Abstract: to corrosion，wear，and other damages. It causes abnormal vibrations and radiated noise，leading to malfunctions，which seriously affects the safe and stable operation of gas transmission systems. To timely and effectively recognize and locate the abnormal sound in pressure pipeline，the abnormal sound detection method is proposed for pressure pipeline based on acoustic information deep fusion. Firstly，the acoustic information deep fusion framework is constructed，including data-level fusion based on sensor bandwidth and decision-level fusion based on information weight allocation. The multi-channel raw acoustic signals are deeply fused at both the data and decision levels；Then，the acoustic information deep fusion framework is applied to multi-channel sound signals of pressure pipelines to achieve abnormal sound recognition and localization for pressure pipelines. The proposed method is tested by the pressure pipeline experimental datasets. The experimental results demonstrate that the proposed method can accurately recognize and locate the abnormal sounds in pressure pipelines，where the accuracy can reach over 92% under different conditions.