Title : 
Dam Safety Monitoring Forecast Model Based on CPSO
         
        
            Author : 
Zhang Lei ; Ziyang, L.
         
        
            Author_Institution : 
Coll. of Water Conservancy & Hydropower Eng, Hohai Univ., Nanjing
         
        
        
        
        
        
            Abstract : 
By using steepest descend algorithm to calculate the networks weights, traditional BP networks model in the dam safety monitoring is complex in calculation process and will easily fall into local extreme point. To solve the shortages, the cooperative particle swarm optimization algorithm is proposed to optimize the weights of the neural networks for dam safety monitoring. Firstly, the calculation of the networks weights is converted into the particle swarm optimization. Then the calculation is realized by the cooperative particle swarm optimization. The result of application shows that with easy calculation, fast convergence and high precision, the neural network model based on the cooperative particle swarm optimization algorithm provides a useful new method for the dam safety monitoring.
         
        
            Keywords : 
backpropagation; computerised monitoring; condition monitoring; construction industry; dams; neural nets; particle swarm optimisation; safety; BP networks model; cooperative particle swarm optimisation; dam safety monitoring forecast model; neural networks; steepest descend algorithm; Convergence; Educational institutions; Hydroelectric power generation; Monitoring; Neural networks; Particle swarm optimization; Predictive models; Safety; Space technology; Water conservation;
         
        
        
        
            Conference_Titel : 
Intelligent Systems and Applications, 2009. ISA 2009. International Workshop on
         
        
            Conference_Location : 
Wuhan
         
        
            Print_ISBN : 
978-1-4244-3893-8
         
        
            Electronic_ISBN : 
978-1-4244-3894-5
         
        
        
            DOI : 
10.1109/IWISA.2009.5072798