The Effects of Seamounts on Sound Propagation in Deep Water

A propagation experiment was conducted in the South China Sea in 2014 with a flat bottom and seamounts respectively by using explosive sources. The effects of seamounts on sound propagation are analyzed by using the broadband signals. It is observed that the transmission loss （TL） decreases up to 7 dB for the signals in the first shadow zone due to the seamount reflection. Moreover, the TL might increase more than 30 dB in the converge zone due to the shadowing by seamounts. Abnormal TLs and pulse arrival structures at different ranges are explained by using the ray and wave theory. The experimental TLs and arrival pulses are compared with the numerical results and found to be in good agreement.

Research Progress of Buckling Propagation Experiment of Deep-Water Pipelines

In recent years, the extraction of fossil resources, especially oil and gas in deep and ultra-deep water areas has been playing a more important role and been paid more attention to. For this reason, the working depth of submarine pipelines, which are used for the transportation of oil and gas, has been increasing sharply. As the main failure pattern of deep-water pipelines, buckling and its propagation problem have drawn more attention of many research institutions and engineering units around the world. Based on the existing research, the summary of experiments and their outcomes of deep-water pipeline buckling failure is made in this paper. Research status and developing prospects of the experiments of buckling propagation and buckle arrestor are discussed in detail.

Prediction of SMILE surgical cutting formula based on back propagation neural network

AIM:To predict cutting formula of small incision lenticule extraction(SMILE)surgery and assist clinicians in identifying candidates by deep learning of back propagation(BP)neural network.METHODS:A prediction program was developed by a BP neural network.There were 13188 pieces of data selected as training validation.Another 840 eye samples from 425 patients were recruited for reverse verification of training results.Precision of prediction by BP neural network and lenticule thickness error between machine learning and the actual lenticule thickness in the patient data were measured.RESULTS:After training 2313 epochs,the predictive SMILE cutting formula BP neural network models performed best.The values of mean squared error and gradient are 0.248 and 4.23,respectively.The scatterplot with linear regression analysis showed that the regression coefficient in all samples is 0.99994.The final error accuracy of the BP neural network is-0.003791±0.4221102μm.CONCLUSION:With the help of the BP neural network,the program can calculate the lenticule thickness and residual stromal thickness of SMILE surgery accurately.Combined with corneal parameters and refraction of patients,the program can intelligently and conveniently integrate medical information to identify candidates for SMILE surgery.

Optimizing the Diameter of Plugging Balls in Deep Shale Gas Wells

Deep shale gas reserves that have been fractured typically have many relatively close perforation holes. Due to theproximity of each fracture during the formation of the fracture network, there is significant stress interference,which results in uneven fracture propagation. It is common practice to use “balls” to temporarily plug fractureopenings in order to lessen liquid intake and achieve uniform propagation in each cluster. In this study, a diameteroptimization model is introduced for these plugging balls based on a multi-cluster fracture propagationmodel and a perforation dynamic abrasion model. This approach relies on proper consideration of the multiphasenature of the considered problem and the interaction force between the involved fluid and solid phases. Accordingly,it can take into account the behavior of the gradually changing hole diameter due to proppant continuousperforation erosion. Moreover, it can provide useful information about the fluid-dynamic behavior of the consideredsystem before and after plugging. It is shown that when the diameter of the temporary plugging ball is1.2 times that of the perforation hole, the perforation holes of each cluster can be effectively blocked.

Development of tomographic reconstruction for three-dimensional optical imaging:From the inversion of light propagation to artificial intelligence

Optical molecular tomography(OMT)is an imaging modality which uses an optical signal,especially near-infrared light,to reconstruct the three-dimensional information of the light source in biological tissue.With the advantages of being low-cost,noninvasive and having high sensitivity,OMT has been applied in preclinical and clinical research.However,due to its serious ill-posedness and illcondition,the solution of OMT requires heavy data analysis and the reconstruction quality is limited.Recently,the artificial intelligence(commonly known as AI)-based methods have been proposed to provide a different tool to solve the OMT problem.In this paper,we review the progress on OMT algorithms,from conventional methods to AI-based methods,and we also give a prospective towards future developments in this domain.

Deep learning for pore-scale two-phase flow:Modelling drainage in realistic porous media

This paper introduces a deep learning workflow to predict phase distributions within complex geometries during two-phase capillary-dominated drainage.We utilize subsamples from Computerized Tomography(CT)images of rocks and incorporate pixel size,interfacial tension,contact angle,and pressure as inputs.First,an efficient morphology-based simulator creates a diverse dataset of phase distributions.Then,two commonly used convolutional and recurrent neural networks are explored and their deficiencies are highlighted,particularly in capturing phase connectivity.Subsequently,we develop a Higher-Dimensional Vision Transformer(HD-ViT)that drains pores solely based on their size,with phase connectivity enforced as a post-processing step.This enables inference for images of varying sizes,resolutions,and inlet-outlet setup.After training on a massive dataset of over 9.5 million instances,HD-ViT achieves excellent performance.We demonstrate the accuracy and speed advantage of the model on new and larger sandstone and carbonate images.We further evaluate HD-ViT against experimental fluid distribution images and the corresponding Lattice-Boltzmann simulations,producing similar outcomes in a matter of seconds.In the end,we train and validate a 3D version of the model.

基于BP神经网络的Deep Web实体识别方法

针对现有实体识别方法自动化水平不高、适应性差等不足,提出一种基于反向传播(BP)神经网络的Deep Web实体识别方法。该方法将实体分块后利用反向传播神经网络的自主学习特性,将语义块相似度值作为反向传播神经网络的输入,通过训练得到正确的实体识别模型,从而实现对异构数据源的自动化实体识别。实验结果表明,所提方法的应用不仅能够减少实体识别中的人工干预,而且能够提高实体识别的效率和准确率。

Investigation of crack segmentation and fast evaluation of crack propagation, based on deep learning

Identifying crack and predicting crack propagation are critical processes for the risk assessment of engineering structures.Most traditional approaches to crack modeling are faced with issues of high computational costs and excessive computing time.To address this issue,we explore the potential of deep learning(DL)to increase the efficiency of crack detection and forecasting crack growth.However,there is no single algorithm that can fit all data sets well or can apply in all cases since specific tasks vary.In the paper,we present DL models for identifying cracks,especially on concrete surface images,and for predicting crack propagation.Firstly,SegNet and U-Net networks are used to identify concrete cracks.Stochastic gradient descent(SGD)and adaptive moment estimation(Adam)algorithms are applied to minimize loss function during iterations.Secondly,time series algorithms including gated recurrent unit(GRU)and long short-term memory(LSTM)are used to predict crack propagation.The experimental findings indicate that the U-Net is more robust and efficient than the SegNet for identifying crack segmentation and achieves the most outstanding results.For evaluation of crack propagation,GRU and LSTM are used as DL models and results show good agreement with the experimental data.

C-Rank:一种Deep Web数据记录可信度评估方法

针对Web信息可信度问题,提出了一种为Deep Web数据记录计算可信度的有效方法C-Rank。该方法为每一条记录构造一个S-R可信度网络,包含两种类型顶点及三种类型边。首先基于可信度传播的思想,利用顶点出度为每一个顶点计算其局部可信度值;再利用Record顶点入度及相邻Site顶点的可信度值,为该Record顶点计算权值;继而求得整个S-R网络的全局可信度值。实验证明,C-Rank方法能够合理而有效地评价数据记录的可信度,从而达到甄别虚假信息,为用户推荐可信数据记录的目的。该方法普遍适用于Deep Web的各个领域。

某深海钻井船DP3动力定位能力分析

世界主要海事机构对动力定位能力等级都进行了定义。文章梳理了各主要海事机构对动力定位系统的要求;针对DP3等级动力定位深海钻井船特点,介绍了风、浪、流等环境载荷计算方法以及动力定位能力的评估方法 ;对一艘DP3级的钻井船进行实例分析,对其动力定位能力进行评估,并对DP3级钻井船的动力定位系统设计提出建议。

Nonlinear Contact Between Inner Walls of Deep Sea Pipelines in Buckling Process

In order to study buckling propagation mechanism in deep sea pipelines, the contact between pipeline's inner walls in buckling process was studied. A two-dimensional ring model was used to represent the pipeline and a nonlinear spring model was adopted to simulate the contact between inner walls. Based on the elastoplastic constitutive relationship and the principle of virtual work theory, the coupling effect of pipeline's nonlinear large deformation and wall contact was included in the theoretical analysis with the aid of MATLAB, and the application scope of the theoretical model was also discussed. The calculated results show that during the loading process, the change in external pressure is closely related to the distribution of section stress, and once the walls are contacting each other, the external pressure increases and then remains stable after it reaches a specific value. Without fracture, the pipeline section will stop showing deformation. The results of theoretical calculations agree well with those of numerical simulations. Finally, in order to ensure reliability and accuracy of the theoretical results, the collapse pressure and propagation pressure were both verified by numerical simulations and experiments. Therefore, the theoretical model can be used to analyze pipeline's buckling deformation and contact between pipeline's inner walls, which forms the basis for further research on three-dimensional buckling propagation.

Labeling Malicious Communication Samples Based on Semi-Supervised Deep Neural Network

The limited labeled sample data in the field of advanced security threats detection seriously restricts the effective development of research work.Learning the sample labels from the labeled and unlabeled data has received a lot of research attention and various universal labeling methods have been proposed.However,the labeling task of malicious communication samples targeted at advanced threats has to face the two practical challenges:the difficulty of extracting effective features in advance and the complexity of the actual sample types.To address these problems,we proposed a sample labeling method for malicious communication based on semi-supervised deep neural network.This method supports continuous learning and optimization feature representation while labeling sample,and can handle uncertain samples that are outside the concerned sample types.According to the experimental results,our proposed deep neural network can automatically learn effective feature representation,and the validity of features is close to or even higher than that of features which extracted based on expert knowledge.Furthermore,our proposed method can achieve the labeling accuracy of 97.64%~98.50%,which is more accurate than the train-then-detect,kNN and LPA methodsin any labeled-sample proportion condition.The problem of insufficient labeled samples in many network attack detecting scenarios,and our proposed work can function as a reference for the sample labeling tasks in the similar real-world scenarios.

Deep Learning Applications for COVID-19 Analysis:A State-of-the-Art Survey

The COVID-19 has resulted in catastrophic situation and the deaths of millions of people all over the world.In this paper,the predictions of epidemiological propagation models,such as SIR and SEIR,are introduced to analyze the earlier COVID-19 propagation.The deep learning methods combined with transfer learning are familiar with classification-detection approaches based on chest X-ray and CT images are presented in detail.Besides,deep learning approaches have also been applied to lung ultrasound(LUS),which has been shown to be more sensitive than chest X-ray and CT images in detecting COVID-19.In the absence of a vaccine,the machine learning-related approaches are applied to analyze vaccine candidates in the realm of biology and medicine.The telehealth system played a major role in combating the pandemic from all aspects and reducing contact with patients during this period.Natural language processing-related methods are utilized to analyze tweets related to the COVID-19 epidemic on social media,and further analyze public sentiment and subject modeling,so as to arrange corresponding measures to appease public sentiment.In particular,this survey is to summarize and analyze the contributions made in various fields during the COVID-19 pandemic by considering both the contribution of deep learning in chest X-ray and CT images,as well as the application of the latest LUS during the COVID-19 pandemic.Telehealth and the importance of public sentiment analysis during a pandemic were also described in detail.

Rock mass quality classification based on deep learning:A feasibility study for stacked autoencoders

Objective and accurate evaluation of rock mass quality classification is the prerequisite for reliable sta-bility assessment.To develop a tool that can deliver quick and accurate evaluation of rock mass quality,a deep learning approach is developed,which uses stacked autoencoders(SAEs)with several autoencoders and a softmax net layer.Ten rock parameters of rock mass rating(RMR)system are calibrated in this model.The model is trained using 75%of the total database for training sample data.The SAEs trained model achieves a nearly 100%prediction accuracy.For comparison,other different models are also trained with the same dataset,using artificial neural network(ANN)and radial basis function(RBF).The results show that the SAEs classify all test samples correctly while the rating accuracies of ANN and RBF are 97.5%and 98.7%,repectively,which are calculated from the confusion matrix.Moreover,this model is further employed to predict the slope risk level of an abandoned quarry.The proposed approach using SAEs,or deep learning in general,is more objective and more accurate and requires less human inter-vention.The findings presented here shall shed light for engineers/researchers interested in analyzing rock mass classification criteria or performing field investigation.

基于改进LDPC码的深空通信优化过程仿真

传统深空通信过程中的LDPC码设计结构具有随机性,使得译码和编码的复杂度增加,具有较高的运算复杂度,不能实现译码性能和复杂度间的平衡,会在临界处产生较大的误码率,无法确保深空通信的顺利传输,提出基于删除塑造法以及WBF算法的LDPC码深空通信优化方法,采用删除塑造法获取既能实现线性编码,又包含最小环长的LDPC码,确保LDPC码原有的度序列分布,通过WBF算法实现LDPC码的译码,提高深空通信信道的纠错性能,将码字规范当成LDPC译码算法的终止规则,在每次迭代后分析译码器尝试性译码结果是否以大概率正确,进而降低译码的迭代次数,优化深空通信性能。通过融入加性高斯白噪声的深空通信信道的仿真结果说明,改进的LDPC译码算法极大提高了译码的效率,在最大迭代次数、码长、码率以及平均运行时间减少的比例等指标都优于传统算法。

Norm-DP模型行人检测优化算法

传统深度金字塔模型作为一种有效的行人检测算法备受关注,融合可变形部件模型和卷积神经网络模型,但特征提取部分使用的算法像素区域的大小不同,导致模型之间不能完全融合,在行人数量多、姿势复杂和有遮挡情况时的检测效果不理想。因此,提出一种基于规范化函数的深度金字塔模型(Norm-DP)算法,使用规范化函数融合可变形部件模型和卷积神经网络模型,直接从金字塔特征中提取正负样本,使用隐变量支持向量机进行模型训练,结合柔性非最大抑制(soft-NMS)算法和边界框回归(BBR)算法对定位框进行优化。分别使用INRIA和MS COCO数据集进行实验验证,在行人数量多、姿势复杂和有遮挡情况时,检测精度高于最优的可变形部件模型算法、卷积神经网络算法、深度金字塔模型算法和结合区域选择的卷积神经网络算法。

基于深度残差收缩网络的LDPC译码算法

为了研究瑞利衰落信道下提高低密度奇偶校验码(low density parity check,LDPC)信道译码算法纠错性能的方法,结合神经网络技术,提出一种基于深度残差收缩网络(deep residual shrinkage networks,DRSN)的归一化最小和(normalized min-sum,NMS)译码算法(简称DRSN-NMS译码算法)。首先,本译码算法使用深度残差收缩网络预测信道增益;然后结合接收信号计算对数似然比(log likelihood ratio,LLR),将其作为译码算法的输入进行译码,DRSN通过学习接收信号中噪声的相关特征,以抑制噪声的方法使预测结果更加接近真实信道增益;最后使用实现较简便的NMS算法进行译码。仿真试验结果表明,在高信噪比环境下,本译码算法的误码率最低时接近常规算法误码率的1/3,译码性能得到一定的提高。本研究结果可为译码算法降低误码率提供参考。

Deep learning based Doppler frequency offset estimation for 5G-NR downlink in HSR scenario

In the fifth-generation new radio(5G-NR) high-speed railway(HSR) downlink,a deep learning(DL) based Doppler frequency offset(DFO) estimation scheme is proposed by using the back propagation neural network(BPNN).The proposed method mainly includes pre-training,training,and estimation phases,where the pre-training and training belong to the off-line stage,and the estimation is the online stage.To reduce the performance loss caused by the random initialization,the pre-training method is employed to acquire a desirable initialization,which is used as the initial parameters of the training phase.Moreover,the initial DFO estimation is used as input along with the received pilots to further improve the estimation accuracy.Different from the training phase,the initial DFO estimation in pre-training phase is obtained by the data and pilot symbols.Simulation results show that the mean squared error(MSE) performance of the proposed method is better than those of the available algorithms,and it has acceptable computational complexity.

深层页岩气储层水力压裂裂缝扩展影响机理

现有中浅层页岩气压裂取得的认识难以解释深层页岩气储层压裂过程中水力裂缝扩展的影响机理。为了研究四川盆地深层页岩气储层水力压裂裂缝扩展机理,文中以泸州深层页岩气区LS1平台为研究对象,进行基于地质-工程一体化的水力压裂裂缝扩展数值模拟与分析。首先,根据泸州区块目标井区储层的地质概况,建立地质模型,明确地质力学属性;然后,基于微地震和蚂蚁体数据,建立符合真实储层构造特性的离散天然裂缝网络;在此基础上,根据现场实际施工数据,建立了基于DFN的水力压裂复杂裂缝扩展模型,并基于微地震监测结果对模型进行了验证;最后,还研究了4个单因素对储层改造体积的影响特点。研究结果对深层页岩气储层水力压裂复杂缝网研究有一定的指导作用。

深层地热花岗岩体地震波数值模拟及传播机制

深层地热资源是一种可再生的、蕴藏巨大能量的清洁能源,但其地球物理响应特征不明确,中深层地热探测成功率较低。为了研究地震波在深层地热岩体中的传播规律与波场特征,建立两种深层地热花岗岩模型,并使用等效交错网格有限差分法实现声波与弹性波的数值模拟。结果表明:地热花岗岩体速度在温度的影响下要高于围岩的,会产生高速屏蔽现象,使得透射波能量变弱,限制了地热岩体下部地震波传播能量;相比于声波,弹性波具有更丰富的波场信息,波型与能量转换使得弹性波地震记录也比声波地震记录复杂。