Multivariate time series forecasting is crucial for constructing digital twin systems for urban utility tunnels. We collect diverse environmental sensor data for multivariate time series forecasting, ensuring tunnel safety. However, static sensor networks usually utilize fixed distances to reflect the spatial correlation, making it struggle to capture the dynamic spatial correlations among them. In addition, different environmental factors in utility tunnels exhibit temporal features of different periods. To overcome these challenges, we propose a spatio-temporal model, which can adaptively learn graph structures to grasp dynamic spatial correlations among different environmental factors and employ a temporal convolutional module to capture various temporal features among different environmental factors. Additionally, we integrate a linear capture module with a nonlinear feature in parallel, forming the graph and temporal convolution-linear capture networks (GTCLNs). We carry out experiments utilizing real-world datasets from Suzhou utility tunnels, demonstrating that our model outperforms baseline models and provides support for the precise construction of digital twin systems.
WangTTanLXieS, et al.Development and applications of common utility tunnels in china. Tunnel Underground Space Technol2018; 76: 92–106.
2.
Canto-PerelloJCuriel-EsparzaJ. Risks and potential hazards in utility tunnels for urban areas. In: Proceedings of the institution of civil engineers-municipal engineer, Vol. 156, 2003, pp.51–56. Thomas Telford Ltd.
3.
HuangPDengXHuangW, et al.Research on safety of operation and maintenance of utility tunnel based on bim and computer technology. In: Journal of physics: Conference series, Vol. 1815, 2021, p.012009. IOP Publishing.
4.
GuoJLvZ. Application of digital twins in multiple fields. Multimed Tools Appl2022; 81: 26941–26967.
5.
LiuMFangSDongH, et al.Review of digital twin about concepts, technologies, and industrial applications. J Manufact Syst2021; 58: 346–361.
6.
TaoFChengJQiQ, et al.Digital twin-driven product design, manufacturing and service with big data. Int J Adv Manufact Technol2018; 94: 3563–3576.
7.
YuGZhangSHuM, et al.Prediction of highway tunnel pavement performance based on digital twin and multiple time series stacking. Adv Civil Eng2020; 2020: 8824135.
8.
HuWHeYLiuZ, et al.Toward a digital twin: time series prediction based on a hybrid ensemble empirical mode decomposition and bo-lstm neural networks. J Mech Design2021; 143: 051705.
9.
HamiltonJD. Time series analysis. Princeton, NJ: Princeton university press, 2020.
10.
WilliamsBMHoelLA. Modeling and forecasting vehicular traffic flow as a seasonal arima process: theoretical basis and empirical results. J Transport Eng2003; 129: 664–672.
11.
ZivotEWangJ. Vector autoregressive models for multivariate time series. In: Modeling financial time series with S-PLUS®, 2006. pp.369–413. Springer.
12.
ZhangGP. Time series forecasting using a hybrid arima and neural network model. Neurocomputing2003; 50: 159–175.
13.
WuZPanSLongG, et al.Connecting the dots: multivariate time series forecasting with graph neural networks. In: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, 2020, pp.753–763.
14.
ZhangNLinAShangP. Multidimensional k-nearest neighbor model based on eemd for financial time series forecasting. Phys A: Stat Mech its Appl2017; 477: 161–173.
15.
ShihSYSunFKLeeHy. Temporal pattern attention for multivariate time series forecasting. Mach Learn2019; 108: 1421–1441.
16.
ChangYYSunFYWuYH, et al.A memory-network based solution for multivariate time-series forecasting. arXiv preprint arXiv:180902105 2018.
17.
HuangSWangDWuX, et al.Dsanet: dual self-attention network for multivariate time series forecasting. In: Proceedings of the 28th ACM international conference on information and knowledge management, 2019, pp.2129–2132.
18.
ZhouKLiFCaiH, et al.Estimation of the natural gas leakage source with different monitoring sensor networks in an underground utility tunnel: From the perspectives of energy security. Energy Build2022; 254: 111645.
19.
Canto-PerelloJCuriel-EsparzaJCalvoV. Criticality and threat analysis on utility tunnels for planning security policies of utilities in urban underground space. Expert Syst Appl2013; 40: 4707–4714.
20.
HaiNGongDLiuS. Ontology knowledge base combined with bayesian networks for integrated corridor risk warning. Comput Commun2021; 174: 190–204.
21.
ChenZLChenJYLiuH, et al.Present status and development trends of underground space in chinese cities: evaluation and analysis. Tunnel Underground Space Technol2018; 71: 253–270.
22.
GuoJQianYWangZ, et al.Research on common operation and maintenance disasters and countermeasures of urban underground integrated pipe corridors. Disast Sci2019; 34: 27–33.
23.
BaiYWuJLiuK, et al.Energy-based coupling risk assessment (cra) model for urban underground utility tunnels. Reliab Eng Syst Safety2024; 250: 110255.
24.
LaiGChangWCYangY, et al.Modeling long-and short-term temporal patterns with deep neural networks. In: The 41st international ACM SIGIR conference on research & development in information retrieval, 2018, pp.95–104.
25.
WuHXuJWangJ, et al.Autoformer: decomposition transformers with auto-correlation for long-term series forecasting. Adv Neural Inf Process Syst2021; 34: 22419–22430.
26.
ShabaniAAbdiAMengL, et al.Scaleformer: iterative multi-scale refining transformers for time series forecasting. arXiv preprint arXiv:220604038 2022.
27.
LiuYHuTZhangH, et al.itransformer: inverted transformers are effective for time series forecasting. arXiv preprint arXiv:231006625 2023.
28.
YuBYinHZhuZ. Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. arXiv preprint arXiv:170904875, 2017.
29.
LiZLZhangGWYuJ, et al.Dynamic graph structure learning for multivariate time series forecasting. Pattern Recognit2023; 138: 109423.
30.
YeJLiuZDuB, et al.Learning the evolutionary and multi-scale graph structure for multivariate time series forecasting. In: Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, 2022, pp.2296–2306.
31.
HuangGLiuRLiuM, et al.Modeling and simulating nonstationary thunderstorm winds based on multivariate ar-garch. J Wind Eng Indust Aerodyn2021; 211: 104565.
32.
LiuHDongZJiangR, et al.Staeformer: spatio-temporal adaptive embedding makes vanilla transformer sota for traffic forecasting. arXiv preprint arXiv:230810425 2023.
