摘要
A self-adaptive control method is proposed based on an artificial neural network(ANN)with accelerated evolutionary programming(AEP)algorithm.The neural network is used to model the uncertainty process,from which the teacher signals are produced online to regulate the parameters of the controller.The accelerated evolutionary programming is used to train the neural network.The experiment results show that the method can obviously improve the dynamic performance of uncertainty systems.
A self-adaptive control method is proposed based on an artificial neural network （ANN） with accelerated evolutionary programming （AEP） algorithm. The neural network is used to model the uncertainty process, from which the teacher signals are produced online to regulate the parameters of the controller. The accelerated evolutionary programming is used to train the neural network. The experiment results show that the method can obviously improve the dynamic performance of uncertainty systems.
基金
Key Equipment Project of China Petroleum & Chemical Corporation(SINOPEC)(No.J W05008)
