Data Driven CAN Node Reliability Assessment for Manufacturing System

The reliability of the Controller Area Network（CAN） is critical to the performance and safety of the system. However, direct bus-off time assessment tools are lacking in practice due to inaccessibility of the node information and the complexity of the node interactions upon errors. In order to measure the mean time to bus-off（MTTB） of all the nodes, a novel data driven node bus-off time assessment method for CAN network is proposed by directly using network error information. First, the corresponding network error event sequence for each node is constructed using multiple-layer network error information. Then, the generalized zero inflated Poisson process（GZIP） model is established for each node based on the error event sequence. Finally, the stochastic model is constructed to predict the MTTB of the node. The accelerated case studies with different error injection rates are conducted on a laboratory network to demonstrate the proposed method, where the network errors are generated by a computer controlled error injection system. Experiment results show that the MTTB of nodes predicted by the proposed method agree well with observations in the case studies. The proposed data driven node time to bus-off assessment method for CAN networks can successfully predict the MTTB of nodes by directly using network error event data.

Controller area network node reliability assessment based on observable node information

Controller area network(CAN) based fieldbus technologies have been widely used in networked manufacturing systems. As the information channel of the system, the reliability of the network is crucial to the system throughput, product quality, and work crew safety. However, due to the inaccessibility of the nodes' internal states, direct assessment of the reliability of CAN nodes using the nodes' internal error counters is infeasible. In this paper, a novel CAN node reliability assessment method, which uses node's time to bus-off as the reliability measure, is proposed. The method estimates the transmit error counter(TEC) of any node in the network based on the network error log and the information provided by the observable nodes whose error counters are accessible.First, a node TEC estimation model is established based on segmented Markov chains. It considers the sparseness of the distribution of the CAN network errors. Second, by learning the differences between the model estimates and the actual values from the observable node, a Bayesian network is developed for the estimation updating mechanism of the observable nodes. Then, this estimation updating mechanism is transferred to general CAN nodes with no TEC value accessibility to update the TEC estimation. Finally, a node reliability assessment method is developed to predict the time to reach bus-off state of the nodes. Case studies are carried out to demonstrate the effectiveness of the proposed methodology. Experimental results show that the estimates using the proposed model agree well with actual observations.