Fault diagnosis of 5G networks faces the challenges of heavy reliance on human experience and insufficient fault samples and relevant monitoring data.The digital twin technology can realize the interaction between vir...Fault diagnosis of 5G networks faces the challenges of heavy reliance on human experience and insufficient fault samples and relevant monitoring data.The digital twin technology can realize the interaction between virtual space and physical space through the fusion of model and data,providing a new paradigm for fault diagnosis.In this paper,we first propose a network digital twin model and apply it to 5G network diagnosis.We then use an improved Average Wasserstein GAN with Gradient Penalty(AWGAN-GP)method to discover and predict failures in the twin network.Finally,we use XGBoost algorithm to locate the faults in physical network in real time.Extensive simulation results show that the proposed approach can significantly increase fault prediction and diagnosis accuracy in the case of a small number of labeled failure samples in 5G networks.展开更多
In recent years, Digital Twin (DT) has gained significant interestfrom academia and industry due to the advanced in information technology,communication systems, Artificial Intelligence (AI), Cloud Computing (CC),and ...In recent years, Digital Twin (DT) has gained significant interestfrom academia and industry due to the advanced in information technology,communication systems, Artificial Intelligence (AI), Cloud Computing (CC),and Industrial Internet of Things (IIoT). The main concept of the DT isto provide a comprehensive tangible, and operational explanation of anyelement, asset, or system. However, it is an extremely dynamic taxonomydeveloping in complexity during the life cycle that produces a massive amountof engendered data and information. Likewise, with the development of AI,digital twins can be redefined and could be a crucial approach to aid theInternet of Things (IoT)-based DT applications for transferring the data andvalue onto the Internet with better decision-making. Therefore, this paperintroduces an efficient DT-based fault diagnosis model based on machinelearning (ML) tools. In this framework, the DT model of the machine isconstructed by creating the simulation model. In the proposed framework,the Genetic algorithm (GA) is used for the optimization task to improvethe classification accuracy. Furthermore, we evaluate the proposed faultdiagnosis framework using performance metrics such as precision, accuracy,F-measure, and recall. The proposed framework is comprehensively examinedusing the triplex pump fault diagnosis. The experimental results demonstratedthat the hybrid GA-ML method gives outstanding results compared to MLmethods like LogisticRegression (LR), Na飗e Bayes (NB), and SupportVectorMachine (SVM). The suggested framework achieves the highest accuracyof 95% for the employed hybrid GA-SVM. The proposed framework willeffectively help industrial operators make an appropriate decision concerningthe fault analysis for IIoT applications in the context of Industry 4.0.展开更多
Electro-hydraulic control valves are key hydraulic components for industrial applications and aerospace,which controls electro-hydraulic motion.With the development of automation,digital technology,and communication t...Electro-hydraulic control valves are key hydraulic components for industrial applications and aerospace,which controls electro-hydraulic motion.With the development of automation,digital technology,and communication technology,electro-hydraulic control valves are becoming more digital,integrated,and intelligent in order to meet the requirements of Industry 4.0.This paper reviews the state of the art development for electro-hydraulic control valves and their related technologies.This review paper considers three aspects of state acquisition through sensors or indirect acquisition technologies,control strategies along with digital controllers and novel valves,and online maintenance through data interaction and fault diagnosis.The main features and development trends of electro-hydraulic control valves oriented to Industry 4.0 are discussed.展开更多
Existing research on fault diagnosis for polymer electrolyte membrane fuel cells(PEMFC)has advanced significantly,yet performance is hindered by variations in data distributions and the requirement for extensive fault...Existing research on fault diagnosis for polymer electrolyte membrane fuel cells(PEMFC)has advanced significantly,yet performance is hindered by variations in data distributions and the requirement for extensive fault data.In this study,a cross-domain adaptive health diagnosis method for PEMFC is proposed,integrating the digital twin model and transfer convolutional diagnosis model.A physical-based high-fidelity digital twin model is developed to obtain diverse and high-quality datasets for training diagnosis method.To extract long-term time series features from the data,a temporal convolutional network(TCN)is proposed as a pre-trained diagnosis model for the source domain,with feature extraction layers that can be reused to the transfer learning network.It is demonstrated that the proposed pre-trained model can hold the ability to accurately diagnose the various fuel cell faults,including pressure,drying,flow,and flooding faults,with 99.92%accuracy,through the effective capture of the long-term dependencies in time series data.Finally,a domain adaptive transfer convolutional network(DATCN)is established to improve the diagnosis accuracy across diverse fuel cells by learning domain-invariant features.The results show that the DATCN model,tested on three different target domain devices with adversarial training using only 10%normal data,can achieve an average accuracy of 98.5%(30%improved over traditional diagnosis models).This proposed method provides an effective solution for accurate cross-domain diagnosis of PEMFC devices,significantly reducing the reliance on extensive fault data.展开更多
This paper presents modified version of a realistic test tool suitable to Design For Testability （DFT） and Built-ln Self Test （BIST） environments. A comprehensive tool is developed in the form of a test simulator....This paper presents modified version of a realistic test tool suitable to Design For Testability （DFT） and Built-ln Self Test （BIST） environments. A comprehensive tool is developed in the form of a test simulator. The simulator is capable of providing a required goal of test for the Circuit Under Test （CUT）. The simulator uses the approach of fault diagnostics with fault grading procedures to provide the optimum tests. The current version of the simulator embeds features of exhaustive and pseudo-random test generation schemes along with the search solutions of cost effective test goals. The simulator provides facilities of realizing all possible pseudo-random sequence generators with all possible combinations of seeds. The tool is developed on a common Personal Computer （PC） platform and hence no special software is required. Thereby, it is a low cost tool hence economical. The tool is very much suitable for determining realistic test sequences for a targeted goal of testing for any CUT. The developed tool incorporates flexible Graphical User Interface （GUI） procedures and can be operated without any special programming skill. The tool is debugged and tested with the results of many bench mark circuits. Further, this developed tool can be utilized for educational purposes for many courses such as fault-tolerant computing, fault diagnosis, digital electronics, and safe-reliable-testable digital logic designs.展开更多
基金supported by Natural Science Foundation of China(61871237,92067101)Program to Cultivate Middle-aged and Young Science Leaders of Universities of Jiangsu Province+1 种基金Key R&D plan of Jiangsu Province(BE2021013-3)。
文摘Fault diagnosis of 5G networks faces the challenges of heavy reliance on human experience and insufficient fault samples and relevant monitoring data.The digital twin technology can realize the interaction between virtual space and physical space through the fusion of model and data,providing a new paradigm for fault diagnosis.In this paper,we first propose a network digital twin model and apply it to 5G network diagnosis.We then use an improved Average Wasserstein GAN with Gradient Penalty(AWGAN-GP)method to discover and predict failures in the twin network.Finally,we use XGBoost algorithm to locate the faults in physical network in real time.Extensive simulation results show that the proposed approach can significantly increase fault prediction and diagnosis accuracy in the case of a small number of labeled failure samples in 5G networks.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project Number (PNURSP2022R197),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘In recent years, Digital Twin (DT) has gained significant interestfrom academia and industry due to the advanced in information technology,communication systems, Artificial Intelligence (AI), Cloud Computing (CC),and Industrial Internet of Things (IIoT). The main concept of the DT isto provide a comprehensive tangible, and operational explanation of anyelement, asset, or system. However, it is an extremely dynamic taxonomydeveloping in complexity during the life cycle that produces a massive amountof engendered data and information. Likewise, with the development of AI,digital twins can be redefined and could be a crucial approach to aid theInternet of Things (IoT)-based DT applications for transferring the data andvalue onto the Internet with better decision-making. Therefore, this paperintroduces an efficient DT-based fault diagnosis model based on machinelearning (ML) tools. In this framework, the DT model of the machine isconstructed by creating the simulation model. In the proposed framework,the Genetic algorithm (GA) is used for the optimization task to improvethe classification accuracy. Furthermore, we evaluate the proposed faultdiagnosis framework using performance metrics such as precision, accuracy,F-measure, and recall. The proposed framework is comprehensively examinedusing the triplex pump fault diagnosis. The experimental results demonstratedthat the hybrid GA-ML method gives outstanding results compared to MLmethods like LogisticRegression (LR), Na飗e Bayes (NB), and SupportVectorMachine (SVM). The suggested framework achieves the highest accuracyof 95% for the employed hybrid GA-SVM. The proposed framework willeffectively help industrial operators make an appropriate decision concerningthe fault analysis for IIoT applications in the context of Industry 4.0.
基金Supported by NSFC-Zhejiang Joint Fund(Grant No.U1509204)National Natural Science Foundation of China(Grant Nos.51835009,51922093).
文摘Electro-hydraulic control valves are key hydraulic components for industrial applications and aerospace,which controls electro-hydraulic motion.With the development of automation,digital technology,and communication technology,electro-hydraulic control valves are becoming more digital,integrated,and intelligent in order to meet the requirements of Industry 4.0.This paper reviews the state of the art development for electro-hydraulic control valves and their related technologies.This review paper considers three aspects of state acquisition through sensors or indirect acquisition technologies,control strategies along with digital controllers and novel valves,and online maintenance through data interaction and fault diagnosis.The main features and development trends of electro-hydraulic control valves oriented to Industry 4.0 are discussed.
基金supported by the National Key Research and Development Program of China(Grant No.2023YFB4005800)National Natural Science Foundation of China(grant No.52241702).
文摘Existing research on fault diagnosis for polymer electrolyte membrane fuel cells(PEMFC)has advanced significantly,yet performance is hindered by variations in data distributions and the requirement for extensive fault data.In this study,a cross-domain adaptive health diagnosis method for PEMFC is proposed,integrating the digital twin model and transfer convolutional diagnosis model.A physical-based high-fidelity digital twin model is developed to obtain diverse and high-quality datasets for training diagnosis method.To extract long-term time series features from the data,a temporal convolutional network(TCN)is proposed as a pre-trained diagnosis model for the source domain,with feature extraction layers that can be reused to the transfer learning network.It is demonstrated that the proposed pre-trained model can hold the ability to accurately diagnose the various fuel cell faults,including pressure,drying,flow,and flooding faults,with 99.92%accuracy,through the effective capture of the long-term dependencies in time series data.Finally,a domain adaptive transfer convolutional network(DATCN)is established to improve the diagnosis accuracy across diverse fuel cells by learning domain-invariant features.The results show that the DATCN model,tested on three different target domain devices with adversarial training using only 10%normal data,can achieve an average accuracy of 98.5%(30%improved over traditional diagnosis models).This proposed method provides an effective solution for accurate cross-domain diagnosis of PEMFC devices,significantly reducing the reliance on extensive fault data.
文摘This paper presents modified version of a realistic test tool suitable to Design For Testability （DFT） and Built-ln Self Test （BIST） environments. A comprehensive tool is developed in the form of a test simulator. The simulator is capable of providing a required goal of test for the Circuit Under Test （CUT）. The simulator uses the approach of fault diagnostics with fault grading procedures to provide the optimum tests. The current version of the simulator embeds features of exhaustive and pseudo-random test generation schemes along with the search solutions of cost effective test goals. The simulator provides facilities of realizing all possible pseudo-random sequence generators with all possible combinations of seeds. The tool is developed on a common Personal Computer （PC） platform and hence no special software is required. Thereby, it is a low cost tool hence economical. The tool is very much suitable for determining realistic test sequences for a targeted goal of testing for any CUT. The developed tool incorporates flexible Graphical User Interface （GUI） procedures and can be operated without any special programming skill. The tool is debugged and tested with the results of many bench mark circuits. Further, this developed tool can be utilized for educational purposes for many courses such as fault-tolerant computing, fault diagnosis, digital electronics, and safe-reliable-testable digital logic designs.
