Multi-Innovation Gradient Iterative Locally Weighted Learning Identification for A Nonlinear Ship Maneuvering System

This paper explores a highly accurate identification modeling approach for the ship maneuvering motion with fullscale trial. A multi-innovation gradient iterative(MIGI) approach is proposed to optimize the distance metric of locally weighted learning(LWL), and a novel non-parametric modeling technique is developed for a nonlinear ship maneuvering system. This proposed method’s advantages are as follows: first, it can avoid the unmodeled dynamics and multicollinearity inherent to the conventional parametric model; second, it eliminates the over-learning or underlearning and obtains the optimal distance metric; and third, the MIGI is not sensitive to the initial parameter value and requires less time during the training phase. These advantages result in a highly accurate mathematical modeling technique that can be conveniently implemented in applications. To verify the characteristics of this mathematical model, two examples are used as the model platforms to study the ship maneuvering.

Network community identification method based on individual-centered theory

The studies show that numerous complex networks have clustering effect.It is an indispensable step to identify node clusters in network,namely community,in which nodes are closely related,and in many applications such as identification of ringleaders in anti-criminal and anti-terrorist network,efficient storage of data in Wireless Sensor Network(WSN).At present,most of community identification methods still require the specifications of the number or the scale of community by user and still can not handle overlapping nodes.In an attempt to solve these problems,a network community identification method based on utility value is proposed,which is a function of each node's clustering coefficient and degree.This method makes use of individual-centered theory for reference and can automatically determine the number of communities.In addition,this method is an overlapping community identification method in nature.It is shown through contrastive experiments that this method is more efficient than other methods based on individual-centered theory when they control the same amount of information.Finally,a research direction is proposed for network community identification method based on the individual-centered theory.

Research of the DBN Algorithm Based on Multi-innovation Theory and Application of Social Computing

Aimed at the problems of small gradient, low learning rate, slow convergence error when the DBN using back-propagation process to fix the network connection weight and bias, proposing a new algorithm that combines with multi-innovation theory to improve standard DBN algorithm, that is the multi-innovation DBN(MI-DBN). It sets up a new model of back-propagation process in DBN algorithm, making the use of single innovation in previous algorithm extend to the use of innovation of the preceding multiple period, thus increasing convergence rate of error largely. To study the application of the algorithm in the social computing, and recognize the meaningful information about the handwritten numbers in social networking images. This paper compares MI-DBN algorithm with other representative classifiers through experiments. The result shows that MI-DBN algorithm, comparing with other representative classifiers, has a faster convergence rate and a smaller error for MNIST dataset recognition. And handwritten numbers on the image also have a precise degree of recognition.

Soil pore identification with the adaptive fuzzy C-means method based on computed tomography images

The complex geometry and topology of soil is widely recognised as the key driver in many ecological processes. X-ray computed tomography (CT) provides insight into the internal structure of soil pores automatically and accurately. Until recently, there have not been methods to identify soil pore structures. This has restricted the development of soil science, particularly regarding pore geometry and spatial distribution. Through the adoption of the fuzzy clustering theory and the establishment of pore identification rules, a novel pore identification method is described to extract pore structures from CT soil images. The robustness of the adaptive fuzzy C-means method (AFCM), the adaptive threshold method, and Image-Pro Plus tools were compared on soil specimens under different conditions, such as frozen, saturated, and dry situations. The results demonstrate that the AFCM method is suitable for identifying pore clusters, especially tiny pores, under various soil conditions. The method would provide an optional technique for the study of soil micromorphology.

Identification on rock and soil parameters for vibration drilling rock in metal mine based on fuzzy least square support vector machine

A single freedom degree model of drilling bit-rock was established according to the vibration mechanism and its dynamic characteristics. Moreover, a novel identification method of rock and soil parameters for vibration drilling based on the fuzzy least squares(FLS)-support vector machine(SVM) was developed, in which the fuzzy membership function was set by using linear distance, and its parameters, such as penalty factor and kernel parameter, were optimized by using adaptive genetic algorithm. And FLS-SVM identification on rock and soil parameters for vibration drilling was made by changing the input/output data from single freedom degree model of drilling bit-rock. The results of identification simulation and resonance column experiment show that relative error of natural frequency for some hard sand from identification simulation and resonance column experiment is 1.1% and the identification precision based on the fuzzy least squares-support vector machine is high.

A Technology for Online Parameter Identification of Permanent Magnet Synchronous Motor

Accuracy of the motor parameters is important in realizing high performance control of permanent magnet synchronous motor(PMSM).However,the inductance and resistance of motor winding vary with the change of temperature,rotor position and current frequency.In this paper,a technology based on circuit model is introduced for realizing online identification of the parameter of PMSM.In the proposed method,a set of nonlinear equations containing the parameters to be identified is established.Considering that it is very difficult to obtain the analytical solution of a nonlinear system of equations,Newton iterative method is used for solving the equations.Both the simulation and testing results confirm the effectiveness of the method presented.

Data fusion of radar and IFF for aircraft identification

The problem of identification of friend-or-foe aircraft in the actual application condition is addressed.A hybrid algorithm combining fuzzy neutral network with probability factor（FNNP）,multi-level fuzzy comprehensive evaluation and the DempsterShafer（D-S） theory is proposed.This hybrid algorithm constructs a complete process from generating the fuzzy database to the final identification,realizes the identification of friend-or-foe automatically if the training samples or expert’s experience can be obtained,and reduces the effect of uncertainties in the process of identification.At the same time,the whole algorithm can update the identification result with the augment of observations.The performance of the proposed algorithm is assessed by simulations.Results show that the proposed algorithm can successfully deduce the aircraft’s identity even if the observations have measurement errors.

GTD MODEL-BASED TIME-SHIFT INVARIANT TARGET IDENTIFICATION USING MATCHING PURSUITS AND LIKELIHOOD RATIO TESTS

In order to improve the identification capability of ultra wide-band radar,this paper in-troduces a step-variant multiresolution approach for the time-shift parameter estimation. Subsequently,combining with the approach,a Geometrical Theory of Diffraction(GTD) model-based time-shift Invariant method to target identification using Matching Pursuits and Likelihood Ratio Test(IMPLRT) is developed. Simulation results using measured scattering signatures of two targets in an ultra wide-band chamber are presented contrasting the performance of the IMPLRT to the Wang's MPLRT technique.

An Optimized Damage Identification Method of Beam Using Wavelet and Neural Network

An optimized damage identification method of beam combined wavelet with neural network is presented in an attempt to improve the calculation iterative speed and accuracy damage identification. The mathematical model is developed to identify the structure damage based on the theory of finite elements and rotation modal parameters. The model is integrated with BP neural network optimization approach which utilizes the Genetic algorithm optimization method. The structural rotation modal parameters are performed with the continuous wavelet transform through the Mexico hat wavelet. The location of structure damage is identified by the maximum of wavelet coefficients. Then, the multi-scale wavelet coefficients modulus maxima are used as the inputs of the BP neural network, and through training and updating the optimal weight and threshold value to obtain the ideal output which is used to describe the degree of structural damage. The obtained results demonstrate the effectiveness of the proposed approach in simultaneously improving the structural damage identification precision including the damage locating and severity.

Identification of Critical Lines in Power System Based on Optimal Load Shedding

Based on risk theory, considering the probability of an accident and the severity of the sequence, combining N-1 and N-2 security check, this paper puts forward a new risk index, which uses the amount of optimal load shedding as the severity of an accident consequence to identify the critical lines in power system. Taking IEEE24-RTS as an example, the simulation results verify the correctness and effectiveness of the proposed index.

基于熵产理论的多级液力透平能量耗散机理分析

液力透平作为一种液体余压能回收装置,在小水电建设和能量回收领域得到广泛应用,但其内部能量损失特性不清。以两级径流式液力透平为研究对象,基于熵产理论和Omega涡识别准则分析了各过流部件内能量耗散机理。结果表明:速度脉动和壁面效应是能量损失的主要来源,设计工况下二者总占比为98.03%。叶轮和导叶是透平内能量耗散的主要区域;小流量工况,叶轮损失占比较高;大流量工况下,导叶损失占比较高。叶轮内的能量损失源于叶片前缘分离涡、吸力面回流涡以及叶片尾缘涡等不稳定流动现象,而相对液流角与叶片进口安放角的不匹配是导致叶轮内产生不稳定流动的根本原因;在导叶和导叶Ⅱ-反导叶中,不同流量下导致其能量耗散的因素基本保持一致,叶片前缘失速涡和流动分离等劣态流动引起的动量交换是导致能量损失的主要原因。环形吸水室内流动的非对称性导致导叶Ⅰ各流道内熵产率分布不均匀,而导叶Ⅱ-反导叶通过正导叶的整流减小了冲击效应,各流道内熵产率分布均匀且高熵区较小。

“互联网+”背景下投资者—创业企业认同内涵、维度及量表开发

在“互联网+”背景下,创业企业与创业资本之间的博弈更加复杂,因此获得投资者认可成为创业企业亟待解决的关键问题。然而,已有研究缺乏投资者认同测量工具,使得研究无法深入。基于这一背景,遵循扎根理论方法,首先对11位从事风险投资的机构投资者进行深度访谈并对5位相关专家进行开放式问卷调研,获取10个针对投资者—创业企业认同的初始题项。然后,对初始题项进行探索性因子分析和验证性因子分析,最终开发出由认可感(包含6个题项)和成就感(包含3个题项)组成的9题项投资者—创业企业认同测量量表。实证检验发现该量表对获取创业融资具有预测作用,可为指导创业企业获取融资提供新视角和新方法,并为后续创业企业与投资者关系研究提供有效测量工具。

基于滑窗OPTICS算法和DATA-SSI算法的桥梁模态参数智能化识别

针对现有基于数据驱动的随机子空间(data-driven stochastic subspace identification,DATA-SSI)算法存在的不足,无法实现稳定图中真假模态的智能化筛选,提出了一种新的模态参数智能化识别算法。首先通过引入滑窗技术来实现对输入信号的合理划分,以避免虚假模态和模态遗漏现象的出现;其次通过引入OPTICS(ordering points to identify the clustering structure)密度聚类算法实现稳定图中真实模态的智能化筛选,最后将所提算法运用于某实际大型斜拉桥主梁结构的频率和模态振型识别过程中。结果表明,所提改进算法识别的频率值结果与理论值(MIDAS有限元结果)以及实际值(现场动力特性实测结果)间的误差均在5%以内,且识别的模态振型图与理论模态振型图具有很高的相似性。

D-S证据理论在空中目标识别中的应用现状与展望

D-S证据理论作为一种多源信息融合工具,在空中目标识别领域中得到了广泛应用。对D-S证据理论进行了概述;简要梳理了D-S证据理论在空中目标识别领域中的发展脉络,并提出应用中需要解决的三类关键问题;围绕上述问题,重点对该领域中的BPA获取、证据冲突度量、证据融合的应用现状进行综述;最后,基于空域控制视角,对D-S证据理论在该领域中的应用进行了展望。研究可为空中目标识别领域的理论发展和工程应用提供参考。

基于博弈的干支交汇水域船舶汇入意图识别

文中基于博弈理论和船舶碰撞危险度量方法,构造包含安全收益、时间收益和规则约束的汇入决策收益函数,采用船舶冲突排序运算方法量化确定汇入决策时机,构建干支交汇水域船舶汇入意图识别模型.为精准估计模型权重,以决策收益最大化为下层目标,意图识别误差最小化为上层目标,设计基于双层优化方法的模型参数估计框架.运用长江江苏段实测数据验证了所提模型的有效性.结果表明:本文所提模型的汇入意图识别准确率达到了94.64%.

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。

企业创新生态系统演化影响因素识别——基于扎根理论编码的探索性研究

企业创新生态系统在中国尚属新生事物,目前许多企业创新生态系统的演化正以惊人的速度失败,不仅影响了企业创新创造活力的发挥,而且还严重阻碍了中国科技创新能力的提升及经济社会的发展。针对学界关于企业创新生态系统演化影响因素研究较少的现状,遵循扎根理论的编码方法步骤,对中国10家创新生态系统核心企业的董事长、总经理、研发部长、事业部首席执行官进行半结构化访谈,结合有关公开披露信息、新闻报道、期刊文献等二手资料收集,构建企业创新生态系统演化影响因素模型,包括4个主范畴以及对应的10个子范畴。结果发现:吸收能力(获取与消化外部知识、转化与应用外部知识、研发投入)、组织间信任、网络嵌入性(关系嵌入、网络中心性)和环境冗余度(基础设施支撑性、配套商可得性、人才支撑、政策支持)这4个主范畴对企业创新生态系统演化均存在显著影响,但对系统影响的作用方式和路径不同,其中吸收能力是内驱因素,组织间信任是微观情境因素,网络嵌入性是中观情境因素,环境冗余度是宏观情境因素。最后基于研究结论,分别得出对政府和创新生态系统核心企业在提高环境冗余度、营造信任文化环境、搭建信息资源共享战略平台和充分重视外部知识对现有知识的有用性、坚持创新生态系统思维等方面的启示。

中华民族共同体理论的探索与建构

建设中华民族共同体、铸牢中华民族共同体意识是当前我国民族工作的重要目标,亦受学界诸多关注。论文基于大量的文献,对“民族”“共同体”“认同”理论进行梳理,将学界关于中华民族共同体研究的成果综合化、系统化、框架化。在此基础上,论文尝试对中华民族共同体理论进行初步建构:全面评估中华民族共同体建设的资源;深刻阐释“中华民族”“共同”“体”3个元概念;聚焦何为中华民族共同体意识,以及如何铸牢中华民族共同体意识进行学理性分析,以期实现中国模式的理论自信和制度自信。

中医护理模式对亚健康患者的影响

目的分析基于中医体质辨识学说的中医护理模式对亚健康患者的影响。方法本研究为随机对照试验。前瞻性选取2021年4月至2023年4月连云港市中医院治未病中心收治的100例处于亚健康状态患者作为研究对象。采用随机数字表法,将患者分为对照组(50例)和观察组(50例)。对照组男29例,女21例;年龄(40.20±2.01)岁;疲劳症状持续时间(6.45±1.43)个月。观察组男31例,女19例;年龄(39.98±2.40)岁;疲劳症状持续时间(6.37±1.40)个月。对照组采用常规护理,观察组在对照组基础上采用基于中医体质辨识学说的中医护理模式。两组均连续干预30 d。比较两组干预前后中医症候积分、生活质量[欧洲五维生存质量量表(EQ-5D)]。采用独立样本t检验、配对t检验和χ^(2)检验。结果干预后,观察组中医症候积分中的体倦乏力、神疲懒言、口淡不渴、食少纳呆评分均低于对照组[(1.01±0.30)分比(1.25±0.69)分、(1.43±0.22)分比(1.66±0.59)分、(1.00±0.35)分比(1.29±0.46)分、(0.73±0.22)分比(1.04±0.41)分](均P<0.05)。观察组EQ-5D中的行动能力、自我管理能力、活动能力、疼痛或不适、焦虑或抑郁评分均高于对照组[(2.01±0.64)分比(1.78±0.14)分、(1.95±0.43)分比(1.72±0.34)分、(1.82±0.26)分比(1.67±0.27)分、(2.01±0.27)分比(1.90±0.12)分、(1.92±0.14)分比(1.78±0.30)分](均P<0.05)。结论基于中医体质辨识学说的中医护理模式可改善亚健康患者中医症候积分,提高生活质量。

论污染环境罪因果关系司法认定困境及路径探寻——因果关系双层次理论之提倡

近年来,污染环境犯罪呈常态化发展趋势,但污染环境罪因果关系的认定面临诸多困难,导致许多污染环境犯罪并未受到相应的刑事惩罚。以“污染环境罪”和“因果关系”为关键词确定232份刑事一审判决文书为样本并进行多角度实证分析,发现污染环境案件因果关系具有特殊性,在理论供给、认定技术等方面存在诸多认定困境。基于此,笔者提倡因果关系双层次理论,采用疫学因果关系和原因力标准,科学建构污染环境罪因果关系认定路径,并就其关键问题提出可行性对策。