面最大沉降进行预测分析。结果显示,RNN对隧道沉降的预测结果优于传统的BP神经网络模型,并且RNN在连续未知区段的预测结果比BPNN更加稳定。     

Realtime prediction of hard rock TBM advance rate using temporal convolutional network (TCN) with tunnel construction big data

Real-time dynamic adjustment of the tunnel bore machine (TBM) advance rate according to the rock-machine interaction parameters is of great significance to the adaptability of TBM and its efficiency in construction. This paper proposes a real-time predictive model of TBM advance rate using the temporal convolutional network (TCN), based on TBM construction big data. The prediction model was built using an experimental database, containing 235 data sets, established from the construction data from the Jilin Water-Diversion Tunnel Project in China. The TBM operating parameters, including total thrust, cutterhead rotation, cutterhead torque and penetration rate, are selected as the input parameters of the model. The TCN model is found outperforming the recurrent neural network (RNN) and long short-term memory (LSTM) model in predicting the TBM advance rate with much smaller values of mean absolute percentage error than the latter two. The penetration rate and cutterhead torque of the current moment have significant influence on the TBM advance rate of the next moment. On the contrary, the influence of the cutterhead rotation and total thrust is moderate. The work provides a new concept of real-time prediction of the TBM performance for highly efficient tunnel construction.     

Real-time rock mass condition prediction with TBM tunneling big data using a novel rock–machine mutual feedback perception method

Real-time perception of rock mass information is of great importance to efficient tunneling and hazard prevention in tunnel boring machines (TBMs). In this study, a TBM–rock mutual feedback perception method based on data mining (DM) is proposed, which takes 10 tunneling parameters related to surrounding rock conditions as input features. For implementation, first, the database of TBM tunneling parameters was established, in which 10,807 tunneling cycles from the Songhua River water conveyance tunnel were accommodated. Then, the spectral clustering (SC) algorithm based on graph theory was introduced to cluster the TBM tunneling data. According to the clustering results and rock mass boreability index, the rock mass conditions were classified into four classes, and the reasonable distribution intervals of the main tunneling parameters corresponding to each class were presented. Meanwhile, based on the deep neural network (DNN), the real-time prediction model regarding different rock conditions was established. Finally, the rationality and adaptability of the proposed method were validated via analyzing the tunneling specific energy, feature importance, and training dataset size. The proposed TBM–rock mutual feedback perception method enables the automatic identification of rock mass conditions and the dynamic adjustment of tunneling parameters during TBM driving. Furthermore, in terms of the prediction performance, the method can predict the rock mass conditions ahead of the tunnel face in real time more accurately than the traditional machine learning prediction methods.     

QPSO-ILF-ANN-based optimization of TBM control parameters considering tunneling energy efficiency

In recent years, tunnel boring machines (TBMs) have been widely used in tunnel construction. However, the TBM control parameters set based on operator experience may not necessarily be suitable for certain geological conditions. Hence, a method to optimize TBM control parameters using an improved loss function-based artificial neural network (ILF-ANN) combined with quantum particle swarm optimization (QPSO) is proposed herein. The purpose of this method is to improve the TBM performance by optimizing the penetration and cutterhead rotation speeds. Inspired by the regularization technique, a custom artificial neural network (ANN) loss function based on the penetration rate and rock-breaking specific energy as TBM performance indicators is developed in the form of a penalty function to adjust the output of the network. In addition, to overcome the disadvantage of classical error backpropagation ANNs, i.e., the ease of falling into a local optimum, QPSO is adopted to train the ANN hyperparameters (weight and bias). Rock mass classes and tunneling parameters obtained in real time are used as the input of the QPSO-ILF-ANN, whereas the cutterhead rotation speed and penetration are specified as the output. The proposed method is validated using construction data from the Songhua River water conveyance tunnel project. Results show that, compared with the TBM operator and QPSO-ANN, the QPSO-ILF-ANN effectively increases the TBM penetration rate by 14.85% and 13.71%, respectively, and reduces the rock-breaking specific energy by 9.41% and 9.18%, respectively.     

卷积神经网络在结构损伤诊断中的应用

对卷积神经网络(CNN)在工程结构损伤诊断中的应用进行了深入探讨; 以多层框架结构节点损伤位置的识别问题为研究对象,构建了可以直接从结构动力反应信号中进行学习并完成分类诊断的基于原始信号和傅里叶频域信息的一维卷积神经网络模型和基于小波变换数据的二维卷积神经网络模型; 从输入数据样本类别、训练时间、预测准确率、浅层与深层卷积神经网络以及不同损伤程度的影响等多方面进行了研究。结果表明:卷积神经网络能从结构动力反应信息中有效提取结构的损伤特征,且具有很高的识别精度; 相比直接用加速度反应样本,使用傅里叶变换后的频域数据作为训练样本能使CNN的收敛速度更快、更稳定,并且深层CNN的性能要好于浅层CNN; 将卷积神经网络用于工程结构损伤诊断具有可行性,特别是在大数据处理和解决复杂问题能力方面与其他传统诊断方法相比有很大优势,应用前景广阔。     

An ANN-based approach to predict blast-induced ground vibration of Gol-E-Gohar iron ore mine,Iran简

Blast-induced ground vibration is one of the inevitable outcomes of blasting in mining projects and may cause substantial damage to rock mass as well as nearby structures and human beings. In this paper, an attempt has been made to present an application of artificial neural network (ANN) to predict the blast-induced ground vibration of the Gol-E-Gohar (GEG) iron mine, Iran. A four-layer feed-forward back propagation multi-layer perceptron (MLP) was used and trained with Levenberg–Marquardt algorithm. To construct ANN models, the maximum charge per delay, distance from blasting face to monitoring point, stemming and hole depth were taken as inputs, whereas peak particle velocity (PPV) was considered as an output parameter. A database consisting of 69 data sets recorded at strategic and vulnerable locations of GEG iron mine was used to train and test the generalization capability of ANN models. Coefficient of determination (R²) and mean square error (MSE) were chosen as the indicators of the performance of the networks. A network with architecture 4-11-5-1 and R² of 0.957 and MSE of 0.000722 was found to be optimum. To demonstrate the supremacy of ANN approach, the same 69 data sets were used for the prediction of PPV with four common empirical models as well as multiple linear regression (MLR) analysis. The results revealed that the proposed ANN approach performs better than empirical and MLR models.     

Performance prediction of hard rock Tunnel Boring Machines (TBMs) in difficult ground

Performance prediction of TBMs is an essential part of project scheduling and cost estimation. This process involves a good understanding of the complexities in the site geology, machine specification, and site management. Various approaches have been used over the years to estimate TBM performance in a given ground condition, many of them were successful and within an acceptable range, while some missing the actual machine performance by a notable margin. Experience shows that the best approach for TBM performance prediction is to use various models to examine the range of estimated machine penetration and advance rates and choose a rate that best represents the working conditions that is closest to the setting of the model used for the estimation. This allows the engineers to avoid surprises and to identify the parameters that could dominate machine performance in each case. This paper reviews the existing models for performance prediction of TBMs and some of the ongoing research on developing better models for improved accuracy of performance estimate and increasing TBM utilization.     

A unified convolutional neural network integrated with conditional random field for pipe defect segmentation

Semantic segmentation of closed‐circuit television (CCTV) images can facilitate automatic severity assessment of sewer pipe defects by assigning defect labels to each pixel on the image, from which defect types, locations, and geometric information can be obtained. In this study, a unified neural network, namely DilaSeg‐CRF, is proposed by fully integrating a deep convolutional neural network (CNN) with dense conditional random field (CRF) for improving the segmentation accuracy. First, DilaSeg is constructed with dilated convolution and multiscale techniques for producing feature maps with high resolution. The steps of the dense CRF inference algorithm are converted into CNN operations, which are then formulated as recurrent neural network (RNN) layers. The DilaSeg‐CRF is proposed by integrating DilaSeg with the RNN layers. Images containing three common types of sewer defects are collected from CCTV inspection videos and are annotated with ground truth labels, after which the proposed models are trained and evaluated. Experiments demonstrate that the end‐to‐end trainable DilaSeg‐CRF can improve the segmentation significantly, with an increase of 32% and 20% in mean intersection over union (mIoU) values compared with fully convolutional network (FCN‐8s) and DilaSeg, respectively. Our proposed DilaSeg‐CRF also achieves faster inference speed than FCN and eliminates the manual postprocessing for refining the segmentation results.     

Examining the influence of TBM-ground interaction on electrical resistivity imaging ahead of the TBM

Tunnel excavation by means of tunnel boring machines (TBMs) is susceptible to unknown changes ahead of the tunnel face. Geophysics offers a technique called electrical resistivity that can continuously, in real-time, spatially map the formation in front of the TBM. Electrical resistivity has been successfully established for many applications including vadoze zone hydrology, oil/gas location, mineral location and failure detection in geo-structures. Yet it has not been well-established for TBM excavations. This is in part due to the complexity of the TBM tunneling environment and the uncertain influence this environment may have on the success of TBM-integrated-electrical resistivity to predict changes ahead of the tunnel face. One significant uncertainty lies in the interface region that exists around the TBM created during the modification of the virgin formation by a mechanical mixing action of the rotating cutterhead and the injection of additives used to aid in the extraction of the muck and protect the cutting tools from frictional wear. In this study, we investigate the influence of this interface region on TBM-integrated-electrical resistivity for both hard rock and soft ground tunneling conditions through finite element modeling. Regarding the performance of TBM-integrated-electrical resistivity to detect changes ahead of the cutting face, the interface region holds significant influence for both earth pressure balance (EPB) and open mode tunneling conditions. Electrical resistivity for slurry based tunneling is not influenced by the interface region. Simulations suggest that TBM-integrated-electrical resistivity can be sensitive to a formation change that is located up to five diameters in front of the TBM.     

Theoretical model of the equivalent elastic modulus of a cobblestone–soil matrix for TBM tunneling

Cobblestone–soil mixed ground is a composite comprising cobblestones surrounded by soil. It is typical mixed-face ground encountered during tunnel boring machine (TBM) tunneling, and it may result in cutter wear, jamming of the roller cutterhead, poor TBM performance and cost overruns. The present paper investigates the deformation problem of cobblestone–soil mixed-face ground during TBM excavation. The ground under study is composed of two components (soil matrix and cobblestones) usually firmly bonded together at the interface, and can be regarded as a continuum. Previous studies have proposed many theoretical models for a composite material with two components. Representative models include the parallel model, series model, and effective medium theory model. Nonetheless, these models are limited by their assumptions and preconditions. In the present study, under an assumption of uniform strain, analytical solutions were derived for the equivalent elastic modulus while the cobblestone is assumed to be perfectly spherical or ellipsoidal. Triaxial compression tests were carried out to validate the analytical solutions. The equivalent elastic modulus derived from the triaxial experiments and theoretical models matched rather closely. The analytical solutions are helpful in clarifying the deformation of such ground and enhancing TBM performance.     

Deep learning model for estimating the mechanical properties of concrete containing silica fume exposed to high temperatures

In this study, the deep learning models for estimating the mechanical properties of concrete containing silica fume subjected to high temperatures were devised. Silica fume was used at concentrations of 0%, 5%, 10%, and 20%. Cube specimens (100 mm × 100 mm × 100 mm) were prepared for testing the compressive strength and ultrasonic pulse velocity. They were cured at 20°C±2°C in a standard cure for 7, 28, and 90 d. After curing, they were subjected to temperatures of 20°C, 200°C, 400°C, 600°C, and 800°C. Two well-known deep learning approaches, i.e., stacked autoencoders and long short-term memory (LSTM) networks, were used for forecasting the compressive strength and ultrasonic pulse velocity of concrete containing silica fume subjected to high temperatures. The forecasting experiments were carried out using MATLAB deep learning and neural network tools, respectively. Various statistical measures were used to validate the prediction performances of both the approaches. This study found that the LSTM network achieved better results than the stacked autoencoders. In addition, this study found that deep learning, which has a very good prediction ability with little experimental data, was a convenient method for civil engineering.     

城市公园声景长时感知模型研究—以加拿大温哥华市3个城市公园为例

为探究循环神经网络(RNN)对长时间模拟城市公园声景感知响度(PLS)和感知协调度(PHS)的适用性,采用具有时序记忆和延迟功能的Elman神经网络和NARX神经网络分别进行验证.将城市公园声景和光景客观指标作为输入层,PLS和PHS作为输出层进行神经网络训练和模拟.研究结果显示:1)PLS和PHS同时与等效A声级(L...     

Case studies of TBM tunneling performance in rock–soil interface mixed ground

This paper investigates the performance of tunnel boring machines (TBMs) in rock–soil mixed-face ground based on TBM tunneling projects in Singapore. Currently several methods are available to estimate TBM tunneling performance in homogenous rock or soil. However, the existing models cannot be effectively applied to predict TBM penetration rate in mixed ground. The tunnels in this study were excavated in adverse mixed-face ground conditions. The geological profiles and the TBM operational parameters are compiled and analyzed. The influence of different geological face compositions on the performance of the TBMs is studied. The statistical analysis shows that there is a possible correlation between the mixed-face ground characteristics and the TBM advancement. Different approaches are used to find a reliable model. Finally, a method is proposed to predict the TBM performance in mixed-face ground for project planning and optimization.     

Digital image correlation-based structural state detection through deep learning

This paper presents a new approach for automatical classification of structural state through deep learning. In this work, a Convolutional Neural Network (CNN) was designed to fuse both the feature extraction and classification blocks into an intelligent and compact learning system and detect the structural state of a steel frame; the input was a series of vibration signals, and the output was a structural state. The digital image correlation (DIC) technology was utilized to collect vibration information of an actual steel frame, and subsequently, the raw signals, without further pre-processing, were directly utilized as the CNN samples. The results show that CNN can achieve 99% classification accuracy for the research model. Besides, compared with the backpropagation neural network (BPNN), the CNN had an accuracy similar to that of the BPNN, but it only consumes 19% of the training time. The outputs of the convolution and pooling layers were visually displayed and discussed as well. It is demonstrated that: 1) the CNN can extract the structural state information from the vibration signals and classify them; 2) the detection and computational performance of the CNN for the incomplete data are better than that of the BPNN; 3) the CNN has better anti-noise ability.     

Interpretable deep learning for roof fall hazard detection in underground mines

Roof falls due to geological conditions are major hazards in the mining industry, causing work time loss, injuries, and fatalities. There are roof fall problems caused by high horizontal stress in several large-opening limestone mines in the eastern and midwestern United States. The typical hazard management approach for this type of roof fall hazards relies heavily on visual inspections and expert knowledge. In this context, we proposed a deep learning system for detection of the roof fall hazards caused by high horizontal stress. We used images depicting hazardous and non-hazardous roof conditions to develop a convolutional neural network (CNN) for autonomous detection of hazardous roof conditions. To compensate for limited input data, we utilized a transfer learning approach. In the transfer learning approach, an already-trained network is used as a starting point for classification in a similar domain. Results show that this approach works well for classifying roof conditions as hazardous or safe, achieving a statistical accuracy of 86.4%. This result is also compared with a random forest classifier, and the deep learning approach is more successful at classification of roof conditions. However, accuracy alone is not enough to ensure a reliable hazard management system. System constraints and reliability are improved when the features used by the network are understood. Therefore, we used a deep learning interpretation technique called integrated gradients to identify the important geological features in each image for prediction. The analysis of integrated gradients shows that the system uses the same roof features as the experts do on roof fall hazards detection. The system developed in this paper demonstrates the potential of deep learning in geotechnical hazard management to complement human experts, and likely to become an essential part of autonomous operations in cases where hazard identification heavily depends on expert knowledge. Moreover, deep learning-based systems reduce expert exposure to hazardous conditions.     

Structural health monitoring using extremely compressed data through deep learning

This study introduces a novel convolutional neural network (CNN)‐based approach for structural health monitoring (SHM) that exploits a form of measured compressed response data through transfer learning (TL)‐based techniques. The implementation of the proposed methodology allows damage identification and localization within a realistic large‐scale system. To validate the proposed method, first, a well‐known benchmark model is numerically simulated. Using acceleration response histories, as well as compressed response data in terms of discrete histograms, CNN models are trained, and the robustness of the CNN architectures is evaluated. Finally, pretrained CNNs are fine‐tuned to be adaptable for three‐parameter, extremely compressed response data, based on the response mean, standard deviation, and a scale factor. The performance of each CNN implementation is assessed using training accuracy histories as well as confusion matrices, along with other performance metrics. In addition to the numerical study, the performance of the proposed method is demonstrated using experimental vibration response data for verification and validation. The results indicate that deep TL can be implemented effectively for SHM of similar structural systems with different types of sensors.     

Deep learning-based evaluation of factor of safety with confidence interval for tunnel deformation in spatially variable soil

The random finite difference method (RFDM) is a popular approach to quantitatively evaluate the influence of inherent spatial variability of soil on the deformation of embedded tunnels. However, the high computational cost is an ongoing challenge for its application in complex scenarios. To address this limitation, a deep learning-based method for efficient prediction of tunnel deformation in spatially variable soil is proposed. The proposed method uses one-dimensional convolutional neural network (CNN) to identify the pattern between random field input and factor of safety of tunnel deformation output. The mean squared error and correlation coefficient of the CNN model applied to the newly untrained dataset was less than 0.02 and larger than 0.96, respectively. It means that the trained CNN model can replace RFDM analysis for Monte Carlo simulations with a small but sufficient number of random field samples (about 40 samples for each case in this study). It is well known that the machine learning or deep learning model has a common limitation that the confidence of predicted result is unknown and only a deterministic outcome is given. This calls for an approach to gauge the model's confidence interval. It is achieved by applying dropout to all layers of the original model to retrain the model and using the dropout technique when performing inference. The excellent agreement between the CNN model prediction and the RFDM calculated results demonstrated that the proposed deep learning-based method has potential for tunnel performance analysis in spatially variable soils.     

基于贝叶斯优化RF-BiLSTM的盾构机掘进速度预测的研究

盾构机掘进速度的预测是保障盾构施工的重要参考指标。为了实现盾构机掘进速度的预测,本文提出了基于贝叶斯优化RF-BiLSTM的盾构机掘进速度预测方法,即TPE-RF-BiLSTM。首先通过随机森林实现盾构机运行数据的筛选,接着利用BiLSTM实现对盾构机掘进速度的预测。此外,为了提高超参数的搜索效率,贝叶斯优化被用于掘进速度预测模型的超参数搜索,以自动化的构建掘进速度的预测模型。最后,通过郑州某地铁施工段的真实数据验证所提方法,实验结果表明,所提的方法能够有效实现掘进速度的预测。即R2=0.9650,RMSE=1.684,表现优于XGBoost,LSTM等广泛应用的成熟机器学习算法。     

基于改进的距离判别分析法的南水北调西线工程TBM施工围岩分级

 对马氏距离判别法和层次分析法存在的不足进行改进,将改进的距离判别分析法应用于南水北调西线工程TBM施工围岩分级中。根据TBM施工特点和相关研究成果,将TBM施工围岩分级标准定为4级。选用岩石强度、岩组特征、结构面间距、结构面与洞轴线夹角以及石英含量5项指标作为判别因子,以南水北调西线工程杜柯河-玛柯河段实例数据作为学习样本进行训练,建立TBM施工围岩分级的改进的距离判别分析模型,利用得到的线性判别函数对待判样本进行分级。最后,将改进的距离判别分析法得到的判定结果与传统马氏距离判别法、RTBM法以及RMR方法得到的判别结果进行对比分析,验证了改进的距离判别分析法的有效性。研究结果表明,改进的距离判别分析法具有预测精度高等优点,为TBM施工围岩分级提供了一种新的有效方法。     

Real-time analysis and prediction of shield cutterhead torque using optimized gated recurrent unit neural network

An accurate prediction of earth pressure balance (EPB) shield moving performance is important to ensure the safety tunnel excavation. A hybrid model is developed based on the particle swarm optimization (PSO) and gated recurrent unit (GRU) neural network. PSO is utilized to assign the optimal hyperparameters of GRU neural network. There are mainly four steps: data collection and processing, hybrid model establishment, model performance evaluation and correlation analysis. The developed model provides an alternative to tackle with time-series data of tunnel project. Apart from that, a novel framework about model application is performed to provide guidelines in practice. A tunnel project is utilized to evaluate the performance of proposed hybrid model. Results indicate that geological and construction variables are significant to the model performance. Correlation analysis shows that construction variables (main thrust and foam liquid volume) display the highest correlation with the cutterhead torque (CHT). This work provides a feasible and applicable alternative way to estimate the performance of shield tunneling.