Hybrid ensemble soft computing approach for predicting penetration rate of tunnel boring machine in a rock environment

This study implements a hybrid ensemble machine learning method for forecasting the rate of penetration (ROP) of tunnel boring machine (TBM), which is becoming a prerequisite for reliable cost assessment and project scheduling in tunnelling and underground projects in a rock environment. For this purpose, a sum of 185 datasets was collected from the literature and used to predict the ROP of TBM. Initially, the main dataset was utilised to construct and validate four conventional soft computing (CSC) models, i.e. minimax probability machine regression, relevance vector machine, extreme learning machine, and functional network. Consequently, the estimated outputs of CSC models were united and trained using an artificial neural network (ANN) to construct a hybrid ensemble model (HENSM). The outcomes of the proposed HENSM are superior to other CSC models employed in this study. Based on the experimental results (training RMSE = 0.0283 and testing RMSE = 0.0418), the newly proposed HENSM is potential to assist engineers in predicting ROP of TBM in the design phase of tunnelling and underground projects.     

Prediction of flyrock distance induced by mine blasting using a novel Harris Hawks optimization-based multi-layer perceptron neural network

In mining or construction projects, for exploitation of hard rock with high strength properties, blasting is frequently applied to breaking or moving them using high explosive energy. However, use of explosives may lead to the flyrock phenomenon. Flyrock can damage structures or nearby equipment in the surrounding areas and inflict harm to humans, especially workers in the working sites. Thus, prediction of flyrock is of high importance. In this investigation, examination and estimation/forecast of flyrock distance induced by blasting through the application of five artificial intelligent algorithms were carried out. One hundred and fifty-two blasting events in three open-pit granite mines in Johor, Malaysia, were monitored to collect field data. The collected data include blasting parameters and rock mass properties. Site-specific weathering index (WI), geological strength index (GSI) and rock quality designation (RQD) are rock mass properties. Multi-layer perceptron (MLP), random forest (RF), support vector machine (SVM), and hybrid models including Harris Hawks optimization-based MLP (known as HHO-MLP) and whale optimization algorithm-based MLP (known as WOA-MLP) were developed. The performance of various models was assessed through various performance indices, including a10-index, coefficient of determination (R²), root mean squared error (RMSE), mean absolute percentage error (MAPE), variance accounted for (VAF), and root squared error (RSE). The a10-index values for MLP, RF, SVM, HHO-MLP and WOA-MLP are 0.953, 0.933, 0.937, 0.991 and 0.972, respectively. R² of HHO-MLP is 0.998, which achieved the best performance among all five machine learning (ML) models.     

Online sequential extreme learning machine in river water quality (turbidity) prediction: a comparative study on different data mining approaches

As a measure of water quality, water turbidity might be a source of water pollution in drinking water resources. Henceforth, having a reliable tool for predicting turbidity values based on common water quantity/quality measured parameters is of great importance. In the present paper, the performance of the online sequential extreme learning machine (OS‐ELM) in predicting daily values of turbidity in Brandywine Creek, Pennsylvania, is evaluated. For this purpose, in addition to the developed OS‐ELM, several data‐driven models, that is, multilayer perceptron neural network (MLPANN), the classification and regression tree (CART), the group method of data handling (GMDH) and the response surface method (RSM) have been applied. The general findings of the study confirm the superiority of the OS‐ELM model over the other applied models so that the OS‐ELM improved the averaged RMSE of the predicted values 9.1, 11.7, 20.5 and 29.3% over the MLPANN, GMDH, RSM and CART models, respectively.     

Data-driven estimation of joint roughness coefficient

Joint roughness is one of the most important issues in the hydromechanical behavior of rock mass. Therefore, the joint roughness coefficient (JRC) estimation is of paramount importance in geomechanics engineering applications. Studies show that the application of statistical parameters alone may not produce a sufficiently reliable estimation of the JRC values. Therefore, alternative data-driven methods are proposed to assess the JRC values. In this study, Gaussian process (GP), K-star, random forest (RF), and extreme gradient boosting (XGBoost) models are employed, and their performance and accuracy are compared with those of benchmark regression formula (i.e. Z₂, R_p, and SD_i) for the JRC estimation. To analyze the models’ performance, 112 rock joint profile datasets having eight common statistical parameters (R_ave, R_max, SD_h, i_ave, SD_i, Z₂, R_p, and SF) and one output variable (JRC) are utilized, of which 89 and 23 datasets are used for training and validation of models, respectively. The interpretability of the developed XGBoost model is presented in terms of feature importance ranking, partial dependence plots (PDPs), feature interaction, and local interpretable model-agnostic explanations (LIME) techniques. Analyses of results show that machine learning models demonstrate higher accuracy and precision for estimating JRC values compared with the benchmark empirical equations, indicating the generalization ability of the data-driven models in better estimation accuracy.     

Concrete corrosion in wastewater systems: Prediction and sensitivity analysis using advanced extreme learning machine

The implementation of novel machine learning models can contribute remarkably to simulating the degradation of concrete due to environmental factors. This study considers the sulfuric acid corrosive factor in wastewater systems to simulate concrete mass loss using five machine learning models. The models include three different types of extreme learning machines, including the standard, online sequential, and kernel extreme learning machines, in addition to the artificial neural network, classification and regression tree model, and statistical multiple linear regression model. The reported values of concrete mass loss for six different types of concrete are the target values of the machine learning models. The input variability was assessed based on two scenarios prior to the application of the predictive models. For the first assessment, the machine learning models were developed using all the available cement and concrete mixture input variables; the second assessment was conducted based on the gamma test approach, which is a sensitivity analysis technique. Subsequently, the sensitivity analysis of the most effective parameters for concrete corrosion was tested using three different approaches. The adopted methodology attained optimistic and reliable modeling results. The online sequential extreme learning machine model demonstrated superior performance over the other investigated models in predicting the concrete mass loss of different types of concrete.     

Prediction of shield tunneling-induced ground settlement using machine learning techniques

Predicting the tunneling-induced maximum ground surface settlement is a complex problem since the settlement depends on plenty of intrinsic and extrinsic factors. This study investigates the efficiency and feasibility of six machine learning (ML) algorithms, namely, back-propagation neural network, wavelet neural network, general regression neural network (GRNN), extreme learning machine, support vector machine and random forest (RF), to predict tunneling-induced settlement. Field data sets including geological conditions, shield operational parameters, and tunnel geometry collected from four sections of tunnel with a total of 3.93 km are used to build models. Three indicators, mean absolute error, root mean absolute error, and coefficient of determination the (R²) are used to demonstrate the performance of each computational model. The results indicated that ML algorithms have great potential to predict tunneling-induced settlement, compared with the traditional multivariate linear regression method. GRNN and RF algorithms show the best performance among six ML algorithms, which accurately recognize the evolution of tunneling-induced settlement. The correlation between the input variables and settlement is also investigated by Pearson correlation coefficient.     

A generic framework for geotechnical subsurface modeling with machine learning

This study introduces a generic framework for geotechnical subsurface modeling, which accounts for spatial autocorrelation with local mapping machine learning(ML) methods. Instead of using XY coordinate fields directly as model input, a series of autocorrelated geotechnical distance fields(GDFs) is designed to enable the ML models to infer the spatial relationship between the sampled locations and unknown locations. The whole framework using GDF with ML methods is named GDF-ML. This framework is...     

Prediction of rockhead using a hybrid N-XGBoost machine learning framework

The spatial information of rockhead is crucial for the design and construction of tunneling or underground excavation. Although the conventional site investigation methods (i.e. borehole drilling) could provide local engineering geological information, the accurate prediction of the rockhead position with limited borehole data is still challenging due to its spatial variation and great uncertainties involved. With the development of computer science, machine learning (ML) has been proved to be a promising way to avoid subjective judgments by human beings and to establish complex relationships with mega data automatically. However, few studies have been reported on the adoption of ML models for the prediction of the rockhead position. In this paper, we proposed a robust probabilistic ML model for predicting the rockhead distribution using the spatial geographic information. The framework of the natural gradient boosting (NGBoost) algorithm combined with the extreme gradient boosting (XGBoost) is used as the basic learner. The XGBoost model was also compared with some other ML models such as the gradient boosting regression tree (GBRT), the light gradient boosting machine (LightGBM), the multivariate linear regression (MLR), the artificial neural network (ANN), and the support vector machine (SVM). The results demonstrate that the XGBoost algorithm, the core algorithm of the probabilistic N-XGBoost model, outperformed the other conventional ML models with a coefficient of determination (R²) of 0.89 and a root mean squared error (RMSE) of 5.8 m for the prediction of rockhead position based on limited borehole data. The probabilistic N-XGBoost model not only achieved a higher prediction accuracy, but also provided a predictive estimation of the uncertainty. Thus, the proposed N-XGBoost probabilistic model has the potential to be used as a reliable and effective ML algorithm for the prediction of rockhead position in rock and geotechnical engineering.     

Multiclass stand-alone and ensemble machine learning algorithms utilised to classify soils based on their physico-chemical characteristics

This study has provided an approach to classify soil using machine learning. Multiclass elements of stand-alone machine learning algorithms (i.e. logistic regression (LR) and artificial neural network (ANN)), decision tree ensembles (i.e. decision forest (DF) and decision jungle (DJ)), and meta-ensemble models (i.e. stacking ensemble (SE) and voting ensemble (VE)) were used to classify soils based on their intrinsic physico-chemical properties. Also, the multiclass prediction was carried out across multiple cross-validation (CV) methods, i.e. train validation split (TVS), k-fold cross-validation (KFCV), and Monte Carlo cross-validation (MCCV). Results indicated that the soils' clay fraction (CF) had the most influence on the multiclass prediction of natural soils' plasticity while specific surface and carbonate content (CC) possessed the least within the nature of the dataset used in this study. Stand-alone machine learning models (LR and ANN) produced relatively less accurate predictive performance (accuracy of 0.45, average precision of 0.5, and average recall of 0.44) compared to tree-based models (accuracy of 0.68, average precision of 0.71, and recall rate of 0.68), while the meta-ensembles (SE and VE) outperformed (accuracy of 0.75, average precision of 0.74, and average recall rate of 0.72) all the models utilised for multiclass classification. Sensitivity analysis of the meta-ensembles proved their capacities to discriminate between soil classes across the methods of CV considered. Machine learning training and validation using MCCV and KFCV methods enabled better prediction while also ensuring that the dataset was not overfitted by the machine learning models. Further confirmation of this phenomenon was depicted by the continuous rise of the cumulative lift curve (LC) of the best performing models when using the MCCV technique. Overall, this study demonstrated that soil's physico-chemical properties do have a direct influence on plastic behaviour and, therefore, can be relied upon to classify soils.     

Response surface models for CFD predictions of air diffusion performance index in a displacement ventilated office

Based on the Response Surface Methodology (RSM), the development of first- and second-order models for predicting the Air Diffusion Performance Index (ADPI) in a displacement-ventilated office is presented. By adopting the technique of Computational Fluid Dynamics (CFD), the new ADPI models developed are used to investigate the effect of simultaneous variation of three design variables in a displacement ventilation case, i.e. location of the displacement diffuser (L_dd), supply temperature (T) and exhaust position (L_ex) on the comfort parameter ADPI. The RSM analyses are carried out with the aid of a statistical software package MINITAB. In the current study, the separate effect of individual design variable as well as the second-order interactions between these variables, are investigated. Based on the variance analyses of both the first- and second-order RSM models, the most influential design variable is the supply temperature. In addition, it is found that the interactions of supply temperature with other design variables are insignificant, as deduced from the second-order RSM model. The optimised ADPI value is subsequently obtained from the model equations.     

基于LS-SVM的粉煤灰混凝土强度预测模型

提出一种基于最小二乘支持向量机(LS-SVM)的粉煤灰混凝土强度智能预测模型,并给出了相应的步骤和算法。通过该模型分析了水胶比、水泥用量、粉煤灰替代率及砂率等因素对粉煤灰混凝土强度的影响。在此基础上,对不同配比所浇注的混凝土强度进行预测,有助于准确认识混凝土强度随配比参数的变化规律。与多元线性回归、神经网络及标准SVM模型比较,该模型的优点为:(1)采用了结构风险最小化准则,在最小化样本误差的同时减小模型泛化误差的上界,提高了模型小样本泛化能力;(2)将迭代学习算法转换为求解线性方程组,使得整个模型仅有一个全局最优点,解决局部最小问题;(3)用等式约束代替标准SVM算法中的不等式约束,将求解二次规划问题转化为直接求解线性矩阵方程,有效提高建模速度。用该模型对混凝土的强度预测实例表明,其建模速度比标准SVM高近1个数量级,预测误差仅为SVM方法的20%、BP神经网络方法的10%左右。     

Forecasting short-term electricity load using hybrid support vector regression with grey catastrophe and random forest modeling

This paper develops a novel short-term load forecasting model that hybridizes several machine learning methods, such as support vector regression (SVR), grey catastrophe (GC (1,1)), and random forest (RF) modeling. The modeling process is based on the minimization of both SVR and risk. GC is used to process and extract catastrophe points in the long term to reduce randomness. RF is used to optimize forecasting performance by exploiting its superior optimization capability. The proposed SVR-GC-RF model has higher forecasting accuracy (MAPE values are 6.35% and 6.21%, respectively) using electric loads from Australian-Energy-Market-Operator; it can provide analytical support to forecast electricity consumption accurately.     

A comparative study on machine learning modeling for mass movement susceptibility mapping (a case study of Iran)

Mass movements are among the most dangerous natural hazards in mountainous regions. The present study employs machine learning (ML) models for mass movement susceptibility mapping (MMSM) in Iran based on a comprehensive dataset of 864 mass movements which include debris flow, landslide, and rockfall during the last 42 years (1977–2019) as well as 12 conditional factors. The results of validation stage show that RF (random forest) is the most viable model for mass movement susceptibility maps. In addition, MARS (multivariate adaptive regression splines), MDA (mixture discriminant additive), and BRT (boosted regression trees) models also provide relatively accurate results. Results of the AUC for validation of produced maps were 0.968, 0.845, 0.828, and 0.765 for RF, MARS, MDA, and BRT, respectively. Based on MMSM generated by RF model, 32% of study area is identified to be under high and very high susceptibility classes. Most of the endangered areas for mass movement are in the west and central parts of the Chaharmahal and Bakhtiari Province. In addition, our findings indicate that elevation, slope angle, distance from roads, and distance from faults are critical factors for mass movement. Our results provide a perspective view for decision makers to mitigate natural hazards.

     

Analysis of ground surface settlement in anisotropic clays using extreme gradient boosting and random forest regression models

Excessive ground surface settlement induced by pit excavation (i.e. braced excavation) can potentially result in damage to the nearby buildings and facilities. In this paper, extensive finite element analyses have been carried out to evaluate the effects of various structural, soil and geometric properties on the maximum ground surface settlement induced by braced excavation in anisotropic clays. The anisotropic soil properties considered include the plane strain shear strength ratio (i.e. the ratio of the passive undrained shear strength to the active one) and the unloading shear modulus ratio. Other parameters considered include the support system stiffness, the excavation width to excavation depth ratio, and the wall penetration depth to excavation depth ratio. Subsequently, the maximum ground surface settlement of a total of 1479 hypothetical cases were analyzed by various machine learning algorithms including the ensemble learning methods (extreme gradient boosting (XGBoost) and random forest regression (RFR) algorithms). The prediction models developed by the XGBoost and RFR are compared with that of two conventional regression methods, and the predictive accuracy of these models are assessed. This study aims to highlight the technical feasibility and applicability of advanced ensemble learning methods in geotechnical engineering practice.     

Machine learning-based automatic control of tunneling posture of shield machine

For a tunnel driven by a shield machine, the posture of the driving machine is essential to the construction quality and environmental impact. However, the machine posture is controlled by the experienced driver of shield machine by setting hundreds of tunneling parameters empirically. Machine learning(ML) algorithm is an alternative method that can let the computer to learn from the driver’s operation and try to model the relationship between parameters automatically. Thus, in this paper, three...     

Reliability analysis of slopes considering spatial variability of soil properties based on efficiently identified representative slip surfaces

Slope reliability analysis considering inherent spatial variability (ISV) of soil properties is time-consuming when response surface method (RSM) is used, because of the “curse of dimensionality”. This paper proposes an effective method for identification of representative slip surfaces (RSSs) of slopes with spatially varied soils within the framework of limit equilibrium method (LEM), which utilizes an adaptive K-means clustering approach. Then, an improved slope reliability analysis based on the RSSs and RSM considering soil spatial variability, in perspective of computation efficiency, is established. The detailed implementation procedure of the proposed method is well documented, and the ability of the method in identifying RSSs and estimating reliability is investigated via three slope examples. Results show that the proposed method can automatically identify the RSSs of slope with only one evaluation of the conventional deterministic slope stability model. The RSSs are invariant with the statistics of soil properties, which allows parametric studies that are often required in slope reliability analysis to be efficiently achieved with ease. It is also found that the proposed method provides comparable values of factor of safety (FS) and probability of failure (P_f) of slopes with those obtained from direct analysis and literature.     

Soft computing for solar radiation potential assessment in Algeria

ABSTRACT

Precise estimation of solar radiation is a highly required parameter for the design and assessment of solar energy applications. Over the past years, many machine learning techniques have been proposed in order to improve the forecasting performance using different input attributes. The aim of this study is the forecasting of one day ahead of horizontal global solar radiation using a set of meteorological and geographical inputs. In this respect, the Gaussian process regression methodology (GPR) and least-square support vector machine (LS-SVM) with different kernels are evaluated in order to select the most appropriate forecasting model. In order to assess the proposed models, the southern Algerian city, Ghardaia regions, was selected for this study. A historical data of five years (2013–2017) of meteorological data collected at Renewable Energies (URAER) in Ghardaia city are used. The achieved results demonstrate that all the proposed models give approximately similar results in terms of statistical indicators. In term of processing time, all the models showed acceptable computational efficiency with less computational costs of the GPR model among all machine learning models.     

Data-driven vision-based inspection for reinforced concrete beams and slabs: Quantitative damage and load estimation

We show that computer-vision-based inspection can relate surface observations to quantitative damage and load level estimates in common reinforced concrete beams and slabs subjected to monotonic loading. This work is related to an earlier study focused on shear-critical beams and slabs (i.e., specimens lacking shear reinforcement), but here an expanded image database has been assembled to include specimens with both flexural and shear reinforcement such as would be found in practice. Using this expanded data set, a supervised machine learning algorithm builds cross-validated predictive models capable of estimating internal loads (i.e., shear and moment) and damage levels based on surface crack pattern images. The expanded data set contains a total of 127 specimens and 862 images captured in past studies across a range of load and damage levels. Textural and geometric attributes of surface crack patterns were used for feature engineering and tuning of predictive models. The expanded data set enables comparison of the estimation accuracy for shear-critical and shear-reinforced beams and slabs considered separately and in combined form. This includes the capability to categorize whether shear reinforcement is present or not. Estimation models based on surface observations for shear-reinforced elements are found to be comparable to those for shear-critical beams and slabs, with variability observed due to loading type range, member geometries, whether categorization is combined with regression, and the image feature sets used.     

Comparison of machine learning methods for ground settlement prediction with different tunneling datasets

This study integrates different machine learning (ML) methods and 5-fold cross-validation (CV) method to estimate the ground maximal surface settlement (MSS) induced by tunneling. We further investigate the applicability of artificial intelligent (AI) based prediction through a comparative study of two tunnelling datasets with different sizes and features. Four different ML approaches, including support vector machine (SVM), random forest (RF), back-propagation neural network (BPNN), and deep neural network (DNN), are utilized. Two techniques, i.e. particle swarm optimization (PSO) and grid search (GS) methods, are adopted for hyperparameter optimization. To assess the reliability and efficiency of the predictions, three performance evaluation indicators, including the mean absolute error (MAE), root mean square error (RMSE), and Pearson correlation coefficient (R), are calculated. Our results indicate that proposed models can accurately and efficiently predict the settlement, while the RF model outperforms the other three methods on both datasets. The difference in model performance on two datasets (Datasets A and B) reveals the importance of data quality and quantity. Sensitivity analysis indicates that Dataset A is more significantly affected by geological conditions, while geometric characteristics play a more dominant role on Dataset B.     

An ANN-based approach to predict blast-induced ground vibration of Gol-E-Gohar iron ore mine,Iran简

Blast-induced ground vibration is one of the inevitable outcomes of blasting in mining projects and may cause substantial damage to rock mass as well as nearby structures and human beings. In this paper, an attempt has been made to present an application of artificial neural network (ANN) to predict the blast-induced ground vibration of the Gol-E-Gohar (GEG) iron mine, Iran. A four-layer feed-forward back propagation multi-layer perceptron (MLP) was used and trained with Levenberg–Marquardt algorithm. To construct ANN models, the maximum charge per delay, distance from blasting face to monitoring point, stemming and hole depth were taken as inputs, whereas peak particle velocity (PPV) was considered as an output parameter. A database consisting of 69 data sets recorded at strategic and vulnerable locations of GEG iron mine was used to train and test the generalization capability of ANN models. Coefficient of determination (R²) and mean square error (MSE) were chosen as the indicators of the performance of the networks. A network with architecture 4-11-5-1 and R² of 0.957 and MSE of 0.000722 was found to be optimum. To demonstrate the supremacy of ANN approach, the same 69 data sets were used for the prediction of PPV with four common empirical models as well as multiple linear regression (MLR) analysis. The results revealed that the proposed ANN approach performs better than empirical and MLR models.