A prediction model for horizontal run-out distance of landslides triggered by Wenchuan earthquake

The peak ground acceleration （PGA）, the volume of a sliding mass V, the height of a mountain HL and the slope angle θ of a mountain are four important parameters affecting the horizontal run-out distance of a landslide L. Correlations among them are studied statistically based on field investigations from 67 landslides triggered by the ground shaking and other factors during the Wenchuan earthquake, and then a prediction model for horizontal run-out distance L is developed in this study. This model gives due consideration to the implications of the above four parameters on the horizontal run-out distance L and the validity of the model is verified by the Donghekou and Magong Woqian landslides. At the same time, the advantages of the model are shown by comparing it with two other common prediction methods. The major findings drawn from the analyses and comparisons are： （1） an exponential relationship exists between L and log V, L and log HL, L and log PGA separately, but a negative exponential relationship exists between L and log tan0, which agrees with the statistical results; and （2） according to the analysis results of the relative relationship between the height of a mountain （H） and the place where the landslides occur, the probabilities at distances of2H/3-H, H/3-2H/3, and O-H/3 are 70.8%, 15.4%, and 13.8%, respectively, revealing that most landslides occurred at a distance of H/2-H. This prediction model can provide an effective technical support for the prevention and mitigation of landslide hazards.

Rapid prediction models for 3D geometry of landslide dam considering the damming process

The geometry of a landslide dam plays a critical role in its stability and failure mode,and is influenced by the damming process.However,there is a lack of understanding of the factors that affect the 3D geometry of a landslide dam.To address this gap,we conducted a study using the smoothed particle hydrodynamics numerical method to investigate the evolution of landslide dams.Our study included 17 numerical simulations to examine the effects of several factors on the geometry of landslide dams,including valley inclination,sliding angle,landslide velocity,and landslide mass repose angle.Based on this,three rapid prediction models were established for calculating the maximum height,the minimum height,and the maximum width of a landslide dam.The results show that the downstream width of a landslide dam remarkably increases with the valley inclination.The position of the maximum dam height along the valley direction is independent of external factors and is always located in the middle of the landslide width area.In contrast,that position of the maximum dam height across the valley direction is significantly influenced by the sliding angle and landslide velocity.To validate our models,we applied them to three typical landslide dams and found that the calculated values of the landslide dam geometry were in good agreement with the actual values.The findings of the current study provide a better understanding of the evolution and geometry of landslide dams,giving crucial guidance for the prediction and early warning of landslide dam disasters.

Wear mechanism and life prediction of the ripper in a 9-m-diameter shield machine tunneling project of the Beijing new airport line in a sand-pebble stratum

Tool wear is a noteworthy problem in the process of shield tunneling,and the degree of wear varies with stratum.The sand-pebble strata in Beijing are typically mechanically unstable.However,many subways are buried wholly or partially in sand-pebble strata.Taking the Beijing New Airport line tunneling project as research background,this study evaluated the wear characteristics of the multiconfiguration rippers of a 9-m-diameter spoke-type shield tunneling machine in a sand-pebble stratum.The wear values of five ripper teeth and ripper flanks were analyzed based on field-measured data from the Beijing New Airport line project.As the analytical results show,the wear value generally increases as the installation radius enlarges with the rise of cutting trace length.The wear of the 190-rippers was divided into five categories:pedestal wear,ripper teeth collapse,uniform wear,ripper teeth falling off and ripper flank wear.Uniform wear of the ripper teeth and ripper flank wear were the two abrasion types of the 190-rippers.The teeth of the 155-rippers mostly maintained their cutting capacity under the protection of the 190-rippers.A wear prediction model of linear fitting field data was developed for a 190-ripper face to obtain the optimum shield driving distance in the sand-pebble stratum.The average wear coefficients of the 190-ripper before and after replacement matched well,being 0.045 and 0.066 mm/km,respectively.The results of this study provide a theoretical reference for tool wear prediction in shield construction under similar geological conditions.

Improved Relative-transformation Principal Component Analysis Based on Mahalanobis Distance and Its Application for Fault Detection

主要部件分析(PCA ) 广泛地在过程工业被使用了，它能维持最大的差错察觉率。尽管许多问题在 PCA 被处理了，一些必要问题仍然保持未解决。这研究以下列方法为差错察觉性能改进 PCA。第一，一个相对转变计划基于 Mahalanobis 距离(MD ) 被介绍消除数据的尺寸的效果而不是无尺寸的标准化，并且改进精确性和差错察觉的即时性能。理论推导证明那相对转变能直接基于 MD 消除尺寸的效果并且在结果显示出的相对空间，分析和模拟给 PCA 的合理解释它的优势和有效性。第二，一个改进摆平的预言错误(SPE ) 统计数值被给改进标准化 PCA 的差错察觉表演，它能使标准化基于 PCA 的差错察觉方法成为对实际工业过程合适的更多。最后，二个改进方法被联合更有效地检测差错。建议方法被使用在热连续滚动过程检测 looper 系统的单个差错和多差错，模拟结果以易感知，精确性和差错察觉的即时性能为差错察觉性能表明这些改进的有效性。

基于IDP的重型商用车自适应距离域预见性巡航控制策略

为降低重型商用车燃油消耗、减少运输成本,本文协调“人-车-路”交互体系,将车辆与智能网联环境下的多维度信息进行融合,提出了一种基于迭代动态规划(iterative dynamic programming,IDP)的自适应距离域预见性巡航控制策略(adaptive range predictive cruise control strategy,ARPCC)。首先结合车辆状态与前方环境多维度信息,基于车辆纵向动力学建立自适应距离域模型对路网重构,简化网格数量并利用IDP求取全局最优速度序列。其次,在全局最优速度序列的基础上,求取自适应距离域内的分段最优速度序列,实现车辆控制状态的快速求解。最后,利用Matlab/Simulink进行验证。结果表明,通过多次迭代缩小网格,该算法有效提高了计算效率和车辆燃油经济性。

多域蛋白质残基间距离深度学习预测方法

自然界生物中,大约有超过三分之二的真核蛋白质含有多个结构域.虽然AlphaFold2已经实现了端到端的蛋白质结构预测的重大突破,对于单域的静态蛋白质结构的预测精度几乎达到了实验测定的水平,但是对于多域蛋白质结构的预测精度仍然有待提高.本文提出了一种名为MDDpre的多域蛋白质残基距离预测方法.首先从多序列比对和模板中提取了序列谱、位置熵、互信息、去除背景噪声的互信息、平均接触势能、MSA特征矩阵、行注意力矩阵以及模板域间距离特征,然后设计了一个集合了三角形更新、轴向注意力机制和卷积残差块的网络来预测多域蛋白质的域间和域内距离.在62个多域蛋白质的实验结果表明,MDDpre优于现有的方法,能够有效提升多域蛋白质的残基距离预测精度.

汶川震区山洪灾害场次洪水最大携沙量预测模型

汶川地震后,震区产生了大量松散堆积体,受强降水影响产生了破坏性更强的山洪灾害,加剧了灾害的危险性,增加了灾害防治的困难度,研究震区山洪灾害可为评估灾害的风险性及后续的管理提供依据。本研究以66处历史山洪灾害作为样本数据,进行可量算影响因子的相关性分析,揭示山洪灾害的携沙量影响机制,确定流域面积、主沟长度、相对高差、物源量四个影响因子作为主控因子,基于SPSS进行非线性回归分析,建立了基于场次洪水最大携沙量及最大携沙距离的估算模型,并选取了汶川县和都江堰市的共23处山洪水沙灾害数据进行了模型的验证且与其他模型对比。结果表明,本研究建立的模型可靠性好,精度更高。研究成果有助于预测汶川震区潜在的山洪水沙灾害区域,为山洪水沙灾害的风险评估提供依据。

改进的MVO-GRNN神经网络岩爆预测模型研究

准确预测岩爆烈度等级能有效指导岩爆灾害的防控。根据影响岩爆发生及烈度等级的3个因素构建岩爆评价指标体系,提出一种基于改进多元宇宙算法(Improved Multi-Verse Optimizer,IMVO)优化广义回归神经网络(General Regression Neural Network,GRNN)的岩爆预测模型。在普通多元宇宙算法(MVO)的基础上,运用自适应平衡机制调节MVO算法中的虫洞存在概率(V_(WEP))和旅行距离率(V_(TDR))两个重要参数来改进该算法;再运用改进的多元宇宙算法优化广义回归神经网络的光滑度,通过训练数据优选出最佳光滑因子σ,得到IMVO-GRNN神经网络岩爆烈度预测模型;最后结合工程实例验证模型的性能。研究表明,该模型相比传统模型寻优能力更强,精度更高,为岩爆预测提供了一种新的思路。

海上高速航行船舶触礁距离实时计算方法

为了提高船舶航行安全性,并应对航行过程潜在碰撞风险,提出海上高速航行船舶触礁距离实时计算方法。通过航海雷达探测船舶航行环境中的礁石目标,确定极坐标系下的位置坐标后,将其转换地心垂直坐标系下,构建基于PLSTM-FCN的船舶航迹预测模型,从船舶自动识别系统中获取高速航行船舶历史位置、航速、航向、船舶长度、宽度以及吃水深度等AIS数据,将其作为模型输入,模型输出为船舶航行实时位置预测结果,结合礁石目标位置,完成触礁距离的实时计算。实验结果表明,该方法可预测船舶航行航迹,预测MSE值仅为0.002 2;可实现船舶触礁距离的实时计算,计算结果与实际距离误差介于0.77~1.55之间。

基于极限学习机模型参数优化的光伏功率区间预测技术

提出一种基于极限学习机(ELM)模型参数优化的光伏功率区间预测技术.首先,提出加权欧氏距离作为光伏功率预测区间评估指标,筛选历史样本单元并优化ELM训练集;然后,提出ELM参数混合寻优算法,利用精英保留策略遗传算法与分位数回归优化ELM模型隐层输入及输出权重与偏置参数,并采用训练后的模型预测光伏功率区间;最后,基于光伏电站与气象站历史数据构建实际算例,预测光伏功率区间,并与其他方法得到的结果进行对比.算例结果表明:所提方法在增加区间预测可信度的同时,能较大程度提高区间预测准确度.

含粗骨料尾砂膏体长距离管输流变特性及阻力预测

为探明质量浓度、粗骨料含量、灰砂质量比和水化时间对膏体长距离管输流变特性的影响,本文基于正交设计开展流变实验,采用回归分析建立流变参数预测模型,在此基础上通过理论推导建立管道阻力预测模型,采用现场实测数据验证阻力预测结果的可靠性。结果表明:含粗骨料尾砂膏体属于宾汉流体,质量浓度和粗骨料含量对膏体流变参数的影响最显著;屈服应力随质量浓度的增大呈指数增长,随粗骨料含量的增加呈指数减小,随水化时间的增加呈线性增长,与灰砂质量比的关系不大;塑性粘度随质量浓度的增大呈指数增长,随粗骨料含量的增加呈线性减小,随灰砂质量比和水化时间的增加呈线性增长;建立的流变参数预测模型平均误差小于4.3%,基于宾汉流变模型建立的管道阻力模型预测值比现场实测值偏大12.5%,满足工程应用的精度要求。

结构化最大间隔双支持向量机在股票预测中的应用

股票价格受政策、宏观经济以及公司经营状况等多方因素的影响,且各因素之间存在较高的相关性,因此股票数据存在的高噪声、非平稳等特性使得股票预测充满困难。为了减少数据中存在的噪声对股价预测准确性的影响,基于马氏距离的类间隔可分性,提出了结构化最大间隔双支持向量机,其分别针对正类样本和负类样本,寻找两个非平行的超平面,使每一类样本离本类样本的欧式距离尽可能小,同时离异类超平面的马氏距离尽可能大。8组基准数据集的实验结果表明,该方法在含噪声数据的分类问题上具有稳定的准确率,从而提升了模型的预测性能和抗噪能力。同时将其应用到股票涨跌趋势预测中,通过对上证综指、上证A指、上证380指数以及中国平安等14只股票实证分析的结果表明,相较于其他对比模型,结构化最大间隔双支持向量机表现出了较好的预测结果,具有一定的实用价值。

基于Hellinger距离和IOWC-GOWA算子的区间组合预测模型

针对区间型数据的组合预测,该文引入了统计学中衡量两个概率密度函数之间相似程度的指标——Hellinger距离作为构建组合预测模型的最优化准则.在已构建的诱导有序加权连续区间的广义有序加权平均(IOWC-GOWA)算子的基础上,将区间数序列转化为实数序列,建立了一种新的区间数组合预测模型,并通过具体的数据进行分析,验证了该模型的有效性.结果表明:该文所建立的基于Hellinger距离和IOWC-GOWA算子的区间组合预测模型能在单项预测的基础上有效提升预测精度,是一种优性组合预测模型.

商用半挂汽车纵向避撞控制

为降低商用半挂汽车在雨天湿滑路面等危险条件下的追尾事故发生率,基于魔术公式轮胎模型及递推最小二乘算法(RLS)估计路面附着系数,利用BP神经网络预测制动距离,提出一种基于实时制动距离预测(BDP)的安全距离模型,设计了分级避撞控制策略。分别在高低附着系数路面的前车制动(CCRb)、前车静止(CCRs)、前车低速行驶(CCRm)3种工况下进行联合仿真,验证模型有效性。仿真结果表明:高附着系数路面上BDP模型和Mazda模型在3种工况下能够成功避免碰撞,制动结束时BDP模型的停车间距更小,更符合驾驶习惯且兼顾一定的行车效率及驾乘舒适性;低附着系数路面上Mazda模型仅在CCRm工况时成功避撞,BDP模型在3种工况下可以顺利避免碰撞的发生。BDP模型可以有效降低低附着系数路面的追尾事故发生率。

玉米收获机发动机服役状态趋势分析与预警

为提高服役状态下玉米收获机发动机运行的稳定性,以发动机运行数据为分析对象,计算发动机的一个稳定性运行趋势曲线,用以判断发动机是否处于稳定性状态。首先通过获取发动机ECU系统中的运行数据,对发动机正常运行下的数据进行归一化处理,然后基于遗传算法优化的BP神经网络建立预测模型。以发动机转速、农机速度、冷却液温度、系统电压4个参数作为输入对机油压力的数值进行预测,最终预测模型的决定系数达到0.88,证明预测模型拟合度较高,能准确地对发动机的机油压力做出预测。而发动机在正常运行的情况下,机油压力的预测偏差较小,以大量正常运行的机油压力预测值与实际运行值的残差结合实际运行值构建基准向量集合,再以20 000条正常的机油压力的运行预测值与实际运行值的残差结合实际运行值构建评估向量,利用马氏距离计算每个评估向量到基准向量集合的距离值,该距离值可代表发动机正常运行状态下的一个稳定性的指标值。结果表明:得到的20 000个指标值具有一定的聚集性,指标值的大小稳定在0~10之间,所以该指标值在时间序列的一个趋势曲线可以代表发动机服役状态下的一个稳定的趋势,用以判断发动机处于正常或异常状态。

基于用户行为和上下文语义的分层ST-LSTM位置预测

当前的位置预测方法大多没有考虑到用户行为信息,由于用户的访问时间、行为模式等能够在很大程度上反映所处位置,因此在对位置潜在向量进行预训练时有必要使用该信息。进行位置预测时,采样粒度较细的序列长度较长,难以捕获长距离依赖。针对这2个问题,提出了基于用户行为和上下文语义的分层时空长短期记忆网络(Hierarchical Spatiotemporal Long Short-Term Memory Based on User Behavior and Contextual Semantics,CHST-LSTM)模型。该模型通过Transformer编码层处理轨迹数据,将用户相关行为信息考虑在内,融合位置的上下文语义信息,通过预训练得到位置的嵌入表征。根据用户的行为状态分割轨迹阶段,采用编码器-解码器方式对ST-LSTM进行分段分层扩展,利用BiLSTM对全局信息建模,同时处理轨迹的长短期变化,解决长序列的长距离依赖问题。对外卖员用户群体的真实移动轨迹数据进行分析和实验,通过聚类发现其特有的工作模式,在预训练时加入工作模式信息与到访时间信息,得到位置的特征向量并用于预测模型。结果表明CHST-LSTM模型在预测用户下一位置时精度更高。

An AI‑Based Method for Estimating the Potential Runout Distance of Post‑Seismic Debris Flows

The widely distributed sediments following an earthquake presents a continuous threat to local residential areas and infrastructure.These materials become more easily mobilized due to reduced rainfall thresholds.Before establishing an efective management plan for debris fow hazards,it is crucial to determine the potential reach of these sediments.In this study,a deep learning-based method-Dual Attention Network(DAN)-was developed to predict the runout distance of potential debris fows after the 2022 Luding Earthquake,taking into account the topography and precipitation conditions.Given that the availability of reliable precipitation data remains a challenge,attributable to the scarcity of rain gauge stations and the relatively coarse resolution of satellite-based observations,our approach involved three key steps.First,we employed the DAN model to refne the Global Precipitation Measurement(GPM)data,enhancing its spatial and temporal resolution.This refnement was achieved by leveraging the correlation between precipitation and regional environment factors(REVs)at a seasonal scale.Second,the downscaled GPM underwent calibration using observations from rain gauge stations.Third,mean absolute error(MAE),mean square error(MSE),and root mean square error(RMSE)were employed to evaluate the performance of both the downscaling and calibration processes.Then the calibrated precipitation,catchment area,channel length,average channel gradient,and sediment volume were selected to develop a prediction model based on debris fows following the Wenchuan Earthquake.This model was applied to estimate the runout distance of potential debris fows after the Luding Earthquake.The results show that:(1)The calibrated GPM achieves an average MAE of 1.56 mm,surpassing the MAEs of original GPM(4.25 mm)and downscaled GPM(3.83 mm);(2)The developed prediction model reduces the prediction error by 40 m in comparison to an empirical equation;(3)The potential runout distance of debris fows after the Luding Earthquake reaches 0.77 km when intraday rainfall is 100 mm,while the minimum distance value is only 0.06 km.Overall,the developed model ofers a scientifc support for decision makers in taking reasonable measurements for loss reduction caused by post-seismic debris fows.

微封装制造中胶液分配体积计算与预测研究

针对针转移式皮升分辨率超微量胶液分配方法,研究胶液分配初始距离对胶滴体积的影响,建立了基于初始距离量化分配形成微小液滴体积大小的公式。利用像素法对实验胶滴样本图像进行分析并确定出胶滴真实体积大小,并基于实验分析结果利用数值拟合方法建立胶滴体积的数学量化方法;最后,将量化方法与胶滴数学体积模型进行对比分析。根据实验所得数据,推导出了通过初始距离对胶滴体积预测的数学公式。实验结果表明:预测体积、预测接触面积与实际值之间的平均差异率分别为0.47%和0.54%。根据实际工作情况,对胶滴相应参数进行研究与预测,不但可以对胶滴相关配置参数进行精确调整,而且可以对实际封装效果进行初步判断,从而提高封装效率及准确性。

Changes of coastline and tidal flat and its implication for ecological protection under human activities: Take China’s Bohai Bay as an example

The change processes and trends of shoreline and tidal flat forced by human activities are essential issues for the sustainability of coastal area,which is also of great significance for understanding coastal ecological environment changes and even global changes.Based on field measurements,combined with Linear Regression(LR)model and Inverse Distance Weighing(IDW)method,this paper presents detailed analysis on the change history and trend of the shoreline and tidal flat in Bohai Bay.The shoreline faces a high erosion chance under the action of natural factors,while the tidal flat faces a different erosion and deposition patterns in Bohai Bay due to the impact of human activities.The implication of change rule for ecological protection and recovery is also discussed.Measures should be taken to protect the coastal ecological environment.The models used in this paper show a high correlation coefficient between observed and modeling data,which means that this method can be used to predict the changing trend of shoreline and tidal flat.The research results of present study can provide scientific supports for future coastal protection and management.

基于智慧水力学的长距离调水工程调度参数预测方法研究

为提高长距离调水工程调度参数的计算精度,提出了智慧水力学的概念,基于南水北调中线工程的运行监测数据,采用人工智能方法开展了长距离调水工程调度参数预测方法研究。在对数据清洗的基础上,基于长短时记忆神经网络(LSTM)模型建立了白河、十二里河、东赵河节制闸调度参数的预测模型,采用鲸鱼优化算法(WOA)优化模型的超参数并进行调度参数预测。结果表明:3个节制闸的闸前水位和流量预测值与其实测值的最大平均绝对误差分别为0.655 cm和1.326 m^(3)/s,说明智慧水力学理念和人工智能方法在长距离调水工程调度参数预测中的适用性和精准性。研究内容可为实现工程调度参数预测与精准智能调度提供理论基础。