Study on MPGA-BP of Gravity Dam Deformation Prediction

Displacement is an important physical quantity of hydraulic structures deformation monitoring, and its prediction accuracy is the premise of ensuring the safe operation. Most existing metaheuristic methods have three problems: (1) falling into local minimum easily, (2) slowing convergence, and (3) the initial value’s sensitivity. Resolving these three problems and improving the prediction accuracy necessitate the application of genetic algorithm-based backpropagation (GA-BP) neural network and multiple population genetic algorithm (MPGA). A hybrid multiple population genetic algorithm backpropagation (MPGA-BP) neural network algorithm is put forward to optimize deformation prediction from periodic monitoring surveys of hydraulic structures. This hybrid model is employed for analyzing the displacement of a gravity dam in China. The results show the proposed model is superior to an ordinary BP neural network and statistical regression model in the aspect of global search, convergence speed, and prediction accuracy.

Download Full-text

Desiccant wheel system modeling improvement using multiple population genetic algorithm training of neural network

Drying Technology ◽

10.1080/07373937.2016.1260031 ◽

2017 ◽

Vol 35 (14) ◽

pp. 1663-1674 ◽

Cited By ~ 4

Author(s):

Yongli Yang ◽

Hua Cong ◽

Pengcheng Jiang ◽

Fuzhou Feng ◽

Ping Zhang ◽

...

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Population Genetic ◽

System Modeling ◽

Desiccant Wheel ◽

Multiple Population ◽

Population Genetic Algorithm

Download Full-text

Application of Multiple Population Genetic Algorithm in Optimizing Business Process

Artificial Intelligence and Renewables Towards an Energy Transition - Lecture Notes in Networks and Systems ◽

10.1007/978-3-030-63846-7_82 ◽

2020 ◽

pp. 847-855

Author(s):

Nadir Mahammed ◽

Souad Bennabi ◽

Mahmoud Fahsi

Keyword(s):

Genetic Algorithm ◽

Business Process ◽

Population Genetic ◽

Multiple Population ◽

Population Genetic Algorithm

Download Full-text

Optimized Erosion Prediction with MAGA Algorithm Based on BP Neural Network for Submerged Low-Pressure Water Jet

Applied Sciences ◽

10.3390/app10082926 ◽

2020 ◽

Vol 10 (8) ◽

pp. 2926

Author(s):

Yanzhen Chen ◽

Yihuai Hu ◽

Shenglong Zhang ◽

Xiaojun Mei ◽

Qingguo Shi

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Prediction Model ◽

Bp Neural Network ◽

Prediction Accuracy ◽

Water Jet ◽

Erosion Prediction ◽

Pressure Water ◽

Erosion Test ◽

Bp Model

In order to accurately predict the erosion effect of underwater cleaning with an angle nozzle under different working conditions, this paper uses refractory bricks to simulate marine fouling as the erosion target, and studies the optimized erosion prediction model by erosion test based on the submerged low-pressure water jet. The erosion test is conducted by orthogonal experimental design, and experimental data are used for the prediction model. By combining with statistical range and variance analysis methods, the jet pressure, impact time and jet angle are determined as three inputs of the prediction model, and erosion depth is the output index of the prediction model. A virtual data generation method is used to increase the amount of input data for the prediction model. This paper also proposes a Mind-evolved Advanced Genetic Algorithm (MAGA), which has a reliable optimization effect in the verification of four stand test functions. Then, the improved back-propagating (BP) neural network prediction models are established by respectively using Genetic Algorithm (GA) and MAGA optimization algorithms to optimize the initial thresholds and weights of the BP neural network. Compared to the prediction results of the BP and GA-BP models, the R2 of the MAGA-BP model is the highest, reaching 0.9954; the total error is reduced by 47.31% and 35.01%; the root mean square error decreases by 51.05% and 31.80%; and the maximum absolute percentage error decreases by 65.79% and 64.01%, respectively. The average prediction accuracy of the MAGA-BP model is controlled within 3%, which has been significantly improved. The results show that the prediction accuracy of the MAGA-BP prediction model is higher and more reliable, and the MAGA algorithm has a good optimization effect. This optimized erosion prediction method is feasible.

Download Full-text