Abstract

For the safety of power station and people living in downstream area of the river, safety of the dam must be evaluated and monitored on the basis of prototype observation data. Among the evaluation indexes, displacement is proved to be the most convenient and efficient. Therefore it is important to forecast displacement of dam based on the observation data and the causation. Basically, the ANNs (Artificial Neural Networks) are numerical structures inspired by the learning process in the human brain. They are constructed and used as alternative mathematical tools to solve a diversity of problems in the fields of system identification, forecasting, pattern recognition, classification, process control and many others. Genetic algorithm (GA) belongs to a class of evolutionary computation techniques based on models of biological evolution. It has been proved useful in domains that are not well understood, or for search spaces which are too large to be efficiently searched by standard methods. Recently, it is popular to improve capability of neural network by genetic algorithm and apply the model in engineering field. Taking advantage of excellences of genetic algorithm and neural network, a GA neural network model is designed which combines neural network’s self-studying, error revising with genetic algorithm’s comprehensive searching ability. In the paper, standard genetic algorithm is modified at some aspects including coding, selection, crossover and mutation. Then the modified GA is used to calculate weight and threshold values of neural network and to determine the best network structure at the same time. By using this GA neural network model, displacement of dam is calculated on the basis of prototype observation data. To prove the performance of the model, capability and forecast precision are also analyzed. This kind of method provides useful technical support for safety monitoring of dam.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.