中文摘要：

提出一种基于回声状态网络（echo state networks,ESNs）的分类方法,借鉴集成学习的思想,采用随机子空间方法产生特征子集,对应特征子集生成多个储备池。利用回声状态网络仅需训练储备池至输出层的权值这一优点,将分类集成阶段融合于多储备池回声状态网络的学习过程中。基于标准数据集和模拟电路故障诊断的实验验证结果表明,与标准回声状态网络等方法相比,该方法有更低的分类错误率。

英文摘要：

A classifier based on echo state networks（ESNs） is proposed.Inspired by ensemble learning,multiple reservoirs are constructed,which correspond to the feature subsets generated by random subspace method.Classification combination is embedded in the learning of multiple reservoir ESNs,which is benefited from the advantage of ESNs-only the weights of reservoir-to-output connections are computed.Experiment results based on standard datasets and analog circuit fault diagnosis show that the proposed method outperforms the original echo state networks.