Mechanical Fault Diagnosis Based on Band-phase-randomized Surrogate Data and Multifractal

The vibration signals of machinery with various faults often show clear nonlinear characteristics.Currently,fractal dimension analysis as the common useful method for nonlinear signal analysis,is a kind of single fractal form,which only reflects the overall irregularity of signals,but cannot describe its local scaling properties.For comprehensive revealing of internal properties,a combinatorial method based on band-phase-randomized（BPR） surrogate data and multifractal is introduced.BPR surrogate data method is effective to eliminate nonlinearity in specified frequency band for a fault signal,which can be utilized to detect nonlinear degree in whole fault signal by nonlinear titration method,and the overall nonlinear distribution of fault signal is displayed in nonlinear characteristic curve that can be used to analyze the fault signal qualitatively.Then multifractal theory as a quantitative analysis method is used to describe geometrical characteristics and local scaling properties,and asymmetry coefficient of multifractal spectrum and multifractal entropy for fault signals are extracted as new criterions to diagnose machinery faults.Several typical faults include rotor misalignment,transversal crack,and static-dynamic rubbing fault are analyzed,and the results indicate that those faults can be distinguished by the proposed method effectively,which provides a qualitative and quantitative analysis way in the field of machinery fault diagnosis.

Robust H_∞ control of piecewise-linear chaotic systems with random data loss

This paper studies the problem of robust H∞ control of piecewise-linear chaotic systems with random data loss. The communication links between the plant and the controller are assumed to be imperfect （that is, data loss occurs intermittently, which appears typically in a network environment）. The data loss is modelled as a random process which obeys a Bernoulli distribution. In the face of random data loss, a piecewise controller is designed to robustly stabilize the networked system in the sense of mean square and also achieve a prescribed H∞ disturbance attenuation performance based on a piecewise-quadratic Lyapunov function. The required H∞ controllers can be designed by solving a set of linear matrix inequalities （LMIs）. Chua＇s system is provided to illustrate the usefulness and applicability of the developed theoretical results.

THE INFLUENCE OF THE DIFFERENT DISTRIBUTEDPHASE-RANDOMIZED ON THE EXPERIMENTAL DATA OBTAINEd IN DYNAMIC ANALYSIS

In this paper the influence of the differently distributed phase-randontized to the data obtained in dynamic analysis for critical value is studied.The calculation results validate that the sufficient phase-randomized of the different distributed random numbers are less influential on the critical value . This offers the theoretical foundation of the feasibility and practicality of the phase-randomized method.

Forest type identification by random forest classification combined with SPOT and multitemporal SAR data

We developed a forest type classification technology for the Daxing＇an Mountains of northeast China using multisource remote sensing data.A SPOT-5 image and two temporal images of RADARSAT-2 full-polarization SAR were used to identify forest types in the Pangu Forest Farm of the Daxing＇an Mountains.Forest types were identified using random forest（RF） classification with the following data combination types： SPOT-5 alone,SPOT-5 and SAR images in August or November,and SPOT-5 and two temporal SAR images.We identified many forest types using a combination of multitemporal SAR and SPOT-5 images,including Betula platyphylla,Larix gmelinii,Pinus sylvestris and Picea koraiensis forests.The accuracy of classification exceeded 88% and improved by 12% when compared to the classification results obtained using SPOT data alone.RF classification using a combination of multisource remote sensing data improved classification accuracy compared to that achieved using single-source remote sensing data.

ALMOST SURE GLOBAL WELL-POSEDNESS FOR THE FOURTH-ORDER NONLINEAR SCHR?DINGER EQUATION WITH LARGE INITIAL DATA

We consider the fourth-order nonlinear Schr?dinger equation(4NLS)(i?t+εΔ+Δ2)u=c1um+c2(?u)um-1+c3(?u)2um-2,and establish the conditional almost sure global well-posedness for random initial data in Hs(Rd)for s∈(sc-1/2,sc],when d≥3 and m≥5,where sc:=d/2-2/(m-1)is the scaling critical regularity of 4NLS with the second order derivative nonlinearities.Our proof relies on the nonlinear estimates in a new M-norm and the stability theory in the probabilistic setting.Similar supercritical global well-posedness results also hold for d=2,m≥4 and d≥3,3≤m<5.

基于多源数据与随机森林方法的城市建成区提取——以郑州市为例

基于夜间灯光数据的阈值分割法在城镇建成区提取研究中被广泛应用,但由于夜间灯光数据分辨率低、灯光溢出和阈值分割法无法顾及区域差异等问题,一定程度上影响了该方法的提取精度。以郑州市为例,以LJ1-01与NPP/VIIRS两种夜间灯光影像为主要数据源,结合Landsat8中分辨率遥感影像、网络城市兴趣点(POI)及路网数据,利用随机森林分类方法对郑州市2018年建成区进行提取,参考土地利用数据,对RF分类法与NTL、VANUI、BANUI、PANUI、RANUI指数等阈值法进行对比实验和精度评价,评估基于多源数据的随机森林分类方法在城市建成区提取中的优势。实验表明,RF比阈值法提取的建成区更接近真实建成区且提取精度更高,具有更好适用性;LJ1-01数据提取的效果和精度总体优于NPP/VIIRS数据;在采用RF分类时,各类特征的重要性在不同夜光数据源中表现差异较大。

A Data-Driven Car-Following Model Based on the Random Forest

The car-following models are the research basis of traffic flow theory and microscopic traffic simulation. Among the previous work, the theory-driven models are dominant, while the data-driven ones are relatively rare. In recent years, the related technologies of Intelligent Transportation System (ITS) re- presented by the Vehicles to Everything (V2X) technology have been developing rapidly. Utilizing the related technologies of ITS, the large-scale vehicle microscopic trajectory data with high quality can be acquired, which provides the research foundation for modeling the car-following behavior based on the data-driven methods. According to this point, a data-driven car-following model based on the Random Forest (RF) method was constructed in this work, and the Next Generation Simulation (NGSIM) dataset was used to calibrate and train the constructed model. The Artificial Neural Network (ANN) model, GM model, and Full Velocity Difference (FVD) model are em- ployed to comparatively verify the proposed model. The research results suggest that the model proposed in this work can accurately describe the car- following behavior with better performance under multiple performance indicators.

TESTING FOR VARYING DISPERSION OF LONGITUDINAL BINOMIAL DATA IN NONLINEAR LOGISTIC MODELS WITH RANDOM EFFECTS

In this paper, it is discussed that two tests for varying dispersion of binomial data in the framework of nonlinear logistic models with random effects, which are widely used in analyzing longitudinal binomial data. One is the individual test and power calculation for varying dispersion through testing the randomness of cluster effects, which is extensions of Dean(1992) and Commenges et al (1994). The second test is the composite test for varying dispersion through simultaneously testing the randomness of cluster effects and the equality of random-effect means. The score test statistics are constructed and expressed in simple, easy to use, matrix formulas. The authors illustrate their test methods using the insecticide data (Giltinan, Capizzi & Malani (1988)).

Automatic Variable Selection for Single-Index Random Effects Models with Longitudinal Data

We consider the problem of variable selection for the single-index random effects models with longitudinal data. An automatic variable selection procedure is developed using smooth-threshold. The proposed method shares some of the desired features of existing variable selection methods: the resulting estimator enjoys the oracle property;the proposed procedure avoids the convex optimization problem and is flexible and easy to implement. Moreover, we use the penalized weighted deviance criterion for a data-driven choice of the tuning parameters. Simulation studies are carried out to assess the performance of our method, and a real dataset is analyzed for further illustration.

基于随机森林和长短期记忆网络模型的高压气井环空带压预测方法

高压气井在生产过程中持续的环空带压容易引起套管柱变形或挤毁,是高压气井完整性失效的主要原因之一。为解决传统方法环空带压预测精度不高的问题,以鄂尔多斯盆地苏里格气田某高压气井为例,首先利用主成分分析法和相关系数法找到影响环空带压的主要因素,然后使用高压气井井筒温压场理论值和孤立森林模型对主成分进行物理解释和数据清洗,再对清洗后的数据使用随机森林(RF)和长短期记忆网络(LSTM)模型建立了环空带压定量预测模型,并对两类模型进行权重组合,最终建立了精确度高于任意单一模型的RF—LSTM组合环空带压预测新模型。研究结果表明:(1)环空带压的主要影响因子有温度分量、压力分量、产量分量、腐蚀程度、生产状态,而温度分量与环空带压间存在最高关联性;(2)通过错误格式、离群点及基于井筒温压场的数据清洗,可以得到数据清洗后的环空带压影响因素训练集;(3)通过平均绝对误差法(MAE)能够建立误差分数小于任意单一模型,而拟合优度介于两者之间的组合模型,因此可以将具有高拟合优度和低误差分数的两类模型结合,从而组合出同时满足两种分数的组合模型。结论认为:(1)运用大数据挖掘技术及算法进行环空带压定量预测,方法新颖,预测精度高,结果可行;(2)该方法为现场环空带压预测和风险管控提供了决策工具参考,为实现环空带压风险实时预测、预警和管控提供了理论支撑。

Thermal stability and data retention of resistive random access memory with HfOx/ZnO double layers

As an industry accepted storage scheme, hafnium oxide（HfO_x） based resistive random access memory（RRAM）should further improve its thermal stability and data retention for practical applications. We therefore fabricated RRAMs with HfO_x/ZnO double-layer as the storage medium to study their thermal stability as well as data retention. The HfO_x/ZnO double-layer is capable of reversible bipolar switching under ultralow switching current（〈 3 μA） with a Schottky emission dominant conduction for the high resistance state and a Poole–Frenkel emission governed conduction for the low resistance state. Compared with a drastically increased switching current at 120℃ for the single HfO_x layer RRAM, the HfO_x/ZnO double-layer exhibits excellent thermal stability and maintains neglectful fluctuations in switching current at high temperatures（up to 180℃）, which might be attributed to the increased Schottky barrier height to suppress current at high temperatures. Additionally, the HfO_x/ZnO double-layer exhibits 10-year data retention @85℃ that is helpful for the practical applications in RRAMs.

基于ADASYN和WGAN的混合不平衡数据处理方法

为了解决不平衡数据集中少数类样本分类精度较低的问题,提出了一种处理不平衡数据集的ADASYN-WGAN方法。首先,采用ADASYN(adaptive synthetic sampling)算法生成少数类样本,用这些生成样本代替WGAN(wasserstein generative adversarial networks)中的随机噪声;其次,利用WGAN算法生成符合原始数据集分布规律的少数类样本,构建平衡数据集;然后,在6个公开数据集上,采用随机森林分类器对所提方法和4种过采样算法得出的处理结果分别与原始数据集进行对比;最后,通过F1-Score,G-mean和AUC等分类评估指标的表现验证所提方法的有效性。结果表明:在对比实验中,经过ADASYN-WGAN方法得到的平衡数据集在随机森林分类器的十折交叉验证中,4个公开数据集中的各项分类评估指标值均达到最优,虽然另2个公开数据集中的AUC值略低,但其F1-Score和G-mean取得了最高值。所提出的ADASYN-WGAN方法可生成高质量的数据样本,并可为解决不平衡数据集中少数类样本的预测偏差问题提供参考。

贝伐珠单抗联合放化疗对宫颈癌疗效的Meta分析

目的评价贝伐珠单抗联合放化疗治疗宫颈癌的疗效及治疗过程中的安全性。方法对中文数据库维普及英文数据库PubMed等中关于贝伐珠单抗联合放化疗治疗宫颈癌的研究进行检索,收集2010—2023年相关的随机对照试验。采用Review Manager 4.2软件分析患者的完全缓解、部分缓解、疾病稳定及不良反应的发生率,绘制漏斗图评价发表偏倚情况。结果纳入符合本研究的文献9篇,共654例患者(试验组327例,对照组327例)。贝伐珠单抗联合放化疗可提高宫颈癌患者完全缓解、部分缓解和疾病稳定的发生率,不良反应的发生率与单纯放化疗相比,差异无统计学意义(P>0.05)。漏斗图显示纳入的研究尚不认为存在发表偏倚。结论贝伐珠单抗联合放化疗治疗宫颈癌的疗效优于单纯放化疗,与单纯放化疗不良反应的发生率相近。

随机矩阵理论在高速路关键路径辨识中的应用

高速公路网络是我国各地区相互连接的重要纽带,高速公路网络关键路径辨识对确保高速网络的可靠运行具有重要意义。传统的关键路径分析方法基于拓扑结构,未考虑交通网络的运输量特性;而现有的基于运输量数据的分析方法只考虑部分路径的运输量特性,难以反映交通网络的实际运行情况。利用路径运输量数据,搭建运输量随机矩阵模型,针对高速公路网络异常后的运输量变化特性,定义关键路径评估指数,实现异常影响程度的量化评估,在此基础上提出一种基于数据驱动的高速公路网络关键路径辨识方法。最后,采用辽宁省高速公路网络进行分析,验证了所提方法的合理性和有效性,并将该方法应用于城市路网案例中,进一步证明该方法具有普适性。

一种基于新型真随机数发生器的大数据加密方法

为了解决大数据安全性不足的问题,在现场可编程门列阵的基础上,设计了一种融合了链式振荡环、触发器阵列以及异或门阵列的改进大数据加密方法。然后通过与L8M-LBE、R2S-LBE进行对比实验的方式对该方法进行验证。实验结果表明,改进加密方法的NIST测试通过率为97.5%,优于传统真随机数发生器。在加密硬件吞吐率测试方面,改进加密方法的吞吐率为1983.3 Mbps,优于L8M-LBE与R2S-LBE。实验结果证明改进后的真随机数发生器加密性能得到了极高的提升,能够为大数据加密安全提供一个新的思路。

基于工业大数据的重叠社区发现算法

为了深入挖掘和分析工业大数据隐藏的关系、趋势和模式,从而为企业提供更好的决策依据,结合随机游走和标签传播思想,提出一种基于工业大数据的重叠社区发现算法。设计了种子节点选取算法,通过随机游走计算各节点的重要性,选出不相关和重要性高的种子节点;提出重叠社区发现算法,对种子节点赋予唯一标签,迭代进行标签传播直到节点标签不再改变,根据节点标签得到最终的重叠社区划分结果。通过在真实数据集和人工数据集上进行对比实验表明,该算法可以在网络上有效发现高质量的重叠社区,并进一步解决工业大数据的数据分析、信息挖掘等核心问题。

基于车联网大数据的重型货车载重估计方法

针对当前货车载重计算方法普遍存在的成本高昂及泛化性能不明确的问题,提出一种创新的重型货车载重估计方法,方法融合了车辆行驶动力学理论与机器学习算法,通过有监督学习,利用高速通行大数据对模型进行训练与验证.首先采用聚类分析,确定车辆空、半、满载判断阈值,为后续的计算提供了重要依据.随后,利用随机森林算法训练分类模型,用以判断车辆在一段行驶过程中的基本载重情况.在此基础上,进一步在车辆行驶数据中筛选出稳定行驶的小片段,根据车辆系统动力学理论,对这些小片段车重进行计算.最后,根据载重状态的判断结果,对小片段车重结果进行筛选与计算,得到最终车辆载重计算结果.研究表明,在高速通行大数据的验证下,该方法对于空载及满载状态下趟次车重计算结果的整体平均绝对百分比误差(mean absolute percent error,MAPE)均可控制在10%以内,展现了较高的准确性.相比于现有技术,由于该方法无需安装额外传感器,对数据采集、存储、运算设备的要求也相对较低,因此在成本方面具有显著优势.在交通监管、物流运输、基于大数据的产品开发方面具有快速广泛推广的潜力.

基于三维重建的物体空间数据合成增广方法

深度学习目标检测算法需大量训练数据支撑,数据增广是一种自动生成训练样本的有效手段。为在原始样本稀缺时提供大量高质量训练样本,提出一种基于三维重建的物体空间数据增广合成方法,克服现有数据增广要么需要复杂手工建模、要么样本视角多样性不足的问题。首先用少量多视角图像重建目标三维模型,再通过多域随机化图像煊染得到不同环境下任意视角图像,然后将染图与随机背景融合并自动生成标注信息,得到海量多样化合成样本。构建5种训练数据集并在典型目标检测算法上对上述增广方法开展实验验证,结果表明合成样本对原始稀缺样本数据集有显著增强作用,可大幅提高目标检出概率和目标检测定位精度,而且对一般数据集也具有很好的适用性。

基于改进随机森林的大坝监测数据质量评价算法

针对大坝安全监测数据质量评价效率低下、智慧化不足等难题,为了满足大坝高频率自动化采集的实时数据质量评价需要,从准确性、完整性、时效性和连续性4个方面出发提出了6项评价因子及由相关评价规范构成的安全监测历史数据质量评价标准,通过基于AUC值改进的随机森林算法建立了大坝安全监测历史数据质量评价算法,并将该算法应用于新疆柳树沟面板堆石坝多年安全监测历史数据评价。结果表明:通过AUC值改进的随机森林算法优于原始算法,在特征属性数量取3时效果最好,测试集的泛化误差最小仅为0.0195,平均准确率稳定在96.97%附近,10折交叉验证平均准确率达到97.77%,证明了该算法的可行性。

基于随机森林的多源小样本数据快速集成方法

受多源小样本数据属性复杂性的影响,对其进行集成处理时,过拟合和欠拟合情况较为明显。为此,文章提出基于随机森林的多源小样本数据快速集成方法。考虑多源小样本数据自身的属性特征,在构建随机森林模型阶段,充分利用粒向量与多源小样本数据特征的贴合性,将其作为随机森林的基础结构,利用粒化层归一化多源小样本数据,并将输出的粒化结果作为决策层的节点。在集成阶段,根据多源小样本数据与决策层节点之间的距离,集成数据。在测试结果中,数据集成的过拟合情况占比仅为0.29%,欠拟合情况占比也仅为0.27%,具有良好的集成效果。