滚动轴承作为机械设备的重要部件,对其进行剩余使用寿命预测在企业的生产过程中变得越来越重要。目前,虽然主流的卷积神经网络(convolutional neural network, CNN)可以自动地从轴承的振动信号中提取特征,却不能给特征分配不同的权重来...滚动轴承作为机械设备的重要部件,对其进行剩余使用寿命预测在企业的生产过程中变得越来越重要。目前,虽然主流的卷积神经网络(convolutional neural network, CNN)可以自动地从轴承的振动信号中提取特征,却不能给特征分配不同的权重来提高模型对重要特征的关注程度,对于长时间序列容易丢失重要信息。另外,神经网络中隐藏层神经元个数、学习率以及正则化参数等超参数还需要依靠人工经验设置。为了解决上述问题,提出基于灰狼优化(grey wolf optimizer, GWO)算法、优化集合CNN、双向长短期记忆(bidirectional long short term memory, BiLSTM)网络和注意力机制(Attention)轴承剩余使用寿命预测方法。首先,从原始振动信号中提取时域、频域以及时频域特征指标构建可选特征集;然后,通过构建考虑特征相关性、鲁棒性和单调性的综合评价指标筛选出高于设定阈值的轴承退化敏感特征集,作为预测模型的输入;最后,将预测值和真实值的均方误差作为GWO算法的适应度函数,优化预测模型获得最优隐藏层神经元个数、学习率和正则化参数,利用优化后模型进行剩余使用寿命预测,并在公开数据集上进行验证。结果表明,所提方法可在非经验指导下获得最优的超参数组合,优化后的预测模型与未进行优化模型相比,平均绝对误差与均方根误差分别降低了28.8%和24.3%。展开更多
针对基本灰狼算法存在初始种群不均匀、早熟收敛等问题,基于混沌理论从三个方面对灰狼优化(grey wolf optimization,GWO)算法进行改进,提出了混沌灰狼优化(chaotic grey wolf optimization,CGWO)算法用于确定边坡的最小安全系数.首先,...针对基本灰狼算法存在初始种群不均匀、早熟收敛等问题,基于混沌理论从三个方面对灰狼优化(grey wolf optimization,GWO)算法进行改进,提出了混沌灰狼优化(chaotic grey wolf optimization,CGWO)算法用于确定边坡的最小安全系数.首先,采用改进Tent混沌映射提高初始种群多样性;其次,通过混沌扰动策略避免算法陷入局部最优;最后,引入参数混沌非线性调节机制均衡算法的全局开发和局部勘探算力.13个基准测试函数的仿真结果表明,改进后的算法与基本GWO,WOA,PSO以及SCA相比具有更强的综合寻优性能.选取ACADS边坡考核题进行计算分析,CGWO算法表现出较高的计算精度和收敛速度,能够有效地搜索到复杂分层边坡的最小安全系数.对比有限元强度折减法,该方法具有操作简易、搜索区域易于设置等优点.展开更多
Nowadays,wireless communication devices turn out to be transportable owing to the execution of the current technologies.The antenna is the most important component deployed for communication purposes.The antenna plays...Nowadays,wireless communication devices turn out to be transportable owing to the execution of the current technologies.The antenna is the most important component deployed for communication purposes.The antenna plays an imperative role in receiving and transmitting the signals for any sensor network.Among varied antennas,micro strip fractal antenna(MFA)significantly contributes to increasing antenna gain.This study employs a hybrid optimization method known as the elephant clan updated grey wolf algorithm to introduce an optimized MFA design.This method optimizes antenna characteristics,including directivity and gain.Here,the factors,including length,width,ground plane length,height,and feed offset-X and feed offset-Y,are taken into account to achieve the best performance of gain and directivity.Ultimately,the superiority of the suggested technique over state-of-the-art strategies is calculated for various metrics such as cost and gain.The adopted model converges to a minimal value of 0.2872.Further,the spider monkey optimization(SMO)model accomplishes the worst performance over all other existing models like elephant herding optimization(EHO),grey wolf optimization(GWO),lion algorithm(LA),support vector regressor(SVR),bacterial foraging-particle swarm optimization(BF-PSO)and shark smell optimization(SSO).Effective MFA design is obtained using the suggested strategy regarding various parameters.展开更多
文摘滚动轴承作为机械设备的重要部件,对其进行剩余使用寿命预测在企业的生产过程中变得越来越重要。目前,虽然主流的卷积神经网络(convolutional neural network, CNN)可以自动地从轴承的振动信号中提取特征,却不能给特征分配不同的权重来提高模型对重要特征的关注程度,对于长时间序列容易丢失重要信息。另外,神经网络中隐藏层神经元个数、学习率以及正则化参数等超参数还需要依靠人工经验设置。为了解决上述问题,提出基于灰狼优化(grey wolf optimizer, GWO)算法、优化集合CNN、双向长短期记忆(bidirectional long short term memory, BiLSTM)网络和注意力机制(Attention)轴承剩余使用寿命预测方法。首先,从原始振动信号中提取时域、频域以及时频域特征指标构建可选特征集;然后,通过构建考虑特征相关性、鲁棒性和单调性的综合评价指标筛选出高于设定阈值的轴承退化敏感特征集,作为预测模型的输入;最后,将预测值和真实值的均方误差作为GWO算法的适应度函数,优化预测模型获得最优隐藏层神经元个数、学习率和正则化参数,利用优化后模型进行剩余使用寿命预测,并在公开数据集上进行验证。结果表明,所提方法可在非经验指导下获得最优的超参数组合,优化后的预测模型与未进行优化模型相比,平均绝对误差与均方根误差分别降低了28.8%和24.3%。
文摘针对基本灰狼算法存在初始种群不均匀、早熟收敛等问题,基于混沌理论从三个方面对灰狼优化(grey wolf optimization,GWO)算法进行改进,提出了混沌灰狼优化(chaotic grey wolf optimization,CGWO)算法用于确定边坡的最小安全系数.首先,采用改进Tent混沌映射提高初始种群多样性;其次,通过混沌扰动策略避免算法陷入局部最优;最后,引入参数混沌非线性调节机制均衡算法的全局开发和局部勘探算力.13个基准测试函数的仿真结果表明,改进后的算法与基本GWO,WOA,PSO以及SCA相比具有更强的综合寻优性能.选取ACADS边坡考核题进行计算分析,CGWO算法表现出较高的计算精度和收敛速度,能够有效地搜索到复杂分层边坡的最小安全系数.对比有限元强度折减法,该方法具有操作简易、搜索区域易于设置等优点.
文摘Nowadays,wireless communication devices turn out to be transportable owing to the execution of the current technologies.The antenna is the most important component deployed for communication purposes.The antenna plays an imperative role in receiving and transmitting the signals for any sensor network.Among varied antennas,micro strip fractal antenna(MFA)significantly contributes to increasing antenna gain.This study employs a hybrid optimization method known as the elephant clan updated grey wolf algorithm to introduce an optimized MFA design.This method optimizes antenna characteristics,including directivity and gain.Here,the factors,including length,width,ground plane length,height,and feed offset-X and feed offset-Y,are taken into account to achieve the best performance of gain and directivity.Ultimately,the superiority of the suggested technique over state-of-the-art strategies is calculated for various metrics such as cost and gain.The adopted model converges to a minimal value of 0.2872.Further,the spider monkey optimization(SMO)model accomplishes the worst performance over all other existing models like elephant herding optimization(EHO),grey wolf optimization(GWO),lion algorithm(LA),support vector regressor(SVR),bacterial foraging-particle swarm optimization(BF-PSO)and shark smell optimization(SSO).Effective MFA design is obtained using the suggested strategy regarding various parameters.
