Rock tensile strength prediction using empirical and soft computing approaches

Mahdiyar, Amir; Armaghani, Danial Jahed; Marto, Aminaton; Nilashi, Mehrbakhsh; Ismail, Shahrinaz

doi:10.1007/s10064-018-1405-4

Cited by 46 publications

(19 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The obtained results confirmed the superiority of the block punch index over Is 50 in terms of prediction of the BTS. The correlation between TS and Is 50 have been also examined by other studies such as Kahraman and Gunaydin [16], Heidari et al [8], Basu et al [17], Karaman et al [18] and Mahdiyar et al [19]. Sheorey [20] underlined the broadlyacknowledged statement about the correlation of BTS and uniaxial compressive strength (UCS) in rocks, stating that the compressive strength of rock is roughly ten times greater than the BTS of that rock; though, it should be noted that the rock behavior is rather site-specific.…”

Section: Introductionmentioning

confidence: 89%

“…According to their results, the effectiveness of the single compressive strength test in predicting UCS and TS was demonstrated. Mahdiyar et al [19] predicted the TS of rocks using hybrid intelligent models. They used particle swarm optimization (PSO) and imperialist competitive algorithm (ICA) to train the ANN models, and demonstrated the efficiency of their proposed methods in rock TS prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Potential Application of a New Intelligent Based Approach in Predicting the Tensile Strength of Rock

et al. 2020

Self Cite

View full text Add to dashboard Cite

Tensile strength (TS) of rock is one of the important properties in design process of construction civil works such as foundations and tunnels. Brazilian tensile strength (BTS) or splitting test is considered as a well-known method in evaluating TS. The present study attempts to propose a novel metaheuristic approach for the indirect measurement of BTS. This new approach is based on the firefly algorithm (FA) for training and optimizing the consequent parameters of the adaptive neuro-fuzzy inference system (ANFIS). The rock samples collected from a tunnel in Malaysia were tested in the laboratory for the purpose of providing a database consisting of totally 80 samples for analysis. Then, the statistical metrics such as coefficient of determination (R 2) were used to examine the acceptability of the proposed ANFIS-FA and ANFIS models. Finally, it was concluded that the ANFIS-FA (with the R 2 of 0.982) can be effectively used as a robust model to predict BTS. INDEX TERMS Tensile strength, brazilian tensile strength, ANFIS, firefly algorithm.

show abstract

Section: Introductionmentioning

confidence: 89%

Section: Introductionmentioning

confidence: 99%

The Potential Application of a New Intelligent Based Approach in Predicting the Tensile Strength of Rock

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, to evaluate the predicted simple regression equations (linear, power, logarithm, and polynomial) and to select the best equation to estimate both UCS and E t based on LRH value, the evaluation was conducted based on statistical performance indices, coefficient of determination (R 2 ), and root mean square error (RMSE), which has been adapted by many researchers (85,86). A strong correlation model can be considered if R 2 equals 1.0 and RMSE are close to zero (29,33).…”

Section: Regression Analysismentioning

confidence: 99%

Assessing the uniaxial compressive strength and tangent Young’s modulus of basalt rock using the Leeb rebound hardness test

2020

View full text Add to dashboard Cite

Basalt was used as an ornamental stone in any historic and ancient cities in Jordan. Measuring the uniaxial compressive strength (UCS) and the tangent Young’s modulus (Et) in the laboratory requires premium quality specimens with special core dimensions. This research focuses on correlations both UCS and Et with Leeb Rebound Hardness Test (LRH). In the laboratory, UCS, Et, and LRH were performed on 90 core samples extracted from 30 different rock boulders collected from the neighboring area of Umm al-Jimal, a historic city in northeastern Jordan. A strong power correlation with (R2 = 0.888, RMSE = 5.464) was found between non-destructive LRH value and UCS. On the other hand, a moderately strong linear regression with (R2 = 0.792, RMSE = 4.661) was found between Et and LRH. In conclusion, non-destructive LRHs can be used as indictors for evaluating both UCS and Et during the restoration of the historic city Umm al-Jimal and the rehabilitation of other existing structures.

show abstract

“…To select the best predictive neuro-swarm model, five performance indices including variance account for (VAF), R 2 , mean absolute error (MAE), RMSE and the a20-index have been used and applied. These performance indices have been widely utilized to assess model performance in the previous related works [23,[71][72][73][74][75][76][77][78][79][80][81]. The computation formulas of VAF, MAE and a20-index are presented as follows:…”

Section: Resultsmentioning

confidence: 99%

On the Use of Neuro-Swarm System to Forecast the Pile Settlement

et al. 2020

Self Cite

View full text Add to dashboard Cite

In civil engineering applications, piles (deep foundations) are pushed into the ground in order to perform as steady support of structures. As these type of foundations are able to carry a huge amount of load, they should be carefully designed in terms of their settlement. Therefore, the control and estimation of settlement is a significant issue in pilling design and construction. The objective of the present study is to introduce a modeling process of a hybrid intelligence system namely neural network optimized by particle swarm optimization (neuro-swarm) for estimation of pile settlement. To do that, properties results of several piles socketed into rock mass together with their settlements were considered as established databased to propose neuro-swarm model. Then, several sensitivity analyses were carried out to determine the most influential particle swarm optimization parameters for pile settlement prediction. Eventually, five neuro-swarm models were constructed to understand the behavior of this hybrid model on them in pile settlement prediction. As a result, according to results of five performance indices, dataset number 4 showed the highest prediction capacity among all five datasets. The coefficient of determination (R2) and system error values of (0.851 and 0.079) and (0.892 and 0.099) were obtained respectively for train and test stages of the best neuro-swarm model which reveal the capability level of this hybrid model in predicting pile settlement. The modeling process introduced in this study can be useful for the researchers who are interested to work on the same hybrid technique.

show abstract

Rock tensile strength prediction using empirical and soft computing approaches

Cited by 46 publications

References 59 publications

The Potential Application of a New Intelligent Based Approach in Predicting the Tensile Strength of Rock

The Potential Application of a New Intelligent Based Approach in Predicting the Tensile Strength of Rock

Assessing the uniaxial compressive strength and tangent Young’s modulus of basalt rock using the Leeb rebound hardness test

On the Use of Neuro-Swarm System to Forecast the Pile Settlement

Contact Info

Product

Resources

About