Fault Identification in Distributed Sensor Networks Based on Universal Probabilistic Modeling

This paper proposes a holistic modeling scheme for fault identification in distributed sensor networks. The proposed scheme is based on modeling the relationship between two datastreams by means of a hidden Markov model (HMM) trained on the parameters of linear time-invariant dynamic systems which estimate the specific relationship over consecutive time windows. Every system state, including the nominal one is represented by an HMM and the novel data are categorized according to the model producing the highest likelihood. The system is able to understand whether the novel data belongs to the fault dictionary, is fault-free or represent a new fault type. We extensively evaluated the discrimination capabilities of the proposed approach and contrasted it with a multilayer Perceptron using data coming from the Barcelona water distribution network. Nine system states are present in the dataset and the recognition rates are provided in the confusion matrix form.

NTALAMPIRAS Stavros; 

2014-12-01

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

JRC84212

2162-237X,   

http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6932473&isnumber=6104215,    https://publications.jrc.ec.europa.eu/repository/handle/JRC84212,   

10.1109/TNNLS.2014.2362015,