Improved Arithmetic Optimization Algorithm with Multi-Strategy Fusion Mechanism and Its Application in Engineering Design

This article addresses the issues of falling into local optima and insufficient exploration capability in the Arithmetic Optimization Algorithm (AOA), proposing an improved Arithmetic Optimization Algorithm with a multi-strategy mechanism (BSFAOA). This algorithm introduces three strategies within the standard AOA framework: an adaptive balance factor SMOA based on sine functions, a search strategy combining Spiral Search and Brownian Motion, and a hybrid perturbation strategy based on Whale Fall Mechanism and Polynomial Differential Learning. The BSFAOA algorithm is analyzed in depth on the well-known 23 benchmark functions, CEC2019 test functions, and four real optimization problems. The experimental results demonstrate that the BSFAOA algorithm can better balance the exploration and exploitation capabilities, significantly enhancing the stability, convergence mode, and search efficiency of the AOA algorithm.

Hybrid artificial bee colony algorithm with variable neighborhood search and memory mechanism

Artificial bee colony(ABC) is one of the most popular swarm intelligence optimization algorithms which have been widely used in numerical optimization and engineering applications. However, there are still deficiencies in ABC regarding its local search ability and global search efficiency. Aiming at these deficiencies,an ABC variant named hybrid ABC(HABC) algorithm is proposed.Firstly, the variable neighborhood search factor is added to the solution search equation, which can enhance the local search ability and increase the population diversity. Secondly, inspired by the neuroscience investigation of real honeybees, the memory mechanism is put forward, which assumes the artificial bees can remember their past successful experiences and further guide the subsequent foraging behavior. The proposed memory mechanism is used to improve the global search efficiency. Finally, the results of comparison on a set of ten benchmark functions demonstrate the superiority of HABC.

Topology Search of 3-DOF Translational Parallel Manipulators with Three Identical Limbs for Leg Mechanisms

Three-degree of freedom（3-DOF） translational parallel manipulators（TPMs） have been widely studied both in industry and academia in the past decades. However, most architectures of 3-DOF TPMs are created mainly on designers＇ intuition, empirical knowledge, or associative reasoning and the topology synthesis researches of 3-DOF TPMs are still limited. In order to find out the atlas of designs for 3-DOF TPMs, a topology search is presented for enumeration of 3-DOF TPMs whose limbs can be modeled as 5-DOF serial chains. The proposed topology search of 3-DOF TPMs is aimed to overcome the sensitivities of the design solution of a 3-DOF TPM for a LARM leg mechanism in a biped robot. The topology search, which is based on the concept of generation and specialization in graph theory, is reported as a step-by-step procedure with desired specifications, principle and rules of generalization, design requirements and constraints, and algorithm of number synthesis. In order to obtain new feasible designs for a chosen example and to limit the search domain under general considerations, one topological generalized kinematic chain is chosen to be specialized. An atlas of new feasible designs is obtained and analyzed for a specific solution as leg mechanisms. The proposed methodology provides a topology search for 3-DOF TPMs for leg mechanisms, but it can be also expanded for other applications and tasks.

Feedback Mechanism-driven Mutation Reptile Search Algorithm for Optimizing Interpolation Developable Surfaces

Curvature lines are special and important curves on surfaces.It is of great significance to construct developable surface interpolated on curvature lines in engineering applications.In this paper,the shape optimization of generalized cubic ball developable surface interpolated on the curvature line is studied by using the improved reptile search algorithm.Firstly,based on the curvature line of generalized cubic ball curve with shape adjustable,this paper gives the construction method of SGC-Ball developable surface interpolated on the curve.Secondly,the feedback mechanism,adaptive parameters and mutation strategy are introduced into the reptile search algorithm,and the Feedback mechanism-driven improved reptile search algorithm effectively improves the solving precision.On IEEE congress on evolutionary computation 2014,2017,2019 and four engineering design problems,the feedback mechanism-driven improved reptile search algorithm is compared with other representative methods,and the result indicates that the solution performance of the feedback mechanism-driven improved reptile search algorithm is competitive.At last,taking the minimum energy as the evaluation index,the shape optimization model of SGC-Ball interpolation developable surface is established.The developable surface with the minimum energy is achieved with the help of the feedback mechanism-driven improved reptile search algorithm,and the comparison experiment verifies the superiority of the feedback mechanism-driven improved reptile search algorithm for the shape optimization problem.

Electromagnetism-Like Mechanism Algorithm with New Charge Formula for Optimization

The electromagnetism-like(EM)algorithm is a meta-heuristic optimization algorithm,which uses a novel searching mechanism called attraction-repulsion between charged particles.It is worth pointing out that there are two potential problems in the calculation of particle charge by the original EM algorithm.One of the problems is that the information utilization rate of the population is not high,and the other problem is the decline of population diversity when the population size is much greater than the dimension of the problem.In contrast,it is more fully to exploit the useful search information based on the proposed new quadratic formula for charge calculation in this paper.Furthermore,the population size was introduced as a new multiplier term to improve the population diversity.In the end,numerical experiments were used to verify the performance of the proposed method,including a comparison with the original EM algorithm and other well-known methods such as artificial bee colony(ABC),and particle swarm optimization(PSO).The results showed the effectiveness of the proposed algorithm.

Present Tectonic Stress Field in the Capital Region of China Inverted from Focal Mechanisms of Small and Strong Earthquakes

A dense seismic network was installed in the capital region of China in recent years,which makes it possible to resolve the focal mechanisms of small earthquakes. We gathered large earthquake focal mechanisms from the last fifty years and moderate or small earthquake focal mechanisms from between 2002 and 2004,and calculated the present tectonic stress field of the capital region by the grid search method, which weighs different sized earthquakes and can improve the accuracy of the stress field inversion. The analysis of inversion results of different sub-regions shows that the azinuth of the maximum principal compressive stress axis is NE43°- 86° in the Beijing-Zhangjiakou-Datong area,NE38°-86° in the Tangshan area,and NE79°- 81° in the Xingtai area. Inversion results of this paper are similar to previous results,which proves the correctness of the approach. As revealed by the results,the stress field of the capital region is characterized by overall consistency and sub-regional differences. This study provides reference for earthquake mechanism explanation and geodynamics research.

DAAPS: A Deformable-Attention-Based Anchor-Free Person Search Model

Person Search is a task involving pedestrian detection and person re-identification,aiming to retrieve person images matching a given objective attribute from a large-scale image library.The Person Search models need to understand and capture the detailed features and context information of smaller objects in the image more accurately and comprehensively.The current popular Person Search models,whether end-to-end or two-step,are based on anchor boxes.However,due to the limitations of the anchor itself,the model inevitably has some disadvantages,such as unbalance of positive and negative samples and redundant calculation,which will affect the performance of models.To address the problem of fine-grained understanding of target pedestrians in complex scenes and small sizes,this paper proposes a Deformable-Attention-based Anchor-free Person Search model(DAAPS).Fully Convolutional One-Stage(FCOS),as a classic Anchor-free detector,is chosen as the model’s infrastructure.The DAAPS model is the first to combine the Anchor-free Person Search model with Deformable Attention Mechanism,applied to guide the model adaptively adjust the perceptual.The Deformable Attention Mechanism is used to help the model focus on the critical information and effectively improve the poor accuracy caused by the absence of anchor boxes.The experiment proves the adaptability of the Attention mechanism to the Anchor-free model.Besides,with an improved ResNeXt+network frame,the DAAPS model selects the Triplet-based Online Instance Matching(TOIM)Loss function to achieve a more precise end-to-end Person Search task.Simulation experiments demonstrate that the proposed model has higher accuracy and better robustness than most Person Search models,reaching 95.0%of mean Average Precision(mAP)and 95.6%of Top-1 on the CUHK-SYSU dataset,48.6%of mAP and 84.7%of Top-1 on the Person Re-identification in the Wild(PRW)dataset,respectively.

Mobility and constant-orientation workspace analysis of 4UPS-UPU parallel mechanism

One of the key issues for parallel mechanism is the kinematic characteristics,especially the workspace which varies with configuration parameters.A kind of 4UPS-UPU parallel mechanism is designed and its workspace is studied in this paper.First,the mobility of the 4UPS-UPU parallel mechanism is analyzed based on the reciprocal screw theory,and the motion and constraint screw systems of the parallel mechanism are obtained.Then the inverse kinematics is derived by the closed-form kinematics chain.The boundary search method in the polar coordinate system is presented to analyze the constant-orientation workspace of the parallel mechanism.Finally,the influence factors relevant to the workspace,such as the structural parameters and kinematics parameters are analyzed in detail.The relationship between the workspace volume and different parameters are obtained.The conclusions can be used for parameters optimization and path planning of the parallel mechanism.

多舱共配绿色车辆路径问题的改进变邻域搜索算法

针对社区团购前置仓配送场景中“多中心、高时效、多品类、高排放”难题,本文提出多车场带时间窗的绿色多舱车车辆路径问题(MDMCG-VRPTW),构建混合整数线性规划模型,并设计改进的变邻域搜索算法(IVNS)实现求解.采用两阶段混合算法构造高质量初始解.提出均衡抖动策略以充分探索解空间,引入粒度机制以提升局部搜索阶段的寻优效率.标准算例测试结果验证了两阶段初始解构造算法和IVNS算法的有效性.仿真实验结果表明,模型与算法能够有效求解MDMCGVRPTW,且改进策略提高了算法的求解效率和全局搜索能力.最后,基于对配送策略和时效性的敏感性分析,为相关配送企业降本增效提供更多决策依据.

融合均值榜样的反向互学习水母搜索算法

为解决水母搜索算法(jellyfish search algorithm,JS)的洋流运动缺乏多样性、群内运动缺乏引导性、种群间信息无交流,造成搜索速度慢、稳定性差及易早熟的问题,构建了一种融合均值榜样的反向互学习水母搜索算法(oppositional-mutual learning jellyfish search algorithm based on mean-value example,OMLJS).首先在水母跟随洋流运动(全局搜索)部分,利用前两代水母的平均位置代替只考虑上一代水母的平均位置来引导水母个体的位置更新,提高算法的全局搜索能力;其次在水母的群内主动运动(局部搜索)部分,利用最优个体代替随机个体来引导水母进行更有效的搜索,加快算法的收敛速度;然后在水母进入下一次迭代前增加对水母种群进行动态反向互学习步骤,增加种群多样性及增强种群间的信息交流,达到互补另外两个策略,提高算法的整体优化性能.选用12个经典的基准测试优化函数,将OMLJS与5个对比算法从解的平均值、最优值及方差进行对比分析,并用于求解最小生成树问题,OMLJS能够更快地找到最小生成树.实验结果表明,OMLJS的收敛速度、求解精度明显提高.

现象图析学视角下在线健康信息替代搜寻行为机理研究

[目的/意义]探析现象图析学视角下在线健康信息替代搜寻行为的影响因素与生成机理,有助于丰富信息行为研究的理论范式,为解决替代搜寻问题提供相应的建议与参考。[方法/过程]基于意义建构理论模型框架,从“情景—鸿沟—桥梁—结果”4个维度,对在线健康信息替代搜寻行为进行模型要素解析,并利用现象图析学质性方法深入挖掘该行为的内在机理,构建在线健康信息替代搜寻行为机理关系模型。[结果/结论]研究结果揭示了在线健康信息替代搜寻行为机理可分为情景触发、条件控制、桥梁构建、结果反馈4个子机理,并明晰了其机理关系,为今后相关研究者对在线健康信息替代搜寻行为机理研究提供理论借鉴和参考。

基于衍生搜索政治优化算法解决含可再生能源的多区域经济调度问题

随着可再生能源并入多区域电力系统,其不确定性大大增加了电力系统多区域经济调度的复杂度。如何高效求解含有风力和太阳能的多区域经济调度(multi-areaeconomic dispatch containing wind and solar energy,MAEDWS)问题面临着严峻的挑战。针对现有优化算法在处理MAEDWS问题时存在收敛速度慢和求解精度低等不足,该文提出一种基于衍生搜索的政治优化(derivative search-based political optimizer,DSPO)算法。在政治优化算法的基础上,引入首脑引领策略和衍生搜索机制。前者引领候选解前往更有希望的区域,加快收敛速度;后者在区域获胜者周围衍生邻域解,丰富多样性。该文将DSPO算法和其他6种代表性算法应用于MAEDWS问题,并进行对比分析。收敛曲线和性能指标的结果表明DSPO算法在收敛效率、求解精确度、稳定性方面取得了整体最优。

基于麻雀搜索算法改进的YOLOv7-ECA-SSA模型的车辆检测

为解决复杂背景下小目标车辆检测存在的误检、漏检等现象,创新性提出一种改进YOLOv7网络的目标检测算法。首先,为解决小目标车辆存在次要信息干扰问题,将高效通道注意力(ECA)机制融于YOLOv7模型的主干网络特征层,通过自适应学习来增强目标区域信息权重占比,抑制无关信息;其次,为解决神经网络检测模型训练的超参数随机经验设定性问题,将麻雀搜索算法(SSA)对检测模型训练超参数进行优化,通过内外双循环迭代方式,快速收敛出全局最优学习率,进而得到最优组的权重信息,最终提高小目标车辆检测精度。实验结果表明,基于结构优化、超参数优化的YOLOv7-ECA-SSA检测模型在BDD100K数据集上的检测精度为79.01%,比原始模型提高了5.38%,具备更好的小目标车辆检测性能。

基于双模态分解的发电站母线短期负荷预测

母线负荷预测是电力系统运营和规划中至关重要的一项任务,针对电力负荷数据的非线性强以及影响因素多等问题,提出了一种基于双模态分解、深度学习和注意力机制的负荷预测模型。首先,对输入数据进行经验模态分解(Empirical mode decomposition,EMD),通过K-means聚类分析对复杂度相似的分量进行集合得到三个组合分量。其次,使用变分模态分解(Variational mode decomposition, VMD)对组合分量再次进行分解得到不同分量,使用麻雀搜索算法(Sparrow search algorithm,SSA)对变分模态分解的参数进行优化。再次,将变分模态分解得到的分量与影响因素连接并输入长短期记忆网络(Long short-term memory network, LSTM),通过注意力机制挖掘数据内部的相关性,并使用SSA对LSTM网络的参数进行优化。最后,采用宁夏某电站一年的负荷数据进行验证,经过与不同模型的对比分析,所提模型有更高的预测精度。

基于聚类和GBDT的镀锌钢卷力学性能预测

热镀锌钢卷力学性能影响因素之间关系复杂,限制了模型精度的提升。采用k-means算法利用化学成分属性对镀锌钢卷数据集进行聚类,将数据聚成三种模式簇实现样本的优选。利用梯度提升树算法,开展各模式数据集与不划分模式的全数据集下的力学性能建模研究,最后结合网格搜索与交叉验证方法进行模型参数优化。研究结果表明,分模式下模型MAE误差相比于全数据集建模平均减小0.85 MPa。参数优化后,各模式下MAE误差平均减少5.19 MPa,RMSE误差平均减少3.63 MPa,提高了预测模型精度。

量子计算在地球物理学中的应用

量子计算具有强大的计算能力,被视为一种可能对未来产生颠覆性影响的计算方法,可为多种复杂计算问题的求解提供新思路,目前已在多学科或领域实践与应用。近年来,量子计算逐步应用于地球物理研究,多种量子算法及量子计算机的应用为揭示地球内部构造、探测深部资源等提供了技术支持。量子计算具备高效求解科学问题的能力,在地球物理领域具有巨大的应用潜力。为此,系统分析、阐述量子计算原理并总结了量子算法的发展现状,对其在地球物理数据采集、波场模拟、反问题求解等领域的成果进行归纳、分析;通过建立理论模型并进行反演,验证了量子算法的优越性;最后展望了量子计算未来可能的研究方向。

基于主从博弈的园区级综合能源系统动态定价与低碳经济调度

面向园区综合能源系统中供能方与用能方的角色互换,以及园区低碳经济运行的强约束,提出了一种考虑动态参数的阶梯型碳交易机制和需求响应的园区级综合能源系统主从博弈优化调度方法。首先,将园区级综合能源系统中能源运营商(energy system operator,ESO)设定为上层领导者、综合能源系统园区设定为下层跟随者,并且能源运营商以最大化自身效益为目标,通过制定与园区间的购售电价格、碳交易基价、价格增长幅度,引导下层园区优化;下层园区以最小化其运行成本为目标,对上层发布的价格信息做出反应,从而构建主从博弈模型。其次,充分考虑园区级综合能源系统的低碳经济运行约束,在博弈模型中引入考虑动态参数的阶梯型碳交易机制以限制二氧化碳排放量,并在园区侧引入需求响应。最后,利用水母搜索算法对上层发布的购售电价、碳交易基价、价格增长幅度进行优化,利用CPLEX优化下层园区设备出力、需求响应以及购售电计划。仿真结果证明了所提模型和方法的有效性。

基于神经网络架构搜索的细粒度花卉图像分类方法研究

为了提升深度卷积神经网络设计的自动化程度,并进一步提高细粒度花卉图像的分类准确率,提出了一种改进的基于DARTS的神经网络搜索方法,用于自动构建细粒度花卉图像分类模型。首先,通过构建注意力-卷积模块,形成全注意力-卷积搜索空间,增强网络对可判别特征的关注度。其次,通过构建具有更多浅层特征输入节点的密集连接缩减单元(DCR cell),保留更多的浅层特征信息,减少可判别特征信息的损失并促进多尺度特征融合。最后,在堆叠最佳cell时调整DCR cell的位置,构建参数量大小不一的网络模型,以便在更多的终端设备上部署。结果表明,该方法耗时4.5 h搜索到了最佳神经网络模型,在Oxford 102和Flower 17上的分类准确率分别为96.14%和94.12%。与AGNAS等方法相比,在Oxford 102上提高了1.40百分点,在Flower 17上提高了3.09百分点。

基于改进BiGRU的刀具磨损预测

针对双向门控循环神经网络(bidirectional gated recurrent unit,BiGRU)超参数难以确定以及对重要特征捕捉能力较弱的问题,提出了一种改进模型用于刀具磨损预测。模型采用经过下采样的多通道传感器数据作为输入,使用随机搜索算法自适应的确定深度学习模型的最优超参数组合,并引入注意力机制与指数搜索算法增强对全局特征与局部趋势的捕捉能力。模型在PHM2010数据集上进行了实验验证,结果表明,该方法可快速确定超参数组合,并获得更稳定的预测值,具有更好的综合性能。

融合边界处理机制的学习型麻雀搜索算法

为改善麻雀搜索算法(SSA)初始化阶段种群分布不充分,寻优过程中容易受到局部最优解干扰的不足,提出融合边界处理机制的学习型麻雀搜索算法(HSSA)。使用Piecewise map初始化种群,提高种群的分散程度;使用排序配对学习与竞争学习策略分别更新跟随者和警戒者,确保各代的最优解信息能够引导下一代的位置更新;自适应的警戒者数量使得警戒者作用被强调,提供灵活的应变机制;根据不同阶段的寻优特点制定多策略边界处理机制,保留住种群数量的同时,为超出边界的个体提供更加合理的搜索位置。经过12个基准函数的仿真实验,并借助消融实验、Wilcoxon秩和检验等证明了HSSA在收敛速度上的稳定性和寻优的高效性。