1. Developing a hybrid model of salp swarm algorithm-based support vector machine to predict the strength of fiber-reinforced cemented paste backfill
- Author
-
Zhi Yu, Enming Li, Danial Jahed Armaghani, Huang Peisheng, Xin Chen, Jian Zhou, and Xiuzhi Shi
- Subjects
Heuristic (computer science) ,business.industry ,0211 other engineering and technologies ,General Engineering ,Particle swarm optimization ,02 engineering and technology ,Structural engineering ,Computer Science Applications ,Support vector machine ,020303 mechanical engineering & transports ,0203 mechanical engineering ,Robustness (computer science) ,Modeling and Simulation ,Hyperparameter optimization ,Salp swarm algorithm ,Fiber ,business ,Software ,Predictive modelling ,021106 design practice & management ,Mathematics - Abstract
To test the impact of different mixture ratios on backfilling strength in Fankou lead–zinc mine, various mixture ratio designs have been conducted. Meanwhile, to improve the strength of ultra-fine tailings-based cement paste backfill (CPB), two kinds of fibers were utilized in this study, namely polypropylene (PP) fibers and straw fibers. To achieve these, a total of 144 CPB backfilling scenarios with different combinations of influenced factors were tested by uniaxial compressive tests. The test results indicated that polypropylene fibers improve the strength of CPB, while in some scenarios the addition of straw fibers decreases the strength of CPB. In this research, the support vector machine (SVM) technique coupled with three heuristic algorithms, namely genetic algorithms, particle swarm optimization and salp swarm algorithm (SSA), was developed to predict the strength of fiber-reinforced CPB. Also, the optimal performance of metaheuristic algorithms was compared with one fundamental search method, i.e., grid search (GS). The overall performance of four optimal algorithms was calculated by the ranking system. It can be found that these four approaches all presented satisfactory predictive capability. But the metaheuristic algorithms can capture better hyper-parameters for SVM prediction models compared with GS-SVM method. The robustness and generalization of SSA-SVM methods were the most prominent with the R2 values of 0.9245 and 0.9475 for training sets and testing sets. Therefore, SSA-SVM will be recommended to model the complexity of interactions for fiber-reinforced CPB and predict fiber-reinforced CPB strength.
- Published
- 2020