The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study. Li, T., Zhou, Z., Li, S., Sun, C., Yan, R., & Chen, X. Mechanical Systems and Signal Processing, 168:108653, April, 2022. ![The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Deep learning (DL)-based methods have advanced the field of Prognostics and Health Management (PHM) in recent years, because of their powerful feature representation ability. The data in PHM are typically regular data represented in the Euclidean space. Nevertheless, there are an increasing number of applications that consider the relationships and interdependencies of data and represent the data in the form of graphs. Such kind of irregular data in non-Euclidean space pose a huge challenge to the existing DL-based methods, making some important operations (e.g., convolutions) easily applied to Euclidean space but difficult to model graph data in non-Euclidean space. Recently, graph neural networks (GNNs), as the emerging neural networks, have been utilized to model and analyze the graph data. However, there still lacks a guideline on leveraging GNNs for realizing intelligent fault diagnostics and prognostics. To fill this research gap, a practical guideline is proposed in this paper, and a novel intelligent fault diagnostics and prognostics framework based on GNN is established to illustrate how the proposed guideline works. In this framework, three types of graph construction methods are provided, and seven kinds of graph convolutional networks (GCNs) with four different graph pooling methods are investigated. To afford benchmark results for helping further study, a comprehensive evaluation of these models is performed on eight datasets, including six fault diagnosis datasets and two prognosis datasets. Finally, four issues related to the performance of GCNs are discussed and potential research directions are provided. The code library is available at: https://github.com/HazeDT/PHMGNNBenchmark.
@article{li_emerging_2022,
title = {The emerging graph neural networks for intelligent fault diagnostics and prognostics: {A} guideline and a benchmark study},
volume = {168},
issn = {0888-3270},
shorttitle = {The emerging graph neural networks for intelligent fault diagnostics and prognostics},
url = {https://www.sciencedirect.com/science/article/pii/S0888327021009791},
doi = {10.1016/j.ymssp.2021.108653},
abstract = {Deep learning (DL)-based methods have advanced the field of Prognostics and Health Management (PHM) in recent years, because of their powerful feature representation ability. The data in PHM are typically regular data represented in the Euclidean space. Nevertheless, there are an increasing number of applications that consider the relationships and interdependencies of data and represent the data in the form of graphs. Such kind of irregular data in non-Euclidean space pose a huge challenge to the existing DL-based methods, making some important operations (e.g., convolutions) easily applied to Euclidean space but difficult to model graph data in non-Euclidean space. Recently, graph neural networks (GNNs), as the emerging neural networks, have been utilized to model and analyze the graph data. However, there still lacks a guideline on leveraging GNNs for realizing intelligent fault diagnostics and prognostics. To fill this research gap, a practical guideline is proposed in this paper, and a novel intelligent fault diagnostics and prognostics framework based on GNN is established to illustrate how the proposed guideline works. In this framework, three types of graph construction methods are provided, and seven kinds of graph convolutional networks (GCNs) with four different graph pooling methods are investigated. To afford benchmark results for helping further study, a comprehensive evaluation of these models is performed on eight datasets, including six fault diagnosis datasets and two prognosis datasets. Finally, four issues related to the performance of GCNs are discussed and potential research directions are provided. The code library is available at: https://github.com/HazeDT/PHMGNNBenchmark.},
language = {en},
urldate = {2021-12-09},
journal = {Mechanical Systems and Signal Processing},
author = {Li, Tianfu and Zhou, Zheng and Li, Sinan and Sun, Chuang and Yan, Ruqiang and Chen, Xuefeng},
month = apr,
year = {2022},
keywords = {Benchmark results, Graph neural networks, Intelligent fault diagnostics and prognostics, Practical guideline, Prognostics and health management},
pages = {108653},
}
Downloads: 0
{"_id":"AiXcZJrbeo6JSAJTC","bibbaseid":"li-zhou-li-sun-yan-chen-theemerginggraphneuralnetworksforintelligentfaultdiagnosticsandprognosticsaguidelineandabenchmarkstudy-2022","author_short":["Li, T.","Zhou, Z.","Li, S.","Sun, C.","Yan, R.","Chen, X."],"bibdata":{"bibtype":"article","type":"article","title":"The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study","volume":"168","issn":"0888-3270","shorttitle":"The emerging graph neural networks for intelligent fault diagnostics and prognostics","url":"https://www.sciencedirect.com/science/article/pii/S0888327021009791","doi":"10.1016/j.ymssp.2021.108653","abstract":"Deep learning (DL)-based methods have advanced the field of Prognostics and Health Management (PHM) in recent years, because of their powerful feature representation ability. The data in PHM are typically regular data represented in the Euclidean space. Nevertheless, there are an increasing number of applications that consider the relationships and interdependencies of data and represent the data in the form of graphs. Such kind of irregular data in non-Euclidean space pose a huge challenge to the existing DL-based methods, making some important operations (e.g., convolutions) easily applied to Euclidean space but difficult to model graph data in non-Euclidean space. Recently, graph neural networks (GNNs), as the emerging neural networks, have been utilized to model and analyze the graph data. However, there still lacks a guideline on leveraging GNNs for realizing intelligent fault diagnostics and prognostics. To fill this research gap, a practical guideline is proposed in this paper, and a novel intelligent fault diagnostics and prognostics framework based on GNN is established to illustrate how the proposed guideline works. In this framework, three types of graph construction methods are provided, and seven kinds of graph convolutional networks (GCNs) with four different graph pooling methods are investigated. To afford benchmark results for helping further study, a comprehensive evaluation of these models is performed on eight datasets, including six fault diagnosis datasets and two prognosis datasets. Finally, four issues related to the performance of GCNs are discussed and potential research directions are provided. The code library is available at: https://github.com/HazeDT/PHMGNNBenchmark.","language":"en","urldate":"2021-12-09","journal":"Mechanical Systems and Signal Processing","author":[{"propositions":[],"lastnames":["Li"],"firstnames":["Tianfu"],"suffixes":[]},{"propositions":[],"lastnames":["Zhou"],"firstnames":["Zheng"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Sinan"],"suffixes":[]},{"propositions":[],"lastnames":["Sun"],"firstnames":["Chuang"],"suffixes":[]},{"propositions":[],"lastnames":["Yan"],"firstnames":["Ruqiang"],"suffixes":[]},{"propositions":[],"lastnames":["Chen"],"firstnames":["Xuefeng"],"suffixes":[]}],"month":"April","year":"2022","keywords":"Benchmark results, Graph neural networks, Intelligent fault diagnostics and prognostics, Practical guideline, Prognostics and health management","pages":"108653","bibtex":"@article{li_emerging_2022,\n\ttitle = {The emerging graph neural networks for intelligent fault diagnostics and prognostics: {A} guideline and a benchmark study},\n\tvolume = {168},\n\tissn = {0888-3270},\n\tshorttitle = {The emerging graph neural networks for intelligent fault diagnostics and prognostics},\n\turl = {https://www.sciencedirect.com/science/article/pii/S0888327021009791},\n\tdoi = {10.1016/j.ymssp.2021.108653},\n\tabstract = {Deep learning (DL)-based methods have advanced the field of Prognostics and Health Management (PHM) in recent years, because of their powerful feature representation ability. The data in PHM are typically regular data represented in the Euclidean space. Nevertheless, there are an increasing number of applications that consider the relationships and interdependencies of data and represent the data in the form of graphs. Such kind of irregular data in non-Euclidean space pose a huge challenge to the existing DL-based methods, making some important operations (e.g., convolutions) easily applied to Euclidean space but difficult to model graph data in non-Euclidean space. Recently, graph neural networks (GNNs), as the emerging neural networks, have been utilized to model and analyze the graph data. However, there still lacks a guideline on leveraging GNNs for realizing intelligent fault diagnostics and prognostics. To fill this research gap, a practical guideline is proposed in this paper, and a novel intelligent fault diagnostics and prognostics framework based on GNN is established to illustrate how the proposed guideline works. In this framework, three types of graph construction methods are provided, and seven kinds of graph convolutional networks (GCNs) with four different graph pooling methods are investigated. To afford benchmark results for helping further study, a comprehensive evaluation of these models is performed on eight datasets, including six fault diagnosis datasets and two prognosis datasets. Finally, four issues related to the performance of GCNs are discussed and potential research directions are provided. The code library is available at: https://github.com/HazeDT/PHMGNNBenchmark.},\n\tlanguage = {en},\n\turldate = {2021-12-09},\n\tjournal = {Mechanical Systems and Signal Processing},\n\tauthor = {Li, Tianfu and Zhou, Zheng and Li, Sinan and Sun, Chuang and Yan, Ruqiang and Chen, Xuefeng},\n\tmonth = apr,\n\tyear = {2022},\n\tkeywords = {Benchmark results, Graph neural networks, Intelligent fault diagnostics and prognostics, Practical guideline, Prognostics and health management},\n\tpages = {108653},\n}\n\n\n\n","author_short":["Li, T.","Zhou, Z.","Li, S.","Sun, C.","Yan, R.","Chen, X."],"key":"li_emerging_2022","id":"li_emerging_2022","bibbaseid":"li-zhou-li-sun-yan-chen-theemerginggraphneuralnetworksforintelligentfaultdiagnosticsandprognosticsaguidelineandabenchmarkstudy-2022","role":"author","urls":{"Paper":"https://www.sciencedirect.com/science/article/pii/S0888327021009791"},"keyword":["Benchmark results","Graph neural networks","Intelligent fault diagnostics and prognostics","Practical guideline","Prognostics and health management"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["benchmark results","graph neural networks","intelligent fault diagnostics and prognostics","practical guideline","prognostics and health management"],"search_terms":["emerging","graph","neural","networks","intelligent","fault","diagnostics","prognostics","guideline","benchmark","study","li","zhou","li","sun","yan","chen"],"title":"The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study","year":2022}