The early-warning model of equipment chain in gas pipeline based on DNN-HMM

Since the operating state of the compressor unit could be influenced by several factors including connected pipeline, auxiliary system and other related equipment, it is necessary to treat the compressor unit as a sub-chain of the whole pipeline equipment chain. To deal with the indistinguishable phenomena in the compressor unit, including pipeline leakage, ice jam and auxiliary system failure, an innovative early-warning model based on analyses of characteristics of early-warning system and equipment chain is proposed in this thesis, which fully takes advantage of feature extraction of deep belief network (DNN) and hidden state analysis of hidden Markov model (HMM) to estimate the operating status of the compressor unit. Validated by field data, the model is demonstrated to be of preferable accuracy and generalization for early-warning of the equipment chain by results of experiments. Moreover, it is advantageous in terms of processing speed.