Sensor networks provide means to link people with real world by processing data in real time collected from real-world and routing the query results to the right people. Application examples include continuous monitor...Sensor networks provide means to link people with real world by processing data in real time collected from real-world and routing the query results to the right people. Application examples include continuous monitoring of environment, building infrastructures and human health. Many researchers view the sensor networks as databases, and the monitoring tasks are performed as subscriptions, queries, and alert. However, this point is not precise. First, databases can only deal with well-formed data types, with well-defined schema for their interpretation, while the raw data collected by the sensor networks, in most cases, do not fit to this requirement. Second, sensor networks have to deal with very dynamic targets, environment and resources, while databases are more static. In order to fill this gap between sensor networks and databases, we propose a novel approach, referred to as 'spatiotemporal data stream segmentation', or 'stream segmentation' for short, to address the dynamic nature and deal with 'raw' data of sensor networks. Stream segmentation is defined using Bayesian Networks in the context of sensor networks, and two application examples are given to demonstrate the usefulness of the approach.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
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 data gathering manner of wireless sensor networks, in which data is forwarded towards the sink node, would cause the nodes near the sink node to transmit more data than those far from it. Most data gathering mecha...The data gathering manner of wireless sensor networks, in which data is forwarded towards the sink node, would cause the nodes near the sink node to transmit more data than those far from it. Most data gathering mechanisms nowdo not do well in balancing the energy consumption among nodes with different distances to the sink, thus they can hardly avoid the problem that nodes near the sink consume energy more quickly, which may cause the network rupture from the sink node. This paper presents a data gathering mechanism called PODA, which grades the output power of nodes according to their distances from the sink node. PODA balances energy consumption by setting the nodes near the sink with lower output power and the nodes far from the sink with higher output power. Simulation results show that the PODA mechanism can achieve even energy consumption in the entire network, improve energy efficiency and prolong the network lifetime.展开更多
1553B avionics data bus network may fail due to vibration,temperature,humidity or human error.Therefore,the research on detection technology of 1553B avionics data bus network is an important subject.The key technolog...1553B avionics data bus network may fail due to vibration,temperature,humidity or human error.Therefore,the research on detection technology of 1553B avionics data bus network is an important subject.The key technologies are studied by analyzing the possible faults of the network,including four-wire DC resistance measurement method for conductors-to-shield short test and stub continuity test,equivalent impedance measurement of coupling transformer for main bus continuity test,polarity reversal test base on duty ratio measurement,attenuation measurement base on coupler model,and data path integrity test base on bit error rate calculation.Finally,the implementation methods of key technologies are researched,a portable integrated automatic test system of 1553B data bus network is constructed based on PC 104 computer,and the hardware configuration and test process are especially designed.展开更多
Large latency of applications will bring revenue loss to cloud infrastructure providers in the cloud data center. The existing controllers of software-defined networking architecture can fetch and process traffic info...Large latency of applications will bring revenue loss to cloud infrastructure providers in the cloud data center. The existing controllers of software-defined networking architecture can fetch and process traffic information in the network. Therefore, the controllers can only optimize the network latency of applications. However, the serving latency of applications is also an important factor in delivered user-experience for arrival requests. Unintelligent request routing will cause large serving latency if arrival requests are allocated to overloaded virtual machines. To deal with the request routing problem, this paper proposes the workload-aware software-defined networking controller architecture. Then, request routing algorithms are proposed to minimize the total round trip time for every type of request by considering the congestion in the network and the workload in virtual machines（VMs）. This paper finally provides the evaluation of the proposed algorithms in a simulated prototype. The simulation results show that the proposed methodology is efficient compared with the existing approaches.展开更多
Further development of earthquake equipments is closely associated with that of computer technology. Because Embedded PC104 module has the equivalent functions of PC,it has been widely used in recent years,and can pro...Further development of earthquake equipments is closely associated with that of computer technology. Because Embedded PC104 module has the equivalent functions of PC,it has been widely used in recent years,and can provide a new and flexible hardware design environment,but its applications in observation instruments of earth-quake precursor are rare. The present paper introduces in detail the realization of a networked geo-electrical meter by applying the low price,high reliability embedded PC104 industrial computer.展开更多
Bayesian networks (BNs) have become increasingly popular in recent years due to their wide-ranging applications in modeling uncertain knowledge. An essential problem about discrete BNs is learning conditional probabil...Bayesian networks (BNs) have become increasingly popular in recent years due to their wide-ranging applications in modeling uncertain knowledge. An essential problem about discrete BNs is learning conditional probability table (CPT) parameters. If training data are sparse, purely data-driven methods often fail to learn accurate parameters. Then, expert judgments can be introduced to overcome this challenge. Parameter constraints deduced from expert judgments can cause parameter estimates to be consistent with domain knowledge. In addition, Dirichlet priors contain information that helps improve learning accuracy. This paper proposes a constrained Bayesian estimation approach to learn CPTs by incorporating constraints and Dirichlet priors. First, a posterior distribution of BN parameters is developed over a restricted parameter space based on training data and Dirichlet priors. Then, the expectation of the posterior distribution is taken as a parameter estimation. As it is difficult to directly compute the expectation for a continuous distribution with an irregular feasible domain, we apply the Monte Carlo method to approximate it. In the experiments on learning standard BNs, the proposed method outperforms competing methods. It suggests that the proposed method can facilitate solving real-world problems. Additionally, a case study of Wine data demonstrates that the proposed method achieves the highest classification accuracy.展开更多
文摘Sensor networks provide means to link people with real world by processing data in real time collected from real-world and routing the query results to the right people. Application examples include continuous monitoring of environment, building infrastructures and human health. Many researchers view the sensor networks as databases, and the monitoring tasks are performed as subscriptions, queries, and alert. However, this point is not precise. First, databases can only deal with well-formed data types, with well-defined schema for their interpretation, while the raw data collected by the sensor networks, in most cases, do not fit to this requirement. Second, sensor networks have to deal with very dynamic targets, environment and resources, while databases are more static. In order to fill this gap between sensor networks and databases, we propose a novel approach, referred to as 'spatiotemporal data stream segmentation', or 'stream segmentation' for short, to address the dynamic nature and deal with 'raw' data of sensor networks. Stream segmentation is defined using Bayesian Networks in the context of sensor networks, and two application examples are given to demonstrate the usefulness of the approach.
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 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 P. R. China (60434030, 60673178)
文摘The data gathering manner of wireless sensor networks, in which data is forwarded towards the sink node, would cause the nodes near the sink node to transmit more data than those far from it. Most data gathering mechanisms nowdo not do well in balancing the energy consumption among nodes with different distances to the sink, thus they can hardly avoid the problem that nodes near the sink consume energy more quickly, which may cause the network rupture from the sink node. This paper presents a data gathering mechanism called PODA, which grades the output power of nodes according to their distances from the sink node. PODA balances energy consumption by setting the nodes near the sink with lower output power and the nodes far from the sink with higher output power. Simulation results show that the PODA mechanism can achieve even energy consumption in the entire network, improve energy efficiency and prolong the network lifetime.
基金supported by the Key Equipment Research Project of Air Force of China(KJ2011215)
文摘1553B avionics data bus network may fail due to vibration,temperature,humidity or human error.Therefore,the research on detection technology of 1553B avionics data bus network is an important subject.The key technologies are studied by analyzing the possible faults of the network,including four-wire DC resistance measurement method for conductors-to-shield short test and stub continuity test,equivalent impedance measurement of coupling transformer for main bus continuity test,polarity reversal test base on duty ratio measurement,attenuation measurement base on coupler model,and data path integrity test base on bit error rate calculation.Finally,the implementation methods of key technologies are researched,a portable integrated automatic test system of 1553B data bus network is constructed based on PC 104 computer,and the hardware configuration and test process are especially designed.
基金supported by the National Postdoctoral Science Foundation of China(2014M550068)
文摘Large latency of applications will bring revenue loss to cloud infrastructure providers in the cloud data center. The existing controllers of software-defined networking architecture can fetch and process traffic information in the network. Therefore, the controllers can only optimize the network latency of applications. However, the serving latency of applications is also an important factor in delivered user-experience for arrival requests. Unintelligent request routing will cause large serving latency if arrival requests are allocated to overloaded virtual machines. To deal with the request routing problem, this paper proposes the workload-aware software-defined networking controller architecture. Then, request routing algorithms are proposed to minimize the total round trip time for every type of request by considering the congestion in the network and the workload in virtual machines（VMs）. This paper finally provides the evaluation of the proposed algorithms in a simulated prototype. The simulation results show that the proposed methodology is efficient compared with the existing approaches.
基金"The Study of ELF Receiver"from Ministry of Science and Technology (2001BA601B03-01-03).
文摘Further development of earthquake equipments is closely associated with that of computer technology. Because Embedded PC104 module has the equivalent functions of PC,it has been widely used in recent years,and can provide a new and flexible hardware design environment,but its applications in observation instruments of earth-quake precursor are rare. The present paper introduces in detail the realization of a networked geo-electrical meter by applying the low price,high reliability embedded PC104 industrial computer.
基金supported by the National Natural Science Foundation of China(61573285)the Innovation Foundation for Doctor Dissertation of Northwestern Polytechnical University,China(CX201619)
文摘Bayesian networks (BNs) have become increasingly popular in recent years due to their wide-ranging applications in modeling uncertain knowledge. An essential problem about discrete BNs is learning conditional probability table (CPT) parameters. If training data are sparse, purely data-driven methods often fail to learn accurate parameters. Then, expert judgments can be introduced to overcome this challenge. Parameter constraints deduced from expert judgments can cause parameter estimates to be consistent with domain knowledge. In addition, Dirichlet priors contain information that helps improve learning accuracy. This paper proposes a constrained Bayesian estimation approach to learn CPTs by incorporating constraints and Dirichlet priors. First, a posterior distribution of BN parameters is developed over a restricted parameter space based on training data and Dirichlet priors. Then, the expectation of the posterior distribution is taken as a parameter estimation. As it is difficult to directly compute the expectation for a continuous distribution with an irregular feasible domain, we apply the Monte Carlo method to approximate it. In the experiments on learning standard BNs, the proposed method outperforms competing methods. It suggests that the proposed method can facilitate solving real-world problems. Additionally, a case study of Wine data demonstrates that the proposed method achieves the highest classification accuracy.
