论文部分内容阅读
极限学习机(Extreme learning machine,ELM)是一种单隐层前馈神经网络(SLFNs),它随机选择网络的隐含层节点及其参数,训练时仅需调节输出层权值,因此ELM以极快的学习速度获得良好的推广性。考虑到ELM的特征映射函数未知时,可以将核矩阵引入到ELM中。针对模型未知的强非线性连续搅拌反应釜(Continuous Stirred Tank Reactor,CSTR),提出一种基于核极限学习机(Extreme Learning Machine with Kernels,KELM)的NARX模型辨识方法。以仿真的CSTR过程实例进行辨识实验,建立基于NARX-KELM的辨识模型。实验结果表明,在相同条件下,与带动量因子的BP神经网络、模糊神经网络(FNN)、GAP-RBF、MGAP-RBF神经网络、回声状态网络(ESN)、ELM等方法相比,KELM能够有效地改进辨识精度,而且性能更好,这表明了所提方法的有效性和应用潜力。
Extreme learning machine (ELM) is a single hidden-layer feedforward neural network (SLFNs) which randomly selects hidden-layer nodes and their parameters in the network and only needs to adjust the weights of the output layers during training. Therefore, ELM Very fast learning speed get good promotion. Taking into account the ELM’s feature mapping function is unknown, the nuclear matrix can be introduced into the ELM. Aiming at the continuous stirred tank reactor (CSTR) with unknown model, a NARX model identification method based on Extreme Learning Machine with Kernels (KELM) is proposed. The simulation experiment of CSTR process is used to identify the experiment, and the identification model based on NARX-KELM is established. The experimental results show that under the same conditions, compared with BP neural network, FNN, GAP-RBF, MGAP-RBF neural network, ESN, ELM and other factors, Effectively improve the identification accuracy, and better performance, which shows the effectiveness and potential of the proposed method.