摘要
提出了一种适用于神经网络控制器在线学习的ＢＰ算法，它用共扼梯度因子λ确定学习的方向，通过奖惩系数γ调整学习步长η，从而具有高速收敛性、快速跟踪能力及较强的鲁棒性。最后通过一个４层前馈ＮＮ网络对标准控制序列进行学习仿真。
A fast varied step and conjugate gradient based BP algorithm (VSCGBP) is presented in this paper. The VSCGBP is a novel on line BP learning algorithm, which uses a conjugate gradient factor λ to determine the learning direction and uses a bonus penalty coeffient γ to adjust the learning step η . This approach guarantees stability, convergence and robustness of the algorithm. The VSCGBP is compared with the conventional BP algorithm by training a four layer neural network with a standard control series in this paper. Simulation results show that the proposed algorithm is outperformed.
出处
《电力系统自动化》
EI
CSCD
北大核心
1996年第12期25-29,共5页
Automation of Electric Power Systems
关键词
多层神经网络
共扼梯度
BP算法
电力系统
multilayer perceptron(MLP) conjugate gradient bonus penalty coeffient varied step and conjugate gradient based BP algorithm (VSCGBP)
