Estimation of strength parameters of rock using artificial neural networks

The accurate determination of geomechanical properties such as uniaxial compressive strength and shear strength requires considerable time in collecting appropriate samples, their preparation and laboratory testing. To minimize the time and cost, a number of empirical relations have been reported which are widely used for the estimation of complex rock properties from more easily acquired data. This paper reports the use of an artificial neural network to predict the deformation properties of Coal Measure rocks using dynamic wave velocity, point load index, slake durability index and density. The results confirm the applicability of this method.     

Prediction of strength properties of some schistose rocks from petrographic properties using artificial neural networks

Petrographic features of a rock are intrinsic properties, which control the mechanical behaviour of the rock mass at the fundamental level. This paper deals with the application of neural networks for the prediction of uniaxial compressive strength, tensile strength and axial point load strength simultaneously from the mineral composition and textural properties. Statistical analysis has also been conducted for prediction of the same strength properties and compared with the predicted values by neural networks to investigate the authenticity of this approach. The network was trained to predict the uniaxial compressive strength, tensile strength and axial point load strength from the mineralogical composition, grain size, aspect ratio, form factor, area weighting and orientation of foliation planes (planes of weakness). A data set having 112 test results of the four schistose rocks were used to train the network with the back-propagation learning algorithm. Another data set of 28 test results of the four schistose rocks were used to validate the generalization and prediction capabilities of the network.     

Concrete compressive strength prediction using ultrasonic pulse velocity through artificial neural networks

Numerous attempts to use ultrasonic pulse velocity (UPV) as a measure of compressive strength of concrete has been made due to obvious advantages of non-destructive testing methods. The present study is conducted for prediction of compressive strength of concrete based on weight and UPV for two different concrete mixtures (namely M20 and M30) involving specimens of two different sizes and shapes as a result of need for rapid test method for predicting long-term compressive strength of concrete. The prediction is done using multiple regression analysis and artificial neural networks. A comparison between two methods depicts that artificial neural networks can be used to predict the compressive strength of concrete effectively. The results are plotted as experimentally evaluated compressive strength versus predicted strength through both methods of analysis.     

Unconfined compressive strength prediction of soils stabilized using artificial neural networks and support vector machines

This study aims to improve the unconfined compressive strength of soils using additives as well as by predicting the strength behavior of stabilized soils using two artificial-intelligence-based models. The soils used in this study are stabilized using various combinations of cement, lime, and rice husk ash. To predict the results of unconfined compressive strength tests conducted on soils, a comprehensive laboratory dataset comprising 137 soil specimens treated with different combinations of cement, lime, and rice husk ash is used. Two artificial-intelligence-based models including artificial neural networks and support vector machines are used comparatively to predict the strength characteristics of soils treated with cement, lime, and rice husk ash under different conditions. The suggested models predicted the unconfined compressive strength of soils accurately and can be introduced as reliable predictive models in geotechnical engineering. This study demonstrates the better performance of support vector machines in predicting the strength of the investigated soils compared with artificial neural networks. The type of kernel function used in support vector machine models contributed positively to the performance of the proposed models. Moreover, based on sensitivity analysis results, it is discovered that cement and lime contents impose more prominent effects on the unconfined compressive strength values of the investigated soils compared with the other parameters.     

On-line building energy prediction using adaptive artificial neural networks

While most of the existing artificial neural networks (ANN) models for building energy prediction are static in nature, this paper evaluates the performance of adaptive ANN models that are capable of adapting themselves to unexpected pattern changes in the incoming data, and therefore can be used for the real-time on-line building energy prediction. Two adaptive ANN models are proposed and tested: accumulative training and sliding window training. The computational experiments presented in the paper use both simulated (synthetic) data and measured data. In the case of synthetic data, the accumulative training technique appears to have an almost equal performance with the sliding window training approach, in terms of training time and accuracy. In the case of real measurements, the sliding window technique gives better results, compared with the accumulative training, if the coefficient of variance is used as an indicator.     

基于CPTu数据的黏性土不排水抗剪强度#br# 神经网络预测

利用人工神经网络模型,建立基于孔压静力触探（CPTu）现场测试数据的黏性土不排水抗剪强度的预测方法。为建立和验证人工神经网络模型,在3个场地开展CPTu和十字板剪切现场测试,共取得33个测孔的CPTu试验数据和相对应的不排水抗剪强度实测值。通过对比分析不同输入向量、不同网络隐层数、不同神经元数及不同改进算法对人工神经网络模型性能的影响,确定人工神经网络模型的具体形式。通过对训练组数据开展机器学习,所建立的人工神经网络模型能够有效地基于CPTu获得的端阻力和孔隙水压力现场测试数据对黏土不排水抗剪强度进行预测,预测结果与十字板剪切试验实测结果非常接近。与传统用于估算不排水强度的经验关系相比,采用人工神经网络模型预测结果与实测结果相关性显著提高、误差明显降低。     

Prediction of the shear strength of reinforced masonry walls using a large experimental database and artificial neural networks

This paper analyses the accuracy of a selection of expressions currently available to estimate the in-plane shear strength of reinforced masonry (RM) walls, including those presented in some international masonry codes. For this purpose, predictions of such expressions are compared with a set of experimental results reported in the literature. The experimental database includes specimens built with ceramic bricks and concrete blocks tested in partially and fully grouted conditions, which typically present a shear failure mode. Based on the experimental data collected and using artificial neural networks (ANN), this paper presents alternative expressions to the different existing methods to predict the in-plane shear strength of RM walls. The wall aspect ratio, the axial pre-compression level on the wall, the compressive strength of masonry, as well as the amount and spacing of vertical and horizontal reinforcement throughout the wall are taken into consideration as the input parameters for the proposed expressions. The results obtained show that ANN-based proposals give good predictions and in general fit the experimental results better than other calculation methods.     

Prediction of shear strength of steel fiber RC beams using neural networks

This paper presents the development of artificial neural network models for predicting the ultimate shear strength of steel fiber reinforced concrete (SFRC) beams. Two models are constructed using the experimental data from the literature and the results are compared with each other and with the formula proposed by Swamy et al. and Khuntia et al. It is found that the neural network model, with five input parameters, predicts the shear strength of beams more closely than the network with four input parameters. Moreover, the neural network models predict the shear strength of SFRC beams more accurately than the above-mentioned formulas. Further, the accuracy of predicted results is found not biased with concrete strength, shear span to depth ratio and the beam depth. Limited parametric studies show that the network model captures the RC beam’s underlying shear behavior very well.     

Predicting the average size of blasted rocks in aggregate quarries using artificial neural networks

The prediction of the average size of fragments in blasted rock piles produced after blasting in aggregate quarries is essential for decresing the cost of crushing and secondary breaking. There are several conventional and advanced processes to estimate the size of blasted rocks. Among these, the empirical prediction of the expected fragmentation in most cases is carried out by Kuznetsov’s equation (Sov Min Sci 9:144–148, 1973), modified by Lilly (1986) and Cunningham (1987). The present research focuses on the effect of the engineering geological factors and blasting process on the blasted fragments using a more powerful, advanced computational tool, an artificial neural network. In particular, the blast database consists of the blastability index of limestone on the pit face, the quantities of the explosives and of the blasted rock pile, assessing the interaction of these parameters on the blasted rocks. The data were collected from two aggregate quarries, Drymos and Tagarades, near Thessaloniki, in the Central Macedonia region of Greece. This approach indicates significant performance stability, providing the fragmentation size with high accuracy.

     

Solution parameters of carbonate rocks

Hydraulic structures founded on carbonate rocks can be endangered by progressive enlargement of fissures or the formation of solution cavities as aggressive (unsaturated) waters percolate through them. Previous literature describes how both the rate and manner of enlargment of fissures depend upon the solubilities and solution rate constants of soluble rocks. It has also been shown that the safe maximum size of fissures for a given hydraulic structure can be calculated from the solution parameters of the rock. It has been suggested that carbonate rocks of various origins and types have very different solution properties, thus complicating site investigation procedures and the design of foundations. However, this paper describes the results of laboratory experiments on ten distinctly different specimens of carbonate rocks, which show that the solubilities and solution rate constants are all very similar. In pure water, solubilities of different carbonate rocks are virtually the same as pure calcium carbonate and solution rate constants are between 1.2 and 3.3×10^?5 m/s. These differences in solution rate constants are too small to be significant in engineering design. The solution rate constants decrease by a factor of about ten when dissolved by water containing carbon dioxide in the concentration range 5×10^?4 to 3×10^?2 Moles/litre. However within this range of concentrations the rate constants are 1.8 to 2.7×10^?6 m/s. In deciding how to safeguard the foundations of hydraulic structures in carbonate rocks against solution it is therefore not necessary to know the type or geological origin of the carbonate rock. However, to determine the solubility of the rocks the chemical composition of the inflowing seepage water must be known, also the sizes and distributions of fissures must be assessed by direct observations or by other methods such as water tests in boreholes. The paper shows that fissures smaller than about 400 μm are unlikely to be dangerous in most foundations in carbonate rocks. An appropriate grouting programme can be designed for rocks containing large fissures.     

Modeling construction processes using artificial neural networks

The paper evaluates a neural network approach to modeling the dynamics of construction processes that exhibit both discrete and stochastic behavior, providing an alternative to the more conventional method of discrete-event simulation. The incentive for developing the technique is its potential for (i) facilitating model development in situations where there is limited theory describing the dependence between component processes; and (ii) rapid execution of a simulation through parallel processing. The alternative ways in which neural networks can be used to model construction processes are reviewed and their relative merits are identified. The most promising approach, a recursive method of dynamic modeling, is examined in a series of experiments. These involve the application of the technique to two classes of earthmoving system, the first comprising a push-dozer and a fleet of scrapers, and the second a loader and fleet of haul trucks. The viability of the neural network approach is demonstrated in terms of its ability to model the discrete and stochastic behavior of these classes of construction processes. The paper concludes with an indication of some areas for further development of the technique.     

基于人工神经网络的混凝土抗渗性能预测

在进行了正交试验的基础上,采用人工神经网络方法,建立混凝土的氯离子扩散系数与混凝土配比六个参数之间的非线性映射关系,研究各个参数对混凝土抗渗性能的影响,该研究成果可以减少混凝土试配次数,节约大量的人力、物力和时间,为高性能混凝土的研究发展奠定了基础。     

Simulating pavement structural condition using artificial neural networks

This article aims to investigate the feasibility of incorporating of an artificial neural network (ANN) as an innovative technique for modelling the pavement structural condition, into pavement management systems. For the development of the ANN, strain assessment criteria are set in order to characterise the structural condition of flexible asphalt pavements with regards to fatigue failure. This initial task is directly followed with the development of an ANN model for the prediction of strains primarily based on in situ field gathered data and not through the usage of synthetic databases. For this purpose, falling weight deflectometer (FWD) measurements were systematically conducted on a highway network, with ground-penetrating radar providing the required pavement thickness data. The FWD data (i.e. deflections) were back-analysed in order to assess strains that would be utilised as output data in the process of developing the ANN model. A paper exercise demonstrates how the developed ANN model combined with the suggested conceptual approach for characterising pavement structural condition with regard to strain assessment could make provisions for pavement management activities, categorising network pavement sections according to the need for maintenance or rehabilitation. Preliminary results indicate that the ANN technique could help assist policy decision makers in deriving optimum strategies for the planning of pavement infrastructure maintenance.     

Peak shear strength prediction for discontinuities between two different rock types using a neural network approach

The peak shear strength of discontinuities between two different rock types is essential to evaluate the stability of a rock slope with interlayered rocks. However, current research has paid little attention to shear strength parameters of discontinuities with different joint wall compressive strength (DDJCS). In this paper, a neural network methodology was used to predict the peak shear strength of DDJCS considering the effect of joint wall strength combination, normal stress and joint roughness. The database was developed by laboratory direct shear tests on artificial joint specimens with seven different joint wall strength combinations, four designed joint surface topographies and six types of normal stresses. A part of the experimental data was used to train a back-propagation neural network model with a single-hidden layer. The remaining experimental data was used to validate the trained neural network model. The best geometry of the neural network model was determined by the trial-and-error method. For the same data, multivariate regression analysis was also conducted to predict the peak shear strength of DDJCS. Prediction precision of the neural network model and multivariate regression model was evaluated by comparing the predicted peak shear strength of DDJCS with experimental data. The results showed that the capability of the developed neural network model was strong and better than the multivariate regression model. Finally, the established neural network model was applied in the stability evaluation of a typical rock slope with DDJCS as the critical surface in the Badong formation of China.

     

Prediction of blast-induced ground vibration using artificial neural networks

Blasting is still being considered to be one the most important applicable alternatives for conventional tunneling. Ground vibration generated due to blasting is an undesirable phenomenon which is harmful for the nearby habitants and dwellings and should be prevented. In this paper, an attempt has been made to predict blast-induced ground vibration using artificial neural network (ANN) in the Siahbisheh project, Iran. To construct the model maximum charge per delay, distance from blasting face to the monitoring point, stemming and hole depth are taken as input parameters, whereas, peak particle velocity (PPV) is considered as an output parameter. A database consisting of 182 datasets was collected at different strategic and vulnerable locations in and around the project. From the prepared database, 162 datasets were used for the training and testing of the network, whereas 20 randomly selected datasets were used for the validation of the ANN model. A four layer feed-forward back-propagation neural network with topology 4-10-5-1 was found to be optimum. To compare performance of the ANN model with empirical predictors as well as regression analysis, the same database was applied. Superiority of the proposed ANN model over empirical predictors and statistical model was examined by calculating coefficient of determination for predicted and measured PPV. Sensitivity analysis was also performed to get the influence of each parameter on PPV. It was found that distance from blasting face is the most effective and stemming is the least effective parameter on the PPV.     

Prediction of seismic-induced structural damage using artificial neural networks

Contemporary methods for estimating the extent of seismic-induced damage to structures include the use of nonlinear finite element method (FEM) and seismic vulnerability curves. FEM is applicable when a small number of predetermined structures is to be assessed, but becomes inefficient for larger stocks. Seismic vulnerability curves enable damage estimation for classes of similar structures characterised by a small number of parameters, and typically use only one parameter to describe ground motion. Hence, they are unable to extend damage prognosis to wider classes of structures, e.g. buildings with a different number of storeys and/or bays, or capture the full complexity of the relationship between damage and seismic excitation parameters. Motivated by these shortcomings, this study presents a general method for predicting seismic-induced damage using Artificial Neural Networks (ANNs). The approach was to describe both the structure and ground motion using a large number of structural and ground motion properties. The class of structures analysed were 2D reinforced concrete (RC) frames that varied in topology, stiffness, strength and damping, and were subjected to a suite of ground motions. Dynamic structural responses were simulated using nonlinear FEM analysis and damage indices describing the extent of damage calculated. Using the results of the numerical simulations, a mapping between the structural and ground motion properties and the damage indices was than established using an ANN. The performance of the ANN was assessed using several examples and the ANN was found to be capable of successfully predicting damage.     

Mapping rework causes and effects using artificial neural networks

Rework can have adverse effects on the performance and productivity of construction projects. Techniques such as artificial neural networks (ANN) are widely used for prediction and classification problems and thus can be used to map the causes and effects of rework. The traditional back propagation neural network and general regression neural network data from 112 Hong Kong construction projects are used to examine the influence of rework causes on the various project performance indicators such as cost overrun, time overrun, and contractual claims. The results from this research could be used to develop forecasting systems and appropriate intelligent decision support frameworks for enhancing performance in construction projects. Furthermore, analysis of the neural network results indicates that the general regression neural network architecture is better suited for modelling rework causes and their impacts on project performance.

Les travaux de reprise peuvent avoir des effets néfastes sur les performances et la productivité dans les projets de construction. Des techniques comme les réseaux neuronaux artificiels (AAN) sont largement utilisés pour résoudre les problèmes de prévision et de classification et peuvent donc servir à cartographier les causes et les effets des travaux de reprise. Les données de réseaux neuronaux classiques à rétropropagation et les données de réseaux neuronaux à régression générale provenant de 112 projets de construction à Hong Kong sont utilisées pour examiner l'influence des travaux de reprise sur les divers indicateurs de performances de projets, comme les dépassements de coûts, les dépassements de délais et les réclamations contractuelles. Les résultats de cette recherche pourraient servir à développer des systèmes de prévision et des cadres appropriés et intelligents de soutien à la décision pour améliorer les performances de projets de construction. En outre, l'analyse des résultats de réseaux neuronaux indique que l'architecture du réseau neuronal à régression générale convient mieux à la modélisation des causes des travaux de reprise et à leurs conséquences sur les performances des projets.

Mots cle´s: projet de construction, dépassement des coûts, productivité, performances de projets, travaux de reprise, dépassement des délais