code.py是MSCNN结合LSTM结合注意力机制模型诊断程序 XTJU是数据集文件夹(因为西安交大转子数据量太大,因此这里分别选取了工况1下的Bearing1_1文件夹下的2.CVS文件作为outer(外圈故障)数据,选取工况1下的Bearing1_4文件夹下的2.CVS文件作为roller(滚动体故障)数据,选取工况2下的Bearing2_1文件夹下的2.CVS文件作为...
version.py是查看你本地环境库的版本,为了方便你运行代码写的脚本 MSCNN_LSTM_Attention.py是读取原始数据,预处理,磨损状态分类的主程序。 数据量较大,因为本地电脑配置一般, 所以只用了c1数据集进行实验,只需要修改数据集路径,也可以调用c2-c6数据集。 数据集一共有315个表格 数据集开始位置 编辑 数据集截止...
(MSCNN)and Long Short-Term Memory(LSTM)fused with attention mechanism is proposed.To adaptively extract the essential spatial feature information of various sizes,the model creates a multi-scale feature extraction module using the convolutional neural network(CNN)learning process.The learning capacity of...
According to news reporting out of Changchun, People's Republicof China, by NewsRx editors, research stated, "To improve the recognition rate of ultra-weak fiber Bragggrating (UWFBG) arrays in perimeter security monitoring, this paper proposes a msCNN-LSTM combinatorialmodel recognition method, ...
东南大学齿轮箱故障诊断(Python代码,MSCNN结合LSTM结合注意力机制模型,代码有注释) 深度学习奋斗者 运行代码要求:代码运行环境要求:Keras版本>=2.4.0,python版本>=3.6.0 1.东南大学采集数据平台:数据 该数据集包含2个子数据集,包括轴承数据和齿轮数据,这两个子数据集都是在传动系动力学模拟器(DDS)上获取的。(...
2.模型 首先经过尝试,发现第3个振动通道采集的数据对故障更加敏感,这里只选用了第3个振动通道采集的数据作为特征信号。经过重叠采样(1024的长度)切割。 模型采用的就是一维MSCNN结合LSTM结合Attention模型 实验效果(训练集与测试集比例为4:1)
This paper proposes the MSCNN-LSTM-CBAM-SE model for gearbox fault diagnosis, which integrates MSCNN and long short-term memory networks (LSTM). This combination not only effectively extracts and integrates multi-scale spatio-temporal features, but also learns the global dependencies in sequential dat...
Finally, XGBoost and MSCNN combine the advantages of LSTM in dealing with time series. Genetic algorithm (GA) is applied to optimize the parameter set of long-term and short-term memory network (LSTM) network. The spatio-temporal relationship of multi-features is input into LSTM network, and ...