Operating in harsh environments such as high temperature and high pressure for a long time, pressure pipelines are prone to corrosion, wear, and other damages. It can cause abnormal vibrations and radiated noise, leading to malfunctions and seriously affecting the safe and stable operation of gas transmission systems. To timely and effectively recognize and locate abnormal sounds in pressure pipelines, the data and decision-level hybrid fusion is proposed for pressure pipeline abnormal sound detection and pattern recognition. First, the acoustic information deep fusion framework is constructed by deeply fusing multichannel raw acoustic signals at two levels, including data level fusion based on sensor bandwidth and decision level fusion based on information weight allocation. Then, the acoustic information deep fusion framework is applied to multichannel acoustic signals collected from the pressure pipelines for pattern recognition, and it achieves abnormal sound recognition and localization. Specially, the proposed method is tested using publicly datasets GPLA-12 and pressure pipeline experimental datasets. The results illustrate that the proposed method can accurately recognize and locate the abnormal sounds for pressure pipelines pattern recognition. The accuracy exceeded 92% under different working conditions. The superiority of the proposed method is further highlighted by comparing it with other methods.
SoomroAMokhtarAHussinH, et al. Analysis of machine learning models and data sources to forecast burst pressure of petroleum corroded pipelines: a comprehensive review. Eng Fail Anal2024; 155: 107747.
2.
KhabbaziAZabihiMLiR, et al. Mixing hydrogen into natural gas distribution pipeline system through Tee junctions. Int J Hydrogen Energy2024; 49: 1332–1344.
3.
ZhanYLiuLWangZ, et al. Pipeline leakage identification method based on DPR-net and distributed optical fiber acoustic sensing technology. Opt. Commun2025; 574: 131096.
4.
NnokaMJackTASzpunarJ.Effects of different microstructural parameters on the corrosion and cracking resistance of pipeline steels: a review. Eng Fail Anal2024; 159: 108065.
5.
YangXFangHYuX, et al. Study on the mechanism of vibration signal generation in water supply pipeline leaks. Measurement2024; 229: 114415.
6.
ZhangKMaRChenS, et al. Simulation and experimental research on the propagation mechanisms of acoustic energy inside the pipeline to detect the leakage. GeoEnergy Sci Eng2024; 243: 213410.
7.
ShenJGaoEMaT, et al. An unsupervised mixed-up differential replay mechanism for propagation detection of blade crack. Adv Eng Inform2025; 68: 103732.
8.
YaoLZhangYHeT, et al. Natural gas pipeline leak detection based on acoustic signal analysis and feature reconstruction. Appl Energy2023; 352: 121975.
9.
PengLHuYZhangJ, et al. Pipeline leak location method based on SSA-VMD with generalized quadratic cross-correlation. Meas Sci Technol2024; 35: 116105.
10.
ChengLZhangKLuoB, et al. A new numerical model of gas leakage noise from elliptical sealing defects in pipelines. Appl Acoust2024; 217: 109829.
11.
LiangJLiangSMaL, et al. Leak detection for natural gas gathering pipeline using spatio-temporal fusion of practical operation data. Eng Appl Artif Intell2024; 133: 108360.
12.
WangXWangTBiH, et al. ECNet: Network Based on encoder with local convolutional attention and cross layer information fusion for natural gas pipeline leakage detection. IEEE Sens J2024; 24(7): 11886–11894.
13.
LiuSHeR.Decision-level fusion detection method of hydrogen leakage in hydrogen supply system of fuel cell truck. Fuel2024; 367: 131455.
14.
YangJGaoTZhangH, et al. A multi-sensor fault diagnosis method for rotating machinery based on improved fuzzy support fusion and self-normalized spatio-temporal network. Meas Sci Technol2023; 34: 125112.
15.
RanipaKZhuWPSwamyM N S.A novel feature-level fusion scheme with multimodal attention CNN for heart sound classification. Comput Methods Programs Biomed2024; 248: 108122.
16.
ShenJMaTSongD, et al. An embedded physical information network for blade crack detection considering dynamic multi-level credibility. Mech Syst Signal Process2025; 224: 111948.
17.
ZhaoLCaoZDengJ.A review of leak detection methods based on pressure waves in gas pipelines. Measurement2024; 236: 115062.
18.
WangTYinL.A hybrid 3DSE-CNN-2DLSTM model for compound fault detection of wind turbines. Expert Syst Appl2024; 242: 122776.
19.
SarwarUMuhammadMMokhtarA, et al. Hybrid intelligence for enhanced fault detection and diagnosis for industrial gas turbine engine. Results Eng2024; 21: 101841.
20.
JiangHLiWLiuY, et al. A hybrid EMD-GRU model for pressure prediction in air cyclone centrifugal classifiers. Adv Powder Technol2025; 36(1): 104743.
21.
WangWLiuBLiH, et al. Fast time-domain identification of dynamic loads and inversion of dynamic response field for flood discharge sluice structure based on data-level information fusion. Mech Syst Signal Process2025; 232: 112677.
22.
LuoYWangTLuS, et al. Multi-LiDAR-Based 3D object detection via data-level fusion method. Int J Antennas Propag2025; 1: 7833763.
23.
JayasekherAPrajapatiDPalitA, et al. Multi-spectral sensor fusion methodology for the quality assessment of Cymbopogon citratus essential oil. Microchem J2025; 213: 113878.
24.
WangYWangHBaiR, et al. Enhanced rolling bearing fault diagnosis using multimodal deep learning and singular spectrum analysis. Appl Sci2025; 15(9): 4828.
25.
MaDLiuZGaoQ, et al. Few-shot fault diagnosis of EHA based on MTF-ResNet-MA and dual-attribute adaptive decision-level fusion. Measurement2025; 247: 116787.
26.
GhadarahNSAyreD.A comparative analysis of acoustic emission sensor embedding in glass fibre composite. Compos Sci Technol2024; 247: 110392.
27.
RahmanMATaheriHDababnehF, et al. A review of distributed acoustic sensing applications for railroad condition monitoring. Mech Syst Signal Process2024; 208: 110983.
28.
IvancicJAlvesF.Directional multi-resonant micro-electromechanical system acoustic sensor for low frequency detection. Sensors (Basel)2024; 24(9): 2908.
29.
ShiraziMIKhatirSBoutchichaD, et al. Feature extraction and classification of multiple cracks from raw vibrational responses of composite beams using 1D-CNN network. Compos Struct2024; 327: 117701.
30.
SaufiMSRMIshamMFTalibMHA, et al. Extremely low-speed bearing fault diagnosis based on raw signal fusion and de-1d-cnn network. J Vib Eng Technol2024; 12(4): 5935–5951.
31.
SinghSKKhawaleRPHazarikaS, et al. Hybrid physics-infused 1D-CNN based deep learning framework for diesel engine fault diagnostics. Neural Comput Appl2024; 36(28): 17511–17539.
32.
KibreteFWoldemichaelDEGebremedhenHS.Multi-sensor data fusion in intelligent fault diagnosis of rotating machines: a comprehensive review. Measurement2024; 232: 114658.
33.
ChangWGuXZhangX, et al. Numerical study of the soil temperature field affected by natural gas pipeline leakage. Processes2024; 13(1): 36.
34.
GanWLiXWangY, et al. Gas pipeline leakage detection and location by using w-FBG array based micro-strain sensing technology. Meas Sci Technol2024; 35: 056108.
35.
SongDMaTLiY, et al. Data and decision level fusion-based crack detection for compressor blade using acoustic and vibration signal. IEEE Sens J2022; 22(12): 12209–12218.
36.
GaoTYangJZhangB, et al. A fault diagnosis method based on feature-level fusion of multi-sensor information for rotating machinery. Meas Sci Technol2023; 35: 036109.
37.
PuHChenZLiuJ, et al. Research on decision-level fusion method based on structural causal model in system-level fault detection and diagnosis. Eng Appl Artif Intell2023; 126: 107095.
38.
YangXFangCKunduP, et al. A decision-level sensor fusion scheme integrating ultrasonic guided wave and vibration measurements for damage identification. Mech Syst Signal Process2024; 219: 111597.
39.
WangBCaiPWangF, et al. Cavitation mechanism study and failure analysis of high-pressure ball valve. Eng Fail Anal2025; 170: 109269.
40.
ZhaoYWangYZhangM, et al. Failure analysis of the outlet pipeline and ball valve of the circulating pump in the desulfurization liquid concentration tower. Eng Fail Anal2024; 170: 108338.
