Ebook: Information Technology in Geo-Engineering

Joint Technical Committee 2 (JTC2)

JTC2 is a Joint Technical Committee of the three international geo-engineering societies (International Association for Engineering Geology and the Environment (IAEG), International Society for Rock Mechanics (ISRM) and International Society for Soil Mechanics and Geotechnical Engineering (ISSMGE)) on Representation of Geo-Engineering Data.

Information technology has changed our lives and, at the same time, has become widely used in Geo-Engineering. As the science develops, the role that information technology plays becomes more and more important in every aspect of Geo-Engineering, covering investigation, design, construction and maintenance. Moreover, innovative concepts, strategies and technologies have sprung up like mushrooms, and when properly applied in Geo-Engineering have facilitated design processes, improved construction efficiency and lowered maintenance costs. The conference aimed to provide a showcase for engineers, scientists, researchers and educators, to review recent developments and advancements of information technology in Geo-Engineering, and to offer a forum to discuss the future directions of this vital topic.

This event was the first time where academics and practitioners worldwide in the field of information technology in geo-engineering came together, and it provided an insight into a new era of information technology in geo-engineering. We hope that this first conference, and this volume of proceedings, will form the foundation and the impetus for a long-running series of international conferences on a topic that is likely to gain even more importance in the future.

One of the greatest challenges facing civil engineers in the 21st century is the stewardship of ageing civil engineering infrastructure. Nowhere is this more apparent than in underground structures in the major cities around the world. Much of them were constructed more than half a century ago and there is widespread evidence of deterioration. Advances in the development of computer vision and miniature micro-electro-mechanical sensors (MEMS) offer intriguing possibilities that can radically alter the paradigms underlying existing methods of condition assessment and monitoring of such infrastructure. This paper discusses potentials of these technologies for monitoring underground infrastructure.

The use of information technology (IT) in a variety of engineering fields is increasing in order to expedite routine engineering design and analysis procedures. In geotechnical engineering, various types of information technology, such as geographical information system (GIS), artificial intelligence (AI), and numerical simulation, are now being actively used to predict, visualize, and analyze physical parameters. In this paper, the recent development in integration of IT into geotechnical engineering fields are presented with emphasis on the use of GIS in tunnelling risk management. A combined technique that couples the artificial neural network (ANN) and the GIS is then presented. The proposed approach involves the development of ANN(s) using a calibrated finite element model(s) for use as a prediction tool and implementation of the developed ANN(s) into a GIS platform for visualization and analysis of spatial distribution of predicted results. A novel feature of the proposed approach is an ability to expedite a routine geotechnical design process that otherwise require significant time and effort in performing numerical analyses for different design scenarios. Two illustrative examples in which the developed approach was implemented are given; one for an urban tunnelling design project and the other for a soft ground improvement design project. It is shown that the proposed approach can be an efficient and robust decision making tool for routine geotechnical design works. This paper describes the concept and details of the proposed approach and its implementation to an urban tunnel and a soft ground improvement design projects.

Digital geoinformation for the surface and subsurface is virtually never integrated in civil engineering projects. Reasons are that the surface information is gathered by different person's and that the subsurface information is in different formats from the surface information. Likelihood and uncertainty of subsurface models is not quantifiable. To quantify the likelihood and correctness of the subsurface information the civil engineer would have to have full access to the original data, which is not available due to the none integration of the data. In the last 10 years considerable progress has been made in use of geographic information systems but the progress in the integration of data and the addressing of likelihood of subsurface data is limited.

Shield tunnelling method was used from 1920 in Japan. As the innovation of closed type shield technology around 1970's, the number of shield tunnel constructions in urban area increased rapidly. As a result, more than 4000 shield tunnels have been constructed in Japan and maintenance work for aged shield tunnels increases recently. To carry out the maintenance work efficiently, not only the maintenance data after the completion of shield tunnel construction, but also the construction data are necessary. Therefore, JSCE established the technical committee on shield tunnel database in 2007. At first, the TC carried out the questionnaire survey on the database concerned with shield tunnels to the owners and contractors of shield tunnels to grasp present status. From this questionnaire survey, it was found that the maintenance data are well updated by the owners, but the detail construction data become lost according to time passing. Therefore, the TC focused on the detail construction data and discussed the methodology to establish the shield tunnel database on construction data. This paper presents the overview of the shield tunnel database, based on the interim report by the TC.

The European project “Technology Innovation in Underground Construction” is the biggest single research initiative ever undertaken on the topic. Some innovations that resulted from the project and that are associated with some topics of the conference are presented.

A new data mining method of Support Vector Machines (SVM) is applied on the classification of rock mass in tunnels. SVM is a novel powerful leaning method that based on Statistical Learning Theory. SVM can solve small-sample learning problems better than neural network. Eight qualitative indexes, such as rock layer thickness, rock mass structure, inlay condition, weathering condition, groundwater characteristic, joint condition, hammer knocking sound and ground stress, are chose as the judge factors. Twenty two data samples from Niba mountain tunnel are used to train the SVM with different kernels, such as linear, quadratic and polynomial kernel. Use the mapping relationship between judge factors and rock mass classes which the SVM provided class-unknown data samples of rock mass can be discriminated. Ten samples of test data are used to test the accuracy of SVM with different kernels. The result of the classification shows that SVM with polynomial kernel have a high accuracy when classify the rock mass. A website that based on ASP.NET and database has been developed to store the geological data from the tunnel, and using these data the background program which based on SVM can calculate the class that the surrounding rocks of the tunnel belong to, and the result can be show on the web page for engineers to use. So this is an intelligent classification of rock mass method that can be applied to classify rock mass in tunnels and is also a kind of information technologies in Geo-Engineering.

In the present paper, Data Mining techniques has been applied to evaluate the stability of slopes. For this propose, the R (www.r-project.org) software was used together with a user defined application developed at the University of Minho called RMiner. The factor of safety (FS) and probability of failure (PF) were computed for 365 homogeneous slopes using the software SLOPE/W with varying geometric parameters (e.g. height, height of the water surface and slope angle) and geotechnical parameters (weight density, cohesion intercept and angle of shearing resistance). Heights between 10 m and 15 m and slope angles between 40° and 70° were considered. This data allowed building a database to be analyzed using the Data Mining techniques. In this process, several algorithms were used for the prediction of FS and PF, such as multiple regression, regression trees, artificial neural networks, support vector machines and k-nearest neighbours. To evaluate the performance of each technique REC curves (Regression Error Characteristic) and several error measures were used. This application allowed developing reliable models to predict important safety parameters for slopes without a classical limit equilibrium calculation carried out. They also allow performing quick parametric studies for the early stages of slope design. To predict FS, the support vector machines showed the best overall performance. In the case of PF, the artificial neural network proved to be more reliable to predict this parameter. By this study, it was also possible to conclude that cohesion intercept was the parameter with more influence on the assessed safety parameters.

Jet Grouting (JG) technology is currently applied in many geotechnical works for improving mechanics properties of soil, mainly soft-soils. In many geotechnical structures advance design incorporates the serviceability design criteria. For this purpose, deformability properties of the improved soils are needed. In this paper, three data mining models, i.e. Artificial Neural Network (ANN), Support Vector Machine (SVM) and Functional Network (FN), were used to predict the Elastic Young Modulus (E₀) of JG laboratory formulations of cases studies using JG technology for soils improvement. Furthermore, the results obtained were compared with the Eurocode 2 predictive formula, as well as with the CEB-FIP Model Code 1990 approach. The proposed predictive approaches of E₀ can give a valuable contribution in terms of improving the construction control process of JG columns and reducing the costs of laboratory formulations.

This paper introduced the method and principle of a traditional probability neural network (PNN) and an adaptive probability neural network (APNN). Based on inverse problem theory, the question of soil classify is investigated. A new method based on the APNN and RBF neural network is put forward. And an intellectualized analysis system of soil classification is established, consisting of parameter estimation and pat-tern recognition. In the system, the variability of soil physical parameters is thought to be small, whereas variability of mechanics parameters is large. A RBF neural network model is established to reflect mechanics pa-rameters according physics parameters. It can offer a good approach to soil classify by APNN. Examples presented in the paper indicate that this method is neat and effective.

Although the mining residues in a global way can be classified in a single class of granular material, a set of causes lead to a variability of the geotechnical characteristics of the material and of the internal structure of the dams constituted from these. Consequently, to adopt a hypothesis of homogeneity to estimate the mechanical stability of this kind of works (slope stability, liquefaction risk, …), can drive to a not realistic evaluation of the safety. To study the risk of stability of tailings dams, it is necessary to have a probabilistic approach. Indeed, the variability of the soils properties is the main cause of the uncertainty in the geotechnical design. It is thus necessary to know the distribution laws and the characteristics of average, deviation or distribution of the input parameters of soil mechanical models. The obtaining of these laws by laboratory test is boring, expensive and long. This article suggests demonstrating that it is possible to estimate these input parameters and them characteristics of distribution from the measure of the variability on the physical and state characteristics by means of in situ tests. By this way, authors show it is possible to obtain a very good estimation of the friction angle and carry out a probabilistic study of dam stability taking into account the mechanical parameters variability.

This paper introduces a solution of unequal interval deformation prediction by using non-equidistant Grey Model (1,1) (GM(1,1)) which is an effective tool to study uncertain system and can establish a mathematical model based on a spot of data. Firstly, the Grey System Theory is introduced briefly and the modeling process of non-equidistant GM(1,1) is shown. Secondly, the idea of real-time forward simulation is emphasized, which can improve prediction accuracy greatly. Thirdly, an algorithm for unequal interval deformation prediction is studied and realized by MATLAB, and a data fitting problem is verified as well for algorithm's correctness. Fourthly, a comparative analysis between the predicted and actual data is conducted based on a practical engineering, the result shows that the unequal interval grey model is effective whose prediction result is close to the reality and the feedback monitoring information is very important for the accuracy of the prediction. Then, a rebuilding of grey background level based on Lagrange interpolation is carried out. A better accuracy of simulation is got. Finally, some useful suggestions on prediction accuracy enhancement and some problems need to be noticed are mentioned.

A quick and effective emergency rescue of geo-hazards under the conditions of extreme snow and ice disasters relies heavily on information technology tools, particularly decision support system; as the core content of decision support system, reasoning mechanism is significant because it directly determined the decision efficiency of the system and the accuracy of decision results. According to the characteristics of decision of geo-hazards emergency rescue, a rule-based (RBR) and case-based (CBR) hybrid reasoning mechanism is introduced into the emergency rescue decision support system of geo-hazards under the conditions of extreme snow and ice disasters (ERDSS-GHESID). The reasoning mechanism of ERDSS-GHESID is designed by the object-oriented programming method. It is showed that RBR and CBR hybrid reasoning mechanism can better simulate the inference procedure of human experts in the process of emergency rescue decision of geo-hazards under the conditions of extreme snow and ice disasters, showing a high practical value in the ERDSS-GHESID.

In this research, Artificial Neural Networks (ANNs) is used in an attempt to predict collapse potential of gypseous soils. Two models are built; one for collapse potential obtained by single oedemeter test and the other is for collapse potential obtained by double oedemeter test. A database of laboratory measurements for collapse potential is used. Six parameters, which are 1.Gypsum content, 2.Initial void ratio, 3.Total unit weight, 4.Initial water content, 5.Dry unit weight, 6.Soaking pressure. are considered to have the most significant impact on the magnitude of collapse potential and used as an input to the models. The output model is the corresponding collapse potential. Multi-layer perceptron trainings using back propagation algorithm are used in this work. A number of issues in relation to ANN construction such as the effect of ANN geometry and internal parameters on the performance of ANN models are investigated. Information on the relative importance of the factors affecting the collapse potential are presented and practical equations for prediction of collapse potential of single oedemeter test and double oedemeter test in gypseous soils are developed. It is found that ANNs have the ability to predict the collapse potential of single oedemeter test and double oedemeter test in gypseous soil samples with a good degree of accuracy. The ANN models developed to study the impact of the internal network parameters on model performance indicate that ANN performance is sensitive to the number of hidden layer nodes, momentum terms, learning rate, and transfer functions. The sensitivity analysis indicated that the initial void ratio and gypsum content have the most significant affect on the prediction of collapse potential.

This paper presents the data mining application in the civil engineering deformation measurement. The data mining process is described based on a case study. This case is about deformation of residence buildings caused by one of Shanghai tunnel constructions in the vicinity of these buildings. The steps of data cleaning, data Integration, data mining, model assessment, and analysis results expression are given in detail according to the specific condition in the case. The findings in this article provide reference for deformation measuring data analysis, especially for the situation which limited measuring network or relative unstable region.

Based on the CT image of rock, we come up with a new method of CT image analysis and make the best use of information of CT images. Accomplish reinforcement of CT image of rock according to regulating contrast of CT image. The real microstructure, cranny and hole could be extracted through the technique of image segmentation. On the basis stated above, Marching Cube algorithm is applied to conduct a 3D reconstruction of successive CT tomographic images, visualization is implemented on rock cracks distribution during different damage stages, In this way we can get not only the directly visual course of damage propagation but also a digital representation of the actual spatial distribution of different materials in the rock. And we define the damage variable about damage volume and obtained the relation between damage variable and damage deviatoric stress which correspond exactly to the damage propagation characteristics. Lastly, we calculate the box counting dimension of the rock sample, and through observation of the dimension curve, we summarize the changes of rock damage under stress.

Taking health diagnosis of Nanjing Gulou tunnel as background, the principles and methods of making non-destructive testing on the tunnel lining quality by using geological radar were expounded. General rules on the radar images, the thickness of formwork concrete and sprayed concrete, metallic doors and windows, the dense dripping section and the leaking water cranny were interpreted. The detecting results of geological radar show that bugs existing behind the tunnel lining is serious with a consecutive leaking water cranny every 5~7 meters, and the concrete thickness is uneven from 27cm to 37cm. When the tunnel is repaired, it is found that the chiseled structure state and the geological radar detecting results are unanimous.

Serious seepage can influence the stabilization of reservoir dam and accessory structure. In order to monitor the seepage phenomenon of Wohu-Mountain reservoir exactly at real-time, automatic monitoring system for earth dam is developed. For the hardware system, sensors on site and control computer in center control station are connected effectively with four-core cable, data acquisition device and signal conversion equipment. For the software system, advanced hierarchical and distributed structure is adopted in the system to manage and control monitoring sensors. By developing the data base, seepage curve and related analysis can be shown on the system at real-time. And if monitoring data surpass the limited value, the warning information will be given by adopting different ways according to alarming grade. In general, the automatic monitoring system can play an important role in the protection of the safe of reservoir, and exert economic and social benefits of water reservoirs at mostly.

This research study has identified four contributing factors to the success of monitoring tasks activity by a Real-time Soil Deformation Monitoring System (RSDMS). The first factor is the ability to achieve highly accurate observation. Secondly, it is the maximum reliability of the system. Thirdly, the automatic measurement and computation factors and the least is RSDMS has emails alert function to alert undersign engineer with up to date deformation data. To meet this objective the RSDMS is being developed using Microsoft Visual Basic 6.0 which systematically measure and trace for any alteration in the coordinates of monitoring prisms which are potentially caused by soil movements. The RSDMS equipped with functions of logging measured values used for post processing, carry out deformation analysis, targets health checks and events triggering alarm thus will provide a simple, low cost and functional way to record the absolute 3-D displacements especially for a large number of monitoring points. The TM30 robotic total station is used as a geodetic measuring device in RSDMS. All the collected data are then transferred back to the server by using Files Transfer Protocol (FTP) method subsequently processed with STAR*NET, the program embedded in the system for data analysis by Least Squares Adjustment. Any adjusted coordinate differences from the initial survey data will be analyzed further by the targets health check function of the RSDMS thus sending alert emails with event details to the designated authority.

The Ginza Line subway tunnel was opened for service in 1927. A large amount of data on various deterioration indices was acquired. This report describes the results of the diagnoses by utilizing these data. The results of the visual inspection, strength test, and structural analysis indicated the tunnel proved highly satisfactory in terms of load bearing capacity. As regards the durability, the tunnel was almost free of progressive corrosion because of limited water supply if there was no water leakage. Our projection of the progress of deterioration confirmed that there was no possibility of reinforcement corrosion and resultant cracks even 140 years later. Maintenance and repair work, including leak repair and recovery patching, will be implemented for those sections around water-leaking locations where the water content was high and thus the possibility of corrosion was high. We think that it is extremely significant that the maintenance and repair policy could be clearly defined on the basis of quantitative evaluation by acquiring deterioration index data.

Instrumented exploratory drilling in rock has been widely used in geotechnical engineering and in the oil and gas industry to characterize geological formations and to investigate the presence of subsurface cavities and soft spots. Instrumented drilling involves monitoring the drilling process by measuring a number of drilling parameters using sensors that are mounted to the drill rig. The data collection process used in conventional instrumented borehole drilling suffers from several limitations that are associated with the use of cables. The cables are susceptible to damage during drilling and could cause disruption to the drilling process. The objective of this paper is to present an enhanced system for instrumented borehole drilling that was developed to achieve (1) wireless data acquisition that would eliminate the need for cables and allow for remote access and control of the data, (2) automated real-time detection of cavities and soft spots, and (3) enhanced measurement of the rate of penetration using a laser sensor. Field implementation and testing of the wireless drilling system indicated an adequate functionality of the sensors used and their proper communication with the wireless data acquisition system and offered a realistic demonstration of the system.

As an important part of the New Austrian Tunneling Method construction (NATM), the processes of monitoring and measurement are important and indispensable in the tunnel construction, which effectively reflect the rock deformation and its mechanical behavior, and provide a suitable installation time for tunnel lining structure. Scientific analysis and forecast real-timely on monitoring data provide a precondition for supporting the strategic decisions of construction organization, as well as dynamic design. In this paper, the tunnel monitoring method and datum analysis are illustrated through an example of the port tunnel monitoring in Jing wuhuang (chang) highway, Jiangxi province china. Many items monitoring data (vault sinking, peripheral convergence, surface settlement, bolt axial force and drawing force, internal force of steel timbering, internal force of secondary lining) acquired from the field monitoring have been analyzed. The appropriate opportunity of surround rock stabilization after tunnel excavated and second lining are proposed by the analyzed the monitoring datum which can provide some lesson for the future tunnel construction.