Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00078
Xing Gao, Zhirong Tan, Gang Xing
Aiming at the high latency and high load of cloud computing under the Internet of Everything, an edge computing framework is proposed. Secondly, in view of the high heterogeneity of node data under the edge computing framework, which leads to the difficulty of data analysis and processing, this paper proposes an information model with generalization capability to carry the state data of nodes, which reduces the heterogeneity of node data. Ensure that data can be unified access to the edge computing platform. Finally, the information model forms of edge nodes in a variety of application scenarios are discussed, which is helpful to promote the development of edge computing.
{"title":"Edge Node Information Model under the Framework of Edge Computing","authors":"Xing Gao, Zhirong Tan, Gang Xing","doi":"10.1109/PHM2022-London52454.2022.00078","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00078","url":null,"abstract":"Aiming at the high latency and high load of cloud computing under the Internet of Everything, an edge computing framework is proposed. Secondly, in view of the high heterogeneity of node data under the edge computing framework, which leads to the difficulty of data analysis and processing, this paper proposes an information model with generalization capability to carry the state data of nodes, which reduces the heterogeneity of node data. Ensure that data can be unified access to the edge computing platform. Finally, the information model forms of edge nodes in a variety of application scenarios are discussed, which is helpful to promote the development of edge computing.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127095525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00086
Ligang Wu, Changxing Zhao, Zushan Ding, Xiao Zhang, Yiding Wang, Yang Li
UAV s play a pivotal role in the field of security due to their flexibility, high efficiency, and low cost. This article uses yolov4 convolutional neural network technology to achieve the target detection process of power inspection photos. First, use labelimg to accurately label the power inspection training data set, and then use the fusion target detection network yolov4 and the detection-based multi-target tracking algorithm DeepSORT to address the problem of UAV positioning the target. Use the SiamRPN algorithm to achieve high-precision positioning to meet the needs of power inspection services and quickly identify targets in batches.
{"title":"A Multi-Target Tracking and Positioning Technology for UAV Based on Siamrpn Algorithm","authors":"Ligang Wu, Changxing Zhao, Zushan Ding, Xiao Zhang, Yiding Wang, Yang Li","doi":"10.1109/PHM2022-London52454.2022.00086","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00086","url":null,"abstract":"UAV s play a pivotal role in the field of security due to their flexibility, high efficiency, and low cost. This article uses yolov4 convolutional neural network technology to achieve the target detection process of power inspection photos. First, use labelimg to accurately label the power inspection training data set, and then use the fusion target detection network yolov4 and the detection-based multi-target tracking algorithm DeepSORT to address the problem of UAV positioning the target. Use the SiamRPN algorithm to achieve high-precision positioning to meet the needs of power inspection services and quickly identify targets in batches.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128573702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00022
Zhiyong Zhou, Liqiang Zhang, Xianye Zhu, Zhen Chen, Ming Li
Digital simulation such as MATLAB/Simulink is mostly used to study the control algorithm of DC microgrid system, but the operation of microgrid system cannot be simulated realistically. Firstly, control strategy of DC microgrid is developed and verified in this paper, then RT-LAB is used as a hardware-in-the-loop(HIL) simulation platform to realize a connection with the controller. Finally, a HIL simulation platform of 2KW DC microgrid for marine energy generation is built. The proposed method can greatly shorten the development cycle and cost of DC microgrid system for marine energy.
{"title":"Research on DC Microgrid Simulation for Marine Energy and Implementation of RT-LAB Semi-physical Simulation","authors":"Zhiyong Zhou, Liqiang Zhang, Xianye Zhu, Zhen Chen, Ming Li","doi":"10.1109/PHM2022-London52454.2022.00022","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00022","url":null,"abstract":"Digital simulation such as MATLAB/Simulink is mostly used to study the control algorithm of DC microgrid system, but the operation of microgrid system cannot be simulated realistically. Firstly, control strategy of DC microgrid is developed and verified in this paper, then RT-LAB is used as a hardware-in-the-loop(HIL) simulation platform to realize a connection with the controller. Finally, a HIL simulation platform of 2KW DC microgrid for marine energy generation is built. The proposed method can greatly shorten the development cycle and cost of DC microgrid system for marine energy.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116583286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/phm2022-london52454.2022.00038
J. Kuhne, C. Guhmann
{"title":"Defending Against Adversarial Attacks on Time- series with Selective Classification","authors":"J. Kuhne, C. Guhmann","doi":"10.1109/phm2022-london52454.2022.00038","DOIUrl":"https://doi.org/10.1109/phm2022-london52454.2022.00038","url":null,"abstract":"","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114221212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00023
Yu Xu, Liqiang Zhang, Xianye Zhu, Xiangyu Wang, Ming Li
Traditional state of charge (SOC) estimation algorithms require coding for embedded system, which will consume much time. In order to improve the development efficiency, this paper proposes a process for developing a SOC estimation algorithm based on Model-in-the-Loop for Embedded System Test (MiLEST), taking lithium-ion battery as an example. First, an equivalent circuit model is established, the model parameters are identified, and the SOC estimation model is designed. Second, offline simulations are performed to verify the model initially. Last, real-time battery data is collected for real-time simulation, and the model generation codes are downloaded to the embedded system to form MiLEST. The results show that the proposed SOC algorithm development process is efficient and cost-saving.
{"title":"SOC Estimation for Lithium-ion Battery Based on Model-in-the-Loop for Embedded System Test","authors":"Yu Xu, Liqiang Zhang, Xianye Zhu, Xiangyu Wang, Ming Li","doi":"10.1109/PHM2022-London52454.2022.00023","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00023","url":null,"abstract":"Traditional state of charge (SOC) estimation algorithms require coding for embedded system, which will consume much time. In order to improve the development efficiency, this paper proposes a process for developing a SOC estimation algorithm based on Model-in-the-Loop for Embedded System Test (MiLEST), taking lithium-ion battery as an example. First, an equivalent circuit model is established, the model parameters are identified, and the SOC estimation model is designed. Second, offline simulations are performed to verify the model initially. Last, real-time battery data is collected for real-time simulation, and the model generation codes are downloaded to the embedded system to form MiLEST. The results show that the proposed SOC algorithm development process is efficient and cost-saving.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132729658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00042
R. Zemouri, M. Lévesque, Étienne Boucher, M. Kirouac, François Lafleur, Simon Bernier, A. Merkhouf
Whether in the industrial, medical, or real-world domains, more and more data are being collected. The common particularity of all these application domains is that a great part of this data is mostly unlabeled. Thus, designing a learning model with a minimum of labeled data represents a major challenge in the coming years. A particular emphasis has recently been put on unsupervised learning methods based on the idea of autoencoding. The objective of these methods is twofold: to reduce the dimensionality of the input space and to reconstruct the original observation from this lower dimensional representation space. The variational form of these autoencoders, called the Variational Autoencoders (VAEs), is particularly successful in almost all application areas. This enthusiasm comes from the fact that VAEs allow to take advantage of the theoretical foundations of the Variational Bayesian methods and the learning capabilities of artificial neural networks. This review paper gives to the PHM community a synthesis of the latest publications in the PHM domain using the VAEs related to four topics: 1) Data-Driven Soft Sensors for missing values and data outliers, 2) reconstruction error for fault detection, 3) resampling approach for imbalanced data generation and minority class and 4) the variational embedding as PHM preprocessing pipelines and data transformations. After a review of the theoretical foundations and some practical tricks to succeed the implementation of the VAEs in industrial applications, the four main topics used to exploit the VAEs in the PHM domain are detailed. Finally, a global view of the research done at the research institute of Hydro-Québec regarding the diagnosis and failure detection of hydro-generators with VAEs are presented.
{"title":"Recent Research and Applications in Variational Autoencoders for Industrial Prognosis and Health Management: A Survey","authors":"R. Zemouri, M. Lévesque, Étienne Boucher, M. Kirouac, François Lafleur, Simon Bernier, A. Merkhouf","doi":"10.1109/PHM2022-London52454.2022.00042","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00042","url":null,"abstract":"Whether in the industrial, medical, or real-world domains, more and more data are being collected. The common particularity of all these application domains is that a great part of this data is mostly unlabeled. Thus, designing a learning model with a minimum of labeled data represents a major challenge in the coming years. A particular emphasis has recently been put on unsupervised learning methods based on the idea of autoencoding. The objective of these methods is twofold: to reduce the dimensionality of the input space and to reconstruct the original observation from this lower dimensional representation space. The variational form of these autoencoders, called the Variational Autoencoders (VAEs), is particularly successful in almost all application areas. This enthusiasm comes from the fact that VAEs allow to take advantage of the theoretical foundations of the Variational Bayesian methods and the learning capabilities of artificial neural networks. This review paper gives to the PHM community a synthesis of the latest publications in the PHM domain using the VAEs related to four topics: 1) Data-Driven Soft Sensors for missing values and data outliers, 2) reconstruction error for fault detection, 3) resampling approach for imbalanced data generation and minority class and 4) the variational embedding as PHM preprocessing pipelines and data transformations. After a review of the theoretical foundations and some practical tricks to succeed the implementation of the VAEs in industrial applications, the four main topics used to exploit the VAEs in the PHM domain are detailed. Finally, a global view of the research done at the research institute of Hydro-Québec regarding the diagnosis and failure detection of hydro-generators with VAEs are presented.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"374 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132809473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00069
Antoine Proteau, R. Zemouri, Antoine Tahan, Marc Thomas, Wafa Bounouara, Stéphane Agnard
The purpose of this paper is to present and to describe a novel dataset acquired entirely in an industrial environment during multiple regular scheduled production runs. In the monitoring, prognostic and fault detection literature, researchers are often faced with work based on the same popular datasets; for instance, the milling dataset, the Pronostia Bearing Dataset, the IMS Bearing Dataset or the Turbofan Engine Degradation Simulation Dataset. On the one hand, these datasets are the results of either simulations or acquired in a laboratory under controlled environment. On the other hand, a real industrial context might not be adequately represented within these datasets due to less controlled parameters or increased complexity. Consequently, it becomes critical to have access to a way to test and validate research work on both experimental and industrial data. In that mindset, to accelerate the technological transfer to the industry and to ensure that it can quickly profit from the benefits that the monitoring, diagnostic and prognostic research area can provide them, a new dataset acquired at an industrial partner: a machining company located in Quebec City (Qc, Canada) is presented.
{"title":"CNC Machining Quality Prediction Using Variational Autoencoder: A Novel Industrial 2 TB Dataset","authors":"Antoine Proteau, R. Zemouri, Antoine Tahan, Marc Thomas, Wafa Bounouara, Stéphane Agnard","doi":"10.1109/PHM2022-London52454.2022.00069","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00069","url":null,"abstract":"The purpose of this paper is to present and to describe a novel dataset acquired entirely in an industrial environment during multiple regular scheduled production runs. In the monitoring, prognostic and fault detection literature, researchers are often faced with work based on the same popular datasets; for instance, the milling dataset, the Pronostia Bearing Dataset, the IMS Bearing Dataset or the Turbofan Engine Degradation Simulation Dataset. On the one hand, these datasets are the results of either simulations or acquired in a laboratory under controlled environment. On the other hand, a real industrial context might not be adequately represented within these datasets due to less controlled parameters or increased complexity. Consequently, it becomes critical to have access to a way to test and validate research work on both experimental and industrial data. In that mindset, to accelerate the technological transfer to the industry and to ensure that it can quickly profit from the benefits that the monitoring, diagnostic and prognostic research area can provide them, a new dataset acquired at an industrial partner: a machining company located in Quebec City (Qc, Canada) is presented.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133369464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the process of monitoring and fault diagnosis of complex electromechanical equipment, the close coupling between the fault diagnosis process and the front-end equipment can effectively reduce the occurrence of serious faults and significantly improve the economic benefits. In this paper, an Internet of Things (IoT) framework for monitoring and diagnosing industrial equipment is designed and implemented for complex electromechanical equipment running in real-time. All the procedures are physically implemented on a hardware prototype, which includes hardware selection, software configuration, transplanting of machine learning (ML) model and data communication. The framework of the physical platform is universal and flexible. It can be deployed in various monitoring scenarios, and flexibly customize the deployed artificial intelligence (AI) models according to their applications. Three typical machine learning algorithms of SVM, ANN and LSTM models are transplanted to STM32 MCU to compare the results. Finally, the proposed method is experimentally validated on NASA Electro-mechanical actuators (EMAs) data set.
{"title":"A Fault Diagnosis Platform of Actuators on Embedded IoT Microcontrollers","authors":"Shaowei Chen, Yanping Huang, Pengfei Wen, Chunyue Gu, Shuai Zhao","doi":"10.1109/PHM2022-London52454.2022.00044","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00044","url":null,"abstract":"In the process of monitoring and fault diagnosis of complex electromechanical equipment, the close coupling between the fault diagnosis process and the front-end equipment can effectively reduce the occurrence of serious faults and significantly improve the economic benefits. In this paper, an Internet of Things (IoT) framework for monitoring and diagnosing industrial equipment is designed and implemented for complex electromechanical equipment running in real-time. All the procedures are physically implemented on a hardware prototype, which includes hardware selection, software configuration, transplanting of machine learning (ML) model and data communication. The framework of the physical platform is universal and flexible. It can be deployed in various monitoring scenarios, and flexibly customize the deployed artificial intelligence (AI) models according to their applications. Three typical machine learning algorithms of SVM, ANN and LSTM models are transplanted to STM32 MCU to compare the results. Finally, the proposed method is experimentally validated on NASA Electro-mechanical actuators (EMAs) data set.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"382 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133451577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00033
Rui Han, Ping Li, Ziyu Shi
Predictive maintenance of nuclear power plants is the continuous (or regular) condition monitoring and fault diagnosis of important parts of nuclear safety equipment when they are in operation. By judging the state of these equipment, predicting future development trends, making predictive maintenance plans based on development trends and possible failure modes, and determining the time, content, and method of equipment maintenance, as well as the required technical and material support [4]. Implementing predictive maintenance will help to detect early functional degradation, identify weak links in the operation process, and take timely intervention measures to enhance the safety of nuclear power plants, reduce the outage of nuclear power plants, and reduce operation and maintenance costs. The predictive maintenance of nuclear power plants relies on the "Predictive Maintenance Program", which stipulates the content and technology of predictive maintenance. According to the operation and maintenance experience of nuclear power units, the implementation of the predictive maintenance program should at least include three aspects: operation status assessment, equipment status assessment and maintenance implementation strategy. This paper mainly introduces the content of the predictive maintenance program of nuclear power plants, the content and process of the program implementation, and provides technical reference for other nuclear power plants to establish predictive maintenance.
{"title":"Implementation strategy of predictive maintenance in nuclear power plant","authors":"Rui Han, Ping Li, Ziyu Shi","doi":"10.1109/PHM2022-London52454.2022.00033","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00033","url":null,"abstract":"Predictive maintenance of nuclear power plants is the continuous (or regular) condition monitoring and fault diagnosis of important parts of nuclear safety equipment when they are in operation. By judging the state of these equipment, predicting future development trends, making predictive maintenance plans based on development trends and possible failure modes, and determining the time, content, and method of equipment maintenance, as well as the required technical and material support [4]. Implementing predictive maintenance will help to detect early functional degradation, identify weak links in the operation process, and take timely intervention measures to enhance the safety of nuclear power plants, reduce the outage of nuclear power plants, and reduce operation and maintenance costs. The predictive maintenance of nuclear power plants relies on the \"Predictive Maintenance Program\", which stipulates the content and technology of predictive maintenance. According to the operation and maintenance experience of nuclear power units, the implementation of the predictive maintenance program should at least include three aspects: operation status assessment, equipment status assessment and maintenance implementation strategy. This paper mainly introduces the content of the predictive maintenance program of nuclear power plants, the content and process of the program implementation, and provides technical reference for other nuclear power plants to establish predictive maintenance.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134044641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-05-01DOI: 10.1109/PHM2022-London52454.2022.00049
Fenggang Lai, Z. Zhao, Dequan Gao, Wang Luo, Chao Lou, Shengya Han, Chao Ma
In view of the knowledge graph co-construction and sharing requirements for intelligent operation and maintenance of cloud data center complex network systems, this paper constructs an operation and maintenance knowledge graph framework model, proposes a practical method for fault knowledge entity identification and relationship extraction, and develops cloud data center intelligent operation and maintenance knowledge graph. Multi-source knowledge quality verification and automatic update tools, and based on the intelligent operation and maintenance knowledge map, build business scenario applications, and test the effectiveness of the tools.
{"title":"Using Semantic Dependencies to Realize the Construction of Cloud Data Center Operation and Maintenance Knowledge Graph","authors":"Fenggang Lai, Z. Zhao, Dequan Gao, Wang Luo, Chao Lou, Shengya Han, Chao Ma","doi":"10.1109/PHM2022-London52454.2022.00049","DOIUrl":"https://doi.org/10.1109/PHM2022-London52454.2022.00049","url":null,"abstract":"In view of the knowledge graph co-construction and sharing requirements for intelligent operation and maintenance of cloud data center complex network systems, this paper constructs an operation and maintenance knowledge graph framework model, proposes a practical method for fault knowledge entity identification and relationship extraction, and develops cloud data center intelligent operation and maintenance knowledge graph. Multi-source knowledge quality verification and automatic update tools, and based on the intelligent operation and maintenance knowledge map, build business scenario applications, and test the effectiveness of the tools.","PeriodicalId":269605,"journal":{"name":"2022 Prognostics and Health Management Conference (PHM-2022 London)","volume":"9 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132927245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：