Vertical deformation and axial strain are crucial indicators for evaluating pipeline performance. Accurate prediction of these indicators provides essential support for early warning and proactive maintenance. To achieve this, a multi-sensor monitoring system was constructed by combining an embedded static leveling instrument with a long-gauge fiber-optic grating sensor system to sequentially monitor vertical deformation and axial strain. A novel multi-task prediction model, HO-CNN-BiGRU-AM-HMTL, was proposed to capture the spatiotemporal correlations between deformation and strain. The sensitivity of the model’s hyperparameters was examined, and the effects of dataset size (DS) and prediction horizon on model performance were analyzed. The model’s performance was evaluated by comparing it with existing single-task learning (STL) and multi-task learning (MTL) models in terms of prediction accuracy and computational efficiency. The results indicated that hyperparameter tuning of the hippopotamus optimization module enhanced the model’s performance. The DS showed an initial improvement followed by a decline in performance, while the prediction horizon demonstrated a gradual decrease, then a sharp drop. Maintaining the DS between 4 and 5 months and the prediction horizon within 7 days is recommended. The HO-CNN-BiGRU-AM-HMTL model outperformed existing STL and MTL models in prediction accuracy, reducing computation time by 70.13%–88.48% compared to STL and improving it by 4.05%–40.54% over MTL. Although there was some computational overhead, the overall runtime of the model remained under 16 s, meeting the requirements for engineering applications. This study integrates pipeline engineering with deep learning techniques to enable advanced prediction of deformation and strain, providing crucial support for risk warning and proactive maintenance.
LinRQianHHuangZ, et al. Stress test and analysis of pipeline systems under foundation settlement in a natural gas station. J Pipeline Syst Eng Pract2025; 16(2): 04024075.
2.
XiaoRZayedTMeguidMA, et al. Understanding the factors and consequences of pipeline incidents: an analysis of gas transmission pipelines in the US. Eng Fail Anal2023; 152: 107498.
3.
TsatsisAAlvertosAGerolymosN.Fragility analysis of a pipeline under slope failure-induced displacements occurring parallel to its axis. Eng Struct2022; 262: 114331.
4.
HoMEl-BorgiSPatilD, et al. Inspection and monitoring systems subsea pipelines: a review paper. Struct Health Monit2020; 19(2): 606–645.
5.
DinovitzerSSmithRJ.Strain-based pipeline design criteria review. International Pipeline Conference. Am Soc Mech Eng1998; 40238: 763–770.
6.
Canadian Standards Association. Oil and gas pipeline systems: CSA Z662-2015. Toronto, ON, Canada: Canadian Standards Association, 2015.
7.
GB_T 40702-2021. Specification for geohazard prevention of oil and gas pipelines. Beijing: General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, 2021. (In Chinese.)
8.
ChenZYinYYuJ, et al. Internal deformation monitoring for earth-rockfill dam via high-precision flexible pipeline measurements. Autom Constr2022; 136: 104177.
9.
JinZXiaHNiW, et al. Reference point-free measurement of bridge dynamic deflection by fusing hydraulic leveling and accelerometer signals. Struct Control Health Monit2023; 2023(1): 3203261.
10.
ZhangGCuiFZhangX, et al. Research on underground pipeline spatial positioning method based on multi-offset ground penetrating radar. Measure Sci Technol2024; 36(1): 015140.
11.
ShiJWangZZhangY, et al. Full-length strain and damage monitoring for carbon fiber reinforced polymer cable based on optical frequency domain reflectometry. Mech Syst Signal Process2024; 219: 111627.
12.
WangDZhuHWuB, et al. Performance evaluation of underground pipelines subjected to landslide thrust with fiber optic strain sensing nerves. Acta Geotech2024; 19(10): 6993–7009.
13.
WangHXiangPJiangL.Strain transfer theory of industrialized optical fiber-based sensors in civil engineering: a review on measurement accuracy, design and calibration. Sens Actuat A Phys2019; 285: 414–426.
14.
LuXHeSZhangS.Deep learning for automated crack quantification with distributed fiber optic sensing: addressing strain overlap and interface nonlinearity. Autom Constr2025; 176: 106280.
15.
ZhangSLiuHChengJ, et al. A mechanical model to interpret distributed fiber optic strain measurement at displacement discontinuities. Struct Health Monit2021; 20(5): 2584–2603.
16.
ZhangSLiuHCoulibalyAAS, et al. Fiber optic sensing of concrete cracking and rebar deformation using several types of cable. Struct Control Health Monit2021; 28(2): e2664.
SunZWangXHanT, et al. Pipeline deformation monitoring based on long-gauge fiber-optic sensing systems: methods, experiments, and engineering applications. Measurement2025; 248: 116911.
19.
WangJRenLYouR, et al. Experimental study of pipeline deformation monitoring using the inverse finite element method based on the iBeam3 element. Measurement2021; 184: 109881.
20.
BordaCNiklèsMRochatE, et al. Continuous real-time pipeline deformation, 3D positioning and ground movement monitoring along the Sakhalin-Khabarovsk-Vladivostok pipeline. International Pipeline Conference. Am Soc Mech Eng2012; 45134: 179-187.
21.
YanMTanXMahjoubiS, et al. Strain transfer effect on measurements with distributed fiber optic sensors. Autom Constr2022; 139: 104262.
22.
TanXBaoYZhangQ, et al. Strain transfer effect in distributed fiber optic sensors under an arbitrary field. Autom Constr, 2021, 124: 103597.
23.
LeeJLTyanYYWenMH, et al. Development of an IoT-based bridge safety monitoring system. In: 2017 international conference on applied system innovation (ICASI). Sapporo City, Japan. 2017, pp.84–86. New York: IEEE.
24.
SunZWangXHanT, et al. Pipeline deformation prediction based on multi-source monitoring information and novel data-driven model. Eng Struct2025; 337: 120461.
25.
XuYLChenBNgCL, et al. Monitoring temperature effect on a long suspension bridge. Struct Control Health Monit2010; 17(6): 632–653.
26.
LiSWuZ.Development of distributed long-gage fiber optic sensing system for structural health monitoring. Struct Health Monit2007; 6(2): 133-143.
27.
HongWWuZYangC, et al. Investigation on the damage identification of bridges using distributed long-gauge dynamic macrostrain response under ambient excitation. J Intell Mater Syst Struct2012; 23(1): 85–103.
28.
ShenSWuZYangC, et al. An improved conjugated beam method for deformation monitoring with a distributed sensitive fiber optic sensor. Struct Health Monit2010; 9(4): 361–378.
29.
ZhangJTianYYangC, et al. Vibration and deformation monitoring of a long-span rigid-frame bridge with distributed long-gauge sensors. J Aerosp Eng2017; 30(2): B4016014.
30.
SunZWandXHanT, et al. Research on pipeline monitoring and data recovery based on long-gauge FBG sensor systems. J Basic Sci Eng2025; 33(3): 779–791.
31.
WangBZengYFengD.Deep learning-based damage assessment of hinge joints for multi-girder bridges utilizing vehicle-induced bridge responses. Eng Struct2025; 333: 120148.
32.
LiuJZouZGaoK, et al. A novel digital unit cell library generation framework for topology optimization of multi-morphology lattice structures. Compos Struct2025; 354: 118824.
33.
WangBZengYFengD, et al. Track vertical irregularity estimation for railway bridges using a novel and lightweight deep-learning architecture. Vehicle System Dynamics2025; 63: 1597–1624.
34.
LiuJLiuJGaoK, et al. A bioinspired gradient curved auxetic honeycombs with enhanced energy absorption. Int J Mech Sci2025; 291: 110189.
35.
WangKShenTLiuJ, et al. Exploration of computational formulations for wind-induced interference effects on high-rise buildings via KolmogorovArnold network. Dev Built Environ2025; 24: 100770.
36.
LiuJZouZLiZ, et al. A clustering-based multiscale topology optimization framework for efficient design of porous composite structures. Comput Meth Appl Mech Eng2025; 439: 117881.
37.
WeiJShenTWangK, et al. Transfer learning framework for the wind pressure prediction of high-rise building surfaces using wind tunnel experiments and machine learning. Build Environ2025; 271: 112620.
38.
MaleklooAOzerEAlHamaydehM, et al. Machine learning and structural health monitoring overview with emerging technology and high-dimensional data source highlights. Struct Health Monit2022; 21(4): 1906–1955.
39.
LiYSunZMangalathuS, et al. Seismic damage states prediction of in-service bridges using feature-enhanced swin transformer without reliance on damage indicators. Eng Appl Artif Intell2025; 159: 111651.
40.
LiYSunZLiY, et al. A vision transformer-based method for predicting seismic damage states of RC piers: database development and efficient assessment. Reliab Eng Syst Safe2025; 263: 111287.
41.
DuanJXiongJLiY, et al. Deep learning based multimodal biomedical data fusion: an overview and comparative review. Inform Fusion2024: 102536: 1–30.
42.
CuiLChenYDengJ, et al. A novel attLSTM framework combining the attention mechanism and bidirectional LSTM for demand forecasting. Expert Syst Appl2024; 254: 124409.
43.
MugheesNMohsinSAMugheesA, et al. Deep sequence to sequence Bi-LSTM neural networks for day-ahead peak load forecasting. Expert Syst Appl2021; 175: 114844.
44.
YangYFLiaoSMLiuMB.Dynamic prediction of moving trajectory in pipe jacking: GRU-based deep learning framework. Front Struct Civil Eng2023; 17(7): 994–1010.
45.
ChauhanNSKumarNEskandarianA.A novel confined attention mechanism driven Bi-GRU model for traffic flow prediction. IEEE Trans Intel Transp Syst2024; 25(8): 9181–9191.
46.
PanSYangBWangS, et al. Oil well production prediction based on CNN-LSTM model with self-attention mechanism. Energy2023; 284: 128701.
47.
ZhangYXieXLiH, et al. Subway tunnel damage detection based on in-service train dynamic response, variational mode decomposition, convolutional neural networks and long short-term memory. Autom Constr2022; 139: 104293.
48.
DingLFangWLuoH, et al. A deep hybrid learning model to detect unsafe behavior: integrating convolution neural networks and long short-term memory. Autom Constr, 2018; 86: 118–124.
49.
SainiPNagpalBGargP, et al. CNN-BI-LSTM-CYP: a deep learning approach for sugarcane yield prediction. Sustain Energy Technol Assess2023; 57: 103263.
50.
GulMJUrfaGMPaulA, et al. Mid-term electricity load prediction using CNN and Bi-LSTM. J Supercomput2021; 77: 10942–10958.
51.
GuoYLiYQiaoX, et al. BiLSTM multitask learning-based combined load forecasting considering the loads coupling relationship for multienergy system. IEEE Trans Smart Grid2022; 13(5): 3481–3492.
52.
LiXMaXXiaoF, et al. Multistep ahead multiphase production prediction of fractured wells using bidirectional gated recurrent unit and multitask learning. SPE J2023; 28(1): 381–400.
53.
HuangNWangXWangH, et al. Ultra-short-term multi-energy load forecasting for integrated energy systems based on multi-dimensional coupling characteristic mining and multi-task learning. Front Energy Res2024; 12: 1373345.
54.
ZhuangWCaoY.Short-term traffic flow prediction based on CNN-BiLSTM with multicomponent information. Appl Sci2022; 12(17): 8714.
55.
NiuDYuMSunL, et al. Short-term multi-energy load forecasting for integrated energy systems based on CNN-BiGRU optimized by attention mechanism. Appl Energy2022; 313: 118801.
56.
WanHPNiYQ.Bayesian multi-task learning methodology for reconstruction of structural health monitoring data. Struct Health Monit2019; 18(4): 1282–1309.
57.
VandenhendeSGeorgoulisSVan GansbekeW, et al. Multi-task learning for dense prediction tasks: a survey. IEEE Trans Pattern Anal Mach Intell2021; 44(7): 3614–3633.
58.
LiangJLuYSuM.Hga-lstm: LSTM architecture and hyperparameter search by hybrid GA for air pollution prediction. Genet Program Evolvable Mach2024; 25(2): 20.
59.
SunZWangXHanT, et al. Pipeline deformation monitoring based on long-gauge FBG sensing system: missing data recovery and deformation calculation. J Civil Struct Health Monit2025; 15(7): 2433–2453.
60.
WanCHongWLiuJ, et al. Bridge assessment and health monitoring with distributed long-gauge FBG sensors. Int J Distributed Sensor Netw2013; 9(12): 494260.
61.
DB32/T 2880-2016. Design, construction, and maintenance specifications for fiber optic sensing-based health monitoring systems for bridge and tunnel structures. Nanjing: Jiangsu Provincial Bureau of Quality and Technical Supervision, 2016. (In Chinese.)
62.
TSG D7005-2018. Periodic inspection regulations for pressure pipelines—Industrial pipelines. Beijing: General Administration of Quality Supervision, Inspection and Quarantine of the People’s Republic of China, 2018. (In Chinese.)
63.
AmirzehniPSamadianfardSNazemiAH, et al. Evaluating capabilities of the spline and cubic spline interpolation functions in reference evapotranspiration estimation implementing satellite image data. Earth Sci Inform2023; 16(4): 3779–3795.
64.
ZhaoYFuQLuW, et al. Wavelet denoising and cubic spline interpolation for observation data in groundwater pollution source identification problems. Water Supply2019; 19(5): 1454–1462.
65.
SunTLiuMYeH, et al. Point-cloud-based place recognition using CNN feature extraction. IEEE Sens J2019; 19(24): 12175–12186.
66.
KhanASohailAZahooraU, et al. A survey of the recent architectures of deep convolutional neural networks. Artif Intell Rev2020; 53: 5455–5516.
67.
TorresJFHadjoutDSebaaA, et al. Deep learning for time series forecasting: a survey. Big Data2021; 9(1): 3–21.
68.
ZhouGGuoZSunS, et al. A CNN-BiGRU-AM neural network for AI applications in shale oil production prediction. Appl Energy2023; 344: 121249.
69.
Al-SelwiS. M.HassanMFAbdulkadirSJ, et al. LSTM inefficiency in long-term dependencies regression problems. J Adv Res Appl Sci Eng Technol2023; 30(3): 16–31.
70.
WenZZhouRSuH.MR and stacked GRUs neural network combined model and its application for deformation prediction of concrete dam. Expert Syst Appl2022; 201: 117272.
71.
YangJLiuYYagizS, et al. An intelligent procedure for updating deformation prediction of braced excavation in clay using gated recurrent unit neural networks. J Rock Mech Geotech Eng2021; 13(6): 1485–1499.
72.
ZhangXYeJGaoL, et al. Short-term wind power prediction based on ICEEMDAN decomposition and BiTCN–BiGRU-multi-head self-attention model. Electr Eng2025; 107(3): 2645–2662.
73.
SunYLianJTengZ, et al. COVID-19 diagnosis based on swin transformer model with demographic information fusion and enhanced multi-head attention mechanism. Expert Syst Appl2024; 243: 122805.
74.
LinYWangCSongH, et al. Multi-head self-attention transformation networks for aspect-based sentiment analysis. IEEE Access2021; 9: 8762–8770.
75.
KendallGalYCipollaR. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Salt Lake City, Utah, USA. 2018, pp.7482–7491. New York: IEEE.
76.
MirjaliliSMirjaliliSMLewisA.Grey wolf optimizer. Adv Eng Softw2014; 69: 46–61.
77.
SunZLiYBeiY, et al. Compressive strength resistance coefficient of sustainable concrete in sulfate environments: hybrid machine learning model and experimental verification. Mater Today Commun2024; 39: 108667.
78.
MirjaliliS.SCA: a sine cosine algorithm for solving optimization problems. Knowl-Based Syst2016; 96: 120–133.
79.
SunZWangXHuangH, et al. Predicting compressive strength of fiber-reinforced coral aggregate concrete: interpretable optimized XGBoost model and experimental validation. Structures2024; 64: 106516.
80.
MirjaliliSLewisA.The whale optimization algorithm. Adv Eng Softw2016; 95: 51–67.
81.
AbualigahLShehabMAlshinwanM, et al. Salp swarm algorithm: a comprehensive survey. Neural Comput Appl2020; 32(15): 11195–11215.
82.
KennedyJEberhartR.Particle swarm optimization. In: Proceedings of ICNN’95-international conference on neural networks. Perth, WA, Australia. 1995, vol. 4, pp.1942–1948. New York: IEEE.
83.
SunZLiYLiY, et al. Prediction of chloride ion concentration distribution in basalt-polypropylene fiber reinforced concrete based on optimized machine learning algorithm. Mater Today Commun2023; 36: 106565.
MirjaliliSZMirjaliliSSaremiS, et al. Grasshopper optimization algorithm for multi-objective optimization problems. Appl Intell2018; 48: 805–820.
86.
XingBGaoWJXingB, et al. Invasive weed optimization algorithm. In: JanuszKLakhmiCJ (ed.) Innovative computational intelligence: a rough guide to 134 clever algorithms. Cham, Switzerland: Springer, 2014, pp.177–181.
87.
RaoRVSavsaniVJVakhariaDP.Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems. Comp Aided Des2011; 43(3): 303–315.
88.
AmiriMHMehrabiHNMontazeriM, et al. Hippopotamus optimization algorithm: a novel nature-inspired optimization algorithm. Sci Rep2024; 14(1): 5032.
89.
SunZLiYYangY, et al. Splitting tensile strength of basalt fiber reinforced coral aggregate concrete: optimized XGBoost models and experimental validation. Constr Build Mater2024; 416: 135133.
90.
LiYSunZMangalathuS, et al. Machine learning-based full-life-cycle seismic response assessment for in-service bridge piers: comprehensive analysis of interpretability and seismic fragility. Structures2025; 80: 110050.
91.
SunZLiYLiY, et al. Investigation on compressive strength of coral aggregate concrete: hybrid machine learning models and experimental validation. J Build Eng2024; 82: 108220.
92.
SunZLiYSuL, et al. Investigation of electrical resistivity for fiber-reinforced coral aggregate concrete. Constr Build Mater2024; 414: 135011.
93.
WangSCaoJPhilipSY.Deep learning for spatio-temporal data mining: A survey. IEEE Trans Knowl Data Eng2020; 34(8): 3681–3700.
94.
XieSLinHMaT, et al. Prediction of joint roughness coefficient via hybrid machine learning model combined with principal components analysis. J Rock Mech Geotech Eng2025; 17: 2291–2306.
95.
LiYGuanJGuoL.Peridynamic-driven feature-enhanced vision transformer for predicting defects and heterogeneous materials locations: applications of deep learning in inverse problems. Eng Appl Artif Intell2025; 151: 110677.
96.
XieSJiangZLinH, et al. A new integrated intelligent computing paradigm for predicting joints shear strength. Geosci Front2024; 15(6): 101884.
97.
ArunaMVardhanHTripathiAK, et al. Enhancing safety in surface mine blasting operations with IoT based ground vibration monitoring and prediction system integrated with machine learning. Sci Rep2025; 15(1): 3999.
98.
ChalapathyRKhoaNLDSethuvenkatramanS.Comparing multi-step ahead building cooling load prediction using shallow machine learning and deep learning models. Sustain Energy Grids Netw2021; 28: 100543.
99.
MenghaniG.Efficient deep learning: a survey on making deep learning models smaller, faster, and better. ACM Comput Surv2023; 55(12): 1–37.
