Development of fuzzy-GMDH model optimized by GSA to predict rock tensile strength based on experimental datasets
Development of fuzzy-GMDH model optimized by GSA to predict rock tensile strength based on experimental datasets
Hooman Harandizadeh1 Mohammad Mohsen Tawfiq2
1) PhD graduate in Civil Engineering, Department of Civil Engineering, Shahid Bahonar University, Kerman, Iran
2) Professor of Civil Engineering Department, Shahid Bahonar University, Kerman, Iran
IOI Code
:
XEEZ-HBCCE
Publication :
The First Conference on Artificial Intelligence and Smart Computing(aisc2022.semnan.ac.ir)
Abstract :
This research attempts to develop an innovative hybrid intelligent model, namely fuzzy clustering method (GMDH) optimized by gravitational search algorithm (GSA), Fuzzy-GMDH-GSA, to predict rock TS. To create the database, rock samples collected from a tunnel site were evaluated in the laboratory and the database was prepared. For modeling then, a fuzzy-GMDH-GSA model was developed to predict the rock BTS by considering the most effective predictive model. In addition, a fuzzy model as well as a GMDH model were constructed to predict BTS for comparison purposes. The performance of the proposed prediction models was evaluated by comparing the values of several statistical measures such as the correlation coefficient (R). R values of 0.90, 0.86, and 0.86 were obtained for testing datasets of fuzzy-GMDH-GSA, GMDH, and fuzzy models, respectively, indicating that the fuzzy-GMDH-GSA prediction model is able to provide better prediction performance compared to other models. The constructed models results confirmed the effective role of GSA as a powerful optimization algorithm in the performance of the hybrid GMDH-GSA fuzzy model. Also, the results of the sensitivity analysis showed that the point load index is the most effective input on the output of this study.
Keywords : tensile strength gravitational search algorithm optimization algorithm group method of data handling fuzzy system