针对现有基于深度学习的滚动轴承故障诊断方法存在准确度不高、泛化性较差的缺点,提出了一种基于SConvNeXt-ECMS(the ConvNeXt network based on shuffled convolution-efficient channel and multi-scale spatial attention module)与D...针对现有基于深度学习的滚动轴承故障诊断方法存在准确度不高、泛化性较差的缺点,提出了一种基于SConvNeXt-ECMS(the ConvNeXt network based on shuffled convolution-efficient channel and multi-scale spatial attention module)与DBO-RELM(dung beetleoptimizer regularized extreme learning machine)的滚动轴承故障诊断模型。将ECMS注意力机制与分流卷积模块融入ConvNeXt网络,提升ConvNeXt网络的特征提取能力;使用蜣螂优化算法完成参数寻优后的RELM替换网络原有分类层,提升网络对相近特征的分辨能力;利用哈尔滨工业大学航空轴承故障数据集仿真实验,验证所提分流卷积对ConvNeXt网络的提升效果;使用帕德博恩大学数据集进行滚动轴承混合故障诊断实验,验证所提SConvNeXt-ECMS与DBO-RELM模型的分类效果。仿真实验结果表明:所提SConvNeXt网络在航空轴承故障分类任务中,准确率可达100%,优于其他现有网络;帕德博恩大学滚动轴承混合故障诊断实验表明,所提ECMS注意力机制以及DBO-RELM方法均对原网络的性能有进一步的提升,新模型对滚动轴承混合故障的诊断准确率最高可达99.94%,相较于其他现有的滚动轴承故障诊断模型,均具有更高的故障诊断准确率和更强的泛化能力。展开更多
In disaster relief operations,multiple UAVs can be used to search for trapped people.In recent years,many researchers have proposed machine le arning-based algorithms,sampling-based algorithms,and heuristic algorithms...In disaster relief operations,multiple UAVs can be used to search for trapped people.In recent years,many researchers have proposed machine le arning-based algorithms,sampling-based algorithms,and heuristic algorithms to solve the problem of multi-UAV path planning.The Dung Beetle Optimization(DBO)algorithm has been widely applied due to its diverse search patterns in the above algorithms.However,the update strategies for the rolling and thieving dung beetles of the DBO algorithm are overly simplistic,potentially leading to an inability to fully explore the search space and a tendency to converge to local optima,thereby not guaranteeing the discovery of the optimal path.To address these issues,we propose an improved DBO algorithm guided by the Landmark Operator(LODBO).Specifically,we first use tent mapping to update the population strategy,which enables the algorithm to generate initial solutions with enhanced diversity within the search space.Second,we expand the search range of the rolling ball dung beetle by using the landmark factor.Finally,by using the adaptive factor that changes with the number of iterations.,we improve the global search ability of the stealing dung beetle,making it more likely to escape from local optima.To verify the effectiveness of the proposed method,extensive simulation experiments are conducted,and the result shows that the LODBO algorithm can obtain the optimal path using the shortest time compared with the Genetic Algorithm(GA),the Gray Wolf Optimizer(GWO),the Whale Optimization Algorithm(WOA)and the original DBO algorithm in the disaster search and rescue task set.展开更多
随着各种新型雷达的出现或战时预留模式的采用,真实的战场电磁环境将越加复杂,大概率会出现种类未知且参数突变的雷达调制信号,对现有的调制方式识别算法带来严峻挑战。对此,分析雷达调制方式“未知”对识别结果的影响机理,将开集差分...随着各种新型雷达的出现或战时预留模式的采用,真实的战场电磁环境将越加复杂,大概率会出现种类未知且参数突变的雷达调制信号,对现有的调制方式识别算法带来严峻挑战。对此,分析雷达调制方式“未知”对识别结果的影响机理,将开集差分分布对齐(distribution alignment with open set difference,DAOD)算法引入雷达调制方式识别领域,设计具体应用的技术方案,并针对DAOD算法所需参数依靠先验知识或者试探选取问题,利用蜣螂优化(dung beetle optimizer,DBO)算法进行参数优化。仿真结果表明:在单个雷达调制方式未知情形下,精确度Accuracy和F-measure分值的平均值分别可达91.34%和95.11%;在多个雷达调制方式未知情形下,Accuracy和F-measure的平均值分别可达91.37%、93.69%;与DAOD算法相比,上述结果分别提升了3.77%、1.83%、21.17%和12.06%。因此,DBO-DAOD算法可有效提升未知雷达调制方式的识别率。展开更多
基金supported by the National Natural Science Foundation of China(No.62373027).
文摘In disaster relief operations,multiple UAVs can be used to search for trapped people.In recent years,many researchers have proposed machine le arning-based algorithms,sampling-based algorithms,and heuristic algorithms to solve the problem of multi-UAV path planning.The Dung Beetle Optimization(DBO)algorithm has been widely applied due to its diverse search patterns in the above algorithms.However,the update strategies for the rolling and thieving dung beetles of the DBO algorithm are overly simplistic,potentially leading to an inability to fully explore the search space and a tendency to converge to local optima,thereby not guaranteeing the discovery of the optimal path.To address these issues,we propose an improved DBO algorithm guided by the Landmark Operator(LODBO).Specifically,we first use tent mapping to update the population strategy,which enables the algorithm to generate initial solutions with enhanced diversity within the search space.Second,we expand the search range of the rolling ball dung beetle by using the landmark factor.Finally,by using the adaptive factor that changes with the number of iterations.,we improve the global search ability of the stealing dung beetle,making it more likely to escape from local optima.To verify the effectiveness of the proposed method,extensive simulation experiments are conducted,and the result shows that the LODBO algorithm can obtain the optimal path using the shortest time compared with the Genetic Algorithm(GA),the Gray Wolf Optimizer(GWO),the Whale Optimization Algorithm(WOA)and the original DBO algorithm in the disaster search and rescue task set.
文摘随着各种新型雷达的出现或战时预留模式的采用,真实的战场电磁环境将越加复杂,大概率会出现种类未知且参数突变的雷达调制信号,对现有的调制方式识别算法带来严峻挑战。对此,分析雷达调制方式“未知”对识别结果的影响机理,将开集差分分布对齐(distribution alignment with open set difference,DAOD)算法引入雷达调制方式识别领域,设计具体应用的技术方案,并针对DAOD算法所需参数依靠先验知识或者试探选取问题,利用蜣螂优化(dung beetle optimizer,DBO)算法进行参数优化。仿真结果表明:在单个雷达调制方式未知情形下,精确度Accuracy和F-measure分值的平均值分别可达91.34%和95.11%;在多个雷达调制方式未知情形下,Accuracy和F-measure的平均值分别可达91.37%、93.69%;与DAOD算法相比,上述结果分别提升了3.77%、1.83%、21.17%和12.06%。因此,DBO-DAOD算法可有效提升未知雷达调制方式的识别率。
