Cloud-Verhulst hybrid prediction model for dam deformation under uncertain conditions

Uncertainties existing in the process of dam deformation negatively influence deformation prediction. However, existing deformation pre- diction models seldom consider uncertainties. In this study, a cloud-Verhulst hybrid prediction model was established by combing a cloud model with the Verhulst model. The expectation, one of the cloud characteristic parameters, was obtained using the Verhulst model, and the other two cloud characteristic parameters, entropy and hyper-entropy, were calculated by introducing inertia weight. The hybrid prediction model was used to predict the dam deformation in a hydroelectric project. Comparison of the prediction results of the hybrid prediction model with those of a traditional statistical model and the monitoring values shows that the proposed model has higher prediction accuracy than the traditional sta- tistical model. It provides a new approach to predicting dam deformation under uncertain conditions.

Permanent deformation and prediction model of construction and demolition waste under repeated loading

This study aims to reveal the macroscopic permanent deformation(PD)behavior and the internal structural evolution of construction and demolition waste(CDW)under loading.Firstly,the initial matric suction of CDW was measured by the filter paper method.Secondly,the PD of CDW with different humidity and stress states was investigated by repeated load triaxial tests,and a comprehensive prediction model was established.Finally,the discrete element method was performed to analyze the internal structural evolution of CDW during deformation.These results showed that the VAN-GENUCHTEN model could describe the soil-water characteristic curve of CDW well.The PD increases with the increase of the deviator stress and the number of cyclic loading,but the opposite trend was observed when the initial matric suction and confining pressure increased.The proposed model in this study provides a satisfactory prediction of PD.The discrete element method could accurately simulate the macroscopic PD of CDW,and the shear force,interlock force and sliding content increase with the increase of deviator stress during the deformation.The research could provide useful reference for the deformation stability analysis of CDW under cyclic loading.

Comparative Study on Deformation Prediction Models of Wuqiangxi Concrete Gravity Dam Based on Monitoring Data

The deformation prediction models of Wuqiangxi concrete gravity dam are developed,including two statistical models and a deep learning model.In the statistical models,the reliable monitoring data are firstly determined with Lahitte criterion;then,the stepwise regression and partial least squares regression models for deformation prediction of concrete gravity dam are constructed in terms of the reliable monitoring data,and the factors of water pressure,temperature and time effect are considered in the models;finally,according to the monitoring data from 2006 to 2020 of five typical measuring points including J23(on dam section 24^(#)),J33(on dam section 4^(#)),J35(on dam section 8^(#)),J37(on dam section 12^(#)),and J39(on dam section 15^(#))located on the crest of Wuqiangxi concrete gravity dam,the settlement curves of the measuring points are obtained with the stepwise regression and partial least squares regression models.A deep learning model is developed based on long short-term memory(LSTM)recurrent neural network.In the LSTM model,two LSTMlayers are used,the rectified linear unit function is adopted as the activation function,the input sequence length is 20,and the random search is adopted.The monitoring data for the five typical measuring points from 2006 to 2017 are selected as the training set,and the monitoring data from 2018 to 2020 are taken as the test set.From the results of case study,we can find that(1)the good fitting results can be obtained with the two statistical models;(2)the partial least squares regression algorithm can solve the model with high correlation factors and reasonably explain the factors;(3)the prediction accuracy of the LSTM model increases with increasing the amount of training data.In the deformation prediction of concrete gravity dam,the LSTM model is suggested when there are sufficient training data,while the partial least squares regression method is suggested when the training data are insufficient.

Neural network-based model for prediction of permanent deformation of unbound granular materials

Several available mechanistic-empirical pavement design methods fail to include predictive model for permanent deformation(PD)of unbound granular materials(UGMs),which make these methods more conservative.In addition,there are limited regression models capable of predicting the PD under multistress levels,and these models have regression limitations and generally fail to cover the complexity of UGM behaviour.Recent researches are focused on using new methods of computational intelligence systems to address the problems,such as artificial neural network(ANN).In this context,we aim to develop an artificial neural model to predict the PD of UGMs exposed to repeated loads.Extensive repeated load triaxial tests(RLTTs)were conducted on base and subbase materials locally available in Victoria,Australia to investigate the PD properties of the tested materials and to prepare the database of the neural networks.Specimens were prepared over different moisture contents and gradations to cover a wide testing matrix.The ANN model consists of one input layer with five neurons,one hidden layer with twelve neurons,and one output layer with one neuron.The five inputs were the number of load cycles,deviatoric stress,moisture content,coefficient of uniformity,and coefficient of curvature.The sensitivity analysis showed that the most important indicator that impacts PD is the number of load cycles with influence factor of 41%.It shows that the ANN method is rapid and efficient to predict the PD,which could be implemented in the Austroads pavement design method.

4-Dimensional Models of Deformation of the Earth's Crust and Earthquake Prediction

Traditionally, when creating 4-D models of elastic offsets in the Earth’s crust, the data from geodesic and GPS monitoring of offsets on the ground surface, earthquake catalogs, monitoring of the water level and radon content in wells, sea level fluctuations, as well as gravitational and magnetic fields, etc., can be taken as bases for information. In essence, the reason for creating a 4-D model of slow elastic deformations is to approximate the process by a set of plane deformation solitons (solitary waves). The parameters of a set of deformation solitons are obtained by a two-stage inversion. First, the parameters of the model are determined in a kinematic way by the use of a modified simplification of the method. Then, a calibration of the amplitude characteristics of the model is carried out in terms of elastic dynamic offsets. Taking Ural, Northern Tianshan, Greece, and China as examples, models for these regions are created on the basis of seismological, geodesic, deformation, hydrogeological,

Grain size effect on cyclic deformation behavior and springback prediction of Ni-based superalloy foil

In order to clarify the influence of grain size on cyclic deformation response of superalloy sheets and springback behavior,cyclic loading-unloading and shearing tests were performed on the superalloy foils with 0.2 mm in thickness and diverse grain sizes.The results show that,the decline ratio of elastic modulus is weakened with increasing grain size,and the Bauschinger effect becomes evident with decreasing grain size.Meanwhile,U-bending test results determine that the springback is diminished with increasing grain size.The Chaboche,Anisotropic Nonlinear Kinematic(ANK)and Yoshida-Uemori(Y-U)models were utilized to fit the shear stress-strain curves of specimens.It is found that Y-U model is sufficient of predicting the springback.However,the prediction accuracy is degraded with increasing grain size.

Deformation,structure and potential hazard of a landslide based on InSAR in Banbar county,Xizang(Tibet)

The Tibetan Plateau is characterized by complex geological conditions and a relatively fragile ecological environment.In recent years,there has been continuous development and increased human activity in the Tibetan Plateau region,leading to a rising risk of landslides.The landslide in Banbar County,Xizang(Tibet),have been perturbed by ongoing disturbances from human engineering activities,making it susceptible to instability and displaying distinct features.In this study,small baseline subset synthetic aperture radar interferometry(SBAS-InSAR)technology is used to obtain the Line of Sight(LOS)deformation velocity field in the study area,and then the slope-orientation deformation field of the landslide is obtained according to the spatial geometric relationship between the satellite’s LOS direction and the landslide.Subsequently,the landslide thickness is inverted by applying the mass conservation criterion.The results show that the movement area of the landslide is about 6.57×10^(4)m^(2),and the landslide volume is about 1.45×10^(6)m^(3).The maximum estimated thickness and average thickness of the landslide are 39 m and 22 m,respectively.The thickness estimation results align with the findings from on-site investigation,indicating the applicability of this method to large-scale earth slides.The deformation rate of the landslide exhibits a notable correlation with temperature variations,with rainfall playing a supportive role in the deformation process and displaying a certain lag.Human activities exert the most substantial influence on the spatial heterogeneity of landslide deformation,leading to the direct impact of several prominent deformation areas due to human interventions.Simultaneously,utilizing the long short-term memory(LSTM)model to predict landslide displacement,and the forecast results demonstrate the effectiveness of the LSTM model in predicting landslides that are in a continuous development and movement phase.The landslide is still active,and based on the spatial heterogeneity of landslide deformation,new recommendations have been proposed for the future management of the landslide in order to mitigate potential hazards associated with landslide instability.

Deformation Characteristics of Hydrate-Bearing Sediments

The safe and efficient development of natural gas hydrate requires a deep understanding of the deformation behaviors of reservoirs.In this study,a series of triaxial shearing tests are carried out to investigate the deformation properties of hydrate-bearing sediments.Variations of volumetric and lateral strains versus hydrate saturation are analyzed comprehensively.Results indicate that the sediments with high hydrate saturation show dilative behaviors,which lead to strain-softening characteristics during shearing.The volumetric strain curves have a tendency to transform gradually from dilatation to compression with the increase in effective confining pressure.An easy prediction model is proposed to describe the relationship between volumetric and axial strains.The model coefficientβis the key dominating factor for the shape of volumetric strain curves and can be determined by the hydrate saturation and stress state.Moreover,a modified model is established for the calculation of lateral strain.The corresponding determination method is provided for the easy estimation of model coefficients for medium sand sediments containing hydrate.This study provides a theoretical and experimental reference for deformation estimation in natural gas hydrate development.

Time effect and prediction of broken rock bulking coefficient on the base of particle discrete element method

Bulking characteristics of gangue are of great significance for the stability of goafs in mining overburden in the caving zones.In this paper,a particle discrete element method with clusters to represent gangue was adopted to explore the bulking coefficient time effect of the broken rock in the caving zone under three-dimensional triaxial compression condition.The phenomena of stress corrosion,deformation,and failure of rock blocks were simulated in the numerical model.Meanwhile,a new criterion of rock fragments damage was put forward.It was found that the broken rock has obvious viscoelastic properties.A new equation based on the Burgers creep model was proposed to predict the bulking coefficient of broken rock.A deformation characteristic parameter of the prediction equation was analyzed,which can be set as a fixed value in the mid-and long-term prediction of the bulking coefficient.There are quadratic function relationships between the deformation characteristic parameter value and Talbot gradation index,axial pressure and confining pressure.

Dynamic prediction of building subsidence deformation with data-based mechanistic self-memory model

This paper describes a building subsidence deformation prediction model with the self-memorization principle.According to the non-linear specificity and monotonic growth characteristics of the time series of building subsidence deformation,a data-based mechanistic self-memory model considering randomness and dynamic features of building subsidence deformation is established based on the dynamic data retrieved method and the self-memorization equation.This model first deduces the differential equation of the building subsidence deformation system using the dynamic retrieved method,which treats the monitored time series data as particular solutions of the nonlinear dynamic system.Then,the differential equation is evolved into a difference-integral equation by the self-memory function to establish the self-memory model of dynamic system for predicting nonlinear building subsidence deformation.As the memory coefficients of the proposed model are calculated with historical data,which contain useful information for the prediction and overcome the shortcomings of the average prediction,the model can predict extreme values of a system and provide higher fitting precision and prediction accuracy than deterministic or random statistical prediction methods.The model was applied to subsidence deformation prediction of a building in Xi'an.It was shown that the model is valid and feasible in predicting building subsidence deformation with good accuracy.

Modeling hot strip rolling process under framework of generalized additive model

This research develops a new mathematical modeling method by combining industrial big data and process mechanism analysis under the framework of generalized additive models(GAM)to generate a practical model with generalization and precision.Specifically,the proposed modeling method includes the following steps.Firstly,the influence factors are screened using mechanism knowledge and data-mining methods.Secondly,the unary GAM without interactions including cleaning the data,building the sub-models,and verifying the sub-models.Subsequently,the interactions between the various factors are explored,and the binary GAM with interactions is constructed.The relationships among the sub-models are analyzed,and the integrated model is built.Finally,based on the proposed modeling method,two prediction models of mechanical property and deformation resistance for hot-rolled strips are established.Industrial actual data verification demonstrates that the new models have good prediction precision,and the mean absolute percentage errors of tensile strength,yield strength and deformation resistance are 2.54%,3.34%and 6.53%,respectively.And experimental results suggest that the proposed method offers a new approach to industrial process modeling.

特高拱坝变形机理可解释性智能预测模型

针对传统“黑箱”模型可以预测却无法解释拱坝变形的缺陷,利用Shapley Additive Explanation(SHAP)理论对特高拱坝的机器学习变形预测模型进行解构分析,分析水压、温度、时效对特高拱坝不同部位径向水平位移的影响规律。构建特高拱坝变形监测数据的轻量梯度提升算法(Light Gradient Boosting Machine,LightGBM)黑箱预测模型,利用SHAP对存在多重共线性的因子进行剔除,再从整个因子集和单个样本两个角度分析不同影响因子对模型变形预测的贡献度;通过分析拉西瓦特高拱坝坝肩、坝基、拱冠等不同部位的径向水平位移与影响因子间的关系,发现时效因子对高程越高、越靠近拱冠位置的径向水平位移影响越大,温度因子主要影响靠近拱冠位置的径向水平位移,水压因子主要影响高程较高位置的径向水平位移,而坝基和深入坝肩岩体测点的径向水平位移几乎不受水位、温度的影响。解决了以往“黑箱”变形预测模型可视性差、内部机理不明的问题,根据可解释模型得到的相关规律可为特高拱坝的工作性态分析和运行管理提供借鉴。

基于双向门控式宽度学习系统的监测数据结构变形预测

监测数据深度学习预测模型运算量大、实时性差,为此结合宽度学习系统(BLS)和双向长短时记忆(Bi-LSTM)模型的优势,提出基于双向门控式宽度学习系统(Bi-G-BLS)的结构变形预测模型.对BLS的特征节点增加循环反馈和遗忘门结构,提高当前节点对前一节点的依赖关系,分别从正向和反向提取时间序列的内部特征,充分挖掘数据的双向特征,在提高模型预测精确度的同时减少模型预测时间.基于实测的地铁基坑沉降监测数据的测试结果显示,所提预测模型与门控循环单元(GRU)、BLS、Bi-LSTM、G-BLS模型相比,均方根误差(RMSE)、平均绝对误差(MAE)、平均绝对百分比误差(MAPE)平均分别降低了21.04%、12.81%、24.41%;在预测精度相近的情况下,所提模型的预测时间比Bi-LSTM模型降低了99.59%.结果表明,所提模型在预测速度和精确度上较对比模型有明显提升.

一种融合GA和LSTM的边坡变形预测优化网络模型及其应用

考虑到BP神经网络模型忽略边坡监测数据存在的时间相关性,以及LSTM模型由于超参数选择存在主观性而易陷入局部最优等问题,提出一种基于遗传算法和长短期记忆网络(GA-LSTM)相结合的边坡变形预测模型,以发挥遗传算法全局搜索能力和LSTM预测时序数据的优势。以海明矿业露天采场边坡为研究对象,分别采用BP神经网络模型、LSTM网络模型以及GA-LSTM网络模型对边坡监测点GNSS49变形进行预测分析,并对比各模型达到收敛条件的时间。结果表明,GA-LSTM模型与其他模型达到同一收敛条件的时间差异不大,GA-LSTM模型的拟合准确度在0.1~0.2 mm,是LSTM神经网络模型的5~7倍,是BP神经网络模型的10~20倍,具有较高的精度和稳定性,其预测值与实际监测数据基本一致,可为矿山边坡的安全生产、管理以及决策控制提供科学依据。

间歇性循环荷载下冻融风积土变形特性及分数阶预测模型

列车运营对路基的长期作用由振动加载、荷载间歇交替组成,已往研究多只考虑振动加载周期对路基土体强度和变形特性的影响,而忽略了间歇期的影响。为研究间歇性循环荷载作用下风积土路基变形特性,利用GDS DYNTTS冻土动三轴仪,开展不同有效固结围压σ_(3c)、冻融循环次数FT、动应力幅值σ_(d)^(ampl)和振动频率f的间歇性循环荷载下风积土动三轴试验,研究间歇性循环荷载下冻融风积土变形特性及其影响因素。试验结果表明:间歇性循环荷载作用下风积土累积塑性应变曲线呈稳定型、发展型和破坏型三种形态。间歇阶段能够在较大程度上削弱土体的应变累积,从而使其较连续荷载作用下变形减小。基于极差方法,确定动应力幅值是影响风积土累积塑性应变的最重要因素,其余依次为有效固结围压、冻融循环次数、振动频率。采用双Abel黏壶建立考虑间歇性循环荷载作用的冻融风积土分数阶累积塑性应变预测模型,并与试验结果进行了对比分析,二者吻合度较高,说明该文建立的分数阶累积塑性应变数学模型可合理预测间歇性循环荷载作用下风积土路基长期变形特性。研究成果可为季节性冻土地区路基工程设计和灾害防治提供科学依据。

囊袋式注浆对盾构下穿高速铁路路基沉降的控制效果

高铁路基的沉降变形是影响运营安全的重要因素,盾构下穿既有高铁线路施工可诱发高铁路基沉降变形。为有效控制高铁路基沉降,基于数值模拟探究了囊袋式注浆作为高铁路基沉降主动控制措施的有效性。结果表明:注浆囊袋对其周围土体的影响具有局部性,地层等效塑性应变随注浆体埋深的增加而增大,且塑性区厚度通常小于注浆囊袋膨胀厚度的3.0倍。囊袋的埋设深度和膨胀直径对路基抬升整治范围有影响,囊袋埋设越浅其膨胀后对路基抬升的影响效果越明显,且路基表层的隆起变形曲线符合高斯方程。提出了盾构下穿高铁路基时囊袋式注浆控制措施下路基沉降预测模型,可指导盾构下穿高铁路基的沉降控制。

M-CM-GA-BP算法的地表移动变形参数预测模型

针对复杂的开采沉陷预测问题,研究22个工作面采动地表移动变形参数变化规律,提出了一种基于M-CM-GA-BP算法求取地表移动变形参数的预测模型。通过线性加权组合预测方法和遗传算法优化BP神经网络的权值和阈值,融合多元回归模型来提高地表移动变形参数的求取精度,以地表下沉系数q为例,将该模型与其他预测模型预测性能进行对比分析,验证模型的准确性。结果表明,该模型能够有效地提高地表移动变形参数的预测精度,模型的平均相对误差为1.294、均方根误差为0.013,为地表移动变形参数预测提供了一种可行方法。

基于GM(1,1)模型的地铁基坑变形预测研究

在深大基坑开挖过程中,基坑周围土体会受到扰动,势必会影响到基坑、基坑周围建筑物和构筑物的稳定与安全。为解决基坑开挖过程中变形监测周期过长而无法长期监测以及监测数据误差等问题,以某工程实例为依据,对基坑周围地表沉降变形进行监测,以地表沉降监测数据为基础数据建立GM(1,1)预测模型,进行基坑后期沉降变形预测分析。结果表明:该模型预测结果能较好的反映基坑的沉降变形情况,预测精度能满足工程需要,预测结果相对于实际观测值表现出超前现象,可为类似工程建设提供参考。

基于FOA-BP-AdaBoost的大坝变形预测模型及应用

为提升大坝变形监测预测精度,解决变形量受多因素影响等问题,笔者提出了基于果蝇优化算法(FOA)、BP神经网络的AdaBoost强预测组合模型(FOA-BP-AdaBoost),并与BP神经网络模型、FOA-BP神经网络模型应用于工程实例中的预测精度进行多方位量化对比。结果表明:强预测模型集齐了果蝇算法全局优化、BP神经网络局部寻优和AdaBoost“优中选优”的特点,最大程度优化了预测效果;实例应用证实了FOA-BP-AdaBoost模型在大坝变形预测领域的准确性和有效性。该模型已成功应用于工程实例,可为类似工程提供参考。

地铁车站深基坑开挖变形智能多步预测方法

为更好预测深基坑开挖期间地下连续墙的侧向位移变形,基于长短期记忆神经网络(LSTM)智能算法理论构建了LSTM多步预测模型.首先对多步预测模型的多输出策略进行论述,其次详细介绍了LSTM多步预测模型的构建方法,并对模型输入集空间维度和时间维度两项超参数进行探究,以提高模型的预测准确度.最后依托某富水砂土深基坑工程实例,分析了模型预测值与实际监测值的差异.3个典型监测点的数据分析结果表明LSTM多步预测模型具有较强的泛化能力,相关算法对深基坑开挖变形预测方法的改进优化具有参考价值.