Abstract
The tunneling collapse is the main engineering hazard in the construction of the drilling-and-blasting method. The accurate assessment of the tunneling collapse risk has become a key issue in tunnel construction. As for assessing the tunneling collapse risk and providing basic risk controlling strategies, this research proposes a novel multi-source information fusion approach that combines Bayesian network (BN), cloud model (CM), support vector machine (SVM), Dempster–Shafer (D–S) evidence theory, and Monte Carlo (MC) simulation technique. Those methods (CM, BN, SVM) are used to analyze multi-source information (i.e. statistical data, physical sensors, and expert judgment provided by humans) respectively and construct basic probability assignments (BPAs) of input factors under different risk states. Then, these BPAs will be merged at the decision level to achieve an overall risk evaluation, using an improved D–S evidence theory. The MC technology is proposed to simulate the uncertainty and randomness of data. The novel approach has been successfully applied in the case of the Jinzhupa tunnel of the Pu-Yan Highway (Fujian, China). The results indicate that the developed new multi-source information fusion method is feasible for (a) Fusing multi-source information effectively from different models with a high-risk assessment accuracy of 98.1%; (b) Performing strong robustness to bias, which can achieve acceptable risk assessment accuracy even under a 20% bias; and (c) Exhibiting a more outstanding risk assessment performance (97.9% accuracy) than the single-information model (78.8% accuracy) under a high bias (20%). Since the proposed reliable risk analysis method can efficiently integrate multi-source information with conflicts, uncertainties, and bias, it provides an in-depth analysis of the tunnel collapse and the most critical risk factors, and then appropriate remedial measures can be taken at an early stage.
Highlights
An optimization method for the preliminary support parameters was proposed based on the genetic algorithm (GA) and combined covariance Gaussian process regression (CCGPR) coupled algorithm presented to provide a complete information-based construction method for tunnel e ngineering[5]
For expert judgment provided by humans, Bayesian Networks (BN) is used to investigate causal relationships between tunnel collapse and its influential variables based upon the risk/hazard mechanism analysis and expert scores
The tunneling collapse risk assessment results are consistent with reality, which proves the usefulness of the assessment method in the actual construction process
Summary
The highways are extremely important infrastructures for most countries. It ensures communication and development between different regions, especially in the mountains and hilly areas. Z hou[2] proposed a method for tunnel collapse risk analysis based on the fuzzy Analytic Hierarchy Process. Wu et al.[4] proposed an evaluation method based on a dynamic Bayesian network to provide a real-time dynamic risk. Incomplete consideration of information can lead to inaccurate assessment results, which can not provide accurate recommendations to decision makers[8]. This would defeat the purpose of the risk assessment. (1) When multiple sources of information are evaluated differently, D–S theory gives fusion results that are contrary to common sense. To solve the above problems, This research proposes a novel risk assessment approach that integrates Monte–Carlo (MC) simulation technique, normal cloud model (CM), Bayesian networks (BN), probabilistic support vector machine (SVM), and improved D–S evidence theory. This model aims to achieve the following goals: (1) Constructing models to estimate the collapse risk according to the expert judgment, monitoring data, and tunneling collapse database; (2) The judgment of the models is fused to get the final collapse risk assessment result; (3) Evaluating the performance of the models to quantify the quality of judgment
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
