Thedeployment of the Internet of Things(IoT)with smart sensors has facilitated the emergence of fog computing as an important technology for delivering services to smart environments such as campuses,smart cities,and ...Thedeployment of the Internet of Things(IoT)with smart sensors has facilitated the emergence of fog computing as an important technology for delivering services to smart environments such as campuses,smart cities,and smart transportation systems.Fog computing tackles a range of challenges,including processing,storage,bandwidth,latency,and reliability,by locally distributing secure information through end nodes.Consisting of endpoints,fog nodes,and back-end cloud infrastructure,it provides advanced capabilities beyond traditional cloud computing.In smart environments,particularly within smart city transportation systems,the abundance of devices and nodes poses significant challenges related to power consumption and system reliability.To address the challenges of latency,energy consumption,and fault tolerance in these environments,this paper proposes a latency-aware,faulttolerant framework for resource scheduling and data management,referred to as the FORD framework,for smart cities in fog environments.This framework is designed to meet the demands of time-sensitive applications,such as those in smart transportation systems.The FORD framework incorporates latency-aware resource scheduling to optimize task execution in smart city environments,leveraging resources from both fog and cloud environments.Through simulation-based executions,tasks are allocated to the nearest available nodes with minimum latency.In the event of execution failure,a fault-tolerantmechanism is employed to ensure the successful completion of tasks.Upon successful execution,data is efficiently stored in the cloud data center,ensuring data integrity and reliability within the smart city ecosystem.展开更多
Seismic data plays a pivotal role in fault detection,offering critical insights into subsurface structures and seismic hazards.Understanding fault detection from seismic data is essential for mitigating seismic risks ...Seismic data plays a pivotal role in fault detection,offering critical insights into subsurface structures and seismic hazards.Understanding fault detection from seismic data is essential for mitigating seismic risks and guiding land-use plans.This paper presents a comprehensive review of existing methodologies for fault detection,focusing on the application of Machine Learning(ML)and Deep Learning(DL)techniques to enhance accuracy and efficiency.Various ML and DL approaches are analyzed with respect to fault segmentation,adaptive learning,and fault detection models.These techniques,benchmarked against established seismic datasets,reveal significant improvements over classical methods in terms of accuracy and computational efficiency.Additionally,this review highlights emerging trends,including hybrid model applications and the integration of real-time data processing for seismic fault detection.By providing a detailed comparative analysis of current methodologies,this review aims to guide future research and foster advancements in the effectiveness and reliability of seismic studies.Ultimately,the study seeks to bridge the gap between theoretical investigations and practical implementations in fault detection.展开更多
Dear Editor,This letter studies the bipartite consensus tracking problem for heterogeneous multi-agent systems with actuator faults and a leader's unknown time-varying control input. To handle such a problem, the ...Dear Editor,This letter studies the bipartite consensus tracking problem for heterogeneous multi-agent systems with actuator faults and a leader's unknown time-varying control input. To handle such a problem, the continuous fault-tolerant control protocol via observer design is developed. In addition, it is strictly proved that the multi-agent system driven by the designed controllers can still achieve bipartite consensus tracking after faults occur.展开更多
Missing data handling is vital for multi-sensor information fusion fault diagnosis of motors to prevent the accuracy decay or even model failure,and some promising results have been gained in several current studies.T...Missing data handling is vital for multi-sensor information fusion fault diagnosis of motors to prevent the accuracy decay or even model failure,and some promising results have been gained in several current studies.These studies,however,have the following limitations:1)effective supervision is neglected for missing data across different fault types and 2)imbalance in missing rates among fault types results in inadequate learning during model training.To overcome the above limitations,this paper proposes a dynamic relative advantagedriven multi-fault synergistic diagnosis method to accomplish accurate fault diagnosis of motors under imbalanced missing data rates.Firstly,a cross-fault-type generalized synergistic diagnostic strategy is established based on variational information bottleneck theory,which is able to ensure sufficient supervision in handling missing data.Then,a dynamic relative advantage assessment technique is designed to reduce diagnostic accuracy decay caused by imbalanced missing data rates.The proposed method is validated using multi-sensor data from motor fault simulation experiments,and experimental results demonstrate its effectiveness and superiority in improving diagnostic accuracy and generalization under imbalanced missing data rates.展开更多
Supervised learning classification has arisen as a powerful tool to perform data-driven fault diagnosis in dynamical systems,achieving astonishing results.This approach assumes the availability of extensive,diverse an...Supervised learning classification has arisen as a powerful tool to perform data-driven fault diagnosis in dynamical systems,achieving astonishing results.This approach assumes the availability of extensive,diverse and labeled data corpora for train-ing.However,in some applications it may be difficult or not feasible to obtain a large and balanced dataset including enough representative instances of the fault behaviors of interest.This fact leads to the issues of data scarcity and class imbalance,greatly affecting the performance of supervised learning classifiers.Datasets from railway systems are usually both,scarce and imbalanced,turning supervised learning-based fault diagnosis into a highly challenging task.This article addresses time-series data augmentation for fault diagnosis purposes and presents two application cases in the context of railway track.The case studies employ generative adversarial networks(GAN)schemes to produce realistic synthetic samples of geometrical and structural track defects.The goal is to generate samples that enhance fault diagnosis performance;therefore,major attention was paid not only in the generation process,but also in the synthesis quality assessment,to guarantee the suitability of the samples for training of supervised learning classification models.In the first application,a convolutional classifier achieved a test accuracy of 87.5%for the train on synthetic,test on real(TSTR)scenario,while,in the second application,a fully-connected classifier achieved 96.18%in test accuracy for TSTR.The results indicate that the proposed augmentation approach produces samples having equivalent statistical characteristics and leading to a similar classification behavior as real data.展开更多
The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelli...The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelligent fault diagnosis.On the other hand,the vectorization of multi-source sensor signals may not only generate high-dimensional vectors,leading to increasing computational complexity and overfitting problems,but also lose the structural information and the coupling information.This paper proposes a new method for class-imbalanced fault diagnosis of bearing using support tensor machine(STM)driven by heterogeneous data fusion.The collected sound and vibration signals of bearings are successively decomposed into multiple frequency band components to extract various time-domain and frequency-domain statistical parameters.A third-order hetero-geneous feature tensor is designed based on multisensors,frequency band components,and statistical parameters.STM-based intelligent model is constructed to preserve the structural information of the third-order heterogeneous feature tensor for bearing fault diagnosis.A series of comparative experiments verify the advantages of the proposed method.展开更多
Data-driven techniques are reshaping blast furnace iron-making process(BFIP)modeling,but their“black-box”nature often obscures interpretability and accuracy.To overcome these limitations,our mechanism and data co-dr...Data-driven techniques are reshaping blast furnace iron-making process(BFIP)modeling,but their“black-box”nature often obscures interpretability and accuracy.To overcome these limitations,our mechanism and data co-driven strategy(MDCDS)enhances model transparency and molten iron quality(MIQ)prediction.By zoning the furnace and applying mechanism-based features for material and thermal trends,coupled with a novel stationary broad feature learning system(StaBFLS),interference caused by nonstationary process characteristics are mitigated and the intrinsic information embedded in BFIP is mined.Subsequently,by integrating stationary feature representation with mechanism features,our temporal matching broad learning system(TMBLS)aligns process and quality variables using MIQ as the target.This integration allows us to establish process monitoring statistics using both mechanism and data-driven features,as well as detect modeling deviations.Validated against real-world BFIP data,our MDCDS model demonstrates consistent process alignment,robust feature extraction,and improved MIQ modeling—Yielding better fault detection.Additionally,we offer detailed insights into the validation process,including parameter baselining and optimization.展开更多
The Pearl River Estuary(PRE) is located at the onshore-offshore transition zone between South China and South China Sea Basin, and it is of great significant value in discussing tectonic relationships between South Ch...The Pearl River Estuary(PRE) is located at the onshore-offshore transition zone between South China and South China Sea Basin, and it is of great significant value in discussing tectonic relationships between South China block and South China Sea block and seismic activities along the offshore active faults in PRE. However, the researches on geometric characteristics of offshore faults in this area are extremely lacking. To investigate the offshore fault distribution and their geometric features in the PRE in greater detail, we acquired thirteen seismic reflection profiles in 2015. Combining the analysis of the seismic reflection and free-air gravity anomaly data, this paper revealed the location, continuity, and geometry of the littoral fault zone and other offshore faults in PRE. The littoral fault zone is composed of the major Dangan Islands fault and several parallel, high-angle, normal faults, which mainly trend northeast to northeast-to-east and dip to the southeast with large displacements. The fault zone is divided into three different segments by the northwest-trending faults. Moreover, the basement depth around Dangan Islands is very shallow, while it suddenly increases along the islands westward and southward. These has resulted in the islands and neighboring areas becoming the places where the stress accumulates easily. The seismogenic pattern of this area is closely related to the comprehensive effect of intersecting faults together with the low velocity layer.展开更多
For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues： the missing data samples and the non-Gaussian property of the data. However, most of the existing data-d...For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues： the missing data samples and the non-Gaussian property of the data. However, most of the existing data-driven methods cannot be able to handle both of them. Thus, a new Bayesian network classifier based fault detection and diagnosis method is proposed. At first, a non-imputation method is presented to handle the data incomplete samples, with the property of the proposed Bayesian network classifier, and the missing values can be marginalized in an elegant manner. Furthermore, the Gaussian mixture model is used to approximate the non-Gaussian data with a linear combination of finite Gaussian mixtures, so that the Bayesian network can process the non-Gaussian data in an effective way. Therefore, the entire fault detection and diagnosis method can deal with the high-dimensional incomplete process samples in an efficient and robust way. The diagnosis results are expressed in the manner of probability with the reliability scores. The proposed approach is evaluated with a benchmark problem called the Tennessee Eastman process. The simulation results show the effectiveness and robustness of the proposed method in fault detection and diagnosis for large-scale systems with missing measurements.展开更多
Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors ...Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the location of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.展开更多
Focusing on the networked control system with long time-delays and data packet dropout,the problem of observerbased fault detection of the system is studied.According to conditions of data arrival of the controller,th...Focusing on the networked control system with long time-delays and data packet dropout,the problem of observerbased fault detection of the system is studied.According to conditions of data arrival of the controller,the state observers of the system are designed to detect faults when they occur in the system.When the system is normal,the observers system is modeled as an uncertain switched system.Based on the model,stability condition of the whole system is given.When conditions are satisfied,the system is asymptotically stable.When a fault occurs,the observers residual can change rapidly to detect the fault.A numerical example shows the effectiveness of the proposed method.展开更多
The vibration signals of machinery with various faults often show clear nonlinear characteristics.Currently,fractal dimension analysis as the common useful method for nonlinear signal analysis,is a kind of single frac...The vibration signals of machinery with various faults often show clear nonlinear characteristics.Currently,fractal dimension analysis as the common useful method for nonlinear signal analysis,is a kind of single fractal form,which only reflects the overall irregularity of signals,but cannot describe its local scaling properties.For comprehensive revealing of internal properties,a combinatorial method based on band-phase-randomized(BPR)surrogate data and multifractal is introduced.BPR surrogate data method is effective to eliminate nonlinearity in specified frequency band for a fault signal,which can be utilized to detect nonlinear degree in whole fault signal by nonlinear titration method,and the overall nonlinear distribution of fault signal is displayed in nonlinear characteristic curve that can be used to analyze the fault signal qualitatively.Then multifractal theory as a quantitative analysis method is used to describe geometrical characteristics and local scaling properties,and asymmetry coefficient of multifractal spectrum and multifractal entropy for fault signals are extracted as new criterions to diagnose machinery faults.Several typical faults include rotor misalignment,transversal crack,and static-dynamic rubbing fault are analyzed,and the results indicate that those faults can be distinguished by the proposed method effectively,which provides a qualitative and quantitative analysis way in the field of machinery fault diagnosis.展开更多
In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis(FDD) methods have been proposed and impleme...In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis(FDD) methods have been proposed and implemented, the performance of which, however, could be drastically influenced by the common presence of incomplete or missing data in real industrial scenarios. This paper presents a new FDD approach based on an incomplete data imputation technique for process fault recognition. It employs the modified stacked autoencoder,a deep learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification. A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method.展开更多
By systemic processing, comprehensive analysis, and interpretation of gravity data, we confirmed the existence of the west segment of the coastal fault zone(west of Yangjiang to Beibu Bay) in the coastal region of Sou...By systemic processing, comprehensive analysis, and interpretation of gravity data, we confirmed the existence of the west segment of the coastal fault zone(west of Yangjiang to Beibu Bay) in the coastal region of South China. This showed an apparent high gravity gradient in the NEE direction, and worse linearity and less compactness than that in the Pearl River month. This also revealed a relatively large curvature and a complicated gravity structure. In the finding images processed by the gravity data system, each fault was well reflected and primarily characterized by isolines or thick black stripes with a cutting depth greater than 30 km. Though mutually cut by NW-trending and NE-trending faults, the apparent NEE stripe-shaped structure of the west segment of the coastal fault zone remained unchanged,with good continuity and an activity strength higher than that of NW and NE-trending faults. Moreover,we determined that the west segment of the coastal fault zone is the major seismogenic structure responsible for strong earthquakes in the coastal region in the border area of Guangdong, Guangxi, and Hainan.展开更多
The Hori＇s inverse method based on spectral decomposition was applied to estimate coseismic slip distribution on the rupture plane of the 14 November 2001 Ms8.1 Kunlun earthquake based on GPS survey results. The inve...The Hori＇s inverse method based on spectral decomposition was applied to estimate coseismic slip distribution on the rupture plane of the 14 November 2001 Ms8.1 Kunlun earthquake based on GPS survey results. The inversion result shows that the six sliding models can be constrained by the coseismic GPS data. The established slips mainly concentrated along the eastern segment of the fault rupture, and the maximum magnitude is about 7 m. Slip on the eastern segment of the fault rupture represents as purely left-lateral strike-slip. Slip on the western segment of the seismic rupture represents as mainly dip-stip with the maximum dip-slip about 1 m. Total predicted scalar seismic moment is 5.196× 10^2° N.m. Our results constrained by geodetic data are consistent with seismological results.展开更多
A control valve is one of the most widely used machines in hydraulic systems.However,it often works in harsh environments and failure occurs from time to time.An intelligent and robust control valve fault diagnosis is...A control valve is one of the most widely used machines in hydraulic systems.However,it often works in harsh environments and failure occurs from time to time.An intelligent and robust control valve fault diagnosis is therefore important for operation of the system.In this study,a fault diagnosis based on the mathematical model(MM)imputation and the modified deep residual shrinkage network(MDRSN)is proposed to solve the problem that data-driven models for control valves are susceptible to changing operating conditions and missing data.The multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed method.The effects of the proposed method in missing data imputation and fault diagnosis are analyzed.Compared with random and k-nearest neighbor(KNN)imputation,the accuracies of MM-based imputation are improved by 17.87%and 21.18%,in the circumstances of a20.00%data missing rate at valve opening from 10%to 28%.Furthermore,the results show that the proposed MDRSN can maintain high fault diagnosis accuracy with missing data.展开更多
As the demand for wind energy continues to grow at exponential rate, reducing operation and maintenance (O & M) costs and improving reliability have become top priorities in wind turbine maintenance strategies. Pr...As the demand for wind energy continues to grow at exponential rate, reducing operation and maintenance (O & M) costs and improving reliability have become top priorities in wind turbine maintenance strategies. Prediction of wind turbine failures before they reach a catastrophic stage is critical to reduce the O & M cost due to unnecessary scheduled maintenance. A SCADA-data based condition monitoring system, which takes advantage of data already collected at the wind turbine controller, is a cost-effective way to monitor wind turbines for early warning of failures. This article proposes a methodology of fault prediction and automatically generating warning and alarm for wind turbine main bearings based on stored SCADA data using Artificial Neural Network (ANN). The ANN model of turbine main bearing normal behavior is established and then the deviation between estimated and actual values of the parameter is calculated. Furthermore, a method has been developed to generate early warning and alarm and avoid false warnings and alarms based on the deviation. In this way, wind farm operators are able to have enough time to plan maintenance, and thus, unanticipated downtime can be avoided and O & M costs can be reduced.展开更多
In order to increase the fault diagnosis efficiency and make the fault data mining be realized, the decision table containing numerical attributes must be discretized for further calculations. The discernibility matri...In order to increase the fault diagnosis efficiency and make the fault data mining be realized, the decision table containing numerical attributes must be discretized for further calculations. The discernibility matrix-based reduction method depends on whether the numerical attributes can be properly discretized or not.So a discretization algorithm based on particle swarm optimization(PSO) is proposed. Moreover, hybrid weights are adopted in the process of particles evolution. Comparative calculations for certain equipment are completed to demonstrate the effectiveness of the proposed algorithm. The results indicate that the proposed algorithm has better performance than other popular algorithms such as class-attribute interdependence maximization(CAIM)discretization method and entropy-based discretization method.展开更多
Multi-source multi-class classification methods based on multi-class Support Vector Machines and data fusion strategies are proposed in this paper. The centralized and distributed fusion schemes are applied to combine...Multi-source multi-class classification methods based on multi-class Support Vector Machines and data fusion strategies are proposed in this paper. The centralized and distributed fusion schemes are applied to combine information from several data sources. In the centralized scheme, all information from several data sources is centralized to construct an input space. Then a multi-class Support Vector Machine classifier is trained. In the distributed schemes, the individual data sources are proc-essed separately and modelled by using the multi-class Support Vector Machine. Then new data fusion strategies are proposed to combine the information from the individual multi-class Support Vector Machine models. Our proposed fusion strategies take into account that an Support Vector Machine (SVM) classifier achieves classification by finding the optimal classification hyperplane with maximal margin. The proposed methods are applied for fault diagnosis of a diesel engine. The experimental results showed that almost all the proposed approaches can largely improve the diagnostic accuracy. The robustness of diagnosis is also improved because of the implementation of data fusion strategies. The proposed methods can also be applied in other fields.展开更多
基金supported by the Deanship of Scientific Research and Graduate Studies at King Khalid University under research grant number(R.G.P.2/93/45).
文摘Thedeployment of the Internet of Things(IoT)with smart sensors has facilitated the emergence of fog computing as an important technology for delivering services to smart environments such as campuses,smart cities,and smart transportation systems.Fog computing tackles a range of challenges,including processing,storage,bandwidth,latency,and reliability,by locally distributing secure information through end nodes.Consisting of endpoints,fog nodes,and back-end cloud infrastructure,it provides advanced capabilities beyond traditional cloud computing.In smart environments,particularly within smart city transportation systems,the abundance of devices and nodes poses significant challenges related to power consumption and system reliability.To address the challenges of latency,energy consumption,and fault tolerance in these environments,this paper proposes a latency-aware,faulttolerant framework for resource scheduling and data management,referred to as the FORD framework,for smart cities in fog environments.This framework is designed to meet the demands of time-sensitive applications,such as those in smart transportation systems.The FORD framework incorporates latency-aware resource scheduling to optimize task execution in smart city environments,leveraging resources from both fog and cloud environments.Through simulation-based executions,tasks are allocated to the nearest available nodes with minimum latency.In the event of execution failure,a fault-tolerantmechanism is employed to ensure the successful completion of tasks.Upon successful execution,data is efficiently stored in the cloud data center,ensuring data integrity and reliability within the smart city ecosystem.
文摘Seismic data plays a pivotal role in fault detection,offering critical insights into subsurface structures and seismic hazards.Understanding fault detection from seismic data is essential for mitigating seismic risks and guiding land-use plans.This paper presents a comprehensive review of existing methodologies for fault detection,focusing on the application of Machine Learning(ML)and Deep Learning(DL)techniques to enhance accuracy and efficiency.Various ML and DL approaches are analyzed with respect to fault segmentation,adaptive learning,and fault detection models.These techniques,benchmarked against established seismic datasets,reveal significant improvements over classical methods in terms of accuracy and computational efficiency.Additionally,this review highlights emerging trends,including hybrid model applications and the integration of real-time data processing for seismic fault detection.By providing a detailed comparative analysis of current methodologies,this review aims to guide future research and foster advancements in the effectiveness and reliability of seismic studies.Ultimately,the study seeks to bridge the gap between theoretical investigations and practical implementations in fault detection.
基金supported by the National Natural Science Foundation of China(62325304,U22B2046,62073079,62376029)the Jiangsu Provincial Scientific Research Center of Applied Mathematics(BK20233002)the China Postdoctoral Science Foundation(2023M730255,2024T171123)
文摘Dear Editor,This letter studies the bipartite consensus tracking problem for heterogeneous multi-agent systems with actuator faults and a leader's unknown time-varying control input. To handle such a problem, the continuous fault-tolerant control protocol via observer design is developed. In addition, it is strictly proved that the multi-agent system driven by the designed controllers can still achieve bipartite consensus tracking after faults occur.
文摘Missing data handling is vital for multi-sensor information fusion fault diagnosis of motors to prevent the accuracy decay or even model failure,and some promising results have been gained in several current studies.These studies,however,have the following limitations:1)effective supervision is neglected for missing data across different fault types and 2)imbalance in missing rates among fault types results in inadequate learning during model training.To overcome the above limitations,this paper proposes a dynamic relative advantagedriven multi-fault synergistic diagnosis method to accomplish accurate fault diagnosis of motors under imbalanced missing data rates.Firstly,a cross-fault-type generalized synergistic diagnostic strategy is established based on variational information bottleneck theory,which is able to ensure sufficient supervision in handling missing data.Then,a dynamic relative advantage assessment technique is designed to reduce diagnostic accuracy decay caused by imbalanced missing data rates.The proposed method is validated using multi-sensor data from motor fault simulation experiments,and experimental results demonstrate its effectiveness and superiority in improving diagnostic accuracy and generalization under imbalanced missing data rates.
基金supported by the German Research Foundation(DFG)under the project“Efficient Sensor-Based Condition Monitoring Methodology for the Detection and Localization of Faults on the Railway Track(ConMoRAIL)”,Grant No.515687155.
文摘Supervised learning classification has arisen as a powerful tool to perform data-driven fault diagnosis in dynamical systems,achieving astonishing results.This approach assumes the availability of extensive,diverse and labeled data corpora for train-ing.However,in some applications it may be difficult or not feasible to obtain a large and balanced dataset including enough representative instances of the fault behaviors of interest.This fact leads to the issues of data scarcity and class imbalance,greatly affecting the performance of supervised learning classifiers.Datasets from railway systems are usually both,scarce and imbalanced,turning supervised learning-based fault diagnosis into a highly challenging task.This article addresses time-series data augmentation for fault diagnosis purposes and presents two application cases in the context of railway track.The case studies employ generative adversarial networks(GAN)schemes to produce realistic synthetic samples of geometrical and structural track defects.The goal is to generate samples that enhance fault diagnosis performance;therefore,major attention was paid not only in the generation process,but also in the synthesis quality assessment,to guarantee the suitability of the samples for training of supervised learning classification models.In the first application,a convolutional classifier achieved a test accuracy of 87.5%for the train on synthetic,test on real(TSTR)scenario,while,in the second application,a fully-connected classifier achieved 96.18%in test accuracy for TSTR.The results indicate that the proposed augmentation approach produces samples having equivalent statistical characteristics and leading to a similar classification behavior as real data.
基金supported by the National Natural Science Foundation of China(No.52275104)the Science and Technology Innovation Program of Hunan Province(No.2023RC3097).
文摘The monitoring signals of bearings from single-source sensor often contain limited information for characterizing various working condition,which may lead to instability and uncertainty of the class-imbalanced intelligent fault diagnosis.On the other hand,the vectorization of multi-source sensor signals may not only generate high-dimensional vectors,leading to increasing computational complexity and overfitting problems,but also lose the structural information and the coupling information.This paper proposes a new method for class-imbalanced fault diagnosis of bearing using support tensor machine(STM)driven by heterogeneous data fusion.The collected sound and vibration signals of bearings are successively decomposed into multiple frequency band components to extract various time-domain and frequency-domain statistical parameters.A third-order hetero-geneous feature tensor is designed based on multisensors,frequency band components,and statistical parameters.STM-based intelligent model is constructed to preserve the structural information of the third-order heterogeneous feature tensor for bearing fault diagnosis.A series of comparative experiments verify the advantages of the proposed method.
基金supported in part by the National Natural Science Foundation of China(61933015,61703371,62273030)the Central University Basic Research Fund of China(K20200002)(for NGICS Platform,Zhejiang University)the Social Development Project of Zhejiang Provincial Public Technology Research(LGF19F030004,LGG21F030015).
文摘Data-driven techniques are reshaping blast furnace iron-making process(BFIP)modeling,but their“black-box”nature often obscures interpretability and accuracy.To overcome these limitations,our mechanism and data co-driven strategy(MDCDS)enhances model transparency and molten iron quality(MIQ)prediction.By zoning the furnace and applying mechanism-based features for material and thermal trends,coupled with a novel stationary broad feature learning system(StaBFLS),interference caused by nonstationary process characteristics are mitigated and the intrinsic information embedded in BFIP is mined.Subsequently,by integrating stationary feature representation with mechanism features,our temporal matching broad learning system(TMBLS)aligns process and quality variables using MIQ as the target.This integration allows us to establish process monitoring statistics using both mechanism and data-driven features,as well as detect modeling deviations.Validated against real-world BFIP data,our MDCDS model demonstrates consistent process alignment,robust feature extraction,and improved MIQ modeling—Yielding better fault detection.Additionally,we offer detailed insights into the validation process,including parameter baselining and optimization.
基金supported by the National Natural Science Foundation of China(Nos.41506046,41376060,41706054)the Opening Foundation of Key Laboratory of Ocean and Marginal Sea Geology,CAS(No.MSGL15-05)+1 种基金WPOS(No.XDA11030102-02)the Strategic Priority Research Program of the Chinese Academy of Sciences(No.XDA13010101)
文摘The Pearl River Estuary(PRE) is located at the onshore-offshore transition zone between South China and South China Sea Basin, and it is of great significant value in discussing tectonic relationships between South China block and South China Sea block and seismic activities along the offshore active faults in PRE. However, the researches on geometric characteristics of offshore faults in this area are extremely lacking. To investigate the offshore fault distribution and their geometric features in the PRE in greater detail, we acquired thirteen seismic reflection profiles in 2015. Combining the analysis of the seismic reflection and free-air gravity anomaly data, this paper revealed the location, continuity, and geometry of the littoral fault zone and other offshore faults in PRE. The littoral fault zone is composed of the major Dangan Islands fault and several parallel, high-angle, normal faults, which mainly trend northeast to northeast-to-east and dip to the southeast with large displacements. The fault zone is divided into three different segments by the northwest-trending faults. Moreover, the basement depth around Dangan Islands is very shallow, while it suddenly increases along the islands westward and southward. These has resulted in the islands and neighboring areas becoming the places where the stress accumulates easily. The seismogenic pattern of this area is closely related to the comprehensive effect of intersecting faults together with the low velocity layer.
基金supported by the National Natural Science Foundation of China(61202473)the Fundamental Research Funds for Central Universities(JUSRP111A49)+1 种基金"111 Project"(B12018)the Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues： the missing data samples and the non-Gaussian property of the data. However, most of the existing data-driven methods cannot be able to handle both of them. Thus, a new Bayesian network classifier based fault detection and diagnosis method is proposed. At first, a non-imputation method is presented to handle the data incomplete samples, with the property of the proposed Bayesian network classifier, and the missing values can be marginalized in an elegant manner. Furthermore, the Gaussian mixture model is used to approximate the non-Gaussian data with a linear combination of finite Gaussian mixtures, so that the Bayesian network can process the non-Gaussian data in an effective way. Therefore, the entire fault detection and diagnosis method can deal with the high-dimensional incomplete process samples in an efficient and robust way. The diagnosis results are expressed in the manner of probability with the reliability scores. The proposed approach is evaluated with a benchmark problem called the Tennessee Eastman process. The simulation results show the effectiveness and robustness of the proposed method in fault detection and diagnosis for large-scale systems with missing measurements.
基金Supported by the National Natural Science Foundation of China(Grant U1964201,Grant 61790562 and Grant 61803120)by the Fundamental Research Fundsfor the Central Universities.
文摘Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the location of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.
基金supported by the Natural Science Foundation of Jiangsu Province (BK2006202)
文摘Focusing on the networked control system with long time-delays and data packet dropout,the problem of observerbased fault detection of the system is studied.According to conditions of data arrival of the controller,the state observers of the system are designed to detect faults when they occur in the system.When the system is normal,the observers system is modeled as an uncertain switched system.Based on the model,stability condition of the whole system is given.When conditions are satisfied,the system is asymptotically stable.When a fault occurs,the observers residual can change rapidly to detect the fault.A numerical example shows the effectiveness of the proposed method.
基金supported by National Natural Science Foundation of China(Grant No.61077071,Grant No.51075349)Hebei Provincial Natural Science Foundation of China(Grant No.F2011203207)
文摘The vibration signals of machinery with various faults often show clear nonlinear characteristics.Currently,fractal dimension analysis as the common useful method for nonlinear signal analysis,is a kind of single fractal form,which only reflects the overall irregularity of signals,but cannot describe its local scaling properties.For comprehensive revealing of internal properties,a combinatorial method based on band-phase-randomized(BPR)surrogate data and multifractal is introduced.BPR surrogate data method is effective to eliminate nonlinearity in specified frequency band for a fault signal,which can be utilized to detect nonlinear degree in whole fault signal by nonlinear titration method,and the overall nonlinear distribution of fault signal is displayed in nonlinear characteristic curve that can be used to analyze the fault signal qualitatively.Then multifractal theory as a quantitative analysis method is used to describe geometrical characteristics and local scaling properties,and asymmetry coefficient of multifractal spectrum and multifractal entropy for fault signals are extracted as new criterions to diagnose machinery faults.Several typical faults include rotor misalignment,transversal crack,and static-dynamic rubbing fault are analyzed,and the results indicate that those faults can be distinguished by the proposed method effectively,which provides a qualitative and quantitative analysis way in the field of machinery fault diagnosis.
基金supported by the National Natural Science Foundation of China(61433001)Tsinghua University Initiative Scientific Research Program。
文摘In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis(FDD) methods have been proposed and implemented, the performance of which, however, could be drastically influenced by the common presence of incomplete or missing data in real industrial scenarios. This paper presents a new FDD approach based on an incomplete data imputation technique for process fault recognition. It employs the modified stacked autoencoder,a deep learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification. A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method.
基金financially supported by Guangdong Provincial Science and Technology Plan Projects(20178030314082)General Project of National Natural Science Foundation of China (41676057)National Science and Technology Support Program (2015BAK18B01)
文摘By systemic processing, comprehensive analysis, and interpretation of gravity data, we confirmed the existence of the west segment of the coastal fault zone(west of Yangjiang to Beibu Bay) in the coastal region of South China. This showed an apparent high gravity gradient in the NEE direction, and worse linearity and less compactness than that in the Pearl River month. This also revealed a relatively large curvature and a complicated gravity structure. In the finding images processed by the gravity data system, each fault was well reflected and primarily characterized by isolines or thick black stripes with a cutting depth greater than 30 km. Though mutually cut by NW-trending and NE-trending faults, the apparent NEE stripe-shaped structure of the west segment of the coastal fault zone remained unchanged,with good continuity and an activity strength higher than that of NW and NE-trending faults. Moreover,we determined that the west segment of the coastal fault zone is the major seismogenic structure responsible for strong earthquakes in the coastal region in the border area of Guangdong, Guangxi, and Hainan.
基金Supported by National Basic Research Program of China （973 Program） （2009CB320600）, National Natural Science Foundation of China （60828007, 60534010, 60821063）, the Leverhulme Trust （F/00. 120/BC） in the United Kingdom, and the 111 Project （B08015）
基金supported by Chinese Joint Seismological Science Foundation(A07005)basic research foundation from Institute of Earthquake Science,and State Key Basic Research De-velopment and Programming Project of China(2004CB418403)
文摘The Hori＇s inverse method based on spectral decomposition was applied to estimate coseismic slip distribution on the rupture plane of the 14 November 2001 Ms8.1 Kunlun earthquake based on GPS survey results. The inversion result shows that the six sliding models can be constrained by the coseismic GPS data. The established slips mainly concentrated along the eastern segment of the fault rupture, and the maximum magnitude is about 7 m. Slip on the eastern segment of the fault rupture represents as purely left-lateral strike-slip. Slip on the western segment of the seismic rupture represents as mainly dip-stip with the maximum dip-slip about 1 m. Total predicted scalar seismic moment is 5.196× 10^2° N.m. Our results constrained by geodetic data are consistent with seismological results.
基金supported by the National Natural Science Foundation of China(No.51875113)the Natural Science Joint Guidance Foundation of the Heilongjiang Province of China(No.LH2019E027)the PhD Student Research and Innovation Fund of the Fundamental Research Funds for the Central Universities(No.XK2070021009),China。
文摘A control valve is one of the most widely used machines in hydraulic systems.However,it often works in harsh environments and failure occurs from time to time.An intelligent and robust control valve fault diagnosis is therefore important for operation of the system.In this study,a fault diagnosis based on the mathematical model(MM)imputation and the modified deep residual shrinkage network(MDRSN)is proposed to solve the problem that data-driven models for control valves are susceptible to changing operating conditions and missing data.The multiple fault time-series samples of the control valve at different openings are collected for fault diagnosis to verify the effectiveness of the proposed method.The effects of the proposed method in missing data imputation and fault diagnosis are analyzed.Compared with random and k-nearest neighbor(KNN)imputation,the accuracies of MM-based imputation are improved by 17.87%and 21.18%,in the circumstances of a20.00%data missing rate at valve opening from 10%to 28%.Furthermore,the results show that the proposed MDRSN can maintain high fault diagnosis accuracy with missing data.
文摘As the demand for wind energy continues to grow at exponential rate, reducing operation and maintenance (O & M) costs and improving reliability have become top priorities in wind turbine maintenance strategies. Prediction of wind turbine failures before they reach a catastrophic stage is critical to reduce the O & M cost due to unnecessary scheduled maintenance. A SCADA-data based condition monitoring system, which takes advantage of data already collected at the wind turbine controller, is a cost-effective way to monitor wind turbines for early warning of failures. This article proposes a methodology of fault prediction and automatically generating warning and alarm for wind turbine main bearings based on stored SCADA data using Artificial Neural Network (ANN). The ANN model of turbine main bearing normal behavior is established and then the deviation between estimated and actual values of the parameter is calculated. Furthermore, a method has been developed to generate early warning and alarm and avoid false warnings and alarms based on the deviation. In this way, wind farm operators are able to have enough time to plan maintenance, and thus, unanticipated downtime can be avoided and O & M costs can be reduced.
基金the National Natural Science Foundation of China(No.51775090)the General Program of Civil Aviation Flight University of China(No.J2015-39)
文摘In order to increase the fault diagnosis efficiency and make the fault data mining be realized, the decision table containing numerical attributes must be discretized for further calculations. The discernibility matrix-based reduction method depends on whether the numerical attributes can be properly discretized or not.So a discretization algorithm based on particle swarm optimization(PSO) is proposed. Moreover, hybrid weights are adopted in the process of particles evolution. Comparative calculations for certain equipment are completed to demonstrate the effectiveness of the proposed algorithm. The results indicate that the proposed algorithm has better performance than other popular algorithms such as class-attribute interdependence maximization(CAIM)discretization method and entropy-based discretization method.
文摘Multi-source multi-class classification methods based on multi-class Support Vector Machines and data fusion strategies are proposed in this paper. The centralized and distributed fusion schemes are applied to combine information from several data sources. In the centralized scheme, all information from several data sources is centralized to construct an input space. Then a multi-class Support Vector Machine classifier is trained. In the distributed schemes, the individual data sources are proc-essed separately and modelled by using the multi-class Support Vector Machine. Then new data fusion strategies are proposed to combine the information from the individual multi-class Support Vector Machine models. Our proposed fusion strategies take into account that an Support Vector Machine (SVM) classifier achieves classification by finding the optimal classification hyperplane with maximal margin. The proposed methods are applied for fault diagnosis of a diesel engine. The experimental results showed that almost all the proposed approaches can largely improve the diagnostic accuracy. The robustness of diagnosis is also improved because of the implementation of data fusion strategies. The proposed methods can also be applied in other fields.
