A Rtificial Neural Network Based On Automatically Adaptive Genetic Algorithm Using In Dam Safety Monitoring

Artificial neural network, as an artificial intelligence technique, develops rapidly in the recent fifty years, and attains compelling production。 It is mainly applied in pattern identifying, image processing, automation and optimizing, forecast and intelligent information managing, communication and so on。 In the recent few years, many water resource and hydropower workers apply it to the field of dam safety monitoring, and utilize the function approach capacity of Artificial neural network to simulate the complicated relationship of the independent variable and the consequent variable in dam safety monitoring, achieve the function of forecasting the consequent variable according to the independent variable, and attain excellent effect。 But during the using of Artificial neural network in dam safety monitoring, we find some localization and shortcoming: such as the influence of stylebook sequence, the speed and dithering of study, the convergence to local least value or unable convergence。 Sometimes these problem will depress the effect, so we must adopt some corresponding methods and measures to improve the simulating effect and forecasting precision。The dissertation recommends some kinds of methods and measures: such as adjusting the network configuration, connecting value and threshold value by the total value of all stylebooks, adding part of the adjusting value of the last time to the current adjusting value, transforming the stylebooks to standard value, optimizing activation function, appending threshold value to the putout of the nerve cell and so on。 Simultaneity, the author brings forward a new method to optimize the model of artificial neural network 。 It is using the automatically adaptive genetic algorithm to make the network configuration, connecting value and threshold value of artificial neural network better. The method can make the model better and improve the simulating effect and forecasting precision.Genetic algorithm is an arithmetic based on evolution and genetics used to search the optimization 。 The research on Genetic algorithm began in the 1960^th。 it develops rapidly in the recent years, attains great application and theory progress。 It issuccessfully applied to the field of enginery learning, process controK economy forecasting > engineering optimizing and so on<> Genetic algorithm is simple and robust, has strongpoint in parallel process and comprehensive applicability0 Using genetic algorithm to optimize the network configuration -. connecting value and threshold value of artificial neural network can increase the efficiency of the function approach capacity of Artificial neural network? The automatically adaptive genetic algorithm can improve the speed of searching and the efficiency of optimizing?The dissertation detailedly introduces the coming into being and progress ^ idea and theory> coding technique and basal operation flow of genetic algorithm.. The dissertation brings forward the methods and measures to increase the efficiency, sets up the model of Artificial neural network based on automatically adaptive genetic algorithm using in dam safety monitoring o The model is used to analyse the horizontal displacement of the lower dam of guangzhou pumped storage power station, and attains better simulating effect and forecasting precision o The dissertation compares the simulating effect of some models of dam safety monitoring?...