To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network mo...To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.展开更多
A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very co...A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very complicated,and the fault characteristic signal is weak and hard to extract.Firstly,the best wavelet base Cmor 3-3 is selected by comparing 6 different wavelet base types.Secondly,continuous wavelet transform(CWT)is applied to the acquired original vibration signal to generate the feature map and process the gray level.Finally,the improved ResNeXt network is used to diagnose faults in precision machining equipment.The experimental results show that the proposed CWT and the improved ResNeXt algorithm have high accuracy in identifying precision machining equipment faults in complex environments,with an average accuracy of 99.4%。展开更多
针对风机滚动轴承故障诊断需要提取大量复杂特征,提出一种基于注意力机制、ResNext网络和长短时记忆(Long Short Term Memory,LSTM)网络的并行轴承故障诊断模型。首先,将采集的一维振动信号进行预处理;然后,分两路输入到模型中提取特征...针对风机滚动轴承故障诊断需要提取大量复杂特征,提出一种基于注意力机制、ResNext网络和长短时记忆(Long Short Term Memory,LSTM)网络的并行轴承故障诊断模型。首先,将采集的一维振动信号进行预处理;然后,分两路输入到模型中提取特征,其中一路输入到嵌入注意力机制的ResNext模块中,注意力机制可以增加重要特征的权重,减少模型运算量,另一路输入到LSTM网络中提取振动信号在时间序列上的依赖关系;最后,将两路提取到的特征进行融合输入到Softmax层进行故障分类。实验结果表明,与目前基于深度学习的轴承故障诊断方法相比,所提方法在轴承故障分类准确率上表现更好。展开更多
基金supported by National Natural Science Foundation of China(No.61862037)Lanzhou Jiaotong University Tianyou Innovation Team Project(No.TY202002)。
文摘To solve the problems of redundant feature information,the insignificant difference in feature representation,and low recognition accuracy of the fine-grained image,based on the ResNeXt50 model,an MSFResNet network model is proposed by fusing multi-scale feature information.Firstly,a multi-scale feature extraction module is designed to obtain multi-scale information on feature images by using different scales of convolution kernels.Meanwhile,the channel attention mechanism is used to increase the global information acquisition of the network.Secondly,the feature images processed by the multi-scale feature extraction module are fused with the deep feature images through short links to guide the full learning of the network,thus reducing the loss of texture details of the deep network feature images,and improving network generalization ability and recognition accuracy.Finally,the validity of the MSFResNet model is verified using public datasets and applied to wild mushroom identification.Experimental results show that compared with ResNeXt50 network model,the accuracy of the MSFResNet model is improved by 6.01%on the FGVC-Aircraft common dataset.It achieves 99.13%classification accuracy on the wild mushroom dataset,which is 0.47%higher than ResNeXt50.Furthermore,the experimental results of the thermal map show that the MSFResNet model significantly reduces the interference of background information,making the network focus on the location of the main body of wild mushroom,which can effectively improve the accuracy of wild mushroom identification.
基金Funding from the Key Research and development plan of Shaanxi Province"Research on key problems of surface finishing for Aerospace Fastener"(2023-YBGY-386).
文摘A fault diagnosis method based on continuous wavelet transform and improved multi-dimensional residual network was proposed to solve the problem that the working environment of precision machining equipment is very complicated,and the fault characteristic signal is weak and hard to extract.Firstly,the best wavelet base Cmor 3-3 is selected by comparing 6 different wavelet base types.Secondly,continuous wavelet transform(CWT)is applied to the acquired original vibration signal to generate the feature map and process the gray level.Finally,the improved ResNeXt network is used to diagnose faults in precision machining equipment.The experimental results show that the proposed CWT and the improved ResNeXt algorithm have high accuracy in identifying precision machining equipment faults in complex environments,with an average accuracy of 99.4%。
文摘针对风机滚动轴承故障诊断需要提取大量复杂特征,提出一种基于注意力机制、ResNext网络和长短时记忆(Long Short Term Memory,LSTM)网络的并行轴承故障诊断模型。首先,将采集的一维振动信号进行预处理;然后,分两路输入到模型中提取特征,其中一路输入到嵌入注意力机制的ResNext模块中,注意力机制可以增加重要特征的权重,减少模型运算量,另一路输入到LSTM网络中提取振动信号在时间序列上的依赖关系;最后,将两路提取到的特征进行融合输入到Softmax层进行故障分类。实验结果表明,与目前基于深度学习的轴承故障诊断方法相比,所提方法在轴承故障分类准确率上表现更好。
