Real-time prediction of rock mass classification based on TBM operation big data and stacking technique of ensemble learning

Real-time prediction of the rock mass class in front of the tunnel face is essential for the adaptive adjustment of tunnel boring machines(TBMs).During the TBM tunnelling process,a large number of operation data are generated,reflecting the interaction between the TBM system and surrounding rock,and these data can be used to evaluate the rock mass quality.This study proposed a stacking ensemble classifier for the real-time prediction of the rock mass classification using TBM operation data.Based on the Songhua River water conveyance project,a total of 7538 TBM tunnelling cycles and the corresponding rock mass classes are obtained after data preprocessing.Then,through the tree-based feature selection method,10 key TBM operation parameters are selected,and the mean values of the 10 selected features in the stable phase after removing outliers are calculated as the inputs of classifiers.The preprocessed data are randomly divided into the training set(90%)and test set(10%)using simple random sampling.Besides stacking ensemble classifier,seven individual classifiers are established as the comparison.These classifiers include support vector machine(SVM),k-nearest neighbors(KNN),random forest(RF),gradient boosting decision tree(GBDT),decision tree(DT),logistic regression(LR)and multilayer perceptron(MLP),where the hyper-parameters of each classifier are optimised using the grid search method.The prediction results show that the stacking ensemble classifier has a better performance than individual classifiers,and it shows a more powerful learning and generalisation ability for small and imbalanced samples.Additionally,a relative balance training set is obtained by the synthetic minority oversampling technique(SMOTE),and the influence of sample imbalance on the prediction performance is discussed.     

Damage detection of a cable-stayed bridge using feature extraction and selection methods

Abstract

In this paper, a novel approach is presented to detect damage in a cable-stayed bridge based on feature extraction and selection. In the first part of the paper, several features are used in time domain, frequency domain, and time-frequency domain to detect damage. Next, several spectral parameters are introduced as effective features to reduce false alarms. Support vector machine (SVM) technique is employed as a classifier to compare the detection ability of the proposed and conventional features. In the second part of the paper, several feature selection techniques including forward selection, backward elimination, the minimum redundancy and max relevancy, ReliefF and SVM approach based on recursive feature elimination (SVM-RFE) algorithm are employed to improve feature extraction accuracy through selecting and ranking the most discriminative feature as an optimal feature subset. The capability of the proposed approach to detect damage is investigated by a data set obtained from a health monitoring system of a real benchmark problem. The data consists of vibration acceleration of the Yonghe bridge in both healthy and damaged states. Results show that the proposed procedure can effectively reduce false alarms.     

A wavelet-based technique for damage quantification via mode shape decomposition

In this study, a neuro-wavelet technique was proposed for damage identification of cantilever structure. At first, damage localisation was accomplished through mode shape decomposition using discrete wavelet transforms. Subsequently, a damage indicator was defined based on the detail coefficients of the decomposed signals. It was found that distinct patterns relate the damage indicators to damage locations. Considering this property, a neural network ensemble was developed for damage quantification. Damage indicators and damage locations were selected as input parameters for the neural networks. Three individual neural networks were trained by input samples obtained from different combinations of decomposed mode shapes. Then, the outcomes of the individual neural networks were fed to the ensemble neural network for damage quantification. The proposed method was tested on a cantilever structure both experimentally and numerically. Six different damage scenarios including three different damage locations and three different damage severities were introduced to the structure. The results revealed that the proposed method was able to quantify different damage levels with a good precision.     

Autoencoders for unsupervised real-time bridge health assessment

Over the last decades, the rising number of aging infrastructures has progressively fueled much interest toward the field of structural health monitoring. Following the increasing popularity of artificial intelligence algorithms, an autoencoder-based damage detection technique within the context of unsupervised learning is proposed in this paper to provide support for practical engineering applications. The developed methodology uses the autoencoder to reconstruct raw acceleration sequences of user-defined length collected from a healthy structure. To quantify the errors between the original input and the reconstructed output, which may be representative of damage occurrence, two indexes of reconstruction loss are selected as damage-sensitive features. To support damage detection, a selected number of short-time sequences are finally grouped into a unique macrosequence. The novel procedure can effectively both work at the single sensor level, as well as combine the predictive models using an ensemble learning strategy. Avoiding system identification, results obtained in the Z24 bridge demonstrate that the proposed method is quite effective for local damage detection with limited computational effort and using a limited number of sensors, thereby suitable to be easily applicable in the context of real-time bridge assessment.     

Response covariance-based sensor placement for structural damage detection

One important function of a structural health monitoring system is to detect structural damage in a structure. However, this is a very challenging task since the measurement is often incomplete in a civil structure due to a limited number of sensors. This paper presents a response covariance-based sensor placement method for structural damage detection with two objective functions for optimisation. The relationship between the covariance of acceleration responses and the covariance of unit impulse responses of a structure subjected to multiple white noise excitations is first derived. The response covariance-based damage detection method is then presented. Two objective functions based on the response covariance sensitivity and the response independence are, respectively, formulated and finally integrated into a single objective function for optimal sensor placement. Numerical studies are conducted to investigate the feasibility and effectiveness of the proposed method via a three-dimensional frame structure. Numerical results show that the proposed method with the backward sequential sensor placement algorithm is effective for damage detection.     

Application of singular spectrum analysis to structural monitoring and damage diagnosis of bridges

Singular spectrum analysis (SSA) is a novel technique and has proven to be a powerful tool for time series data analysis. Through singular value decomposition of Hankel matrix data, the time series of data can be decomposed into several simple, independent and identifiable components from singular values and singular vectors. It has already been widely applied to process climatic, meteorological, geophysical and economic data. In this paper, we demonstrate that the coupling degree of the 1st and 2nd singular values in SSA contains useful indications on the feature and composition of the analysed signal. The proposed method is successfully applied to the monitoring of structure, such as damage detection of the simulated dynamic system, experimental steel frame, bridge foundation scouring and pier settlement in the laboratory and on-site bridge monitoring during typhoon strike. The proposed algorithm is simple and suitable for structural health monitoring in the field.     

基于时-频域信息的结构系统识别方法研究

结构响应的时域、频域信息均可用来对结构模型进行修正。该文提出频域信息与时域信息相结合的方法,对结构参数以及荷载进行评估。首先,从结构测量加速度信息中提取结构的频域特性,对结构模型进行较为粗略的修正,优化结构模型的振型、频率,使其与测量信息一致。其次,利用时域信息,在状态空间对结构运动微分方程进行零阶离散化,采用正则化方法对模型进行荷载识别,同时基于约束优化方法对结构模型参数进行进一步修正。应用模型缩聚方法,保证计算精度的情况下减少结构模型参数修正和荷载识别的计算量。在数值仿真计算中,基于框架结构的不完备地震时程响应记录,对结构损伤状况进行评估。结果证明,即使在有噪声的情况下,该文提出的结构状态方法依然能够很好地识别结构损伤程度、位置。最后,通过14层加层隔震剪力墙结构的振动台试验进一步验证该文提出的结构参数与荷载识别方法。     

Transfer function‐based Bayesian damage detection under seismic excitation

Transfer function (TF) data are recognized as diagnostic features in damage detection procedure. The objective of this paper is to present a damage detection method in Bayesian paradigm based on TF data due to ground excitation. The measured seismic responses of the structure in the frequency domain are adopted to obtain displacement TFs and the structural natural frequencies are identified from observed TFs. The derived features are utilized for Bayesian structural damage detection. In addition, the challenging issue of underlying flexible soil in real cases has been addressed. The proposed technique is applied to a numerical shear frame to evaluate the capability of the method. An experimental study on a six‐story steel building has been validated to demonstrate the capability of the method for damage detection purpose. The results of studied cases indicated that the proposed method is capable of identifying the location and the severity of damage precisely.     

Improved prediction of slope stability using a hybrid stacking ensemble method based on finite element analysis and field data

Slope failures lead to catastrophic consequences in numerous countries and thus the stability assessment for slopes is of high interest in geotechnical and geological engineering researches.A hybrid stacking ensemble approach is proposed in this study for enhancing the prediction of slope stability.In the hybrid stacking ensemble approach,we used an artificial bee colony(ABC)algorithm to find out the best combination of base classifiers(level 0)and determined a suitable meta-classifier(level 1)from a pool of 11 individual optimized machine learning(OML)algorithms.Finite element analysis(FEA)was conducted in order to form the synthetic database for the training stage(150 cases)of the proposed model while 107 real field slope cases were used for the testing stage.The results by the hybrid stacking ensemble approach were then compared with that obtained by the 11 individual OML methods using confusion matrix,F1-score,and area under the curve,i.e.AUC-score.The comparisons showed that a significant improvement in the prediction ability of slope stability has been achieved by the hybrid stacking ensemble(AUC?90.4%),which is 7%higher than the best of the 11 individual OML methods(AUC?82.9%).Then,a further comparison was undertaken between the hybrid stacking ensemble method and basic ensemble classifier on slope stability prediction.The results showed a prominent performance of the hybrid stacking ensemble method over the basic ensemble method.Finally,the importance of the variables for slope stability was studied using linear vector quantization(LVQ)method.     

Structural Damage Detection Method Using Uncertain Frequency Response Functions

Abstract:   A structural damage detection method using uncertain frequency response functions (FRFs) is presented in this article. Structural damage is detected from the changes in FRFs from the original intact state. The measurements are always contaminated by noise, and sufficient data are often difficult to obtain; making it difficult to detect damage with a finite number of data. To surmount this, we introduce hypothesis testing based on the bootstrap method to statistically prevent detection errors due to measurement noise. The proposed method iteratively zooms in on the damaged elements by excluding the elements which were assessed as undamaged from among the damage candidates, step by step. The proposed approach was applied to numerical simulations using a 2D frame structure and its efficiency was confirmed.     

钢框架非比例损伤识别

提出能够鉴别损伤位置和截面损伤严重程度的钢框架非比例破坏监测方法。所提出的方法由两部分组成,一是损伤识别,二是损伤严重程度分析。损伤识别和严重程度分析均以结构动力性质的变化作为损伤的判据,以此来确定损伤位置和严重程度。所提方法中损伤判别的重要特点是能够在损伤严重程度分析之前,精确地区分不同的损伤区域。与整个结构尺寸相比,损伤区域相对较小,因此,确定损伤严重程度的计算量更小。检测方法的另一个特点是有些特征值或振型对噪声相对不敏感。采用所提检测方法对几个框架进行验证,结果表明,该方法能够成功地检测及量化截面的损伤。     

框架结构震后损伤的精确定位

基于频率易测且精度较高的特点,提出了框架结构损伤诊断的三步法。首先确定损伤杆件:把频率看作损伤参数的函数,以结构的每根杆件为一个单元,通过测量结构损伤前后频率的变化,构造以损伤参数为未知量的线性方程组,求解得到受损的构件。其次,把受损杆件划分成若干单元,再次构建方程组并求解,确定出损伤的具体位置和程度。最后,采用数理统计的方法,解决了由于测量误差影响诊断精度的问题。通过对一个2层框架结构进行数值模拟分析,表明其损伤识别效果较好。     

An efficient method for structural damage detection using a differential evolution algorithm-based optimisation approach

An efficient method employing the differential evolution algorithm (DEA) as an optimisation solver is presented here to identify the multiple damage cases of structural systems. Natural frequency changes of a structure are considered as a criterion for damage occurrence. The structural damage detection problem is first transformed into a standard optimisation problem dealing with continuous variables, and then the DEA is utilised to solve the optimisation problem for finding the site and extent of structural damage. In order to assess the performance of the proposed method for structural damage identification, some illustrative examples are numerically tested, considering also measurement noise. All the numerical results demonstrate the effectiveness of the proposed method for accurately determining the site and extent of multiple-structural damage. Also, the performance of the DEA for damage detection compared to the standard particle swarm optimisation is confirmed by a test example.     

类COMAC指标在桥梁损伤识别中的应用研究

为了研究桥梁结构损伤并探索损伤识别指标,提出基于应变频响函数的参数COMACsfrf作为损伤识别指标。在此基础上采用有限元方法,以一简支板为仿真算例,以结构模型的单元刚度衰减来模拟损伤。结果表明:CO-MACsfrf对损伤的敏感程度高于由振型、应变等推演出的特征指标;该方法可用于结构损伤定位以及定性评价多处损伤。     

Video-based smoke detection with histogram sequence of LBP and LBPV pyramids

Video surveillance systems are widely applied in a variety of fields. Hence, video-based smoke detection is regarded as an effective and inexpensive way for fire detection in an open or large spaces. In order to improve the efficiency of the video-based smoke detection, a novel video-based smoke detection method is proposed by using a histogram sequence of pyramids. The method involves four steps. Firstly, through multi-scale analysis, a 3-level image pyramid is constructed. Secondly, local binary patterns (LBP), which are insensitive to image rotation and illumination conditions, are extracted at each level of the image pyramid with uniform pattern, rotation invariance pattern and rotation invariance uniform pattern to generate an LBP pyramid. Thirdly, local binary patterns based on variance (LBPV) with the same patterns are also adopted in the same way to generate an LBPV pyramid. And fourthly, histograms of the LBP and LBPV pyramids are computed, and then all the histograms are concatenated into an enhanced feature vector. A neural network classifier is trained and used for discrimination of smoke and non-smoke objects. Experimental results show that the features are insensitive to rotation and illumination, and that the method is feasible and effective for video-based smoke detection at interactive frame rates.     

小波分析与神经网络在结构多处损伤监测中的应用

采用小波分析对获得的结构动力响应进行小波分解,根据各种响应信号对损伤的灵敏度选择损伤特征,从而识别结构多次出现损伤的时刻,实现对结构损伤时刻的监控;对结构第1层加速度响应信号做小波包分解,得到各频段能量的特征向量,作为特征参数输入到BP神经网络中实现结构多处损伤位置和程度识别。模拟算例表明,小波分析和BP神经网络联合运用能准确地诊断结构多处损伤的时刻、位置和程度,具有一定的可行性。     

Large-scale building damage assessment using a novel hierarchical transformer architecture on satellite images

This paper presents damage assessment using a hierarchical transformer architecture (DAHiTrA), a novel deep-learning model with hierarchical transformers to classify building damages based on satellite images in the aftermath of natural disasters. Satellite imagery provides real-time and high-coverage information and offers opportunities to inform large-scale postdisaster building damage assessment, which is critical for rapid emergency response. In this work, a novel transformer-based network is proposed for assessing building damage. This network leverages hierarchical spatial features of multiple resolutions and captures the temporal differences in the feature domain after applying a transformer encoder to the spatial features. The proposed network achieves state-of-the-art performance when tested on a large-scale disaster damage data set (xBD) for building localization and damage classification, as well as on LEVIR-CD data set for change detection tasks. In addition, this work introduces a new high-resolution satellite imagery data set, Ida-BD (related to 2021 Hurricane Ida in Louisiana) for domain adaptation. Further, it demonstrates an approach of using this data set by adapting the model with limited fine-tuning and hence applying the model to newly damaged areas with scarce data.     

Structural Damage Detection with Automatic Feature‐Extraction through Deep Learning

Structural damage detection is still a challenging problem owing to the difficulty of extracting damage‐sensitive and noise‐robust features from structure response. This article presents a novel damage detection approach to automatically extract features from low‐level sensor data through deep learning. A deep convolutional neural network is designed to learn features and identify damage locations, leading to an excellent localization accuracy on both noise‐free and noisy data set, in contrast to another detector using wavelet packet component energy as the input feature. Visualization of the features learned by hidden layers in the network is implemented to get a physical insight into how the network works. It is found the learned features evolve with the depth from rough filters to the concept of vibration mode, implying the good performance results from its ability to learn essential characteristics behind the data.     

Developing a Smart Structure Using Integrated Subspace‐Based Damage Detection and Semi‐Active Control

Damage detection in large building structures has always faced challenges due to analyzing the large amount of measured data. In this article, a new damage detection approach based on subspace method is proposed to identify damages using limited output data. Also, a new scheme is presented to develop a smart structure by integrating structural health monitoring with semi‐active control strategy. If damage occurs in such a structure under severe excitations, the proposed scheme has the capability to exert necessary control forces in order to compensate for damage and reduce simultaneously the dynamic response of the structure. The reliability and feasibility of the proposed method are demonstrated by implementing the technique to two shear building structures with semi‐active control devices. Results show that the damage could be identified accurately with saving time and cost due to less computation even under noise existence; and dynamic response is significantly reduced in the smart structure.     

基于不完整频响函数的结构损伤识别方法

对土木工程结构的分析模型,在传感器不完整布置的情况下,推导基于不完整频响函数的"定性—定位—定量"的损伤识别方法。首先,利用不完备的频响函数图形的偏移程度进行损伤的定性判定;然后,建立损伤识别指标对损伤位置进行识别;最后,推导损伤定量计算方法,对损伤程度进行评估。仿真结果表明,本文提出损伤识别3阶段方法,对结构损伤探测的评估能得到比较满意的结果。