检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:孙豫[1] 张雷[2] 周凯 SUN Yu;ZHANG Lei;ZHOU Kai(School of Information Engineering,Zhumadian Vocational and Technical College,Zhumadian 463000;Office of Laboratory and Equipment Management,Shihezi University,Shihezi 832000;China National Machinery Industry Corporation,Beijing 100055)
机构地区:[1]驻马店职业技术学院信息工程学院,河南驻马店463000 [2]石河子大学实验室与设备管理处,新疆石河子832000 [3]中国机械设备工程股份有限公司,北京100055
出 处:《制造业自动化》2025年第1期89-95,共7页Manufacturing Automation
基 金:国家自然科学基金(52175240);校级科研项目(0183/KX000201)。
摘 要:对轴承故障类型的准确诊断有利于提高设备可靠性和效率,在早期诊断和预测故障方面开展研究具有重要意义。目前有一部分诊断方法通过手动提取故障特征进行分类,另一部分使用神经网络的诊断方法,但缺乏网络自适应调参的能力,泛化能力不足。因此提出使用遗传算法优化卷积神经网络进行故障诊断,其中一维卷积神经网络可以提取轴承故障信号中的微弱特征,使用遗传算法对卷积神经网络的网络参数进行自适应调参,提高了模型的诊断精度和泛化能力。实验结果表明,该模型的诊断平均准确率为98.56%,比传统的诊断方法1d-CNN、MLP和SVM分别提高了3.26%,10.45%,13.72%。The accurate diagnosis of bearing fault types is crucial for improving equipment reliability and efficiency,and carries a great significance for conducting research in early diagnosis and prediction of fault.Currently,there are two main approaches in this research.One approach involves the manual extraction of fault features for classification,while the other utilizes the neural networks for diagnosis,which tends to lack the capability of adaptive parameter tuning,resulting in limited generalization performance.Therefore,this paper proposes the utilization of the genetic algorithm to optimize the convolutional neural network for fault diagnosis,where the 1d-CNN can extract subtle features from the bearing vibration signals and employ a genetic algorithm for adaptive parameter tuning,thus enhancing the diagnostic accuracy and generalization capability of the model.Experimental results demonstrate that the proposed method achieves an average diagnosis accuracy of 98.56%,outperforming the traditional methods,namely 1d-CNN,MLP,and SVM,by 3.26%,10.45%,and 13.72%,respectively.These results highlight the superior performance and accuracy of the improved 1d-CNN in bearing fault diagnosis.
分 类 号:TH133.33[机械工程—机械制造及自动化]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15