hazedt/phmgnnbenchmark

this code library is mainly about applying graph neural networks to intelligent diagnostic and prognostic.

phmgnnbenchmark's Issues

about test.py

Hi, Authors！
I wonder if the testing is included in the code. I only saw the training is in the Python file named train_graph_diagnosis.
If the testing is included in the code, could you please tell me which file the corresponding code for testing is in?
Thank you!!

consult testing

Hi, Authors！
I wonder if the testing is included in the code. I only saw the training is in the Python file named train_graph_diagnosis.
If the testing is included in the code, could you please tell me which file the corresponding code for testing is in?
Thank you!!

Hierarchical attention graph convolutional network to fuse multi-sensor signals for remaining useful life prediction

作者您好，这篇论文有参考代码嘛？

请问一下那个如何将原始的数据集转换成图所需要的数据集

Self-collected datasets are invalid

Self-collected datasets are invalid, can you reupload this dataset?

utils\train_graph_utils.py的bug

作者您好，标题的文件中for data in self.dataloaders[phase]:这行代码报错，原因为RuntimeError: The 'data' object was created by an older version of PyG. If this error occurred while loading an already existing dataset, remove the 'processed/' directory in the dataset's root folder and try again.
请问是PyG的版本太高了吗，我用的PyG版本为2.0.1,盼回复！

初学小白不知道如何运行

我在第一次运行的时候train_graph_diagnosis.py 报错
FileNotFoundError: [WinError 3] 系统找不到指定的路径。: './checkpoint\Node_ChebyNet_XJTUGearboxKnn_TD_1102-153115'

运行train_graph_prognosis.py 报错
FileNotFoundError: [Errno 2] No such file or directory: './data/CMAPSS/edge_index_FD001.npy'

图片节点的图分类及传感器的选择问题

作者您好，如果每个节点的输入形式是图片（目前主流算法好像都是默认每个节点的特征都是向量形式的），有没有办法直接对这些图片节点进行类似图卷积的操作，然后再进行graph级别的分类呢？
另外一个问题是如果想要对图上的节点（传感器）进行筛选，这个任务目前有相关办法解决嘛？

train_graph_diagnosis.py

作者您好，代码里缺少了 train_graph_diagnosis.py 文件

预处理CMAPSS数据集

作者您好，想问一下对于CMAPSS寿命预测数据集，如何对其进行预处理得到相应的 edge_index_FD001.npy 和 train_FD001.pkl 文件？有源代码嘛？

Hierarchical attention graph convolutional network to fuse multi-sensor signals for remaining useful life prediction

作者您好，拜读完您的相关论文，收获颇丰。想要复现一下《Hierarchical attention graph convolutional network to fuse multi-sensor signals for remaining useful life prediction》，但是一些部分还有些问题，不知能否分享一下源码？非常感谢，别无他用，仅用于学术研究！

《The emerging graph neural networks for intelligent fault diagnostics and prognostics》

作者您好，《The emerging graph neural networks for intelligent fault diagnostics and prognostics》这篇文章目前在网上还找不到，如果方便的话可以发一份给我嘛？[email protected]，谢谢。另外，有一些关于图网络在多源传感器融合方向的问题想向您咨询一下，希望能加一下您的微信？我的微信号是13218013195