Uniaxial Compressive Strength Prediction for Rock Material in Deep Mine Using Boosting-Based Machine Learning Methods and Optimization Algorithms

Traditional laboratory tests for measuring rock uniaxial compressive strength(UCS)are tedious and timeconsuming.There is a pressing need for more effective methods to determine rock UCS,especially in deep mining environments under high in-situ stress.Thus,this study aims to develop an advanced model for predicting the UCS of rockmaterial in deepmining environments by combining three boosting-basedmachine learning methods with four optimization algorithms.For this purpose,the Lead-Zinc mine in Southwest China is considered as the case study.Rock density,P-wave velocity,and point load strength index are used as input variables,and UCS is regarded as the output.Subsequently,twelve hybrid predictive models are obtained.Root mean square error(RMSE),mean absolute error(MAE),coefficient of determination(R2),and the proportion of the mean absolute percentage error less than 20%(A-20)are selected as the evaluation metrics.Experimental results showed that the hybridmodel consisting of the extreme gradient boostingmethod and the artificial bee colony algorithm(XGBoost-ABC)achieved satisfactory results on the training dataset and exhibited the best generalization performance on the testing dataset.The values of R2,A-20,RMSE,and MAE on the training dataset are 0.98,1.0,3.11 MPa,and 2.23MPa,respectively.The highest values of R2 and A-20(0.93 and 0.96),and the smallest RMSE and MAE values of 4.78 MPa and 3.76MPa,are observed on the testing dataset.The proposed hybrid model can be considered a reliable and effective method for predicting rock UCS in deep mines.

Strength prediction of multi-layered copper-based composites fabricated by accumulative roll bonding

This work aims to evaluate the feasibility of the fabrication of nanostructured Cu/Al/Ag multi-layered composites by accumulative roll bonding(ARB),and to analyze the tensile properties and electrical conductivity of the produced composites.A theoretical model using strengthening mechanisms and some structural parameters extracted from X-ray diffraction is also developed to predict the tensile strength of the composites.It was found that by progression of ARB,the experimental and calculated tensile strengths are enhanced,reach a maximum of about 450 and 510 MPa at the fifth cycle of ARB,respectively and then are reduced.The electrical conductivity decreased slightly by increasing the number of ARB cycles at initial ARB cycles,but the decrease was intensified at the final ARB cycles.In conclusion,the merit of ARB to fabricate this type of multi-layered nanocomposites and the accuracy of the developed model to predict tensile strength were realized.

Yield strength prediction of rolled Al-(1.44-12.40)Si-0.7Mg alloy sheets under T4 condition

The effects of Si content on the microstructure and yield strength of Al-(1.44-12.40)Si-0.7 Mg(wt.%)alloy sheets under the T4 condition were systematically studied via laser scanning confocal microscopy(LSCM),DSC,TEM and tensile tests.The results show that the recrystallization grain of the alloy sheets becomes more refined with an increase in Si content.When the Si content increases from 1.44 to 12.4 wt.%,the grain size of the alloy sheets decreases from approximately 47 to 10μm.Further,with an increase in Si content,the volume fraction of the GP zones in the matrix increases slightly.Based on the existing model,a yield strength model for alloy sheets was proposed.The predicted results are in good agreement with the actual experimental results and reveal the strengthening mechanisms of the Al-(1.44-12.40)Si-0.7 Mg alloy sheets under the T4 condition and how they are influenced by the Si content.

Cubic Meter Compressive Strength Prediction of Concrete

In order to improve the prediction accuracy of compressive strength of concrete,103 groups of concrete data were collected as the samples.We selected seven kinds of ingredients from the concrete samples, using Grid-SVM, PSO-SVM, and GA-SVM models to establish the prediction model of cubic meter compressive strength of concrete.The experimental results show that SVM model based on Grid optimization algorithm,SVM model based on Particle swarm optimization algorithm,SVM model based on Genetic optimization algorithm mean square error respectively are 0.001, 0.489 8, and 0.304 2, correlation coefficients are 0.994 8, 0.994 6, and 0.993 0. It is shown that cubic meter compressive strength prediction method based on Grid-SVM model is the best optimization algorithm.

Prediction of Antifrccze Critical Strength of Infant Age Concrete

The rule of infant age concrete strength development under low temperature and complex affecting factors is researched. An efficient and reliable mathematical forecast model is set up to predict the infant age concrete antifreeze critical strength under low temperature at construction site. On the basis of the revision of concrete equivalent coefficient under complex influencing factors, least-squares curve-fitting method is applied to approximate the concrete strength under standard curing and the forecast formula of concrete compressive strength could be obtained under natural temperature condition by various effects. When the amounts of double-doped are 10% fly ashes and 4% silica fumes as coment replacement, the antifreeze critical strength changes form 3.5-4.1MPa under different low temperature curing. The equivalent coefficient correction formula of concrete under low temperature affected by various factors could be obtained. The obtained equivalent coefficient is suitable for calculating the strength which is between 10% to 40% of standard strength and the curing temperature from 5-20 ℃. The forecast value of concrete antifreeze critical strength under low temperature could be achieved by combining the concrete antifreeze critical strength value with the compressive strength forecast of infant age concrete under low temperature. Then the theory for construction quality control under low temperature is provided.

Field strength prediction of mobile communication network based on GIS

This article describes GIS-based models successfully developed for predicting the coverage of Cityphone cellular network,visualizing the predicted signal strength,and analyzing the field strength coverage.In order to predict the signal coverage strength of communication network more accurately,the spatial and nonspatial databases of a mobile cellular network are combined by GIS and produce the necessary parameters.A GIS model named COST-231-Walfisch–Ikegami model(WIM)is developed for signal coverage prediction in Ho Chi Minh City.Radio-line-of-sight and nonradio-lineof-sight conditions can be determined by this model.In addition,in case of nonradio-line-of-sight conditions,average building height,building separation,building width,incident radio path,and road orientation with respect to the direct radio path were obtained using GIS.Road orientation loss,multiscreen diffraction loss,and shadowing gain were predicted more accurate by this model.The scale of maps in the experiment was 1:2000 and the average of floor height was 3 m because there were no exact building height measurements.Statistical results show that the path loss predicted by the COST 231 WIM overcame the real path loss of each cell station.And this method can be used for signal coverage prediction of mobile cellular network in urban areas.Compared to the current situation with the Ho Chi Minh City Posts and Telecommunications system,this model can be effectively applied to improve the Cityphone mobile network quality as well as capability.Developed GIS models can help designers in predicting cell station coverage using real spatial maps that make the results more reliable.This research can help network operators improve the network quality and capability with the best investment efficiently.

Indoor field strength prediction based on FMM

In this article, the fast multipole method （FMM） is applied to analgze the field strength of an ultra-wideband （UWB） signal. Small coverage of UWB communication systems and high efficiency of the algorithm make it possible to calculate the amplitude of electric field accurately. A homogeneous dielectric body and a multilayered dielectric object are studied. The computational results obtained by applying the FMM agree well with those obtained by applying the method of moments （MoM）.

Compressive strength prediction of sprayed concrete lining in tunnel engineering using hybrid machine learning techniques

Sprayed concrete lining is a commonly employed support measure in tunnel engineering,which plays an important role in construction safety.Compressive strength is a key performance indicator of sprayed concrete lining,and the traditional measuring method is time-consuming and laborious.This paper proposes various hybrid machine learning algorithms to accomplish the advanced prediction of compressive strength of sprayed concrete lining based on the mixture design.Two hundred and five sets of experimental data were collected from a water conveyance tunnel in northwestern China for model construction,and each set of data was made up of six basic input variables(i.e.,water,cement,mineral powder,superplasticizer,coarse aggregate,and fine aggregate)and one output variable(i.e.,compressive strength).In order to eliminate the correlation between input variables,a new composite indicator(i.e.,the water-binder ratio)was introduced to achieve dimensionality reduction.After that,four hybrid models in total were built,namely BPNN-QPSO,SVR-QPSO,ELM-QPSO,and RF-QPSO,where the hyper-parameters of BPNN,SVR,ELM,and RF were auto-tuned by QPSO.Engineering application results indicated that RF-QPSO achieved the lowest mean absolute percentage error(MAPE)of 3.47% and root mean square error(RMSE)of 1.30 and the highest determination coefficient(R^(2))of 0.93 in the four hybrid models.Moreover,RFQPSO had the shortest running time of 0.15 s,followed by SVR-QPSO(0.18 s),ELM-QPSO(1.19 s),and BPNN-QPSO(1.58 s).Compared with BPNN-QPSO,SVR-QPSO,and ELM-QPSO,RF-QPSO performed the most superior performance in terms of both prediction accuracy and running speed.Finally,the importance of input variables on the model performance was quantitatively evaluated,further enhancing the interpretability of RF-QPSO.

Simulation of foamed concrete compressive strength prediction using adaptive neuro-fuzzy inference system optimized by nature-inspired algorithms

Concrete compressive strength prediction is an essential process for material design and sustainability.This study investigates several novel hybrid adaptive neuro-fuzzy inference system(ANFIS)evolutionary models,i.e.,ANFIS-particle swarm optimization(PSO),ANFIS-ant colony,ANFIS-differential evolution(DE),and ANFIS-genetic algorithm to predict the foamed concrete compressive strength.Several concrete properties,including cement content(C),oven dry density(O),water-to-binder ratio(W),and foamed volume(F)are used as input variables.A relevant data set is obtained from open-access published experimental investigations and used to build predictive models.The performance of the proposed predictive models is evaluated based on the mean performance(MP),which is the mean value of several statistical error indices.To optimize each predictive model and its input variables,univariate(C,O,W,and F),bivariate(C-O,C-W,C-F,O-W,O-F,and W-F),trivariate(C-O-W,C-W-F,O-W-F),and four-variate(C-O-W-F)combinations of input variables are constructed for each model.The results indicate that the best predictions obtained using the univariate,bivariate,trivariate,and four-variate models are ANFIS-DE-(O)(MP=0.96),ANFIS-PSO-(C-O)(MP=0.88),ANFIS-DE-(O-W-F)(MP=0.94),and ANFIS-PSO-(C-O-W-F)(MP=0.89),respectively.ANFIS-PSO-(C-O)yielded the best accurate prediction of compressive strength with an MP value of 0.96.

An Analytical Approach for Assessing the Collapse Strength of an Unbonded Flexible Pipe

This paper presents an analytical scheme for predicting the collapse strength of a flexible pipe, which considers the structural interaction between relevant layers. The analytical results were compared with a FEA model and a number of test data, and showed reasonably good agreement. The theoretical analysis showed that the pressure armor layer enhanced the strength of the carcass against buckling, though the barrier weakened this effect. The collapse strength of pipe was influenced by many factors such as the inner radius of the pipe, the thickness of the layers and the mechanical properties of the materials. For example, an increase in the thickness of the barrier will increase contact pressure and in turn reduce the critical pressure.

Machine learning based models for predicting compressive strength of geopolymer concrete

Recently,great attention has been paid to geopolymer concrete due to its advantageous mechanical and environmentally friendly properties.Much effort has been made in experimental studies to advance the understanding of geopolymer concrete,in which compressive strength is one of the most important properties.To facilitate engineering work on the material,an efficient predicting model is needed.In this study,three machine learning(ML)-based models,namely deep neural network(DNN),K-nearest neighbors(KNN),and support vector machines(SVM),are developed for forecasting the compressive strength of the geopolymer concrete.A total of 375 experimental samples are collected from the literature to build a database for the development of the predicting models.A careful procedure for data preprocessing is implemented,by which outliers are examined and removed from the database and input variables are standardized before feeding to the fitting process.The standard K-fold cross-validation approach is applied for evaluating the performance of the models so that overfitting status is well managed,thus the generalizability of the models is ensured.The effectiveness of the models is assessed via statistical metrics including root mean squared error(RMSE),mean absolute error(MAE),correlation coefficient(R),and the recently proposed performance index(PI).The basic mean square error(MSE)is used as the loss function to be minimized during the model fitting process.The three ML-based models are successfully developed for estimating the compressive strength,for which good correlations between the predicted and the true values are obtained for DNN,KNN,and SVM.The numerical results suggest that the DNN model generally outperforms the other two models.

Damage Failure Analysis of Z-Pins Reinforced Composite Adhesively Bonded Single-Lap Joint

In order to study themechanical properties of Z-pins reinforced laminated composite single-lap adhesively bonded joint under un-directional static tensile load,damage failure analysis of the joint was carried out bymeans of test and numerical simulation.The failure mode and mechanism of the joint were analyzed by tensile failure experiments.According to the experimental results,the joint exhibits mixed failure,and the ultimate failure is Z-pins pulling out of the adherend.In order to study the failure mechanism of the joint,the finite element method is used to predict the failure strength.The numerical results are in good agreement with the experimental results,and the error is 6.0%,which proves the validity of the numerical model.Through progressive damage failure analysis,it is found that matrix tensile failure of laminate at the edge of Z-pins occurs first,then adhesive layer failure-proceeds at the edge of Z-pins,and finally matrix-fiber shear failure of the laminate takes place.With the increase of load,the matrix-fiber shear failure expands gradually in the X direction,and at the same time,the matrix tensile failure at the hole edge gradually extends in different directions,which is consistent with the experimental results.

DAMAGE MECHANISM ANALYSIS OF 2D 1×1 BRAIDED COMPOSITES UNDER UNIDIRECTIONAL TENSION

Coupling with the periodical displacement boundary condition,a representative volume element(RVE) model is established to simulate the progressive damage behavior of 2D1×1 braided composites under unidirectional tension by using the nonlinear finite element method.Tsai-Wu failure criterion with various damage modes and Mises criterion are considered for predicting damage initiation and progression of yarns and matrix.The anisotropic damage model for yarns and the isotropic damage model for matrix are used to simulate the microscopic damage propagation of 2D1×1braided composites.Murakami′s damage tensor is adopted to characterize each damage mode.In the simulation process,the damage mechanisms are revealed and the tensile strength of 2D1×1braided composites is predicted from the calculated average stress-average strain curve.Numerical results show good agreement with experimental data,thus the proposed simulation method is verified for damage mechanism analysis of 2D braided composites.

Prediction of underwater target strength

A model as well as its numerical method to calculate target strength of rigid body using Lighthill's acoustic analogy approach which developed from the propeller aircraft sound field study have been presented. The cases of ellipsoid target has been used to demonstrate the approach. The comparison of the numerical results with that of analytical formulation provides a satisfactory check for the validity of the approach. Some reasonable results have been discussed. The advantage of the present model is that it is suitable for any arbitrarily shaped rigid body moving with small Mach number.

Global nonequilibrium energy criterion for predicting strength of 316L stainless steel under complex loadings:Theoretical modeling and experimental validation

Classical strength criteria are developed based on some empirical assumptions and have been widely used in engineering to predict material strength owing to their simplicity. In some cases, however, considerable discrepancies arise between classicalstrength-criteria-based theoretical predictions and experimental results. Recently, a global nonequilibrium thermodynamics model has made important progress over classical models without resorting to any empirical assumptions. A prominent advance of this rational energy model is that it straightforwardly determines the dissipation energy density function, which is pertinent to inherent material ductility, through simple uniaxial and equi-biaxial tensions. In this study, a brief introduction of the nonequilibrium energy model was followed by systematic experimental investigation to determine the dissipation energy function and predict the material strength of pristine 316 L stainless steel-commonly used in engineering-under complex loadings. The results indicated that the strength contours predicted by the nonequilibrium energy criterion for complex loadings are consistent with the experimental results obtained for biaxial tension, implying that the nonequilibrium thermodynamics model is both reasonable and reliable. The prediction error was presumed to be induced by the anisotropy of the 316 L stainless steel sheets.

Influence of accelerated curing on the compressive strength of polymer-modified concrete

In recent building practice,rapid construction is one of the principal requisites.Furthermore,in designing concrete structures,compressive strength is the most significant of all parameters.While 3-d and 7-d compressive strength reflects the strengths at early phases,the ultimate strength is paramount.An effort has been made in this study to develop mathematical models for predicting compressive strength of concrete incorporating ethylene vinyl acetate(EVA)at the later phases.Kolmogorov-Smirnov(KS)goodness-of-fit test was used to examine distribution of the data.The compressive strength of EVA-modified concrete was studied by incorporating various concentrations of EVA as an admixture and by testing at ages of 28,56,90,120,210,and 365 d.An accelerated compressive strength at 3.5 hours was considered as a reference strength on the basis of which all the specified strengths were predicted by means of linear regression fit.Based on the results of KS goodness-of-fit test,it was concluded that KS test statistics value(D)in each case was lower than the critical value 0.521 for a significance level of 0.05,which demonstrated that the data was normally distributed.Based on the results of compressive strength test,it was concluded that the strength of EVA-modified specimens increased at all ages and the optimum dosage of EVA was achieved at 16%concentration.Furthermore,it was concluded that predicted compressive strength values lies within a 6%difference from the actual strength values for all the mixes,which indicates the practicability of the regression equations.This research work may help in understanding the role of EVA as a viable material in polymer-based cement composites.