An improved interval model updating method via adaptive Kriging models

Interval model updating(IMU)methods have been widely used in uncertain model updating due to their low requirements for sample data.However,the surrogate model in IMU methods mostly adopts the one-time construction method.This makes the accuracy of the surrogate model highly dependent on the experience of users and affects the accuracy of IMU methods.Therefore,an improved IMU method via the adaptive Kriging models is proposed.This method transforms the objective function of the IMU problem into two deterministic global optimization problems about the upper bound and the interval diameter through universal grey numbers.These optimization problems are addressed through the adaptive Kriging models and the particle swarm optimization(PSO)method to quantify the uncertain parameters,and the IMU is accomplished.During the construction of these adaptive Kriging models,the sample space is gridded according to sensitivity information.Local sampling is then performed in key subspaces based on the maximum mean square error(MMSE)criterion.The interval division coefficient and random sampling coefficient are adaptively adjusted without human interference until the model meets accuracy requirements.The effectiveness of the proposed method is demonstrated by a numerical example of a three-degree-of-freedom mass-spring system and an experimental example of a butted cylindrical shell.The results show that the updated results of the interval model are in good agreement with the experimental results.

Research on Adaptive TSSA-HKRVM Model for Regression Prediction of Crane Load Spectrum

For the randomness of crane working load leading to the decrease of load spectrum prediction accuracy with time,an adaptive TSSA-HKRVM model for crane load spectrum regression prediction is proposed.The heterogeneous kernel relevance vector machine model(HKRVM)with comprehensive expression ability is established using the complementary advantages of various kernel functions.The combination strategy consisting of refraction reverse learning,golden sine,and Cauchy mutation+logistic chaotic perturbation is introduced to form a multi-strategy improved sparrow algorithm(TSSA),thus optimizing the relevant parameters of HKRVM.The adaptive updatingmechanismof the heterogeneous kernel RVMmodel under themulti-strategy improved sparrow algorithm(TSSA-HKMRVM)is defined by the sliding window design theory.Based on the sample data of the measured load spectrum,the trained adaptive TSSA-HKRVMmodel is employed to complete the prediction of the crane equivalent load spectrum.Applying this method toQD20/10 t×43m×12mgeneral bridge crane,the results show that:compared with other prediction models,although the complexity of the adaptive TSSA-HKRVMmodel is relatively high,the prediction accuracy of the load spectrum under long periods has been effectively improved,and the completeness of the load information during thewhole life cycle is relatively higher,with better applicability.

An Improved Binary Wolf Pack Algorithm Based on Adaptive Step Length and Improved Update Strategy for 0-1 Knapsack Problems

Binary wolf pack algorithm (BWPA) is a kind of intelligence algorithm which can solve combination optimization problems in discrete spaces.Based on BWPA, an improved binary wolf pack algorithm (AIBWPA) can be proposed by adopting adaptive step length and improved update strategy of wolf pack. AIBWPA is applied to 10 classic 0-1 knapsack problems and compared with BWPA, DPSO, which proves that AIBWPA has higher optimization accuracy and better computational robustness. AIBWPA makes the parameters simple, protects the population diversity and enhances the global convergence.

Model updating for real time dynamic substructures based on UKF algorithm

Combining the advantages of numerical simulation with experimental testing,real-time dynamic substructure(RTDS)testing provides a new experimental method for the investigation of engineered structures.However,not all unmodeled parts can be physically tested,as testing is often limited by the capacity of the test facility.Model updating is a good option to improve the modeling accuracy for numerical substructures in RTDS.In this study,a model updating method is introduced,which has great performance in describing this nonlinearity.In order to determine the optimal parameters in this model,an Unscented Kalman Filter(UKF)-based algorithm was applied to extract the knowledge contained in the sensors data.All the parameters that need to be identified are listed as the extended state variables,and the identification was achieved via the step-by-step state prediction and state update process.Effectiveness of the proposed method was verified through a group of experimental data,and results showed good agreement.Furthermore,the proposed method was compared with the Extended Kalman Filter(EKF)-based method,and better accuracy was easily found.The proposed parameter identification method has great applicability for structural objects with nonlinear behaviors and could be extended to research in other engineering fields.

Adaptive Linear Quadratic Regulator for Continuous-Time Systems With Uncertain Dynamics

In this paper, adaptive linear quadratic regulator(LQR) is proposed for continuous-time systems with uncertain dynamics. The dynamic state-feedback controller uses inputoutput data along the system trajectory to continuously adapt and converge to the optimal controller. The result differs from previous results in that the adaptive optimal controller is designed without the knowledge of the system dynamics and an initial stabilizing policy. Further, the controller is updated continuously using input-output data, as opposed to the commonly used switched/intermittent updates which can potentially lead to stability issues. An online state derivative estimator facilitates the design of a model-free controller. Gradient-based update laws are developed for online estimation of the optimal gain. Uniform exponential stability of the closed-loop system is established using the Lyapunov-based analysis, and a simulation example is provided to validate the theoretical contribution.

基于现场可编程门阵列的矩阵求逆算法设计

由于自适应抗干扰算法在更新最优权值时存在时间延时,导致很难满足动态环境下的权值更新率要求。针对该情况已有学者对如何实现快速采样矩阵求逆算法进行研究,但仍存在只适用于低维矩阵,且权值更新率慢的问题。为解决上述问题,提出了一种基于Cholesky分解的采样矩阵求逆算法实现架构。该实现架构主要包括协方差矩阵计算模块、Cholesky分解模块、计算下三角矩阵L的逆矩阵模块、三角矩阵相乘和权值计算模块。设计采用流水线加状态机实现结构有效地解决了因高阶采样矩阵求逆运算量大产生的权值更新率慢的问题。仿真结果表明,在现场可编程门阵列(field programmable gate array,FPGA)的硬件平台上,对于56阶采样矩阵,在100 MHz工作频率下,一次权值的更新时间仅需要1.2 ms。本文所提的实现架构为自适应抗干扰快速求解权值提供了一种切实可行的解决方案,对存在类似需求的权值求解系统具有一定的参考价值。

基于核相关滤波和卡尔曼滤波预测的混合跟踪方法

针对核相关滤波(KCF)跟踪算法在遮挡场景中出现跟踪性能降低甚至跟踪失败的问题,提出了一种核相关滤波和卡尔曼滤波(KF)预测相结合的模型自适应抗遮挡图像目标跟踪算法KCF-KF。首先,考虑到传统KCF目标跟踪算法中缺少遮挡评估的问题,通过引入响应图的峰值旁瓣比来对图像目标的遮挡情况进行判断,并将遮挡类型划分为部分遮挡和严重遮挡。其次,根据遮挡程度采取不同的模型更新策略,当目标无遮挡或者部分遮挡时,替代传统KCF跟踪算法中采用固定学习率更新模型的方法,通过自适应地调整模型学习率来更新目标外观模型,避免跟踪漂移;当目标被严重遮挡时,停止KCF模型更新。最后,应用严重遮挡之前的运动信息构建卡尔曼滤波器状态空间和位置输出模型,设计卡尔曼滤波算法预测运动目标轨迹来估计遮挡情景下的目标位置,从而解决在遮挡场景中目标跟踪失败的问题。采用OTB-2013标准数据集进行大量实验,结果表明:所提的混合跟踪算法KCF-KF的距离精度为0.796,重叠成功率为0.692。与其他传统跟踪算法相比,该混合算法的跟踪精度和跟踪成功率均优于其他算法,并且在遇到目标遮挡挑战时具有更好的跟踪性能,有效地解决了跟踪过程中的遮挡干扰问题。

基于工作面地质模型自适应开采的碰撞检测方法研究

由于综采工作面生产过程中粉尘、水雾导致摄像头视频模糊,通过视频无法常态化实现采煤机和液压支架碰撞检测,使得智能开采技术的实用性受限,文章提出了基于综采工作面高精度地质模型自适应开采的采煤机和液压支架碰撞检测方法。基于综采工作面高精度地质模型的自适应开采系统下发采煤机规划采高数据,结合采煤机的采高传感器数据和液压支架的高度传感器数据,实时对采煤机滚筒和液压支架进行碰撞检测预警,触发预警后采煤机牵引停止,同时自适应开采系统弹出触发碰撞检测支架的视频窗口,待人工处理消警后采煤机继续自适应割煤。结果表明,该方法将综采工作面采煤机和液压支架的相对坐标与地质模型的绝对坐标建立关联,实现基于综采工作面液压支架高度传感器数据和规划的截割数据两种方式的预警,大大提高了综采工作面采煤机和液压支架碰撞检测预警的准确性。

健壮且自适应的学习型近似查询处理方法研究

由于在大规模数据集上执行精确查询耗时较长,因此近似查询处理(AQP)技术常被用于在线分析处理,目的是以较短的交互延迟返回查询结果,并尽可能地降低查询误差。现有的学习型AQP方法与底层数据解耦,将I/O密集型计算转化为CPU密集型计算,但是由于计算资源的限制,该类方法通常基于随机的数据样本进行模型训练,此类训练数据会引起稀有群组缺失问题,导致模型预测准确性不高。针对上述问题,提出一种基于分层样本学习的混合型和积网络模型,并基于该模型设计一种AQP框架。分层样本能够有效避免稀有群组缺失现象,基于该样本训练的模型预测准确性大幅提升。此外,针对数据动态更新的情况,提出一种模型自适应更新策略,使得模型能够及时检测数据偏移现象并自适应地执行更新。实验结果表明,与基于抽样和基于机器学习的AQP方法相比,该模型在真实数据集和合成数据集上的平均相对误差分别约降低18.3%和2.2%,在数据动态更新的场景下,其准确性和查询时延均呈现出良好的稳定性。

面向动态交通流多步预测的时空图模型

为更好表征交通路网中节点之间的动态隐式关系,提出一种基于时空数据嵌入的动态图卷积交通流预测模型。基于路网中节点之间的共现关系,利用深度游走算法将时空数据映射到嵌入空间中学习节点的向量表示;引入时隙嵌入特征与二维空间嵌入特征共同构建三维嵌入邻接张量,用于捕获时空依赖关系;在图卷积网络中添加自适应更新机制,利用循环组件演化图卷积网络的参数,以捕获图序列的动态性。将所提模型应用于基于真实交通数据集的交通流预测,结果验证了其有效性和提取路网隐式关系的准确性。

用于训练神经网络的自适应梯度下降优化算法

由于神经网络规模的扩大,模型训练变得越来越困难.为应对这一问题,提出了一种新的自适应优化算法——Adaboundinject.选取Adam的改进算法Adabound算法,引入动态学习率边界,实现了自适应算法向随机梯度下降(SGD)的平稳过渡.为了避免最小值的超调,减少在最小值附近的振荡,在Adabound的二阶矩中加入一阶矩,利用短期参数更新作为权重,以控制参数更新.为了验证算法性能,在凸环境下,通过理论证明了Adaboundinject具有收敛性.在非凸环境下,进行了多组实验,采用了不同的神经网络模型,通过与其他自适应算法对比,验证了该算法相比其他优化算法具有更好的性能.实验结果表明,Adaboundinject算法在深度学习优化领域具有重要的应用价值,能够有效提高模型训练的效率和精度.

基于改进灰狼算法优化双向长短时记忆神经网络的水冷壁壁温预测

提出一种基于改进灰狼(MGWO)算法优化双向长短时记忆(BiLSTM)神经网络的水冷壁壁温预测模型,灰狼算法采用非线性因子调整策略、自适应位置更新策略和动态权重修改策略进行改进以提升算法的全局寻优能力,利用改进灰狼算法优化BiLSTM模型的隐藏层数量、学习率和正则化参数以提高模型的预测精度,采用新疆某电厂的数据进行预测仿真,结果表明:改进后的算法预测精度更高,在机组升、降负荷时,均可以预测到壁温的变化趋势,模型的平均均方根误差相比于长短时记忆(LSTM)神经网络、BiLSTM模型分别降低了9.86%和3.69%,且可以提前预测到水冷壁壁温的超温情况,对于预防水冷壁超温有重要意义。

基于改进和声搜索的自适应DBSCAN算法

DBSCAN算法作为一种经典的聚类算法被广泛地应用于各领域,但由于其参数的自适应性较差,应用效果完全取决于参数的设置。基于此,提出了基于改进和声搜索的自适应DBSCAN算法,以提高DBSCAN算法的自适应性。算法采用K-平均最近邻算法优化初始种群,从而改善初始种群质量,为后续的进化计算提供优质解;设计了基于双差分的更新算子,提升算法的搜索能力;采用两种更新策略结构避免算法过早收敛,提高和声搜索算法的寻优能力进而全面提升DBSCAN算法的自适应性。采用多种数据集并设计对比实验验证提出的算法。实验结果表明,提出的算法具有更佳的识别能力和自适应性。

纵横比自适应的时空正则化相关滤波算法

在目标跟踪中,传统相关滤波算法无法感知运动目标尺度纵横比变化,且易受复杂环境影响导致跟踪失败。为此,提出了纵横比自适应的时空正则化相关滤波算法。首先,参考平均峰值相关能量(Average peak-to-correlation energy,APCE)和响应峰值对每个特征的响应图进行加权融合,以实现对目标的精确跟踪。其次,结合近正交性和空间正则化提出一种新的一维边界滤波器,通过定位目标包围框的四个边界位置实现对目标尺度和纵横比变化的自适应检测,有效抑制了边界效应带来的负面影响。最后,根据响应输出的峰值旁瓣比(Peak-to-sidelobe ratio,PSR)独立地调节各边界滤波器的学习率,防止模型退化。在OTB数据集上进行了测试,该算法表现出理想的跟踪效果,在各个挑战属性上相较于其他优秀算法均取得了更优结果。

复合式无人机机翼设计及其自适应优化

随着人类社会的进步和城市物流的兴起,以复合式无人机为代表的无人机技术进入了快速发展阶段。在复合式无人机的研制周期中,气动优化设计选型扮演着非常重要的角色。针对基于代理模型的气动优化技术,对其关键参数自适应筛选和设计空间自适应更新进行了研究,形成了参数/空间自适应气动寻优平台,有效提高了气动优化过程中的寻优效率和搜索能力。针对一款复合式无人机提出机翼初步设计方案,并对其进行自适应气动寻优。优化翼根、翼梢翼型及由此生成的优化三维机翼在设计升力系数为1.0时的升阻比均提高5%以上,且对应迎角均减小2°以上。无人机机翼失速特性及滚转操控能力均得到有效提升。

基于织补体系的历史街区衡复策略研究

传统旧街区在城市化进程中的发展停滞是城市更新中亟待解决的问题。文章对沈阳北市场历史街区进行“织补”构建设计,建立起一个以实现街区衡复的目标的和适应城市历史街区发展更新的“织补系统”,以期在城市历史街区更新改造领域的研究工作中发挥理论价值。

基于差分进化-自适应Metropolis算法的桥梁工程研究

提出1种结合差分进化-自适应Metropolis算法(DREAM KZS)和克里金模型的多链贝叶斯模型更新框架。该框架融合敏感度分析以减少参数维度并便于参数选择。此外,利用克里金模型来节省计算成本。该框架还采用DREAM KZS算法与多采样策略,通过考虑模型参数、测量和模型输出之间的交叉协方差来增强后验分布的探索效率。通过增加样本多样性同时减少并行链的数量,实现快速准确的模型更新。结果表明通过对简支梁的数值研究,验证DREAM KZS算法的收敛速度和精度,提出的DREAM KZS贝叶斯模型更新框架在六跨铁路高架桥的模型更新应用中表现出优异的性能,由于需要重复的模型评估,高度耗时和高保真度的有限元模型阻碍有效的模型更新。

Thermal Fatigue Life Estimation and Fracture Mechanics Studies of Multilayered MEMS Structures Using a Sub-Domain Approach

This paper is concerned with the application of a Physics of Failure (PoF) methodology to assessing the reliability of Micro-Electro-Mechanical-System (MEMS) switches. Numerical simulations, based on the finite element method (FEM) using a sub-domain approach, were performed to examine the damage onset (e.g. yielding) due to temperature variations and to simulated the crack propagation different kind of loading conditions and, in particular, thermal fatigue. In this work remeshing techniques were employed in order to understand the evolution of initial flaws due, for instance, to manufacturing processes or originated after thermal fatigue.

基于多分区自适应改进果蝇算法的风光燃储微电网协调控制策略

为了使微电网控制系统中PI控制器的参数能够更好地适应可再生能源的随机性和波动性,提出了基于自适应步长的四分区多策略果蝇优化算法(fruitfly optimizationalgorithm,FOA)对PI参数进行实时优化。首先,以风光燃储微电网不同微源控制系统中的变换器为控制对象,建立微电网整体控制系统模型,基于此模型实时调整PI参数。然后,根据不同果蝇个体的适应度值将果蝇种群分为4个区,同时考虑4个区果蝇收敛性以及多样性的差异,设计不同的自适应更新策略。最后,采用所提算法对各微源控制过程中的PI参数进行寻优,与其他3种智能算法进行对比,验证了所提算法的可行性和优越性。仿真结果表明,所提算法可以使系统变换器响应速度更快,输出更加稳定。

自适应混合策略麻雀搜索算法

针对麻雀搜索算法(sparrow search algorithm,SSA)求解精度低,稳定性不足,易陷入局部最优等问题,提出一种基于自适应混合策略的麻雀搜索算法(adaptive hybrid strategy sparrow search algorithm,AHSSSA)。引入Tent混沌映射初始化种群,增加种群数量,合并两个种群,再利用精英策略得到精英种群,以提高初始解质量;引入自适应周期收敛因子α,加强搜索能力与收敛速度;追随者与预警者位置更新方式调整,在一定程度上防止算法陷入局部最优;引入多项式变异扰动,以解决SSA陷入局部最优问题。利用12种测试函数进行测试,结果表明:AHSSSA比SSA有更好的寻优性能。