刘 钊,孙洁娣,温江涛.基于多层面压缩深度神经网络的轴承故障诊断[J].电子测量与仪器学报,2022,36(7):189-198 |
基于多层面压缩深度神经网络的轴承故障诊断 |
Bearing fault diagnosis method based on multi-dimensioncompressed deep neural network |
|
DOI: |
中文关键词: 轴承故障诊断 深度学习 模型压缩 网络剪枝 参数量化 |
英文关键词:bearing fault diagnosis deep learning model compression network pruning parameter quantification |
基金项目:河北省自然科学基金(E2020203061)项目资助 |
|
|
摘要点击次数: 651 |
全文下载次数: 780 |
中文摘要: |
针对在资源有限的工业环境中难以应用基于深度神经网络的故障诊断模型的问题,提出一种压缩深度神经网络的轴承
故障诊断方法,将结构化剪枝、非结构化剪枝、参数量化及矩阵压缩多层面处理相结合,实现了网络多级压缩。 首先用结构化剪
枝剔除卷积层中输出低秩特征图对应的滤波器;再用非结构化剪枝去除全连接层中非重要性连接;最后通过对权重矩阵的参数
量化减少参数表示所需比特数,并结合权值矩阵压缩存储方法进一步减小了网络的参数存储量。 实验表明提出的压缩方法在
保证较高诊断准确率的前提下,极大减少了网络的参数存储量和浮点运算量,缩短了网络训练时间,加快了网络响应速度,为深
度神经网络方法的工业实际应用进行了有益探索。 |
英文摘要: |
Aiming at the problem that it is difficult to apply the fault diagnosis model based on deep neural network in the industrial
environment with limited resources, a bearing fault diagnosis method based on compressed deep neural network was proposed. Firstly,
the filter corresponding to the output low-rank feature graph in the convolution layer is removed by structural pruning. Then unstructured
pruning was used to remove non-important connections in the whole connection layer. Finally, the number of bits required for parameter
representation is reduced by quantizing the parameters of the weight matrix, and the storage of parameters is further reduced by using the
compression storage method of the weight matrix. Experimental results show that the proposed compression method can greatly reduce the
parameter storage and floating point computation of the network, shorten the training time of the network and speed up the response of the
network on the premise of high diagnostic accuracy, which provides a beneficial exploration for the industrial application of the deep
neural network method. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|