A Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller Model Combined with an Improved Particle Swarm Optimization Method for Fall Detection

In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible to unsafe events(such as falls)that can have disastrous consequences.However,automatically detecting falls fromvideo data is challenging,and automatic fall detection methods usually require large volumes of training data,which can be difficult to acquire.To address this problem,video kinematic data can be used as training data,thereby avoiding the requirement of creating a large fall data set.This study integrated an improved particle swarm optimization method into a double interactively recurrent fuzzy cerebellar model articulation controller model to develop a costeffective and accurate fall detection system.First,it obtained an optical flow(OF)trajectory diagram from image sequences by using the OF method,and it solved problems related to focal length and object offset by employing the discrete Fourier transform(DFT)algorithm.Second,this study developed the D-IRFCMAC model,which combines spatial and temporal(recurrent)information.Third,it designed an IPSO(Improved Particle Swarm Optimization)algorithm that effectively strengthens the exploratory capabilities of the proposed D-IRFCMAC(Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller)model in the global search space.The proposed approach outperforms existing state-of-the-art methods in terms of action recognition accuracy on the UR-Fall,UP-Fall,and PRECIS HAR data sets.The UCF11 dataset had an average accuracy of 93.13%,whereas the UCF101 dataset had an average accuracy of 92.19%.The UR-Fall dataset had an accuracy of 100%,the UP-Fall dataset had an accuracy of 99.25%,and the PRECIS HAR dataset had an accuracy of 99.07%.

Multi-target Collaborative Combat Decision-Making by Improved Particle Swarm Optimizer

A decision-making problem of missile-target assignment with a novel particle swarm optimization algorithm is proposed when it comes to a multiple target collaborative combat situation.The threat function is established to describe air combat situation.Optimization function is used to find an optimal missile-target assignment.An improved particle swarm optimization algorithm is utilized to figure out the optimization function with less parameters,which is based on the adaptive random learning approach.According to the coordinated attack tactics,there are some adjustments to the assignment.Simulation example results show that it is an effective algorithm to handle with the decision-making problem of the missile-target assignment(MTA)in air combat.

基于VMD-LSTM-IPSO-GRU的电力负荷预测

为了挖掘电力负荷数据中的潜藏信息,提高短期负荷预测的精度,针对电力负荷强非线性、非平稳性等特点,提出一种基于变分模态分解(variational mode decomposition,VMD)、长短时记忆神经网络(long-term and short-term memory network,LSTM)、改进的粒子群算法(improve particle swarm optimization,IPSO)和门控循环单元(gated recurrent unit neural network,GRU)的混合预测模型。首先,使用相关性分析确定输入因素,再将负荷数据运用VMD算法结合样本熵分解为一系列本征模态分量(intrinsic mode fuction,IMF)和残差量,进而合理地确定分解层数和惩罚因子;其次,根据过零率将这些量划分为低频和高频,低频分量使用LSTM网络,高频分量利用IPSO-GRU网络分别进行预测;最后,将预测结果重构得到电力负荷的最终结果。仿真结果表明:相对于其他模型,所提混合模型可有效的提取模态特征,具有更高的预测精度。

Short-term Load Prediction of Integrated Energy System with Wavelet Neural Network Model Based on Improved Particle Swarm Optimization and Chaos Optimization Algorithm

To improve energy efficiency and protect the environment,the integrated energy system(IES)becomes a significant direction of energy structure adjustment.This paper innovatively proposes a wavelet neural network(WNN)model optimized by the improved particle swarm optimization(IPSO)and chaos optimization algorithm(COA)for short-term load prediction of IES.The proposed model overcomes the disadvantages of the slow convergence and the tendency to fall into the local optimum in traditional WNN models.First,the Pearson correlation coefficient is employed to select the key influencing factors of load prediction.Then,the traditional particle swarm optimization(PSO)is improved by the dynamic particle inertia weight.To jump out of the local optimum,the COA is employed to search for individual optimal particles in IPSO.In the iteration,the parameters of WNN are continually optimized by IPSO-COA.Meanwhile,the feedback link is added to the proposed model,where the output error is adopted to modify the prediction results.Finally,the proposed model is employed for load prediction.The experimental simulation verifies that the proposed model significantly improves the prediction accuracy and operation efficiency compared with the artificial neural network(ANN),WNN,and PSO-WNN.

Voltage Security Operation Region Calculation Based on Improved Particle Swarm Optimization and Recursive Least Square Hybrid Algorithm

Large-scale voltage collapse incidences, which result in power outages over large regions and extensive economic losses, are presently common occurrences worldwide. To avoid voltage collapse and operate more safely and reliably, it is necessary to analyze the voltage security operation region(VSOR) of power systems, which has become a topic of increasing interest lately. In this paper, a novel improved particle swarm optimization and recursive least square(IPSO-RLS) hybrid algorithm is proposed to determine the VSOR of a power system. Also, stability analysis on the proposed algorithm is carried out by analyzing the errors and convergence accuracy of the obtained results. Firstly, the voltage stability and VSOR-surface of a power system are analyzed in this paper. Secondly, the two algorithms,namely IPSO and RLS algorithms, are studied individually.Based on this understanding, a novel IPSO-RLS hybrid algorithm is proposed to optimize the active and reactive power,and the voltage allowed to identify the VSOR-surface accurately. Finally, the proposed algorithm is validated by using a simulation case study on three wind farm regions of actual Hami Power Grid of China in DIg SILENT/Power Factory software.The error and accuracy of the obtained simulation results are analyzed and compared with those of the particle swarm optimization(PSO), IPSO and IPSO-RLS hybrid algorithms.

基于IPSO-LSTM的新能源汽车锂电池健康状态监测

为监测新能源汽车锂电池的健康状态(SOH),防范电池故障引发安全事故风险,提出改进粒子群算法(IPSO)和长短期记忆(LSTM)神经网络相结合的模型,监测锂电池的SOH。首先,采用Spearman相关性分析法,提取锂电池SOH监测的健康因子;其次,采用线性惯性权重和非对称学习因子改进传统粒子群算法(PSO),利用IPSO算法对LSTM模型的隐含层神经元个数、神经元失活率、批处理值进行关键参数寻优,进一步优化LSTM模型,建立IPSO-LSTM锂电池SOH监测模型;最后,以新能源汽车主流采用的18650锂电池数据集验证IPSO-LSTM模型,并对比分析BP、LSTM和PSO-LSTM这3种模型。结果表明:IPSO-LSTM模型的平均绝对误差(MAE)在0.02以内、均方根误差(RMSE)在0.03以内,监测误差在15%以内,相较于BP、LSTM、PSO-LSTM模型,IPSO-LSTM模型的误差指标值均最小,模型具有更高的精度和稳定性。

基于IPSO算法的短期电力负荷预测模型研究

为有效减小短期电力负荷预测的预测误差,提高预测精度、缩短预测时间,应用改进粒子群优化(IPSO)算法建立了1种短期电力负荷预测模型。通过水平方向和垂直方向的平滑修正,对历史数据的异常负荷点进行识别并修正。利用相同日期类型正常负荷,计算缺失数据填充值。采用模糊化处理,计算日期类型、温度、天气隶属度函数,对短期负荷变化因素进行量化处理。将历史数据的负荷值和量化值作为训练数据。为避免粒子群优化(PSO)算法陷入局部最优,采用IPSO算法找到全局最优解,建立了短期负荷预测模型,实现了短期电力负荷预测。试验结果表明,所设计模型预测结果在休息日和工作日的最大相对误差值、平均相对误差值分别为0.97%、0.53%和0.99%、0.65%,能够有效减小预测误差、提高预测精度、缩短预测时间。该研究为电力系统相关人员进行负荷预测提供了参考。

基于CEEMDAN-IPSO-LSTM的城市轨道交通短时客流预测方法研究

消除客流数据随机噪声和确定神经网络超参数是城市轨道交通短时客流预测组合模型需要解决的关键问题。基于弱化客流数据噪声的自适应噪声完全集成经验模式分解算法(CEEMDAN)将客流时序数据分解为若干个频率和复杂度均不同的固有模态函数分量和剩余分量后,利用引入自适应策略的改进粒子群算法(IPSO)动态求解长短期记忆神经网络(LSTM)超参数的最优值,构建CEEMDAN-IPSO-LSTM组合模型预测城市轨道交通短时客流量。以广州地铁杨箕站自动售检票系统采集的历史进(出)站客流数据为例进行实验,研究结果表明:IPSO算法较PSO算法在基准测试函数Sphere,Sum Squars,Sum of Different Power,Rosenbrock,Rastigrin,Ackley,Griewank和Penalized上的最小值、最大值、平均值和标准差均更接近最佳优化值,CEEMDAN-IPSO-LSTM模型较LSTM模型、CEEMDAN-LSTM模型、CEEMDAN-PSO-LSTM模型的全月全日进(出)站的预测误差评价指标SD,RMSE,MAE和MAPE分别降低了12~40人次(13~35人次)、13~44人次(12~35人次)、6~37人次(12~31人次)和5.08%~46.89%(6.5%~35.1%),R和R2分别提高了0.07%~2.32%(0.86%~3.63%)和0.13%~2.19%(0.67%~1.67%),同时在工作日不同时段和非工作日全日的预测性能均达到最优效果。IPSO算法的收敛速度和参数寻优精度均优于PSO算法,且CEEMDAN-IPSO-LSTM模型可应用于城市轨道交通短时客流量的精确预测,同时可为设计规划线网路线、缓解交通压力、提高乘客出行服务质量等提供基础数据支撑。

经验小波变换和改进S变换结合的电能质量检测与识别方法

为分析不确定干扰因素影响下的实际电力网络电能质量问题,提出一种经验小波变换(EWT)和改进S变换相结合的电能质量检测与识别方法。该方法一方面利用EWT联合归一化直接正交(NDQ)算法和奇异值分解(SVD)算法准确提取调幅-调频分量的频率、幅值和时间参数,另一方面考虑到EWT算法在高噪声环境下瞬时幅值波动的问题,引入改进S变换提取高噪声干扰下的电能质量扰动时频信息,最后,基于EWT和改进S变换提取的扰动特征向量,利用基于改进粒子群优化算法(IPSO)优化支持向量机(SVM)的电能质量扰动识别分类器实现扰动类型的精确识别。仿真和实验表明所提方法在复合扰动识别分类时平均识别准确率为93.23%,且能够准确识别4种实测扰动信号。

XGRouter： high-quality global router in X-architecture with particle swarm optimization

This paper presents a high-quality very large scale integration （VLSI） global router in X-architecture, called XGRouter, that heavily relies on integer linear pro- gramming （ILP） techniques, partition strategy and particle swarm optimization （PSO）. A new ILP formulation, which can achieve more uniform routing solution than other formu- lations and can be effectively solved by the proposed PSO is proposed. To effectively use the new ILP formulation, a partition strategy that decomposes a large-sized problem into some small-sized sub-problems is adopted and the routing re- gion is extended progressively from the most congested re- git）n. In the post-processing stage of XGRouter, maze rout- ing based on new routing edge cost is designed to further optimize the total wire length and mantain the congestion uniformity. To our best knowledge, XGRouter is the first work to use a concurrent algorithm to solve the global rout- ing problem in X-architecture. Experimental results show that XGRouter can produce solutions of higher quality than other global routers. And, like several state-of-the-art global touters, XGRouter has no overflow.

基于IPSO-LSSVM的风电功率短期预测研究

风电功率预测的关键是预测模型的选择和模型性能的优化。选择最小二乘支持向量机(least squares support vector machine,LSSVM)作为风电功率预测模型,使用改进的粒子群算法(improved particle swarm optimization algorithm,IPSO)对影响最小二乘支持向量机回归性能的参数进行优化。在建立了改进的粒子群算法优化最小二乘支持向量机(LSSVM)的风电功率预测模型后,运用该模型对广西某风电场进行了仿真研究。为了对比研究,同时使用前馈(back propagation,BP)神经网络模型和支持向量机(support vector machine,SVM)模型进行了预测。最后采用多种误差指标对三种模型的预测结果进行综合分析。结果表明,使用改进的粒子群算法优化最小二乘向量机(IPSO-LSSVM)的风电功率预测模型具有较高的预测精度。

基于IPSO-BP的风电机组齿轮箱状态监测研究

将改进粒子群算法(IPSO)与BP神经网络相结合,建立齿轮箱正常工作状态下的温度模型并用其进行温度预测。通过合理地选择训练样本,使IPSO-BP模型覆盖齿轮箱的正常工作空间。当齿轮箱工作异常时,其动态特性偏离正常工作空间,导致IPSO-BP网络温度模型预测残差的分布特性发生变化。采用滑动窗口方法实时计算残差的统计分布特性,当残差的均值或标准差超过预先设定的阈值时,发出报警信息,提示运行人员检查设备状态。

基于BP神经网络的上海生鲜农产品物流需求预测

针对传统的生鲜农产品物流非线性需求预测模型收敛速度慢、精度低等问题,构建由改进粒子群(improved particle swarm optimization,IPSO)算法优化反向传播(back propagation,BP)神经网络的预测模型。引入对立学习机制、自适应惯性权重、非对称学习因子提升粒子群(particle swarm optimization,PSO)算法的初始解质量,平衡算法的局部开发和全局搜索能力;利用IPSO算法优化BP神经网络的权值和阈值,解决BP神经网络收敛速度慢、容易陷入局部最优等问题。通过上海生鲜农产品物流需求预测实例对模型的有效性进行验证,结果显示:IPSO-BP神经网络模型在预测精度及收敛速度上均明显优于传统PSO-BP神经网络和BP神经网络模型。

考虑多源协同的主动配电网故障恢复策略

随着科技的发展,主动配电网中面临了多项重要问题,首先,随着大量柔性负荷和电动汽车的接入,负荷种类显著多元化,增加了电网管理的复杂性。其次,可再生能源的随机性和波动性对电网的故障恢复提出了重要挑战。为了应对这些问题,研究提出了一种针对各种能源互动的主动配电网故障恢复策略。该策略建立了一个优化模型,以最大数量可控分布式电源行动和最小功率损失为目标,同时满足系统安全约束。为了建立该模型,使用了改进的二进制粒子群算法和遗传算法。通过在IEEE33节点配电网模型上的仿真分析,实验结果表明,该策略能够有效降低电网损失,并最大程度地恢复失电负荷,为面对可再生能源和多元化负荷挑战的电网管理提供了一种潜在的解决方案。

基于IPSO混沌支持向量机的网络流量预测研究

针对传统混沌支持向量机参数寻优算法的不足,提出了一种改进的粒子群(IPSO)算法。该算法通过延长迭代的开始阶段和最后阶段的搜索时间,实现了算法的全局搜索与局部搜索能力之间的平衡,进而优化模型参数,建立了基于IPSO优化的混沌支持向量机预测模型。应用实例结果表明,该模型对网络流量预测是有效可行的,并具有较高的寻优效率、预测精度和较好的稳态性能。

基于IPSO-BP神经网络的坝基扬压力预测方法研究

针对坝基扬压力预测的传统BP神经网络模型初始权值和阈值随机性强、易陷入局部最优等局限,采用惯性权重动态调整的改进粒子群算法对BP网络的初始权值和阈值进行优化,建立了基于IPSO的BP神经网络坝基扬压力预测模型.通过算例验证算法的优越性及程序的准确性,并以某大坝多年扬压力监测数据进行工程实例应用,结果表明,IPSO-BP扬压力预测模型与传统BP模型相比,拟合相关系数大,统计误差小,预测精度更高.

基于粒子群算法的瞬变电磁检测小车结构优化

利用瞬变电磁法进行管道移动检测的过程中,经常由于检测设备抖动造成检测信号的误差或检测失败。为此,设计了一款可搭载瞬变电磁检测设备的自动检测小车。基于检测小车和埋地管道检测的工作要求,进行可变线圈搭载平台和减震机构设计,并利用解析法对弹簧阻尼器的刚度系数和阻尼系数进行优化。基于ANSYS Workbench软件对上摆臂和车轮连接件进行拓扑优化。基于减震机构的关键零件下摆臂对整体性能的影响,利用CCD中心组合试验法,进行仿真试验设计取得数据,并利用响应面法得出最大应力和质量与下摆臂设计参数的映射关系。采用粒子群算法对映射关系进行优化设计,获得最大应力和质量最小时的下摆臂参数。优化结果表明:采用Adams对优化后的检测小车进行运动学仿真,小车平台质心在竖直方向上位移和速度的峰值分别降低约55.7%和26.5%,均值分别降低约67.9%和24.2%,波动的次数也明显减少,检测小车性能显著增强。所得结论可为检测小车设计提供理论参考,对管道缺陷检测领域具有一定的工程意义。

应用IPSO的无线传感器网络分簇路由算法

在基于分簇的无线传感器网络中,网络是通过附近传感器节点在转发信息到目的节点前进行冗余数据的融合实现节能,从而延长了网络的生命周期。但现存的算法在选择簇首节点的过程中由于忽略了邻居节点的状态信息,容易导致簇内节点过早出现盲节点的现象。进化类算法已经成功应用于许多方面,微粒群算法就是其中之一。提出了一种基于改进型微粒群算法的无线传感器网络分簇路由算法来优化分簇过程。簇首节点的选取综合考虑候选节点和邻居节点的状态信息。仿真结果表明算法的性能得到了较好的改善,并延长了网络的生命周期。

桩筏(箱)基础沉降多步预测控制的IPSO-Elman算法

将改进的粒子群优化(IPSO)算法与Elman神经网络进行了有机结合,形成了IPSO-Elman混合算法.建立桩筏(箱)基础沉降变形期望输出与超前预测输出之间的非线性隐式方程,避开了复杂的岩土工程本构关系和力学参数计算问题.提出的多步预测控制方法,具有很好的全局识别特点和较高的推广预测能力.工程实例分析表明,IPSO-Elamn算法在桩筏(箱)基础沉降的非线性系统动态辨识和在线预测应用方面,具有良好的预测精度,满足工程实际需要.

基于自适应变分模态分解的组合模型风电功率预测

风电机组出力的高波动与随机性,影响电力系统安全稳定运行与风电预测精度,针对此提出结合风电功率波动特性研究的风电功率预测方法。首先从时间与机组规模尺度分析风电功率波动特性,并指导选取合适的风电数据用于风电功率预测;然后建立基于最小二乘支持向量机的风电机组短期功率预测模型,采用自适应变分模态分解实现风电数据分频,并采用改进粒子群优化最小二乘支持向量机模型中影响回归预测的模型参数。实验结果表明,预测模型自适应性较强,通过预测误差评价指标,可证明预测方法的有效性。