Diagnosis of Intermittent Connections for DeviceNet

An intermittent connection is one of the major problems that affect the network reliability and communication quality.However,little attention has been paid to the detection,analysis and localization of the intermittent connections.Partially due to the limitations of the DeviceNet protocol,there is no effective online diagnostic tool available to identify the location of intermittent connection.On the basis of different DeviceNet fault scenarios induced by intermittent connections,a new graph-based diagnostic method is developed to analyze DeviceNet fault patterns,identify the corresponding fault scenarios,and infer the location of the intermittent connection problem by using passively captured network faults.A novel error source analysis tool,which integrates network data-link layer analysis and feature based network physical layer information,is developed to restore the snapshots of the network communication at each intermittent connection induced error.A graph based location identification method is developed to infer the location of the intermittent connections based on the restored error patterns.A 3-node laboratory test-bed,using master-slave polling communication method,is constructed to emulate the intermittent connection induced faults on the network drop cable by using digital switches,whose on/off states are controlled by a computer.During experiments,the network fault diagnosis is conducted by using information collected on trunk cable（backbone）.Experimental study shows that the proposed method is effective to restore the snapshots of the network errors and locate the drop cable that experiences the intermittent connection problem.

Fault Location Identification for Localized Intermittent Connection Problems on CAN Networks

The intermittent connection（IC）of the field-bus in networked manufacturing systems is a common but hard troubleshooting network problem,which may result in system level failures or safety issues.However,there is no online IC location identification method available to detect and locate the position of the problem.To tackle this problem,a novel model based online fault location identification method for localized IC problem is proposed.First,the error event patterns are identified and classified according to different node sources in each error frame.Then generalized zero inflated Poisson process（GZIP）model for each node is established by using time stamped error event sequence.Finally,the location of the IC fault is determined by testing whether the parameters of the fitted stochastic model is statistically significant or not using the confident intervals of the estimated parameters.To illustrate the proposed method,case studies are conducted on a 3-node controller area network（CAN）test-bed,in which IC induced faults are imposed on a network drop cable using computer controlled on-off switches.The experimental results show the parameters of the GZIP model for the problematic node are statistically significant（larger than 0）,and the patterns of the confident intervals of the estimated parameters are directly linked to the problematic node,which agrees with the experimental setup.The proposed online IC location identification method can successfully identify the location of the drop cable on which IC faults occurs on the CAN network.

Availability evaluation of controller area networks under the influence of intermittent connection faults

Controller area networks(CANs),as one of the widely used fieldbuses in the industry,have been extended to the automation field with strict standards for safety and reliability.In practice,factors such as fatigue and insulation wear of the cables can cause intermittent connection(IC)faults to occur frequently in the CAN,which will affect the dynamic behavior and the safety of the system.Hence,quantitatively evaluating the performance of the CAN under the influence of IC faults is crucial to real-time health monitoring of the system.In this paper,a novel methodology is proposed for real-time quantitative evaluation of CAN availability when considering IC faults,with the system availability parameter being calculated based on the network state transition model.First,the causal relationship between IC fault and network error response is constructed,based on which the IC fault arrival rate is estimated.Second,the states of the network considering IC faults are analyzed,and the deterministic and stochastic Petri net(DSPN)model is applied to describe the transition relationship of the states.Then,the parameters of the DSPN model are determined and the availability of the system is calculated based on the probability distribution and physical meaning of markings in the DSPN model.A testbed is constructed and case studies are conducted to verify the proposed methodology under various experimental setups.Experimental results show that the estimation results obtained using the proposed method agree well with the actual values.