Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior predictive capacity, compared to the traditional methods. This paper presents an overview of some soft computing techniques as well as their applications in underground excavations. A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting (XGBoost), Multivariate Adaptive Regression Splines (MARS), Artificial Neural Networks (ANN), and Support Vector Machine (SVM) in estimating the maximum lateral wall deflection induced by braced excavation. This study also discusses the merits and the limitations of some soft computing techniques, compared with the conventional approaches available.

https://dr.ntu.edu.sg/bitstream/10356/146887/2/1-s2.0-S1674987119302361-main.pdf

State-of-the-art review of soft computing applications in underground excavations

The traffic flow prediction is becoming increasingly crucial in Intelligent Transportation Systems. Accurate prediction result is the precondition of traffic guidance, management, and control. To improve the prediction accuracy, a spatiotemporal traffic flow prediction method is proposed combined with k-nearest neighbor (KNN) and long short-term memory network (LSTM), which is called KNN-LSTM model in this paper. KNN is used to select mostly related neighboring stations with the test station and capture spatial features of traffic flow. LSTM is utilized to mine temporal variability of traffic flow, and a two-layer LSTM network is applied to predict traffic flow respectively in selected stations. The final prediction results are obtained by result-level fusion with rank-exponent weighting method. The prediction performance is evaluated with real-time traffic flow data provided by the Transportation Research Data Lab (TDRL) at the University of Minnesota Duluth (UMD) Data Center. Experimental results indicate that the proposed model can achieve a better performance compared with well-known prediction models including autoregressive integrated moving average (ARIMA), support vector regression (SVR), wavelet neural network (WNN), deep belief networks combined with support vector regression (DBN-SVR), and LSTM models, and the proposed model can achieve on average 12.59% accuracy improvement.

/pdf/spatiotemporal-traffic-flow-prediction-with-knn-and-lstm-3snxyuv8jb.pdf

Spatiotemporal Traffic Flow Prediction with KNN and LSTM

BIM-enabled facilities operation and maintenance: A review

Integration of BIM and GIS in sustainable built environment: A review and bibliometric analysis

The current study was carried out to delineate the seasonal hydrochemical characteristics and to quantify the suitability of groundwater for drinking and irrigation purposes in an alluvial plain adjacent to a paper wastewater irrigation zone, northwest China. Groundwater samples were collected from 14 groundwater monitoring wells in pre-monsoon, monsoon and post-monsoon seasons, respectively. Statistical analysis and Chadha diagram were used to delineate the groundwater hydrochemical characteristics. The matter element extension analysis (MEEA) model was proposed to quantify the overall groundwater quality. Irrigation water quality indicators were applied to assess the suitability of groundwater for irrigation purpose. The research results show that the hydrochemical facies for the majority of the groundwater samples is SO4·Cl–Na type with some minor hydrochemical facies of HCO3–Ca·Mg, HCO3–Na, and Cl·SO4–Ca·Mg types. The sequences of ions are Na+ > Ca2+ > Mg2+ > K+ for cations, and HCO3
 − > Cl− > SO4
 2− > CO3
 2− for anions. The major ions and contaminants in the groundwater are controlled by multiple factors including hydrogeological conditions, rock weathering, water–rock interactions and human activities. The values of pH, TDS and TH show reduction in the monsoon season, indicating slight improvement of water quality during the monsoon season. Water quality assessment results based on MEEA show that the overall groundwater quality in the wastewater irrigation zone is generally fair to poor quality. Some groundwater samples are even classified as very poor quality, which is unsuitable for human consumption. They are also unsuitable for irrigation because of potential sodium hazard and salinity hazard. Groundwater from the Yellow River irrigation zone and the alluvial plain is generally suitable for domestic and irrigation uses. Some local water sampling locations may experience water quality improvement during the monsoon season, which, however, will generally not affect the final water quality classification for domestic and irrigation purposes. Interestingly, the study also finds that the variation trend of the correlation degree computed from MEEA can be useful in determining water quality improvement. This study may provide insights for people to make educated decisions in efficient groundwater quality protection and sustainable groundwater quality management.

Seasonal Hydrochemical Characterization and Groundwater Quality Delineation Based on Matter Element Extension Analysis in a Paper Wastewater Irrigation Area, Northwest China

Over the past couple of decades, as a new mathematical tool for addressing a number of tough problems, fractional calculus has been gaining a continually increasing interest in diverse scientific fields, including geotechnical engineering due primarily to geotechnical rheology phenomenon. Unlike the classical constitutive models in which simulation analysis gradually fails to meet the reasonable accuracy of requirement, the fractional derivative models have shown the merits of hereditary phenomena with long memory. Additionally, it is traced that the fractional derivative model is one of the most effective and accurate approaches to describe the rheology phenomenon. In relation to this, an overview aimed first at model structure and parameter determination in combination with application cases based on fractional calculus was provided. Furthermore, this review paper shed light on the practical application aspects of deformation analysis of circular tunnel, rheological settlement of subgrade, and relevant loess researches subjected to the achievements acquired in geotechnical engineering. Finally, concluding remarks and important future investigation directions were pointed out.

/pdf/investigation-progresses-and-applications-of-fractional-2xu6r3zfhv.pdf

Investigation Progresses and Applications of Fractional Derivative Model in Geotechnical Engineering

Compared with electrical strain gauges, fiber Bragg grating (FBG) sensing technology is a relatively novel method for tunnel structural health monitoring, which has a number of advantages including high accuracy, multiplexing, electromagnetic interference resistance, and good repeatability. In order to study the internal force of the tunnel liner and detect the potential safety hazards, series of strain monitoring tests of a loess tunnel, taking into account the complex stress and strain variation of the loess during tunnelling, were performed by employing the tandem linear FBG sensor arrays controlled by the wavelength division multiplexing (WDM) technology. The concrete strain has obvious linear characteristics over time in the early stage and then gradually tends to a stable value. Moreover, after the necessary temperature compensation, loess tunnel structure safety was assessed through the analysis of real-time strain and internal force of the liner concrete, and the FBG monitoring data and safety assessment results indicate that the safety factors of various liner sections all meet the code requirements, which verify the safety and stability of the tunnel liner structure. The FBG sensors-based in situ monitoring technology can be well applied in the loess tunnel structure safety assessment.

/pdf/fiber-bragg-grating-sensors-based-in-situ-monitoring-and-hzhwdjd9cu.pdf

Fiber Bragg Grating Sensors-Based In Situ Monitoring and Safety Assessment of Loess Tunnel

Freeze-proof method and test verification of a cold region tunnel employing electric heat tracing

In the past few decades, as a new tool for analysis of the tough geotechnical problems, artificial neural networks (ANNs) have been successfully applied to address a number of engineering problems, including deformation due to tunnelling in various types of rock mass. Unlike the classical regression methods in which a certain form for the approximation function must be presumed, ANNs do not require the complex constitutive models. Additionally, it is traced that the ANN prediction system is one of the most effective ways to predict the rock mass deformation. Furthermore, it could be envisaged that ANNs would be more feasible for the dynamic prediction of displacements in tunnelling in the future, especially if ANN models are combined with other research methods. In this paper, we summarized the state-of-the-art and future research challenges of ANNs on the tunnel deformation prediction. And the application cases as well as the improvement of ANN models were also presented. The presented ANN models can serve as a benchmark for effective prediction of the tunnel deformation with characters of nonlinearity, high parallelism, fault tolerance, learning, and generalization capability.

/pdf/prediction-of-soil-deformation-in-tunnelling-using-3fvjbhbknh.pdf

Prediction of soil deformation in tunnelling using artificial neural networks

The construction blasting in a new tunnel will undoubtedly influence the structure of existing tunnel. In order to monitor the effect of the blast-induced vibration on the structure of existing tunnel, a wireless sensor network (WSN) was established, which included the blast vibration monitoring system and the wireless remote data acquisition system. An existing railway tunnel was monitored during the construction of a new tunnel in Shaanxi, China. Concrete strain and peak particle velocity (PPV) were adopted to evaluate the influence of new tunnel construction blasting on the structure of existing tunnel. The monitoring results indicated that the concrete strain was different before and after the two tunnels crossing, which was much larger in front of the excavation face, and then it decreased gradually after the crossing. The PPV at the side wall of existing tunnel toward the blasting source was quite higher, and the location of maximum PPV changes with the process of tunnel excavation. When the distance between the existing and new tunnels was 4 m, the PPV reached 11.83 cm/s, which was already beyond the safe value, so the explosive charge should be reduced.

https://journals.sagepub.com/doi/pdf/10.1155/2015/703980

Haobo Fan

Papers

Investigation Progresses and Applications of Fractional Derivative Model in Geotechnical Engineering

Fiber Bragg Grating Sensors-Based In Situ Monitoring and Safety Assessment of Loess Tunnel

Freeze-proof method and test verification of a cold region tunnel employing electric heat tracing

Prediction of soil deformation in tunnelling using artificial neural networks

Blasting vibration monitoring of undercrossing railway tunnel using wireless sensor network