Neural network models become increasingly popular as dynamic modeling tools in the control community. They have many appealing features including nonlinear structures, being able to approximate any functions. While most researchers hold optimistic attitudes towards such models, this paper questions the capability of (deep) neural networks for the modeling of dynamic systems using input-output data. For the identification of linear time-invariant (LTI) dynamic systems, two representative neural network models, Long Short-Term Memory (LSTM) and Cascade Foward Neural Network (CFNN) are compared to the standard Prediction Error Method (PEM) of system identification. In the comparison, four essential aspects of system identification are considered, then several possible defects and neglected issues of neural network based modeling are pointed out. Detailed simulation studies are performed to verify these defects: for the LTI system, both LSTM and CFNN fail to deliver consistent models even in noise-free cases; and they give worse results than PEM in noisy cases.
翻译:神经网络模型作为动态模型工具在控制界越来越受欢迎。 它们有许多吸引特征,包括非线性结构,能够接近任何功能。 虽然大多数研究人员对此类模型持乐观态度, 但本文质疑(深)神经网络利用输入输出数据模拟动态系统的能力。 为了确定线性时变(LTI)动态系统,两个具有代表性的神经网络模型,即长期短期内存(LSTM)和Cascade Foward Neural网络(CFNN)与系统识别的标准预测错误方法(PEM)进行了比较。相比之下,对系统识别的四个基本方面进行了考虑,然后指出了基于神经网络模型的若干可能的缺陷和被忽视的问题。 进行了详细的模拟研究,以核实这些缺陷:对于LTI系统,LSTM和CFNN(CN)都无法提供一致的模型,即使在无噪音情况下也是如此;在噪音案件中,结果比PEM差。