Entity

Time filter

Source Type


Cui D.,Wenshan Water Conservancy Bureau of Yunnan Province
Advances in Science and Technology of Water Resources | Year: 2014

In light of the problems that the prediction accuracy of a linear combination model is not high, the weight of a single prediction model is hard to determine, and the function of a nonlinear combined prediction model is hard to construct, a multiple combined annual runoff prediction model was put forward based on the principle of neural networks such as BP, Elman, RBF, GRNN, so as to maximize the useful information between the input vectors, and give full play to the characteristics of neural network models, such as their nonlinear mapping ability. Using the results of four single prediction models as the input vectors of one combined prediction model, and the observed flow data as the output vector, one combined prediction model with four inputs and one output was constructed. Then, using the result of the one combined prediction model as the input vector for two combined prediction models, and the observed flow data as the output vector, two combined prediction models with four inputs and one output were constructed. Using the same method, multiple combined prediction models with 12 kinds of construction schemes were constructed. Taking the Yili River Yamadu hydrological station in Xinjiang as an example, its annual runoff prediction results were compared with those of four kinds of single BP models and IEA-BP models. The results show that the prediction accuracy and generalization ability of multiple combined prediction models are improved as compared with the single prediction model, and with the increase of the combined number of model, the prediction accuracy tends to be improved. Multiple combined prediction models can improve the prediction accuracy. Source


Cui D.,Wenshan Water Conservancy Bureau of Yunnan Province
Advances in Science and Technology of Water Resources | Year: 2016

The chicken swarm optimization algorithm was validated using 15 complex functions, and the simulated results were compared with those of the Wolf algorithm, particle swarm optimization algorithm, fish swarm algorithm, and genetic algorithm. Using the chicken swarm optimization to search for the optimal projection direction of the projection pursuit model, a projection pursuit evaluation model was established. Using assessment of flood and drought disasters from 1990 to 2013 in Wenshan Prefecture as an example, five flood disaster evaluation indices, including disaster-affected population, and four drought disaster evaluation indices, including the disaster area of crops, were selected, and grading standards for flood and drought disaster assessment were constructed with the mean and standard deviation of the flood and drought disaster projection series. The results show that the chicken swarm optimization algorithm is robust and has high global optimization ability. Using the algorithm to select the optimal projection direction of the projection pursuit model can effectively improve the evaluation accuracy and prevent a high degree of variation from occurring in the optimal projection direction. © 2016, Editorial Board of Advances in Science and Technology of Water Resources, Hohai University. All right reserved. Source


Cui D.,Wenshan Water Conservancy Bureau of Yunnan Province
Advances in Science and Technology of Water Resources | Year: 2014

Due to the multicollinearity problems existing in the variables in the model of multivariate water demand prediction, and the defaults, such as the convergence speed of the BP neural network is slow for it to easily fall into local extreme values, the theories of phase space reconstruction and genetic algorithms (GA) were introduced into the BP neural network water demand prediction model. A GA-BP model for urban water demand prediction based on the theory of phase space reconstruction was put forward. Taking water demand prediction in Shanghai as an example, the effect of the GA-BP urban water demand prediction model was analyzed. The results show that the absolute value of the average relative error and the maximum absolute value of the relative error of the annual water demand prediction for the period of 2005 to 2009 in Shanghai based on the GA-BP urban water demand prediction model are 1.434 4% and 2.767 2%, prospectively, and the relative error of water demand prediction for the period of 2010 to 2011 are 0.513 6% and 0.027 0%, prospectively. The accuracy of the GA-BP model for urban water demand prediction is better than that of the BP neural network prediction model. The GA-BP model for urban water demand prediction based on the theory of phase space reconstruction has better prediction accuracy and generalization ability, being an effective method to improve the water demand prediction accuracy and generalization ability. © 2014, Editorial Board of Advances in Science and Technology of Water Resources, Hohai University. All right reserved. Source


Cui D.,Wenshan Water Conservancy Bureau of Yunnan Province | Jin B.,Wenshan Water Conservancy Bureau of Yunnan Province
Advances in Science and Technology of Water Resources | Year: 2014

The aim of this study is to use the analytic hierarchy process to select 24 indicators from the water ecosystem and socioeconomic system. For archive this goal, 3 levels of water evaluation index system of water ecological civilization and 5 grades of grading standard have been constructed. We assessed the performance of the model through random generation and random selection by constructing the training samples and checking samples between the threshold evaluation standard of water ecological civilization; establishing the evaluation model of water ecological civilization based on random forest regression algorithm; and by constructing radial basis function neural network model as a contrast model. Taking Wenshan Prefecture as an example of comprehensive evaluation of water ecological civilization analysis, the results show that the three evaluation indexes of the water ecological civilization, based on random forest algorithm, are better than that on the radial basis function neural network model. The former has the advantages of high precision, strong generalization ability, fast convergence speed, steady performance and small number of regulation parameters. The overall prediction for 2015, 2020 and 2030 shows that the evaluation results of the eco-civilization of water in Wenshan Prefecture are “basically harmonious” “harmonious” and “ideal”, respectively. Source


Cui D.,Wenshan Water Conservancy Bureau of Yunnan Province | Jin B.,Wenshan Water Conservancy Bureau of Yunnan Province
Journal of Hohai University | Year: 2014

This paper focuses on several key issues of a BP neural network when it is applied to the comprehensive evaluation of water conservancy in a state of relative prosperity. Based on the analytic hierarchy process (AHP), 30 representative indicators were selected out of more than 100 water conservancy indicators, in order to build up a comprehensive evaluation system of water conservancy in a state of relative prosperity and grading standards as well. In practical application, the BP neural network has shortcomings, including the slow convergence and likely occurrence of local extreme values. To overcome these shortcomings, an LM-BP neural network model was established for comprehensive evaluation of water conservancy in a state of relative prosperity. In this case, training and testing samples were generated between standard thresholds using the random interpolation method. A concept of network fitness is proposed as well. The performance of the proposed model was evaluated using the network fitness, the average relative error, and three other statistical indicators. After the evaluation of the model achieved the expected accuracy and generalization ability, it was applied to the comprehensive evaluation of water conservancy in a state of relative prosperity in Wenshan Zhuang and Miao Autonomous Prefecture, and compared with traditional BP and RBF models. The results are as follows: (a) In both the training samples and testing samples, the LM-BP model had higher evaluation accuracy than traditional BP and RBF models by nearly an order of magnitude, indicating that the LM-BP model has high accuracy and generalization capability and is applicable to the comprehensive evaluation of water conservancy in a state of relative prosperity in Wenshan Zhuang and Miao Autonomous Prefecture. In addition, the LM-BP model has the advantages of fast convergence and a high degree of stability. (b) In the year 2010, water conservancy in a state of relative prosperity in Wenshan Zhuang and Miao Autonomous Prefecture and county-level administrative districts was at level I to II, the initial stages. It will reach level III in the year 2020 according to the prediction, which means that the water conservancy in the whole prefecture will basically achieve a state of relative prosperity. Source

Discover hidden collaborations