基于t-SNE-VNWOA的船舶柴油机故障诊断

文中提出一种基于t-SNE-VNWOA-LSSVM故障诊断模型,并进行了台架试验.试验设置了正常工况、供气不足、燃烧提前和单缸断油四种工况,将各种工况采集的缸盖振动信号进行快速傅里叶变换(FFT),提取了13个时域和频域特征,利用t分布邻域嵌入算法(t-SNE)对数据降维、可视化故障特征.结合鲸鱼优化算法(VNWOA)对分类器(LSSVM)初始参数δ2和γ寻优,搭建其故障识别模型,将遗传算法(GA)和粒子群算法(PSO)的寻优诊断结果与之对比.结果表明:基于t-SNE-VNWOA-LSSVM故障诊断模型精度高达96.57%,且具有良好的稳定性及诊断速度.

基于CAE-TSNE的成品油管道运行工况识别

成品油管道运行工况变化频繁,难以精准判断管道运行状态,依靠现场人员进行识别监控易造成误判。本文为实现管道运行工况的准确识别,考虑管道的物理空间特性,分析整理各站运行参数(压力、流量、密度);考虑管道运行的时间序列特性,基于SCADA管道数据构造运行数据矩阵,以克服单一时刻的瞬态扰动。针对管道运行数据高维度、非线性的特点,利用卷积自编码器(CAE)强大的特征压缩及重构能力对管道数据做降噪处理;利用T分布邻域嵌入算法(T-SNE)对管道数据做降维聚类处理,最终建立了基于CAE-TSNE的管道运行工况识别模型。以某两条成品油管道为例,对比主流的非线性分类模型(ANN、DT、RF),结果表明基于CAE-TSNE的工况识别模型精度最高,对降噪后的运行数据识别准确率可达到99%以上,可用于指导现场管道的运行管理。

Distributed Nash Equilibrium Seeking Strategies Under Quantized Communication

This paper is concerned with distributed Nash equi librium seeking strategies under quantized communication. In the proposed seeking strategy, a projection operator is synthesized with a gradient search method to achieve the optimization o players' objective functions while restricting their actions within required non-empty, convex and compact domains. In addition, a leader-following consensus protocol, in which quantized informa tion flows are utilized, is employed for information sharing among players. More specifically, logarithmic quantizers and uniform quantizers are investigated under both undirected and connected communication graphs and strongly connected digraphs, respec tively. Through Lyapunov stability analysis, it is shown that play ers' actions can be steered to a neighborhood of the Nash equilib rium with logarithmic and uniform quantizers, and the quanti fied convergence error depends on the parameter of the quan tizer for both undirected and directed cases. A numerical exam ple is given to verify the theoretical results.

Magnetopause properties at the dusk magnetospheric flank from global magnetohydrodynamic simulations,the kinetic Vlasov equilibrium,and in situ observations--Potential implications for SMILE

We derived the properties of the terrestrial magnetopause(MP)from two modeling approaches,one global–fluid,the other local–kinetic,and compared the results with data collected in situ by the Magnetospheric Multiscale 2(MMS2)spacecraft.We used global magnetohydrodynamic(MHD)simulations of the Earth’s magnetosphere(publicly available from the NASA-CCMC[National Aeronautics and Space Administration–Community Coordinated Modeling Center])and local Vlasov equilibrium models(based on kinetic models for tangential discontinuities)to extract spatial profiles of the plasma and field variables at the Earth’s MP.The global MHD simulations used initial solar wind conditions extracted from the OMNI database at the time epoch when the MMS2 observes the MP.The kinetic Vlasov model used asymptotic boundary conditions derived from the same in situ MMS measurements upstream or downstream of the MP.The global MHD simulations provide a three-dimensional image of the magnetosphere at the time when the MMS2 crosses the MP.The Vlasov model provides a one-dimensional local view of the MP derived from first principles of kinetic theory.The MMS2 experimental data also serve as a reference for comparing and validating the numerical simulations and modeling.We found that the MP transition layer formed in global MHD simulations was generally localized closer to the Earth(roughly by one Earth radius)from the position of the real MP observed by the MMS.We also found that the global MHD simulations overestimated the thickness of the MP transition by one order of magnitude for three analyzed variables:magnetic field,density,and tangential speed.The MP thickness derived from the local Vlasov equilibrium was consistent with observations for all three of these variables.The overestimation of density in the Vlasov equilibrium was reduced compared with the global MHD solutions.We discuss our results in the context of future SMILE(Solar wind Magnetosphere Ionosphere Link Explorer)campaigns for observing the Earth’s MP.

基于tSNE-LSTM算法的工业预测模型

随着工业生产的复杂性和规模的增加,准确的工业预测模型对于提高生产效率和降低成本至关重要。为此,提出一种基于tSNE-LSTM算法的工业预测模型来预测工业生产过程的温度。将t-SNE应用于数据降维和特征提取,然后使用LSTM进行序列建模和预测。该模型结合了t-SNE降维和LSTM循环神经网络的优势,能够有效地捕捉时间序列数据的非线性动态特征,并进行准确预测。在实际工业数据集上的实验验证结果表明,该模型在工业预测任务中具有较高的准确性和鲁棒性。

基于t-SNE的多参数岩体结构面分步聚类方法

结构面聚类是进行岩体稳定性评价的重要步骤。常用聚类方法多以产状作为分组依据,忽略了结构面物理特性指标对岩体稳定性的影响。针对分组依据单一化的不足,综合考虑结构面倾向、倾角、迹长、张开度、填充状态和粗糙度的影响,提出一种基于学生分布随机邻近嵌入(student-distributed stochastic neighbor embedding,简称t-SNE)的多参数岩体结构面分步聚类方法。首先,利用t-SNE算法对除产状外的结构面特征进行数据降维;进而利用模拟退火算法搜索K-means算法的全局最优初始值,并采用分步聚类思想完成聚类。研究表明:所提方法有效地解决了高维空间样本稀疏的问题,同时保留了数据的局部结构与全局结构。新方法相比于传统方法能对空间分布相似区内结构面的物理特性进行精确划分,分组精度更高,且在避免复杂权重值计算的条件下,能有效区分产状与物理特性参数对岩体稳定性的影响差异。最后,将所提方法应用于中国新疆某露天矿坡结构面实测数据分析中,所得分组结果合理可靠,进一步证明该方法在实际工程中的有效性。研究方法可为多参数岩体结构面的分步聚类提供参考。

Numerical analysis for the free-boundary current reversal equilibrium in the AC plasma current operation in a tokamak

In recent decades, tokamak discharges with zero total toroidal current have been reported in tokamak experiments, and this is one of the key problems in alternating current(AC) operations.An efficient free-boundary equilibrium code is developed to investigate such advanced tokamak discharges with current reversal equilibrium configuration. The calculation results show that the reversal current equilibrium can maintain finite pressure and also has considerable effects on the position of the X-point and the magnetic separatrix shape, and hence also on the position of the strike point on the divertor plates, which is extremely useful for magnetic design, MHD stability analysis, and experimental data analysis etc. for the AC plasma current operation on tokamaks.

Kinetic equilibrium reconstruction with internal safety factor profile constraints on EAST tokamak

Reconstruction of plasma equilibrium plays an important role in the analysis and simulation of plasma experiments. The kinetic equilibrium reconstruction with pressure and edge current constraints has been employed on EAST tokamak. However, the internal safety factor(q) profile is not accurate. This paper proposes a new way of incorporating q profile constraints into kinetic equilibrium reconstruction. The q profile is yielded from the Polarimeter Interferometer(POINT)reconstruction. Virtual probes containing information on q profile constraints are added to inputs of the kinetic equilibrium reconstruction program to obtain the final equilibrium. The new equilibrium produces a more accurate internal q profile. This improved method would help analyze EAST experiments.

Equilibrium Strategy of the Pursuit-Evasion Game in Three-Dimensional Space

The pursuit-evasion game models the strategic interaction among players, attracting attention in many realistic scenarios, such as missile guidance, unmanned aerial vehicles, and target defense. Existing studies mainly concentrate on the cooperative pursuit of multiple players in two-dimensional pursuit-evasion games. However, these approaches can hardly be applied to practical situations where players usually move in three-dimensional space with a three-degree-of-freedom control. In this paper,we make the first attempt to investigate the equilibrium strategy of the realistic pursuit-evasion game, in which the pursuer follows a three-degree-of-freedom control, and the evader moves freely. First, we describe the pursuer's three-degree-of-freedom control and the evader's relative coordinate. We then rigorously derive the equilibrium strategy by solving the retrogressive path equation according to the Hamilton-Jacobi-Bellman-Isaacs(HJBI) method, which divides the pursuit-evasion process into the navigation and acceleration phases. Besides, we analyze the maximum allowable speed for the pursuer to capture the evader successfully and provide the strategy with which the evader can escape when the pursuer's speed exceeds the threshold. We further conduct comparison tests with various unilateral deviations to verify that the proposed strategy forms a Nash equilibrium.

Multi-Objective Equilibrium Optimizer for Feature Selection in High-Dimensional English Speech Emotion Recognition

Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.

Magnetic diagnostics layout design for CFETR plasma equilibrium reconstruction

Plasma equilibrium reconstruction provides essential information for tokamak operation and physical analysis.An extensive and reliable set of magnetic diagnostics is required to obtain accurate plasma equilibrium.This study designs and optimizes the magnetic diagnostics layout for the reconstruction of the equilibrium of the plasma according to the scientific objectives,engineering design parameters,and limitations of the Chinese Fusion Engineering Test Reactor(CFETR).Based on the CFETR discharge simulation,magnetic measurement data are employed to reconstruct consistent plasma equilibrium parameters,and magnetic diagnostics'number and position are optimized by truncated Singular value decomposition,verifying the redundancy reliability of the magnetic diagnostics layout design.This provides a design solution for the layout of the magnetic diagnostics system required to control the plasma equilibrium of CFETR,and the developed design and optimization method can provide effective support to design magnetic diagnostics systems for future magnetic confinement fusion devices.

Probabilistic Analysis of Slope Using Finite Element Approach and Limit Equilibrium Approach around Amalpata Landslide of West Central, Nepal

The stability study of the ongoing and recurring Amalpata landslide in Baglung in Nepal’s Gandaki Province is presented in this research. The impacted slope is around 200 meters high, with two terraces that have different slope inclinations. The lower bench, located above the basement, consistently fails and sets others up for failure. The fluctuating water level of the slope, which travels down the slope masses, exacerbates the slide problem. The majority of these rocks are Amalpata landslide area experiences several structural disruptions. The area’s stability must be evaluated in order to prevent and control more harm from occurring to the nearby agricultural land and people living along the slope. The slopes’ failures increase the damages of house existing in nearby area and the erosion of the slope. Two modeling techniques the finite element approach and the limit equilibrium method were used to simulate the slope. The findings show that, in every case, the terrace above the basement is where the majority of the stress is concentrated, with a safety factor of near unity. Using probabilistic slope stability analysis, the failure probability was predicted to be between 98.90% and 100%.

Analysis of Drug Medical Insurance Access Pricing Based on the Perspective of Binary Equilibrium

Objective To study the influencing factors in the process of national medical insurance negotiation and drug pricing from the dualistic equilibrium perspective,and to provide reference for the harmonious management of drug pricing in China.Methods Through the literature analysis and policy review,the pricing subject,pricing basis and price control system in the pricing process of medical-accessed medicines were analyzed from the perspective of binary equilibrium and harmonious management.Results and Conclusion It is found that four balances in the drug pricing process,two balances in pricing basis and three balances in price control system need to be considered,respectively.Drug pricing is the key content of national medical insurance access,which is also the hotspot of the policy in the pharmaceutical fields in recent years.Drug pricing not only reflects the value of drugs,but also reflects a lot of top-level designs of binary equilibriums in medical insurance policy.While the rational design of drug pricing requires the joint efforts of the government,pharmaceutical companies and relevant experts to comprehensively consider many equilibriums,so as to improve the relevant systems.

EEMD熵特征和t-SNE相结合的滚动轴承故障诊断

针对滚动轴承振动信号的非平稳非线性特性,提出了一种采用集合经验模态分解(EEMD)熵特征提取、t-分布邻域嵌入(t-SNE)和粒子群优化-概率神经网络(PSO-PNN)的滚动轴承故障诊断方法。首先,对振动信号应用EEMD算法实现分解,生成多个固有模态函数(IMFs),对生成的含有主要故障信息的模态分量进行选择,以进一步实现熵特征提取,然后对高维特征数据应用t-SNE算法进行降维,最后利用PSO-PNN分类器进行故障识别。通过案例1和案例2的分析结果表明:该方法对滚动轴承故障识别率均达到100%,具有较高的故障识别率,能对滚动轴承的故障类型有效的识别。

基于改进CEEMDAN和t-SNE的故障特征提取方法

针对非线性、非稳定振动信号难以提取有效故障特征的问题,提出一种基于改进自适应噪声完备集合经验模态分解(CEEMDAN)和t-分布随机邻域嵌入(t-SNE)算法相结合的故障特征提取方法。利用三次Hermite插值代替三次样条插值构造包络线,提高传统CEEMDAN对非平稳信号的分解精度;利用改进后的CEEMDAN对原始信号分解并通过相关系数筛选出有效固有模态分量(IMF),提取有效IMF分量的时频特征、奇异值和能量值构建高维混合域特征集;最后,通过t-SNE算法挖掘高维混合域特征信息得到低维敏感特征,并将其输入到支持向量机中进行分类,以分类准确率作为特征提取效果评价指标。在齿轮箱故障模拟实验台进行实验验证,结果表明该方法能够准确地提取故障特征,为故障特征提取提供新思路。

Distributed Nash Equilibrium Seeking for General Networked Games With Bounded Disturbances

This paper is concerned with anti-disturbance Nash equilibrium seeking for games with partial information.First,reduced-order disturbance observer-based algorithms are proposed to achieve Nash equilibrium seeking for games with firstorder and second-order players,respectively.In the developed algorithms,the observed disturbance values are included in control signals to eliminate the influence of disturbances,based on which a gradient-like optimization method is implemented for each player.Second,a signum function based distributed algorithm is proposed to attenuate disturbances for games with secondorder integrator-type players.To be more specific,a signum function is involved in the proposed seeking strategy to dominate disturbances,based on which the feedback of the velocity-like states and the gradients of the functions associated with players achieves stabilization of system dynamics and optimization of players'objective functions.Through Lyapunov stability analysis,it is proven that the players'actions can approach a small region around the Nash equilibrium by utilizing disturbance observerbased strategies with appropriate control gains.Moreover,exponential(asymptotic)convergence can be achieved when the signum function based control strategy(with an adaptive control gain)is employed.The performance of the proposed algorithms is tested by utilizing an integrated simulation platform of virtual robot experimentation platform(V-REP)and MATLAB.

Fully Distributed Nash Equilibrium Seeking for High-Order Players With Actuator Limitations

This paper explores the problem of distributed Nash equilibrium seeking in games, where players have limited knowledge on other players' actions. In particular, the involved players are considered to be high-order integrators with their control inputs constrained within a pre-specified region. A linear transformation for players' dynamics is firstly utilized to facilitate the design of bounded control inputs incorporating multiple saturation functions. By introducing consensus protocols with adaptive and time-varying gains, the unknown actions for players are distributively estimated. Then, a fully distributed Nash equilibrium seeking strategy is exploited, showcasing its remarkable properties: (1) ensuring the boundedness of control inputs;(2) avoiding any global information/parameters;and (3) allowing the graph to be directed. Based on Lyapunov stability analysis, it is theoretically proved that the proposed distributed control strategy can lead all the players' actions to the Nash equilibrium. Finally, an illustrative example is given to validate effectiveness of the proposed method.

Quantum-Inspired Equilibrium Optimizer for Linear Antenna Array

With the rapid development of communication technology,the problem of antenna array optimization plays a crucial role.Among many types of antennas,line antenna arrays(LAA)are the most commonly applied,but the side lobe level(SLL)reduction is still a challenging problem.In the radiation process of the linear antenna array,the high side lobe level will interfere with the intensity of the antenna target radiation direction.Many conventional methods are ineffective in obtaining the maximumside lobe level in synthesis,and this paper proposed a quantum equilibrium optimizer(QEO)algorithm for line antenna arrays.Firstly,the linear antenna array model consists of an array element arrangement.Array factor(AF)can be expressed as the combination of array excitation amplitude and position in array space.Then,inspired by the powerful computing power of quantum computing,an improved quantum equilibrium optimizer combining quantum coding and quantum rotation gate strategy is proposed.Finally,the proposed quantum equilibrium optimizer is used to optimize the excitation amplitude of the array elements in the linear antenna array model by numerical simulation to minimize the interference of the side lobe level to the main lobe radiation.Six differentmetaheuristic algorithms are used to optimize the excitation amplitude in three different arrays of line antenna arrays,the experimental results indicated that the quantum equilibrium optimizer is more advantageous in obtaining the maximum side lobe level reduction.Compared with other metaheuristic optimization algorithms,the quantum equilibrium optimizer has advantages in terms of convergence speed and accuracy.

基于Wasserstein散度的t-SNE相似性度量方法研究

近红外光谱具有高维、高冗余、非线性的特性,严重影响了样本之间的相似性度量的精准,故而提出了一种基于Wasserstein散度的t分布随机近邻嵌入算法(Wt-SNE)。基于流形学习算法思想,利用高斯分布将高维数据的距离转换为概率分布,使用更加偏重长尾分布的方式t分布表示低维空间中对应数据点的概率分布。将高维数据的概率分布嵌入映射至低维度空间,重构低维流形结构,引入Wasserstein散度度量两个空间内概率分布的差异,通过降低散度值来提高两个分布的相似度,以此来实现高维数据降维处理。为验证Wt-SNE算法的有效性,首先对烟叶近红外光谱数据进行降维投影,并与PCA、 LPP、 t-SNE算法比较,结果表明Wt-SNE算法降维后的数据,在低维空间内样本类别边界更加明显。其次,采用KNN、 SVM和PLS-DA分类器对降维后的数据进行烟叶产地预测,准确率分别为93.8%、 91.5%、 92.7%,表明降维后的数据不仅重构了原始光谱的空间结构而且保留了样本间的相似度关系。最后,选取某一卷烟叶组配方中的烟叶进行单料目标烟叶的替换,根据备选样本与目标样本之间的马氏距离选取替换样本。实验表明,Wt-SNE选取的替换烟叶与目标烟叶相似度最高,烟碱、总糖等化学成分含量与目标烟叶差异较小,香气、烟气、口感得分表现出较高的一致性。该方法能够有效度量烟叶近红外光谱之间的相似性,为卷烟叶组配方的维护提供有力的依据。

基于深度自编码器和t-SNE算法的电梯故障预警

为提高电梯承运质量,针对电梯轿厢系统,设计基于深度自编码器(DAE)和t分布随机邻域嵌入算法(t-SNE)相结合的电梯轿厢系统故障预警模型。通过计算电梯轿厢系统运行时振动信号的重构误差,并将其与预警阈值进行对比分析,可以直观地对振动信号波形进行分类,判别轿厢系统运行是否出现异常,通过t-SNE算法进行可视化分析。实验结果表明:该模型能够有效实现电梯轿厢系统的故障实时预警功能,为电梯的预防性维护提供依据。