Comparative study on vulnerability assessment for urban buried gas pipeline network based on SVM and ANN methods

Abstract Vulnerability assessment is an effective way to identify systemic weaknesses, thus to provide scientific guidance to make management decisions and avoid potential accidents. Support Vector Machine (SVM) and Artificial Neural Network (ANN) have shown great superiority on vulnerability assessment in many fields. However, their applications on the relationship analysis between the state features of urban buried gas pipeline network and the corresponding vulnerability level have not yet been reported. This paper proposed a uniform framework of the novel application of SVM and ANN methods to vulnerability assessment of urban buried gas pipeline network, and performed a comparison between these two methods on various aspects. The analysis methodology follows a four-stage procedure. First, various indexes influencing vulnerability are selected and quantified for further data generation process, by which enough training and validation samples are obtained. The architecture, essential algorithms and optimized parameters for the application of these two methods are determined by the next process of model selection. The model selection phase for ANN is far more complex than that for SVM, which makes it easy for ANN to come to over-fitting. The third stage is to train SVM and ANN on the training set and to evaluate the performance on the executions of the validation set. The results show that the training outputs of SVM (MSE = 2.74E-4) are better fitted with the desired outputs than that of ANN (MSE = 1.92E-2). The SVM model (SMAPE = 0.79%) is able to output satisfying values when applied to unknown samples and is more accurate than the ANN model (SMAPE = 8.64%) in prediction. Finally, a sample gas pipeline network was used to demonstrate the feasibility and practicability of these two models, where the results are similar and consistent with the reality. The proposed methods can be used in practical applications to support better safety management.

[1]  Mario Vanhoucke,et al.  Support Vector Machine Regression for project control forecasting , 2014 .

[2]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[3]  R. Kasperson,et al.  A framework for vulnerability analysis in sustainability science , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Wei Liang,et al.  A comprehensive risk evaluation method for natural gas pipelines by combining a risk matrix with a bow-tie model , 2015 .

[5]  R. P. Cleaver,et al.  A model for the initial stages following the rupture of a natural gas transmission pipeline , 2015 .

[6]  Qingsheng Wang,et al.  Experimental studies of crevice corrosion for buried pipeline with disbonded coatings under cathodic protection , 2014 .

[7]  Yuichi Moriguchi,et al.  A graph theory-based methodology for vulnerability assessment of supply chains using the life cycle inventory database , 2018 .

[8]  Manolis Papadrakakis,et al.  Vulnerability analysis of large concrete dams using the continuum strong discontinuity approach and neural networks , 2008 .

[9]  Gabriele Landucci,et al.  Vulnerability assessment of chemical facilities to intentional attacks based on Bayesian Network , 2018, Reliab. Eng. Syst. Saf..

[10]  Mario Vanhoucke,et al.  A simulation and evaluation of earned value metrics to forecast the project duration , 2005, J. Oper. Res. Soc..

[11]  Humberto Varum,et al.  A Theory of Vulnerability of Water Pipe Network (TVWPN) , 2010 .

[12]  Qingsheng Wang,et al.  Consequence analysis of accidental release of supercritical carbon dioxide from high pressure pipelines , 2016 .

[13]  John V. Farr,et al.  Infrastructure Risk Analysis Model , 2000 .

[14]  J.-H. Lee,et al.  An Approach to Risk Management of City Gas Pipeline , 2004 .

[15]  Sybil Derrible,et al.  A geographical and multi-criteria vulnerability assessment of transportation networks against extreme earthquakes , 2016, Reliab. Eng. Syst. Saf..

[16]  Shouyang Wang,et al.  Forecasting stock market movement direction with support vector machine , 2005, Comput. Oper. Res..

[17]  Xiangyang Wang,et al.  An SVM-based robust digital image watermarking against desynchronization attacks , 2008, Signal Process..

[18]  Federico Milano,et al.  A computational intelligence-based suite for vulnerability assessment of electrical power systems , 2010, Simul. Model. Pract. Theory.

[19]  Ernesto Salzano,et al.  Seismic vulnerability of gas and liquid buried pipelines , 2014 .

[20]  Neha Pahuja,et al.  Vulnerability assessment of urban road network from urban flood , 2018, International Journal of Disaster Risk Reduction.

[21]  F. Zhang,et al.  Ecological vulnerability assessment based on multi-sources data and SD model in Yinma River Basin, China , 2017 .

[22]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[23]  Ming Yang,et al.  Dynamic failure analysis of process systems using neural networks , 2017 .

[24]  Goutam Saha,et al.  On robustness of speech based biometric systems against voice conversion attack , 2015, Appl. Soft Comput..

[25]  K. Gnana Sheela,et al.  Review on Methods to Fix Number of Hidden Neurons in Neural Networks , 2013 .

[26]  Stefano Marrone,et al.  On synergies of cyber and physical security modelling in vulnerability assessment of railway systems , 2015, Comput. Electr. Eng..

[27]  Faisal Khan,et al.  SVAPP methodology: A predictive security vulnerability assessment modeling method , 2016 .

[28]  Kenneth J. Berry,et al.  A Chronicle of Permutation Statistical Methods , 2014 .

[29]  Hamid R. Safavi,et al.  Conjunctive Use of Surface Water and Groundwater: Application of Support Vector Machines (SVMs) and Genetic Algorithms , 2013, Water Resources Management.

[30]  Víctor Yepes,et al.  A discursive, many-objective approach for selecting more-evolved urban vulnerability assessment models , 2018 .

[31]  Altan Kayran,et al.  Aircraft vulnerability assessment against fragmentation warhead , 2017 .

[32]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[33]  Sheng-Hsun Hsu,et al.  Application of SVM and ANN for intrusion detection , 2005, Comput. Oper. Res..

[34]  Brane Širok,et al.  Towards more detailed determination of third party impact on risk on natural gas pipelines: Influence of population density , 2015 .

[35]  Nubia Velasco,et al.  Optimal sectioning of hydrocarbon transport pipeline by volume minimization, environmental and social vulnerability assessment , 2016 .

[36]  Shuang Li,et al.  Framework for the vulnerability assessment of structure under mainshock-aftershock sequences , 2017 .

[37]  Z Y Han,et al.  Comparison study on qualitative and quantitative risk assessment methods for urban natural gas pipeline network. , 2011, Journal of hazardous materials.

[38]  Biswajeet Pradhan,et al.  Effectiveness evaluation of objective and subjective weighting methods for aquifer vulnerability assessment in urban context , 2016 .

[39]  B. Pradhan,et al.  A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. , 2018, The Science of the total environment.

[40]  Qingsheng Wang,et al.  A mathematical model of crevice corrosion for buried pipeline with disbonded coatings under cathodic protection , 2016 .

[41]  Barry Charles Ezell,et al.  Infrastructure Vulnerability Assessment Model (I‐VAM) , 2007, Risk analysis : an official publication of the Society for Risk Analysis.

[42]  Faisal Khan,et al.  Failure probability analysis of the urban buried gas pipelines using Bayesian networks , 2017 .

[43]  He Sha,et al.  Study on corrosion reliability of oil/gas pipelines based on enhanced Hamacher Operator and Bayesian Assessment , 2017 .

[44]  Shiliang Sun,et al.  Multitask multiclass support vector machines: Model and experiments , 2013, Pattern Recognit..

[45]  Laurence Smith,et al.  The role of expert opinion in environmental modelling , 2012, Environ. Model. Softw..

[46]  Mac McKee,et al.  Multi-time scale stream flow predictions: The support vector machines approach , 2006 .

[47]  Valerio Cozzani,et al.  Quantitative assessment of environmental risk due to accidental spills from onshore pipelines , 2015 .

[48]  S. Corsi,et al.  Territorial vulnerability and local conflicts perspectives for waste disposals siting. A case study in Lombardy region (Italy) , 2017 .

[49]  Rahman Khatibi,et al.  Groundwater vulnerability indices conditioned by Supervised Intelligence Committee Machine (SICM). , 2017, The Science of the total environment.

[50]  Trevor Page,et al.  Eliciting fuzzy distributions from experts for ranking conceptual risk model components , 2012, Environ. Model. Softw..

[51]  Valerio Cozzani,et al.  Security vulnerability assessment of gas pipelines using Discrete-time Bayesian network , 2017 .